id	sid	tid	token	lemma	pos
10_1101-2021_01_02_425006	1	1	Analysis	analysis	NN
10_1101-2021_01_02_425006	1	2	of	of	IN
10_1101-2021_01_02_425006	1	3	next-	next-	JJ
10_1101-2021_01_02_425006	1	4	and	and	CC
10_1101-2021_01_02_425006	1	5	third	third	JJ
10_1101-2021_01_02_425006	1	6	-	-	HYPH
10_1101-2021_01_02_425006	1	7	generation	generation	NN
10_1101-2021_01_02_425006	1	8	RNA	RNA	NNP
10_1101-2021_01_02_425006	1	9	-	-	HYPH
10_1101-2021_01_02_425006	1	10	Seq	Seq	NNP
10_1101-2021_01_02_425006	1	11	data	datum	NNS
10_1101-2021_01_02_425006	1	12	reveals	reveal	VBZ
10_1101-2021_01_02_425006	1	13	the	the	DT
10_1101-2021_01_02_425006	1	14	structures	structure	NNS
10_1101-2021_01_02_425006	1	15	of	of	IN
10_1101-2021_01_02_425006	1	16	alternative	alternative	JJ
10_1101-2021_01_02_425006	1	17	transcription	transcription	NN
10_1101-2021_01_02_425006	1	18	units	unit	NNS
10_1101-2021_01_02_425006	1	19	in	in	IN
10_1101-2021_01_02_425006	1	20	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	1	21	genomes	genome	NNS
10_1101-2021_01_02_425006	1	22	1	1	CD
10_1101-2021_01_02_425006	1	23	Analysis	Analysis	NNP
10_1101-2021_01_02_425006	1	24	of	of	IN
10_1101-2021_01_02_425006	1	25	next-	next-	JJ
10_1101-2021_01_02_425006	1	26	and	and	CC
10_1101-2021_01_02_425006	1	27	third	third	JJ
10_1101-2021_01_02_425006	1	28	-	-	HYPH
10_1101-2021_01_02_425006	1	29	generation	generation	NN
10_1101-2021_01_02_425006	1	30	RNA	RNA	NNP
10_1101-2021_01_02_425006	1	31	-	-	HYPH
10_1101-2021_01_02_425006	1	32	Seq	Seq	NNP
10_1101-2021_01_02_425006	1	33	data	datum	NNS
10_1101-2021_01_02_425006	1	34	reveals	reveal	VBZ
10_1101-2021_01_02_425006	1	35	the	the	DT
10_1101-2021_01_02_425006	1	36	structures	structure	NNS
10_1101-2021_01_02_425006	1	37	of	of	IN
10_1101-2021_01_02_425006	1	38	1	1	CD
10_1101-2021_01_02_425006	1	39	alternative	alternative	JJ
10_1101-2021_01_02_425006	1	40	transcription	transcription	NN
10_1101-2021_01_02_425006	1	41	units	unit	NNS
10_1101-2021_01_02_425006	1	42	in	in	IN
10_1101-2021_01_02_425006	1	43	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	1	44	genomes	genome	NNS
10_1101-2021_01_02_425006	1	45	2	2	CD
10_1101-2021_01_02_425006	1	46	Qi	Qi	NNP
10_1101-2021_01_02_425006	1	47	Wang1	wang1	NN
10_1101-2021_01_02_425006	1	48	,	,	,
10_1101-2021_01_02_425006	1	49	Zhaoqian	Zhaoqian	NNP
10_1101-2021_01_02_425006	1	50	Liu1,2	Liu1,2	NNP
10_1101-2021_01_02_425006	1	51	,	,	,
10_1101-2021_01_02_425006	1	52	Bo	Bo	NNP
10_1101-2021_01_02_425006	1	53	Yan3	Yan3	NNP
10_1101-2021_01_02_425006	1	54	,	,	,
10_1101-2021_01_02_425006	1	55	Wen	Wen	NNP
10_1101-2021_01_02_425006	1	56	-	-	HYPH
10_1101-2021_01_02_425006	1	57	Chi	Chi	NNP
10_1101-2021_01_02_425006	1	58	Chou4	chou4	NN
10_1101-2021_01_02_425006	1	59	,	,	,
10_1101-2021_01_02_425006	1	60	Laurence	Laurence	NNP
10_1101-2021_01_02_425006	1	61	Ettwiller3	Ettwiller3	NNP
10_1101-2021_01_02_425006	1	62	,	,	,
10_1101-2021_01_02_425006	1	63	Qin	Qin	NNP
10_1101-2021_01_02_425006	1	64	Ma2,†	Ma2,†	NNP
10_1101-2021_01_02_425006	1	65	,	,	,
10_1101-2021_01_02_425006	1	66	and	and	CC
10_1101-2021_01_02_425006	1	67	Bingqiang	Bingqiang	NNP
10_1101-2021_01_02_425006	1	68	3	3	CD
10_1101-2021_01_02_425006	1	69	Liu1,†	Liu1,†	VBD
10_1101-2021_01_02_425006	1	70	4	4	CD
10_1101-2021_01_02_425006	1	71	1	1	CD
10_1101-2021_01_02_425006	1	72	School	School	NNP
10_1101-2021_01_02_425006	1	73	of	of	IN
10_1101-2021_01_02_425006	1	74	Mathematics	Mathematics	NNP
10_1101-2021_01_02_425006	1	75	,	,	,
10_1101-2021_01_02_425006	1	76	Shandong	Shandong	NNP
10_1101-2021_01_02_425006	1	77	University	University	NNP
10_1101-2021_01_02_425006	1	78	,	,	,
10_1101-2021_01_02_425006	1	79	Jinan	Jinan	NNP
10_1101-2021_01_02_425006	1	80	250200	250200	CD
10_1101-2021_01_02_425006	1	81	,	,	,
10_1101-2021_01_02_425006	1	82	China	China	NNP
10_1101-2021_01_02_425006	1	83	.	.	.
10_1101-2021_01_02_425006	2	1	5	5	CD
10_1101-2021_01_02_425006	2	2	2	2	CD
10_1101-2021_01_02_425006	2	3	Department	Department	NNP
10_1101-2021_01_02_425006	2	4	of	of	IN
10_1101-2021_01_02_425006	2	5	Biomedical	Biomedical	NNP
10_1101-2021_01_02_425006	2	6	Informatics	Informatics	NNP
10_1101-2021_01_02_425006	2	7	,	,	,
10_1101-2021_01_02_425006	2	8	College	College	NNP
10_1101-2021_01_02_425006	2	9	of	of	IN
10_1101-2021_01_02_425006	2	10	Medicine	Medicine	NNP
10_1101-2021_01_02_425006	2	11	,	,	,
10_1101-2021_01_02_425006	2	12	The	the	DT
10_1101-2021_01_02_425006	2	13	Ohio	Ohio	NNP
10_1101-2021_01_02_425006	2	14	State	State	NNP
10_1101-2021_01_02_425006	2	15	University	University	NNP
10_1101-2021_01_02_425006	2	16	,	,	,
10_1101-2021_01_02_425006	2	17	Columbus	Columbus	NNP
10_1101-2021_01_02_425006	2	18	,	,	,
10_1101-2021_01_02_425006	2	19	6	6	CD
10_1101-2021_01_02_425006	2	20	OH	oh	NN
10_1101-2021_01_02_425006	2	21	43210	43210	CD
10_1101-2021_01_02_425006	2	22	,	,	,
10_1101-2021_01_02_425006	2	23	USA	USA	NNP
10_1101-2021_01_02_425006	2	24	.	.	.
10_1101-2021_01_02_425006	3	1	7	7	CD
10_1101-2021_01_02_425006	3	2	3	3	CD
10_1101-2021_01_02_425006	3	3	New	New	NNP
10_1101-2021_01_02_425006	3	4	England	England	NNP
10_1101-2021_01_02_425006	3	5	Biolabs	Biolabs	NNP
10_1101-2021_01_02_425006	3	6	Inc.	Inc.	NNP
10_1101-2021_01_02_425006	3	7	,	,	,
10_1101-2021_01_02_425006	3	8	Ipswich	Ipswich	NNP
10_1101-2021_01_02_425006	3	9	,	,	,
10_1101-2021_01_02_425006	3	10	MA	MA	NNP
10_1101-2021_01_02_425006	3	11	01938	01938	CD
10_1101-2021_01_02_425006	3	12	,	,	,
10_1101-2021_01_02_425006	3	13	USA	USA	NNP
10_1101-2021_01_02_425006	3	14	.	.	.
10_1101-2021_01_02_425006	4	1	8	8	CD
10_1101-2021_01_02_425006	4	2	4	4	CD
10_1101-2021_01_02_425006	4	3	Infectious	Infectious	NNP
10_1101-2021_01_02_425006	4	4	Disease	Disease	NNP
10_1101-2021_01_02_425006	4	5	and	and	CC
10_1101-2021_01_02_425006	4	6	Microbiome	Microbiome	NNP
10_1101-2021_01_02_425006	4	7	Program	Program	NNP
10_1101-2021_01_02_425006	4	8	,	,	,
10_1101-2021_01_02_425006	4	9	Broad	Broad	NNP
10_1101-2021_01_02_425006	4	10	Institute	Institute	NNP
10_1101-2021_01_02_425006	4	11	of	of	IN
10_1101-2021_01_02_425006	4	12	MIT	MIT	NNP
10_1101-2021_01_02_425006	4	13	and	and	CC
10_1101-2021_01_02_425006	4	14	Harvard	Harvard	NNP
10_1101-2021_01_02_425006	4	15	,	,	,
10_1101-2021_01_02_425006	4	16	Cambridge	Cambridge	NNP
10_1101-2021_01_02_425006	4	17	,	,	,
10_1101-2021_01_02_425006	4	18	MA	MA	NNP
10_1101-2021_01_02_425006	4	19	9	9	CD
10_1101-2021_01_02_425006	4	20	02142	02142	CD
10_1101-2021_01_02_425006	4	21	,	,	,
10_1101-2021_01_02_425006	4	22	USA	USA	NNP
10_1101-2021_01_02_425006	4	23	.	.	.
10_1101-2021_01_02_425006	5	1	10	10	CD
10_1101-2021_01_02_425006	5	2	†Corresponding	†corresponding	NN
10_1101-2021_01_02_425006	5	3	author	author	NN
10_1101-2021_01_02_425006	5	4	.	.	.
10_1101-2021_01_02_425006	6	1	Email	email	NN
10_1101-2021_01_02_425006	6	2	:	:	:
10_1101-2021_01_02_425006	6	3	bingqiang@sdu.edu.cn	bingqiang@sdu.edu.cn	NNP
10_1101-2021_01_02_425006	6	4	(	(	-LRB-
10_1101-2021_01_02_425006	6	5	B.L.	B.L.	NNP
10_1101-2021_01_02_425006	7	1	)	)	-RRB-
10_1101-2021_01_02_425006	7	2	;	;	:
10_1101-2021_01_02_425006	7	3	qin.ma@osumc.edu	qin.ma@osumc.edu	NNP
10_1101-2021_01_02_425006	7	4	(	(	-LRB-
10_1101-2021_01_02_425006	7	5	Q.M.	Q.M.	NNP
10_1101-2021_01_02_425006	7	6	)	)	-RRB-
10_1101-2021_01_02_425006	8	1	11	11	CD
10_1101-2021_01_02_425006	8	2	ABSTRACT	ABSTRACT	NNP
10_1101-2021_01_02_425006	8	3	12	12	CD
10_1101-2021_01_02_425006	8	4	Alternative	alternative	JJ
10_1101-2021_01_02_425006	8	5	transcription	transcription	NN
10_1101-2021_01_02_425006	8	6	units	unit	NNS
10_1101-2021_01_02_425006	8	7	(	(	-LRB-
10_1101-2021_01_02_425006	8	8	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	8	9	)	)	-RRB-
10_1101-2021_01_02_425006	8	10	are	be	VBP
10_1101-2021_01_02_425006	8	11	dynamically	dynamically	RB
10_1101-2021_01_02_425006	8	12	encoded	encode	VBN
10_1101-2021_01_02_425006	8	13	under	under	IN
10_1101-2021_01_02_425006	8	14	different	different	JJ
10_1101-2021_01_02_425006	8	15	conditions	condition	NNS
10_1101-2021_01_02_425006	8	16	or	or	CC
10_1101-2021_01_02_425006	8	17	13	13	CD
10_1101-2021_01_02_425006	8	18	environmental	environmental	JJ
10_1101-2021_01_02_425006	8	19	stimuli	stimulus	NNS
10_1101-2021_01_02_425006	8	20	in	in	IN
10_1101-2021_01_02_425006	8	21	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	8	22	genomes	genome	NNS
10_1101-2021_01_02_425006	8	23	,	,	,
10_1101-2021_01_02_425006	8	24	and	and	CC
10_1101-2021_01_02_425006	8	25	genome	genome	NN
10_1101-2021_01_02_425006	8	26	-	-	HYPH
10_1101-2021_01_02_425006	8	27	scale	scale	NN
10_1101-2021_01_02_425006	8	28	identification	identification	NN
10_1101-2021_01_02_425006	8	29	of	of	IN
10_1101-2021_01_02_425006	8	30	ATUs	atu	NNS
10_1101-2021_01_02_425006	8	31	is	be	VBZ
10_1101-2021_01_02_425006	8	32	essential	essential	JJ
10_1101-2021_01_02_425006	8	33	for	for	IN
10_1101-2021_01_02_425006	8	34	14	14	CD
10_1101-2021_01_02_425006	8	35	studying	study	VBG
10_1101-2021_01_02_425006	8	36	the	the	DT
10_1101-2021_01_02_425006	8	37	emergence	emergence	NN
10_1101-2021_01_02_425006	8	38	of	of	IN
10_1101-2021_01_02_425006	8	39	human	human	JJ
10_1101-2021_01_02_425006	8	40	diseases	disease	NNS
10_1101-2021_01_02_425006	8	41	caused	cause	VBN
10_1101-2021_01_02_425006	8	42	by	by	IN
10_1101-2021_01_02_425006	8	43	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	8	44	organisms	organism	NNS
10_1101-2021_01_02_425006	8	45	.	.	.
10_1101-2021_01_02_425006	9	1	However	however	RB
10_1101-2021_01_02_425006	9	2	,	,	,
10_1101-2021_01_02_425006	9	3	it	-PRON-	PRP
10_1101-2021_01_02_425006	9	4	is	be	VBZ
10_1101-2021_01_02_425006	9	5	unrealistic	unrealistic	JJ
10_1101-2021_01_02_425006	9	6	to	to	TO
10_1101-2021_01_02_425006	9	7	15	15	CD
10_1101-2021_01_02_425006	9	8	identify	identify	VB
10_1101-2021_01_02_425006	9	9	all	all	DT
10_1101-2021_01_02_425006	9	10	ATUs	atu	NNS
10_1101-2021_01_02_425006	9	11	using	use	VBG
10_1101-2021_01_02_425006	9	12	experimental	experimental	JJ
10_1101-2021_01_02_425006	9	13	techniques	technique	NNS
10_1101-2021_01_02_425006	9	14	,	,	,
10_1101-2021_01_02_425006	9	15	due	due	IN
10_1101-2021_01_02_425006	9	16	to	to	IN
10_1101-2021_01_02_425006	9	17	the	the	DT
10_1101-2021_01_02_425006	9	18	complexity	complexity	NN
10_1101-2021_01_02_425006	9	19	and	and	CC
10_1101-2021_01_02_425006	9	20	dynamic	dynamic	JJ
10_1101-2021_01_02_425006	9	21	nature	nature	NN
10_1101-2021_01_02_425006	9	22	of	of	IN
10_1101-2021_01_02_425006	9	23	ATUs	atu	NNS
10_1101-2021_01_02_425006	9	24	.	.	.
10_1101-2021_01_02_425006	10	1	16	16	CD
10_1101-2021_01_02_425006	10	2	Here	here	RB
10_1101-2021_01_02_425006	10	3	we	-PRON-	PRP
10_1101-2021_01_02_425006	10	4	present	present	VBP
10_1101-2021_01_02_425006	10	5	the	the	DT
10_1101-2021_01_02_425006	10	6	first	first	JJ
10_1101-2021_01_02_425006	10	7	-	-	HYPH
10_1101-2021_01_02_425006	10	8	of	of	IN
10_1101-2021_01_02_425006	10	9	-	-	HYPH
10_1101-2021_01_02_425006	10	10	its	-PRON-	PRP$
10_1101-2021_01_02_425006	10	11	-	-	HYPH
10_1101-2021_01_02_425006	10	12	kind	kind	NN
10_1101-2021_01_02_425006	10	13	computational	computational	JJ
10_1101-2021_01_02_425006	10	14	framework	framework	NN
10_1101-2021_01_02_425006	10	15	,	,	,
10_1101-2021_01_02_425006	10	16	named	name	VBN
10_1101-2021_01_02_425006	10	17	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	10	18	,	,	,
10_1101-2021_01_02_425006	10	19	for	for	IN
10_1101-2021_01_02_425006	10	20	genome	genome	NN
10_1101-2021_01_02_425006	10	21	-	-	HYPH
10_1101-2021_01_02_425006	10	22	scale	scale	NN
10_1101-2021_01_02_425006	10	23	ATU	ATU	NNP
10_1101-2021_01_02_425006	10	24	17	17	CD
10_1101-2021_01_02_425006	10	25	prediction	prediction	NN
10_1101-2021_01_02_425006	10	26	based	base	VBN
10_1101-2021_01_02_425006	10	27	on	on	IN
10_1101-2021_01_02_425006	10	28	next	next	JJ
10_1101-2021_01_02_425006	10	29	-	-	HYPH
10_1101-2021_01_02_425006	10	30	generation	generation	NN
10_1101-2021_01_02_425006	10	31	RNA	RNA	NNP
10_1101-2021_01_02_425006	10	32	-	-	HYPH
10_1101-2021_01_02_425006	10	33	Seq	Seq	NNP
10_1101-2021_01_02_425006	10	34	data	datum	NNS
10_1101-2021_01_02_425006	10	35	.	.	.
10_1101-2021_01_02_425006	11	1	The	the	DT
10_1101-2021_01_02_425006	11	2	framework	framework	NN
10_1101-2021_01_02_425006	11	3	utilizes	utilize	VBZ
10_1101-2021_01_02_425006	11	4	a	a	DT
10_1101-2021_01_02_425006	11	5	convex	convex	NNP
10_1101-2021_01_02_425006	11	6	quadratic	quadratic	NNP
10_1101-2021_01_02_425006	11	7	18	18	CD
10_1101-2021_01_02_425006	11	8	.CC	.CC	,
10_1101-2021_01_02_425006	11	9	-	-	HYPH
10_1101-2021_01_02_425006	11	10	BY	by	IN
10_1101-2021_01_02_425006	11	11	-	-	HYPH
10_1101-2021_01_02_425006	11	12	NC	NC	NNP
10_1101-2021_01_02_425006	11	13	-	-	HYPH
10_1101-2021_01_02_425006	11	14	ND	ND	NNP
10_1101-2021_01_02_425006	11	15	4.0	4.0	CD
10_1101-2021_01_02_425006	11	16	International	International	NNP
10_1101-2021_01_02_425006	11	17	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	11	18	under	under	IN
10_1101-2021_01_02_425006	11	19	a	a	DT
10_1101-2021_01_02_425006	11	20	(	(	-LRB-
10_1101-2021_01_02_425006	11	21	which	which	WDT
10_1101-2021_01_02_425006	11	22	was	be	VBD
10_1101-2021_01_02_425006	11	23	not	not	RB
10_1101-2021_01_02_425006	11	24	certified	certify	VBN
10_1101-2021_01_02_425006	11	25	by	by	IN
10_1101-2021_01_02_425006	11	26	peer	peer	NN
10_1101-2021_01_02_425006	11	27	review	review	NN
10_1101-2021_01_02_425006	11	28	)	)	-RRB-
10_1101-2021_01_02_425006	11	29	is	be	VBZ
10_1101-2021_01_02_425006	11	30	the	the	DT
10_1101-2021_01_02_425006	11	31	author	author	NN
10_1101-2021_01_02_425006	11	32	/	/	SYM
10_1101-2021_01_02_425006	11	33	funder	funder	NN
10_1101-2021_01_02_425006	11	34	,	,	,
10_1101-2021_01_02_425006	11	35	who	who	WP
10_1101-2021_01_02_425006	11	36	has	have	VBZ
10_1101-2021_01_02_425006	11	37	granted	grant	VBN
10_1101-2021_01_02_425006	11	38	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	11	39	a	a	DT
10_1101-2021_01_02_425006	11	40	license	license	NN
10_1101-2021_01_02_425006	11	41	to	to	TO
10_1101-2021_01_02_425006	11	42	display	display	VB
10_1101-2021_01_02_425006	11	43	the	the	DT
10_1101-2021_01_02_425006	11	44	preprint	preprint	NN
10_1101-2021_01_02_425006	11	45	in	in	IN
10_1101-2021_01_02_425006	11	46	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	11	47	.	.	.
10_1101-2021_01_02_425006	12	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	12	2	is	be	VBZ
10_1101-2021_01_02_425006	12	3	made	make	VBN
10_1101-2021_01_02_425006	12	4	The	the	DT
10_1101-2021_01_02_425006	12	5	copyright	copyright	NN
10_1101-2021_01_02_425006	12	6	holder	holder	NN
10_1101-2021_01_02_425006	12	7	for	for	IN
10_1101-2021_01_02_425006	12	8	this	this	DT
10_1101-2021_01_02_425006	12	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	12	10	version	version	NN
10_1101-2021_01_02_425006	12	11	posted	post	VBD
10_1101-2021_01_02_425006	12	12	January	January	NNP
10_1101-2021_01_02_425006	12	13	6	6	CD
10_1101-2021_01_02_425006	12	14	,	,	,
10_1101-2021_01_02_425006	12	15	2021	2021	CD
10_1101-2021_01_02_425006	12	16	.	.	.
10_1101-2021_01_02_425006	12	17	;	;	:
10_1101-2021_01_02_425006	12	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	12	19	:	:	:
10_1101-2021_01_02_425006	12	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	12	21	preprint	preprint	NN
10_1101-2021_01_02_425006	12	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	12	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	12	24	2	2	CD
10_1101-2021_01_02_425006	12	25	programming	programming	NN
10_1101-2021_01_02_425006	12	26	model	model	NN
10_1101-2021_01_02_425006	12	27	to	to	TO
10_1101-2021_01_02_425006	12	28	seek	seek	VB
10_1101-2021_01_02_425006	12	29	an	an	DT
10_1101-2021_01_02_425006	12	30	optimum	optimum	JJ
10_1101-2021_01_02_425006	12	31	expression	expression	NN
10_1101-2021_01_02_425006	12	32	combination	combination	NN
10_1101-2021_01_02_425006	12	33	of	of	IN
10_1101-2021_01_02_425006	12	34	all	all	DT
10_1101-2021_01_02_425006	12	35	of	of	IN
10_1101-2021_01_02_425006	12	36	the	the	DT
10_1101-2021_01_02_425006	12	37	to	to	TO
10_1101-2021_01_02_425006	12	38	-	-	HYPH
10_1101-2021_01_02_425006	12	39	be	be	VB
10_1101-2021_01_02_425006	12	40	-	-	HYPH
10_1101-2021_01_02_425006	12	41	identified	identify	VBN
10_1101-2021_01_02_425006	12	42	ATUs	atu	NNS
10_1101-2021_01_02_425006	12	43	.	.	.
10_1101-2021_01_02_425006	13	1	19	19	CD
10_1101-2021_01_02_425006	13	2	The	the	DT
10_1101-2021_01_02_425006	13	3	predicted	predict	VBN
10_1101-2021_01_02_425006	13	4	ATUs	atu	NNS
10_1101-2021_01_02_425006	13	5	in	in	IN
10_1101-2021_01_02_425006	13	6	E.	E.	NNP
10_1101-2021_01_02_425006	13	7	coli	coli	NNS
10_1101-2021_01_02_425006	13	8	reached	reach	VBD
10_1101-2021_01_02_425006	13	9	a	a	DT
10_1101-2021_01_02_425006	13	10	precision	precision	NN
10_1101-2021_01_02_425006	13	11	of	of	IN
10_1101-2021_01_02_425006	13	12	0.77/0.74	0.77/0.74	NN
10_1101-2021_01_02_425006	13	13	and	and	CC
10_1101-2021_01_02_425006	13	14	a	a	DT
10_1101-2021_01_02_425006	13	15	recall	recall	NN
10_1101-2021_01_02_425006	13	16	of	of	IN
10_1101-2021_01_02_425006	13	17	0.75/0.76	0.75/0.76	NN
10_1101-2021_01_02_425006	13	18	in	in	IN
10_1101-2021_01_02_425006	13	19	the	the	DT
10_1101-2021_01_02_425006	13	20	two	two	CD
10_1101-2021_01_02_425006	13	21	RNA-20	rna-20	CD
10_1101-2021_01_02_425006	13	22	Sequencing	sequencing	NN
10_1101-2021_01_02_425006	13	23	datasets	dataset	NNS
10_1101-2021_01_02_425006	13	24	compared	compare	VBN
10_1101-2021_01_02_425006	13	25	with	with	IN
10_1101-2021_01_02_425006	13	26	the	the	DT
10_1101-2021_01_02_425006	13	27	benchmarked	benchmarke	VBN
10_1101-2021_01_02_425006	13	28	ATUs	atu	NNS
10_1101-2021_01_02_425006	13	29	from	from	IN
10_1101-2021_01_02_425006	13	30	third	third	JJ
10_1101-2021_01_02_425006	13	31	-	-	HYPH
10_1101-2021_01_02_425006	13	32	generation	generation	NN
10_1101-2021_01_02_425006	13	33	RNA	RNA	NNP
10_1101-2021_01_02_425006	13	34	-	-	HYPH
10_1101-2021_01_02_425006	13	35	Seq	Seq	NNP
10_1101-2021_01_02_425006	13	36	data	datum	NNS
10_1101-2021_01_02_425006	13	37	.	.	.
10_1101-2021_01_02_425006	14	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	14	2	21	21	CD
10_1101-2021_01_02_425006	14	3	believe	believe	VBP
10_1101-2021_01_02_425006	14	4	that	that	IN
10_1101-2021_01_02_425006	14	5	the	the	DT
10_1101-2021_01_02_425006	14	6	ATUs	atu	NNS
10_1101-2021_01_02_425006	14	7	identified	identify	VBN
10_1101-2021_01_02_425006	14	8	by	by	IN
10_1101-2021_01_02_425006	14	9	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	14	10	can	can	MD
10_1101-2021_01_02_425006	14	11	provide	provide	VB
10_1101-2021_01_02_425006	14	12	fundamental	fundamental	JJ
10_1101-2021_01_02_425006	14	13	knowledge	knowledge	NN
10_1101-2021_01_02_425006	14	14	to	to	TO
10_1101-2021_01_02_425006	14	15	guide	guide	VB
10_1101-2021_01_02_425006	14	16	the	the	DT
10_1101-2021_01_02_425006	14	17	22	22	CD
10_1101-2021_01_02_425006	14	18	reconstruction	reconstruction	NN
10_1101-2021_01_02_425006	14	19	of	of	IN
10_1101-2021_01_02_425006	14	20	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	14	21	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	14	22	networks	network	NNS
10_1101-2021_01_02_425006	14	23	in	in	IN
10_1101-2021_01_02_425006	14	24	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	14	25	genomes	genome	NNS
10_1101-2021_01_02_425006	14	26	.	.	.
10_1101-2021_01_02_425006	15	1	23	23	CD
10_1101-2021_01_02_425006	15	2	INTRODUCTION	introduction	NN
10_1101-2021_01_02_425006	15	3	24	24	CD
10_1101-2021_01_02_425006	15	4	An	an	DT
10_1101-2021_01_02_425006	15	5	operon	operon	NN
10_1101-2021_01_02_425006	15	6	in	in	IN
10_1101-2021_01_02_425006	15	7	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	15	8	genomes	genome	NNS
10_1101-2021_01_02_425006	15	9	is	be	VBZ
10_1101-2021_01_02_425006	15	10	defined	define	VBN
10_1101-2021_01_02_425006	15	11	as	as	IN
10_1101-2021_01_02_425006	15	12	a	a	DT
10_1101-2021_01_02_425006	15	13	group	group	NN
10_1101-2021_01_02_425006	15	14	of	of	IN
10_1101-2021_01_02_425006	15	15	consecutive	consecutive	JJ
10_1101-2021_01_02_425006	15	16	genes	gene	NNS
10_1101-2021_01_02_425006	15	17	regulated	regulate	VBN
10_1101-2021_01_02_425006	15	18	by	by	IN
10_1101-2021_01_02_425006	15	19	a	a	DT
10_1101-2021_01_02_425006	15	20	common	common	JJ
10_1101-2021_01_02_425006	15	21	25	25	CD
10_1101-2021_01_02_425006	15	22	promoter	promoter	NN
10_1101-2021_01_02_425006	15	23	that	that	WDT
10_1101-2021_01_02_425006	15	24	all	all	DT
10_1101-2021_01_02_425006	15	25	share	share	VBP
10_1101-2021_01_02_425006	15	26	the	the	DT
10_1101-2021_01_02_425006	15	27	same	same	JJ
10_1101-2021_01_02_425006	15	28	terminator	terminator	NN
10_1101-2021_01_02_425006	15	29	(	(	-LRB-
10_1101-2021_01_02_425006	15	30	1	1	CD
10_1101-2021_01_02_425006	15	31	)	)	-RRB-
10_1101-2021_01_02_425006	15	32	.	.	.
10_1101-2021_01_02_425006	16	1	Genes	gene	NNS
10_1101-2021_01_02_425006	16	2	in	in	IN
10_1101-2021_01_02_425006	16	3	the	the	DT
10_1101-2021_01_02_425006	16	4	same	same	JJ
10_1101-2021_01_02_425006	16	5	operon	operon	NN
10_1101-2021_01_02_425006	16	6	generally	generally	RB
10_1101-2021_01_02_425006	16	7	encode	encode	VBP
10_1101-2021_01_02_425006	16	8	proteins	protein	NNS
10_1101-2021_01_02_425006	16	9	26	26	CD
10_1101-2021_01_02_425006	16	10	with	with	IN
10_1101-2021_01_02_425006	16	11	relevant	relevant	JJ
10_1101-2021_01_02_425006	16	12	or	or	CC
10_1101-2021_01_02_425006	16	13	similar	similar	JJ
10_1101-2021_01_02_425006	16	14	biological	biological	JJ
10_1101-2021_01_02_425006	16	15	functions	function	NNS
10_1101-2021_01_02_425006	16	16	;	;	:
10_1101-2021_01_02_425006	16	17	e.g.	e.g.	RB
10_1101-2021_01_02_425006	16	18	,	,	,
10_1101-2021_01_02_425006	16	19	lacZ	lacZ	NNP
10_1101-2021_01_02_425006	16	20	,	,	,
10_1101-2021_01_02_425006	16	21	lacY	lacy	CD
10_1101-2021_01_02_425006	16	22	,	,	,
10_1101-2021_01_02_425006	16	23	and	and	CC
10_1101-2021_01_02_425006	16	24	lacA	lacA	VBD
10_1101-2021_01_02_425006	16	25	in	in	IN
10_1101-2021_01_02_425006	16	26	the	the	DT
10_1101-2021_01_02_425006	16	27	lac	lac	NNP
10_1101-2021_01_02_425006	16	28	operon	operon	NNP
10_1101-2021_01_02_425006	16	29	encode	encode	NNP
10_1101-2021_01_02_425006	16	30	proteins	protein	VBZ
10_1101-2021_01_02_425006	16	31	27	27	CD
10_1101-2021_01_02_425006	16	32	that	that	WDT
10_1101-2021_01_02_425006	16	33	help	help	VBP
10_1101-2021_01_02_425006	16	34	cells	cell	NNS
10_1101-2021_01_02_425006	16	35	use	use	VB
10_1101-2021_01_02_425006	16	36	lactose	lactose	NN
10_1101-2021_01_02_425006	16	37	(	(	-LRB-
10_1101-2021_01_02_425006	16	38	1	1	CD
10_1101-2021_01_02_425006	16	39	,	,	,
10_1101-2021_01_02_425006	16	40	2	2	CD
10_1101-2021_01_02_425006	16	41	)	)	-RRB-
10_1101-2021_01_02_425006	16	42	.	.	.
10_1101-2021_01_02_425006	17	1	With	with	IN
10_1101-2021_01_02_425006	17	2	decades	decade	NNS
10_1101-2021_01_02_425006	17	3	of	of	IN
10_1101-2021_01_02_425006	17	4	research	research	NN
10_1101-2021_01_02_425006	17	5	on	on	IN
10_1101-2021_01_02_425006	17	6	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	17	7	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	17	8	regulation	regulation	NN
10_1101-2021_01_02_425006	17	9	,	,	,
10_1101-2021_01_02_425006	17	10	the	the	DT
10_1101-2021_01_02_425006	17	11	28	28	CD
10_1101-2021_01_02_425006	17	12	operon	operon	NNP
10_1101-2021_01_02_425006	17	13	model	model	NN
10_1101-2021_01_02_425006	17	14	has	have	VBZ
10_1101-2021_01_02_425006	17	15	been	be	VBN
10_1101-2021_01_02_425006	17	16	found	find	VBN
10_1101-2021_01_02_425006	17	17	to	to	TO
10_1101-2021_01_02_425006	17	18	have	have	VB
10_1101-2021_01_02_425006	17	19	complex	complex	JJ
10_1101-2021_01_02_425006	17	20	mechanisms	mechanism	NNS
10_1101-2021_01_02_425006	17	21	that	that	WDT
10_1101-2021_01_02_425006	17	22	control	control	VBP
10_1101-2021_01_02_425006	17	23	expression	expression	NN
10_1101-2021_01_02_425006	17	24	(	(	-LRB-
10_1101-2021_01_02_425006	17	25	3	3	CD
10_1101-2021_01_02_425006	17	26	-	-	SYM
10_1101-2021_01_02_425006	17	27	5	5	CD
10_1101-2021_01_02_425006	17	28	)	)	-RRB-
10_1101-2021_01_02_425006	17	29	.	.	.
10_1101-2021_01_02_425006	18	1	Multiple	multiple	JJ
10_1101-2021_01_02_425006	18	2	29	29	CD
10_1101-2021_01_02_425006	18	3	studies	study	NNS
10_1101-2021_01_02_425006	18	4	have	have	VBP
10_1101-2021_01_02_425006	18	5	shown	show	VBN
10_1101-2021_01_02_425006	18	6	that	that	IN
10_1101-2021_01_02_425006	18	7	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	18	8	genes	gene	NNS
10_1101-2021_01_02_425006	18	9	are	be	VBP
10_1101-2021_01_02_425006	18	10	dynamically	dynamically	RB
10_1101-2021_01_02_425006	18	11	transcribed	transcribe	VBN
10_1101-2021_01_02_425006	18	12	under	under	IN
10_1101-2021_01_02_425006	18	13	different	different	JJ
10_1101-2021_01_02_425006	18	14	triggering	trigger	VBG
10_1101-2021_01_02_425006	18	15	30	30	CD
10_1101-2021_01_02_425006	18	16	conditions	condition	NNS
10_1101-2021_01_02_425006	18	17	,	,	,
10_1101-2021_01_02_425006	18	18	leading	lead	VBG
10_1101-2021_01_02_425006	18	19	to	to	IN
10_1101-2021_01_02_425006	18	20	shared	share	VBN
10_1101-2021_01_02_425006	18	21	genes	gene	NNS
10_1101-2021_01_02_425006	18	22	among	among	IN
10_1101-2021_01_02_425006	18	23	different	different	JJ
10_1101-2021_01_02_425006	18	24	mRNA	mRNA	NNS
10_1101-2021_01_02_425006	18	25	transcripts	transcript	NNS
10_1101-2021_01_02_425006	18	26	(	(	-LRB-
10_1101-2021_01_02_425006	18	27	6	6	CD
10_1101-2021_01_02_425006	18	28	-	-	SYM
10_1101-2021_01_02_425006	18	29	8	8	CD
10_1101-2021_01_02_425006	18	30	)	)	-RRB-
10_1101-2021_01_02_425006	18	31	.	.	.
10_1101-2021_01_02_425006	19	1	This	this	DT
10_1101-2021_01_02_425006	19	2	dynamic	dynamic	JJ
10_1101-2021_01_02_425006	19	3	architecture	architecture	NN
10_1101-2021_01_02_425006	19	4	31	31	CD
10_1101-2021_01_02_425006	19	5	can	can	MD
10_1101-2021_01_02_425006	19	6	be	be	VB
10_1101-2021_01_02_425006	19	7	redefined	redefine	VBN
10_1101-2021_01_02_425006	19	8	by	by	IN
10_1101-2021_01_02_425006	19	9	all	all	DT
10_1101-2021_01_02_425006	19	10	of	of	IN
10_1101-2021_01_02_425006	19	11	the	the	DT
10_1101-2021_01_02_425006	19	12	alternative	alternative	JJ
10_1101-2021_01_02_425006	19	13	transcription	transcription	NN
10_1101-2021_01_02_425006	19	14	units	unit	NNS
10_1101-2021_01_02_425006	19	15	(	(	-LRB-
10_1101-2021_01_02_425006	19	16	a.k.a	a.k.a	JJ
10_1101-2021_01_02_425006	19	17	.	.	NNP
10_1101-2021_01_02_425006	19	18	,	,	,
10_1101-2021_01_02_425006	19	19	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	19	20	)	)	-RRB-
10_1101-2021_01_02_425006	19	21	(	(	-LRB-
10_1101-2021_01_02_425006	19	22	3	3	CD
10_1101-2021_01_02_425006	19	23	,	,	,
10_1101-2021_01_02_425006	19	24	5	5	CD
10_1101-2021_01_02_425006	19	25	)	)	-RRB-
10_1101-2021_01_02_425006	19	26	,	,	,
10_1101-2021_01_02_425006	19	27	and	and	CC
10_1101-2021_01_02_425006	19	28	more	more	JJR
10_1101-2021_01_02_425006	19	29	details	detail	NNS
10_1101-2021_01_02_425006	19	30	can	can	MD
10_1101-2021_01_02_425006	19	31	be	be	VB
10_1101-2021_01_02_425006	19	32	32	32	CD
10_1101-2021_01_02_425006	19	33	found	find	VBN
10_1101-2021_01_02_425006	19	34	in	in	IN
10_1101-2021_01_02_425006	19	35	fig	fig	NN
10_1101-2021_01_02_425006	19	36	.	.	.
10_1101-2021_01_02_425006	20	1	S1	S1	NNS
10_1101-2021_01_02_425006	20	2	.	.	.
10_1101-2021_01_02_425006	21	1	33	33	CD
10_1101-2021_01_02_425006	21	2	ATU	ATU	NNP
10_1101-2021_01_02_425006	21	3	identification	identification	NN
10_1101-2021_01_02_425006	21	4	is	be	VBZ
10_1101-2021_01_02_425006	21	5	of	of	IN
10_1101-2021_01_02_425006	21	6	fundamental	fundamental	JJ
10_1101-2021_01_02_425006	21	7	importance	importance	NN
10_1101-2021_01_02_425006	21	8	for	for	IN
10_1101-2021_01_02_425006	21	9	understanding	understand	VBG
10_1101-2021_01_02_425006	21	10	the	the	DT
10_1101-2021_01_02_425006	21	11	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	21	12	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	21	13	34	34	CD
10_1101-2021_01_02_425006	21	14	mechanisms	mechanism	NNS
10_1101-2021_01_02_425006	21	15	of	of	IN
10_1101-2021_01_02_425006	21	16	bacteria	bacteria	NNS
10_1101-2021_01_02_425006	21	17	,	,	,
10_1101-2021_01_02_425006	21	18	and	and	CC
10_1101-2021_01_02_425006	21	19	these	these	DT
10_1101-2021_01_02_425006	21	20	dynamic	dynamic	JJ
10_1101-2021_01_02_425006	21	21	structures	structure	NNS
10_1101-2021_01_02_425006	21	22	have	have	VBP
10_1101-2021_01_02_425006	21	23	been	be	VBN
10_1101-2021_01_02_425006	21	24	demonstrated	demonstrate	VBN
10_1101-2021_01_02_425006	21	25	to	to	TO
10_1101-2021_01_02_425006	21	26	be	be	VB
10_1101-2021_01_02_425006	21	27	associated	associate	VBN
10_1101-2021_01_02_425006	21	28	with	with	IN
10_1101-2021_01_02_425006	21	29	35	35	CD
10_1101-2021_01_02_425006	21	30	human	human	JJ
10_1101-2021_01_02_425006	21	31	diseases	disease	NNS
10_1101-2021_01_02_425006	21	32	(	(	-LRB-
10_1101-2021_01_02_425006	21	33	9	9	CD
10_1101-2021_01_02_425006	21	34	-	-	SYM
10_1101-2021_01_02_425006	21	35	12	12	CD
10_1101-2021_01_02_425006	21	36	)	)	-RRB-
10_1101-2021_01_02_425006	21	37	.	.	.
10_1101-2021_01_02_425006	22	1	For	for	IN
10_1101-2021_01_02_425006	22	2	example	example	NN
10_1101-2021_01_02_425006	22	3	,	,	,
10_1101-2021_01_02_425006	22	4	Bhat	Bhat	NNP
10_1101-2021_01_02_425006	22	5	et	et	NNP
10_1101-2021_01_02_425006	22	6	al	al	NNP
10_1101-2021_01_02_425006	22	7	.	.	.
10_1101-2021_01_02_425006	23	1	studied	study	VBD
10_1101-2021_01_02_425006	23	2	the	the	DT
10_1101-2021_01_02_425006	23	3	alr	alr	NNP
10_1101-2021_01_02_425006	23	4	-	-	HYPH
10_1101-2021_01_02_425006	23	5	groEL1	groel1	NN
10_1101-2021_01_02_425006	23	6	operon	operon	NNP
10_1101-2021_01_02_425006	23	7	,	,	,
10_1101-2021_01_02_425006	23	8	which	which	WDT
10_1101-2021_01_02_425006	23	9	is	be	VBZ
10_1101-2021_01_02_425006	23	10	essential	essential	JJ
10_1101-2021_01_02_425006	23	11	for	for	IN
10_1101-2021_01_02_425006	23	12	the	the	DT
10_1101-2021_01_02_425006	23	13	36	36	CD
10_1101-2021_01_02_425006	23	14	survival	survival	NN
10_1101-2021_01_02_425006	23	15	or	or	CC
10_1101-2021_01_02_425006	23	16	virulence	virulence	NN
10_1101-2021_01_02_425006	23	17	of	of	IN
10_1101-2021_01_02_425006	23	18	M.	M.	NNP
10_1101-2021_01_02_425006	23	19	tuberculosis	tuberculosis	NN
10_1101-2021_01_02_425006	23	20	(	(	-LRB-
10_1101-2021_01_02_425006	23	21	9	9	CD
10_1101-2021_01_02_425006	23	22	,	,	,
10_1101-2021_01_02_425006	23	23	11	11	CD
10_1101-2021_01_02_425006	23	24	)	)	-RRB-
10_1101-2021_01_02_425006	23	25	,	,	,
10_1101-2021_01_02_425006	23	26	the	the	DT
10_1101-2021_01_02_425006	23	27	causative	causative	JJ
10_1101-2021_01_02_425006	23	28	agent	agent	NN
10_1101-2021_01_02_425006	23	29	of	of	IN
10_1101-2021_01_02_425006	23	30	tuberculosis	tuberculosis	NN
10_1101-2021_01_02_425006	23	31	(	(	-LRB-
10_1101-2021_01_02_425006	23	32	TB	TB	NNP
10_1101-2021_01_02_425006	23	33	)	)	-RRB-
10_1101-2021_01_02_425006	23	34	,	,	,
10_1101-2021_01_02_425006	23	35	and	and	CC
10_1101-2021_01_02_425006	23	36	found	find	VBD
10_1101-2021_01_02_425006	23	37	that	that	IN
10_1101-2021_01_02_425006	23	38	37	37	CD
10_1101-2021_01_02_425006	23	39	.CC	.CC	,
10_1101-2021_01_02_425006	23	40	-	-	HYPH
10_1101-2021_01_02_425006	23	41	BY	by	IN
10_1101-2021_01_02_425006	23	42	-	-	HYPH
10_1101-2021_01_02_425006	23	43	NC	NC	NNP
10_1101-2021_01_02_425006	23	44	-	-	HYPH
10_1101-2021_01_02_425006	23	45	ND	ND	NNP
10_1101-2021_01_02_425006	23	46	4.0	4.0	CD
10_1101-2021_01_02_425006	23	47	International	International	NNP
10_1101-2021_01_02_425006	23	48	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	23	49	under	under	IN
10_1101-2021_01_02_425006	23	50	a	a	DT
10_1101-2021_01_02_425006	23	51	(	(	-LRB-
10_1101-2021_01_02_425006	23	52	which	which	WDT
10_1101-2021_01_02_425006	23	53	was	be	VBD
10_1101-2021_01_02_425006	23	54	not	not	RB
10_1101-2021_01_02_425006	23	55	certified	certify	VBN
10_1101-2021_01_02_425006	23	56	by	by	IN
10_1101-2021_01_02_425006	23	57	peer	peer	NN
10_1101-2021_01_02_425006	23	58	review	review	NN
10_1101-2021_01_02_425006	23	59	)	)	-RRB-
10_1101-2021_01_02_425006	23	60	is	be	VBZ
10_1101-2021_01_02_425006	23	61	the	the	DT
10_1101-2021_01_02_425006	23	62	author	author	NN
10_1101-2021_01_02_425006	23	63	/	/	SYM
10_1101-2021_01_02_425006	23	64	funder	funder	NN
10_1101-2021_01_02_425006	23	65	,	,	,
10_1101-2021_01_02_425006	23	66	who	who	WP
10_1101-2021_01_02_425006	23	67	has	have	VBZ
10_1101-2021_01_02_425006	23	68	granted	grant	VBN
10_1101-2021_01_02_425006	23	69	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	23	70	a	a	DT
10_1101-2021_01_02_425006	23	71	license	license	NN
10_1101-2021_01_02_425006	23	72	to	to	TO
10_1101-2021_01_02_425006	23	73	display	display	VB
10_1101-2021_01_02_425006	23	74	the	the	DT
10_1101-2021_01_02_425006	23	75	preprint	preprint	NN
10_1101-2021_01_02_425006	23	76	in	in	IN
10_1101-2021_01_02_425006	23	77	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	23	78	.	.	.
10_1101-2021_01_02_425006	24	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	24	2	is	be	VBZ
10_1101-2021_01_02_425006	24	3	made	make	VBN
10_1101-2021_01_02_425006	24	4	The	the	DT
10_1101-2021_01_02_425006	24	5	copyright	copyright	NN
10_1101-2021_01_02_425006	24	6	holder	holder	NN
10_1101-2021_01_02_425006	24	7	for	for	IN
10_1101-2021_01_02_425006	24	8	this	this	DT
10_1101-2021_01_02_425006	24	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	24	10	version	version	NN
10_1101-2021_01_02_425006	24	11	posted	post	VBD
10_1101-2021_01_02_425006	24	12	January	January	NNP
10_1101-2021_01_02_425006	24	13	6	6	CD
10_1101-2021_01_02_425006	24	14	,	,	,
10_1101-2021_01_02_425006	24	15	2021	2021	CD
10_1101-2021_01_02_425006	24	16	.	.	.
10_1101-2021_01_02_425006	24	17	;	;	:
10_1101-2021_01_02_425006	24	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	24	19	:	:	:
10_1101-2021_01_02_425006	24	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	24	21	preprint	preprint	NN
10_1101-2021_01_02_425006	24	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	24	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	24	24	3	3	CD
10_1101-2021_01_02_425006	24	25	the	the	DT
10_1101-2021_01_02_425006	24	26	regulation	regulation	NN
10_1101-2021_01_02_425006	24	27	of	of	IN
10_1101-2021_01_02_425006	24	28	the	the	DT
10_1101-2021_01_02_425006	24	29	sub	sub	NN
10_1101-2021_01_02_425006	24	30	-	-	JJ
10_1101-2021_01_02_425006	24	31	operon	operon	NNP
10_1101-2021_01_02_425006	24	32	is	be	VBZ
10_1101-2021_01_02_425006	24	33	distinct	distinct	JJ
10_1101-2021_01_02_425006	24	34	from	from	IN
10_1101-2021_01_02_425006	24	35	the	the	DT
10_1101-2021_01_02_425006	24	36	main	main	JJ
10_1101-2021_01_02_425006	24	37	operon	operon	NN
10_1101-2021_01_02_425006	24	38	(	(	-LRB-
10_1101-2021_01_02_425006	24	39	alr	alr	NNP
10_1101-2021_01_02_425006	24	40	-	-	HYPH
10_1101-2021_01_02_425006	24	41	groEL1	groEL1	NNP
10_1101-2021_01_02_425006	24	42	operon	operon	NN
10_1101-2021_01_02_425006	24	43	)	)	-RRB-
10_1101-2021_01_02_425006	24	44	under	under	IN
10_1101-2021_01_02_425006	24	45	stress	stress	NN
10_1101-2021_01_02_425006	24	46	,	,	,
10_1101-2021_01_02_425006	24	47	38	38	CD
10_1101-2021_01_02_425006	24	48	especially	especially	RB
10_1101-2021_01_02_425006	24	49	during	during	IN
10_1101-2021_01_02_425006	24	50	heat	heat	NN
10_1101-2021_01_02_425006	24	51	shock	shock	NN
10_1101-2021_01_02_425006	24	52	,	,	,
10_1101-2021_01_02_425006	24	53	pH	pH	NNP
10_1101-2021_01_02_425006	24	54	,	,	,
10_1101-2021_01_02_425006	24	55	and	and	CC
10_1101-2021_01_02_425006	24	56	SDS	SDS	NNP
10_1101-2021_01_02_425006	24	57	stresses	stress	NNS
10_1101-2021_01_02_425006	24	58	(	(	-LRB-
10_1101-2021_01_02_425006	24	59	9	9	CD
10_1101-2021_01_02_425006	24	60	)	)	-RRB-
10_1101-2021_01_02_425006	24	61	.	.	.
10_1101-2021_01_02_425006	25	1	Another	another	DT
10_1101-2021_01_02_425006	25	2	example	example	NN
10_1101-2021_01_02_425006	25	3	is	be	VBZ
10_1101-2021_01_02_425006	25	4	Helicobacter	Helicobacter	NNP
10_1101-2021_01_02_425006	25	5	pylori	pylori	NN
10_1101-2021_01_02_425006	25	6	,	,	,
10_1101-2021_01_02_425006	25	7	a	a	DT
10_1101-2021_01_02_425006	25	8	39	39	CD
10_1101-2021_01_02_425006	25	9	gastric	gastric	JJ
10_1101-2021_01_02_425006	25	10	pathogen	pathogen	NN
10_1101-2021_01_02_425006	25	11	that	that	WDT
10_1101-2021_01_02_425006	25	12	is	be	VBZ
10_1101-2021_01_02_425006	25	13	the	the	DT
10_1101-2021_01_02_425006	25	14	primary	primary	JJ
10_1101-2021_01_02_425006	25	15	known	know	VBN
10_1101-2021_01_02_425006	25	16	risk	risk	NN
10_1101-2021_01_02_425006	25	17	factor	factor	NN
10_1101-2021_01_02_425006	25	18	for	for	IN
10_1101-2021_01_02_425006	25	19	gastric	gastric	JJ
10_1101-2021_01_02_425006	25	20	cancer	cancer	NN
10_1101-2021_01_02_425006	25	21	(	(	-LRB-
10_1101-2021_01_02_425006	25	22	12	12	CD
10_1101-2021_01_02_425006	25	23	)	)	-RRB-
10_1101-2021_01_02_425006	25	24	.	.	.
10_1101-2021_01_02_425006	26	1	Sharma	Sharma	NNP
10_1101-2021_01_02_425006	26	2	et	et	NNP
10_1101-2021_01_02_425006	26	3	al	al	NNP
10_1101-2021_01_02_425006	26	4	.	.	.
10_1101-2021_01_02_425006	27	1	found	find	VBD
10_1101-2021_01_02_425006	27	2	an	an	DT
10_1101-2021_01_02_425006	27	3	40	40	CD
10_1101-2021_01_02_425006	27	4	acid	acid	NN
10_1101-2021_01_02_425006	27	5	-	-	HYPH
10_1101-2021_01_02_425006	27	6	induced	induce	VBN
10_1101-2021_01_02_425006	27	7	sub	sub	JJ
10_1101-2021_01_02_425006	27	8	-	-	HYPH
10_1101-2021_01_02_425006	27	9	operon	operon	JJ
10_1101-2021_01_02_425006	27	10	cag22	cag22	NNP
10_1101-2021_01_02_425006	27	11	-	-	SYM
10_1101-2021_01_02_425006	27	12	18	18	CD
10_1101-2021_01_02_425006	27	13	transcribed	transcribe	VBN
10_1101-2021_01_02_425006	27	14	from	from	IN
10_1101-2021_01_02_425006	27	15	the	the	DT
10_1101-2021_01_02_425006	27	16	primary	primary	JJ
10_1101-2021_01_02_425006	27	17	cag25	cag25	-RRB-
10_1101-2021_01_02_425006	27	18	-	-	SYM
10_1101-2021_01_02_425006	27	19	18	18	CD
10_1101-2021_01_02_425006	27	20	operon	operon	NN
10_1101-2021_01_02_425006	27	21	in	in	IN
10_1101-2021_01_02_425006	27	22	the	the	DT
10_1101-2021_01_02_425006	27	23	cag	cag	NNP
10_1101-2021_01_02_425006	27	24	41	41	CD
10_1101-2021_01_02_425006	27	25	pathogenicity	pathogenicity	NN
10_1101-2021_01_02_425006	27	26	island	island	NN
10_1101-2021_01_02_425006	27	27	of	of	IN
10_1101-2021_01_02_425006	27	28	the	the	DT
10_1101-2021_01_02_425006	27	29	H.	H.	NNP
10_1101-2021_01_02_425006	27	30	pylori	pylori	NN
10_1101-2021_01_02_425006	27	31	genome	genome	NN
10_1101-2021_01_02_425006	27	32	under	under	IN
10_1101-2021_01_02_425006	27	33	acid	acid	JJ
10_1101-2021_01_02_425006	27	34	stress	stress	NN
10_1101-2021_01_02_425006	27	35	(	(	-LRB-
10_1101-2021_01_02_425006	27	36	10	10	CD
10_1101-2021_01_02_425006	27	37	)	)	-RRB-
10_1101-2021_01_02_425006	27	38	.	.	.
10_1101-2021_01_02_425006	28	1	The	the	DT
10_1101-2021_01_02_425006	28	2	mechanism	mechanism	NN
10_1101-2021_01_02_425006	28	3	of	of	IN
10_1101-2021_01_02_425006	28	4	the	the	DT
10_1101-2021_01_02_425006	28	5	complex	complex	JJ
10_1101-2021_01_02_425006	28	6	ATU	ATU	NNP
10_1101-2021_01_02_425006	28	7	42	42	CD
10_1101-2021_01_02_425006	28	8	structure	structure	NN
10_1101-2021_01_02_425006	28	9	in	in	IN
10_1101-2021_01_02_425006	28	10	these	these	DT
10_1101-2021_01_02_425006	28	11	pathogenic	pathogenic	JJ
10_1101-2021_01_02_425006	28	12	bacteria	bacteria	NNS
10_1101-2021_01_02_425006	28	13	can	can	MD
10_1101-2021_01_02_425006	28	14	help	help	VB
10_1101-2021_01_02_425006	28	15	us	-PRON-	PRP
10_1101-2021_01_02_425006	28	16	to	to	TO
10_1101-2021_01_02_425006	28	17	study	study	VB
10_1101-2021_01_02_425006	28	18	the	the	DT
10_1101-2021_01_02_425006	28	19	emergence	emergence	NN
10_1101-2021_01_02_425006	28	20	of	of	IN
10_1101-2021_01_02_425006	28	21	human	human	JJ
10_1101-2021_01_02_425006	28	22	diseases	disease	NNS
10_1101-2021_01_02_425006	28	23	caused	cause	VBN
10_1101-2021_01_02_425006	28	24	by	by	IN
10_1101-2021_01_02_425006	28	25	43	43	CD
10_1101-2021_01_02_425006	28	26	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	28	27	organisms	organism	NNS
10_1101-2021_01_02_425006	28	28	.	.	.
10_1101-2021_01_02_425006	29	1	44	44	CD
10_1101-2021_01_02_425006	29	2	Several	several	JJ
10_1101-2021_01_02_425006	29	3	newly	newly	RB
10_1101-2021_01_02_425006	29	4	developed	develop	VBN
10_1101-2021_01_02_425006	29	5	techniques	technique	NNS
10_1101-2021_01_02_425006	29	6	have	have	VBP
10_1101-2021_01_02_425006	29	7	provided	provide	VBN
10_1101-2021_01_02_425006	29	8	a	a	DT
10_1101-2021_01_02_425006	29	9	comprehensive	comprehensive	JJ
10_1101-2021_01_02_425006	29	10	view	view	NN
10_1101-2021_01_02_425006	29	11	of	of	IN
10_1101-2021_01_02_425006	29	12	the	the	DT
10_1101-2021_01_02_425006	29	13	E.	E.	NNP
10_1101-2021_01_02_425006	29	14	coli	coli	VBZ
10_1101-2021_01_02_425006	29	15	45	45	CD
10_1101-2021_01_02_425006	29	16	transcriptome	transcriptome	DT
10_1101-2021_01_02_425006	29	17	by	by	IN
10_1101-2021_01_02_425006	29	18	identifying	identify	VBG
10_1101-2021_01_02_425006	29	19	full	full	JJ
10_1101-2021_01_02_425006	29	20	-	-	HYPH
10_1101-2021_01_02_425006	29	21	length	length	NN
10_1101-2021_01_02_425006	29	22	primary	primary	JJ
10_1101-2021_01_02_425006	29	23	transcripts	transcript	NNS
10_1101-2021_01_02_425006	29	24	(	(	-LRB-
10_1101-2021_01_02_425006	29	25	13	13	CD
10_1101-2021_01_02_425006	29	26	-	-	SYM
10_1101-2021_01_02_425006	29	27	17	17	CD
10_1101-2021_01_02_425006	29	28	)	)	-RRB-
10_1101-2021_01_02_425006	29	29	.	.	.
10_1101-2021_01_02_425006	30	1	For	for	IN
10_1101-2021_01_02_425006	30	2	example	example	NN
10_1101-2021_01_02_425006	30	3	,	,	,
10_1101-2021_01_02_425006	30	4	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	30	5	-	-	HYPH
10_1101-2021_01_02_425006	30	6	Cappable	cappable	JJ
10_1101-2021_01_02_425006	30	7	-	-	HYPH
10_1101-2021_01_02_425006	30	8	seq	seq	NN
10_1101-2021_01_02_425006	30	9	46	46	CD
10_1101-2021_01_02_425006	30	10	(	(	-LRB-
10_1101-2021_01_02_425006	30	11	6	6	CD
10_1101-2021_01_02_425006	30	12	)	)	-RRB-
10_1101-2021_01_02_425006	30	13	combines	combine	VBZ
10_1101-2021_01_02_425006	30	14	the	the	DT
10_1101-2021_01_02_425006	30	15	isolation	isolation	NN
10_1101-2021_01_02_425006	30	16	of	of	IN
10_1101-2021_01_02_425006	30	17	the	the	DT
10_1101-2021_01_02_425006	30	18	full	full	JJ
10_1101-2021_01_02_425006	30	19	-	-	HYPH
10_1101-2021_01_02_425006	30	20	length	length	NN
10_1101-2021_01_02_425006	30	21	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	30	22	primary	primary	NN
10_1101-2021_01_02_425006	30	23	transcriptome	transcriptome	VBN
10_1101-2021_01_02_425006	30	24	with	with	IN
10_1101-2021_01_02_425006	30	25	PacBio	PacBio	NNP
10_1101-2021_01_02_425006	30	26	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	30	27	(	(	-LRB-
10_1101-2021_01_02_425006	30	28	Single	Single	NNP
10_1101-2021_01_02_425006	30	29	47	47	CD
10_1101-2021_01_02_425006	30	30	Molecule	Molecule	NNP
10_1101-2021_01_02_425006	30	31	,	,	,
10_1101-2021_01_02_425006	30	32	Real	Real	NNP
10_1101-2021_01_02_425006	30	33	-	-	HYPH
10_1101-2021_01_02_425006	30	34	Time	time	NN
10_1101-2021_01_02_425006	30	35	)	)	-RRB-
10_1101-2021_01_02_425006	30	36	sequencing	sequence	VBG
10_1101-2021_01_02_425006	30	37	(	(	-LRB-
10_1101-2021_01_02_425006	30	38	6	6	CD
10_1101-2021_01_02_425006	30	39	)	)	-RRB-
10_1101-2021_01_02_425006	30	40	,	,	,
10_1101-2021_01_02_425006	30	41	and	and	CC
10_1101-2021_01_02_425006	30	42	simultaneous	simultaneous	JJ
10_1101-2021_01_02_425006	30	43	5	5	CD
10_1101-2021_01_02_425006	30	44	’	'	''
10_1101-2021_01_02_425006	30	45	and	and	CC
10_1101-2021_01_02_425006	30	46	3	3	CD
10_1101-2021_01_02_425006	30	47	’	'	''
10_1101-2021_01_02_425006	30	48	end	end	NN
10_1101-2021_01_02_425006	30	49	sequencing	sequencing	NN
10_1101-2021_01_02_425006	30	50	(	(	-LRB-
10_1101-2021_01_02_425006	30	51	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	30	52	-	-	HYPH
10_1101-2021_01_02_425006	30	53	seq	seq	NNP
10_1101-2021_01_02_425006	30	54	)	)	-RRB-
10_1101-2021_01_02_425006	30	55	(	(	-LRB-
10_1101-2021_01_02_425006	30	56	7	7	CD
10_1101-2021_01_02_425006	30	57	)	)	-RRB-
10_1101-2021_01_02_425006	30	58	48	48	CD
10_1101-2021_01_02_425006	30	59	captures	capture	NNS
10_1101-2021_01_02_425006	30	60	both	both	DT
10_1101-2021_01_02_425006	30	61	transcription	transcription	NN
10_1101-2021_01_02_425006	30	62	start	start	NN
10_1101-2021_01_02_425006	30	63	sites	site	NNS
10_1101-2021_01_02_425006	30	64	(	(	-LRB-
10_1101-2021_01_02_425006	30	65	TSSs	TSSs	NNP
10_1101-2021_01_02_425006	30	66	)	)	-RRB-
10_1101-2021_01_02_425006	30	67	and	and	CC
10_1101-2021_01_02_425006	30	68	transcription	transcription	NN
10_1101-2021_01_02_425006	30	69	termination	termination	NN
10_1101-2021_01_02_425006	30	70	sites	site	NNS
10_1101-2021_01_02_425006	30	71	(	(	-LRB-
10_1101-2021_01_02_425006	30	72	TTSs	TTSs	NNPS
10_1101-2021_01_02_425006	30	73	)	)	-RRB-
10_1101-2021_01_02_425006	30	74	via	via	IN
10_1101-2021_01_02_425006	30	75	49	49	CD
10_1101-2021_01_02_425006	30	76	circularization	circularization	NN
10_1101-2021_01_02_425006	30	77	of	of	IN
10_1101-2021_01_02_425006	30	78	transcripts	transcript	NNS
10_1101-2021_01_02_425006	30	79	(	(	-LRB-
10_1101-2021_01_02_425006	30	80	17	17	CD
10_1101-2021_01_02_425006	30	81	)	)	-RRB-
10_1101-2021_01_02_425006	30	82	.	.	.
10_1101-2021_01_02_425006	31	1	Despite	despite	IN
10_1101-2021_01_02_425006	31	2	the	the	DT
10_1101-2021_01_02_425006	31	3	great	great	JJ
10_1101-2021_01_02_425006	31	4	progress	progress	NN
10_1101-2021_01_02_425006	31	5	in	in	IN
10_1101-2021_01_02_425006	31	6	experimental	experimental	JJ
10_1101-2021_01_02_425006	31	7	techniques	technique	NNS
10_1101-2021_01_02_425006	31	8	,	,	,
10_1101-2021_01_02_425006	31	9	there	there	EX
10_1101-2021_01_02_425006	31	10	are	be	VBP
10_1101-2021_01_02_425006	31	11	still	still	RB
10_1101-2021_01_02_425006	31	12	50	50	CD
10_1101-2021_01_02_425006	31	13	some	some	DT
10_1101-2021_01_02_425006	31	14	deficiencies	deficiency	NNS
10_1101-2021_01_02_425006	31	15	.	.	.
10_1101-2021_01_02_425006	32	1	On	on	IN
10_1101-2021_01_02_425006	32	2	the	the	DT
10_1101-2021_01_02_425006	32	3	one	one	CD
10_1101-2021_01_02_425006	32	4	hand	hand	NN
10_1101-2021_01_02_425006	32	5	,	,	,
10_1101-2021_01_02_425006	32	6	the	the	DT
10_1101-2021_01_02_425006	32	7	read	read	VBN
10_1101-2021_01_02_425006	32	8	depth	depth	NN
10_1101-2021_01_02_425006	32	9	and	and	CC
10_1101-2021_01_02_425006	32	10	error	error	NN
10_1101-2021_01_02_425006	32	11	rate	rate	NN
10_1101-2021_01_02_425006	32	12	of	of	IN
10_1101-2021_01_02_425006	32	13	the	the	DT
10_1101-2021_01_02_425006	32	14	third	third	JJ
10_1101-2021_01_02_425006	32	15	-	-	HYPH
10_1101-2021_01_02_425006	32	16	generation	generation	NN
10_1101-2021_01_02_425006	32	17	sequencing	sequence	VBG
10_1101-2021_01_02_425006	32	18	51	51	CD
10_1101-2021_01_02_425006	32	19	used	use	VBN
10_1101-2021_01_02_425006	32	20	in	in	IN
10_1101-2021_01_02_425006	32	21	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	32	22	-	-	HYPH
10_1101-2021_01_02_425006	32	23	Cappable	cappable	JJ
10_1101-2021_01_02_425006	32	24	-	-	HYPH
10_1101-2021_01_02_425006	32	25	seq	seq	NN
10_1101-2021_01_02_425006	32	26	have	have	VBP
10_1101-2021_01_02_425006	32	27	an	an	DT
10_1101-2021_01_02_425006	32	28	impact	impact	NN
10_1101-2021_01_02_425006	32	29	on	on	IN
10_1101-2021_01_02_425006	32	30	ATU	ATU	NNP
10_1101-2021_01_02_425006	32	31	prediction	prediction	NN
10_1101-2021_01_02_425006	32	32	compared	compare	VBN
10_1101-2021_01_02_425006	32	33	with	with	IN
10_1101-2021_01_02_425006	32	34	Illumina	Illumina	NNP
10_1101-2021_01_02_425006	32	35	-	-	HYPH
10_1101-2021_01_02_425006	32	36	based	base	VBN
10_1101-2021_01_02_425006	32	37	RNA-52	rna-52	CD
10_1101-2021_01_02_425006	32	38	Seq	Seq	NNP
10_1101-2021_01_02_425006	32	39	(	(	-LRB-
10_1101-2021_01_02_425006	32	40	7	7	CD
10_1101-2021_01_02_425006	32	41	,	,	,
10_1101-2021_01_02_425006	32	42	18	18	CD
10_1101-2021_01_02_425006	32	43	)	)	-RRB-
10_1101-2021_01_02_425006	32	44	.	.	.
10_1101-2021_01_02_425006	33	1	On	on	IN
10_1101-2021_01_02_425006	33	2	the	the	DT
10_1101-2021_01_02_425006	33	3	other	other	JJ
10_1101-2021_01_02_425006	33	4	hand	hand	NN
10_1101-2021_01_02_425006	33	5	,	,	,
10_1101-2021_01_02_425006	33	6	the	the	DT
10_1101-2021_01_02_425006	33	7	time	time	NN
10_1101-2021_01_02_425006	33	8	-	-	HYPH
10_1101-2021_01_02_425006	33	9	consuming	consume	VBG
10_1101-2021_01_02_425006	33	10	,	,	,
10_1101-2021_01_02_425006	33	11	laborious	laborious	JJ
10_1101-2021_01_02_425006	33	12	,	,	,
10_1101-2021_01_02_425006	33	13	and	and	CC
10_1101-2021_01_02_425006	33	14	costly	costly	JJ
10_1101-2021_01_02_425006	33	15	properties	property	NNS
10_1101-2021_01_02_425006	33	16	of	of	IN
10_1101-2021_01_02_425006	33	17	these	these	DT
10_1101-2021_01_02_425006	33	18	53	53	CD
10_1101-2021_01_02_425006	33	19	experimental	experimental	JJ
10_1101-2021_01_02_425006	33	20	techniques	technique	NNS
10_1101-2021_01_02_425006	33	21	make	make	VBP
10_1101-2021_01_02_425006	33	22	them	-PRON-	PRP
10_1101-2021_01_02_425006	33	23	unrealistic	unrealistic	JJ
10_1101-2021_01_02_425006	33	24	to	to	TO
10_1101-2021_01_02_425006	33	25	be	be	VB
10_1101-2021_01_02_425006	33	26	generally	generally	RB
10_1101-2021_01_02_425006	33	27	applicable	applicable	JJ
10_1101-2021_01_02_425006	33	28	to	to	IN
10_1101-2021_01_02_425006	33	29	ATU	ATU	NNP
10_1101-2021_01_02_425006	33	30	predictions	prediction	NNS
10_1101-2021_01_02_425006	33	31	in	in	IN
10_1101-2021_01_02_425006	33	32	bacteria	bacteria	NNS
10_1101-2021_01_02_425006	33	33	54	54	CD
10_1101-2021_01_02_425006	33	34	under	under	IN
10_1101-2021_01_02_425006	33	35	specific	specific	JJ
10_1101-2021_01_02_425006	33	36	conditions	condition	NNS
10_1101-2021_01_02_425006	33	37	.	.	.
10_1101-2021_01_02_425006	34	1	Thus	thus	RB
10_1101-2021_01_02_425006	34	2	,	,	,
10_1101-2021_01_02_425006	34	3	novel	novel	JJ
10_1101-2021_01_02_425006	34	4	and	and	CC
10_1101-2021_01_02_425006	34	5	robust	robust	JJ
10_1101-2021_01_02_425006	34	6	computational	computational	JJ
10_1101-2021_01_02_425006	34	7	methods	method	NNS
10_1101-2021_01_02_425006	34	8	for	for	IN
10_1101-2021_01_02_425006	34	9	ATU	ATU	NNP
10_1101-2021_01_02_425006	34	10	identification	identification	NN
10_1101-2021_01_02_425006	34	11	in	in	IN
10_1101-2021_01_02_425006	34	12	55	55	CD
10_1101-2021_01_02_425006	34	13	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	34	14	genomes	genome	NNS
10_1101-2021_01_02_425006	34	15	based	base	VBN
10_1101-2021_01_02_425006	34	16	on	on	IN
10_1101-2021_01_02_425006	34	17	RNA	RNA	NNP
10_1101-2021_01_02_425006	34	18	-	-	HYPH
10_1101-2021_01_02_425006	34	19	Seq	Seq	NNP
10_1101-2021_01_02_425006	34	20	are	be	VBP
10_1101-2021_01_02_425006	34	21	urgently	urgently	RB
10_1101-2021_01_02_425006	34	22	needed	need	VBN
10_1101-2021_01_02_425006	34	23	.	.	.
10_1101-2021_01_02_425006	35	1	56	56	CD
10_1101-2021_01_02_425006	35	2	.CC	.CC	:
10_1101-2021_01_02_425006	35	3	-	-	HYPH
10_1101-2021_01_02_425006	35	4	BY	by	IN
10_1101-2021_01_02_425006	35	5	-	-	HYPH
10_1101-2021_01_02_425006	35	6	NC	NC	NNP
10_1101-2021_01_02_425006	35	7	-	-	HYPH
10_1101-2021_01_02_425006	35	8	ND	ND	NNP
10_1101-2021_01_02_425006	35	9	4.0	4.0	CD
10_1101-2021_01_02_425006	35	10	International	International	NNP
10_1101-2021_01_02_425006	35	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	35	12	under	under	IN
10_1101-2021_01_02_425006	35	13	a	a	DT
10_1101-2021_01_02_425006	35	14	(	(	-LRB-
10_1101-2021_01_02_425006	35	15	which	which	WDT
10_1101-2021_01_02_425006	35	16	was	be	VBD
10_1101-2021_01_02_425006	35	17	not	not	RB
10_1101-2021_01_02_425006	35	18	certified	certify	VBN
10_1101-2021_01_02_425006	35	19	by	by	IN
10_1101-2021_01_02_425006	35	20	peer	peer	NN
10_1101-2021_01_02_425006	35	21	review	review	NN
10_1101-2021_01_02_425006	35	22	)	)	-RRB-
10_1101-2021_01_02_425006	35	23	is	be	VBZ
10_1101-2021_01_02_425006	35	24	the	the	DT
10_1101-2021_01_02_425006	35	25	author	author	NN
10_1101-2021_01_02_425006	35	26	/	/	SYM
10_1101-2021_01_02_425006	35	27	funder	funder	NN
10_1101-2021_01_02_425006	35	28	,	,	,
10_1101-2021_01_02_425006	35	29	who	who	WP
10_1101-2021_01_02_425006	35	30	has	have	VBZ
10_1101-2021_01_02_425006	35	31	granted	grant	VBN
10_1101-2021_01_02_425006	35	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	35	33	a	a	DT
10_1101-2021_01_02_425006	35	34	license	license	NN
10_1101-2021_01_02_425006	35	35	to	to	TO
10_1101-2021_01_02_425006	35	36	display	display	VB
10_1101-2021_01_02_425006	35	37	the	the	DT
10_1101-2021_01_02_425006	35	38	preprint	preprint	NN
10_1101-2021_01_02_425006	35	39	in	in	IN
10_1101-2021_01_02_425006	35	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	35	41	.	.	.
10_1101-2021_01_02_425006	36	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	36	2	is	be	VBZ
10_1101-2021_01_02_425006	36	3	made	make	VBN
10_1101-2021_01_02_425006	36	4	The	the	DT
10_1101-2021_01_02_425006	36	5	copyright	copyright	NN
10_1101-2021_01_02_425006	36	6	holder	holder	NN
10_1101-2021_01_02_425006	36	7	for	for	IN
10_1101-2021_01_02_425006	36	8	this	this	DT
10_1101-2021_01_02_425006	36	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	36	10	version	version	NN
10_1101-2021_01_02_425006	36	11	posted	post	VBD
10_1101-2021_01_02_425006	36	12	January	January	NNP
10_1101-2021_01_02_425006	36	13	6	6	CD
10_1101-2021_01_02_425006	36	14	,	,	,
10_1101-2021_01_02_425006	36	15	2021	2021	CD
10_1101-2021_01_02_425006	36	16	.	.	.
10_1101-2021_01_02_425006	36	17	;	;	:
10_1101-2021_01_02_425006	36	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	36	19	:	:	:
10_1101-2021_01_02_425006	36	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	36	21	preprint	preprint	NN
10_1101-2021_01_02_425006	36	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	36	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	36	24	4	4	CD
10_1101-2021_01_02_425006	36	25	Fortunately	fortunately	RB
10_1101-2021_01_02_425006	36	26	,	,	,
10_1101-2021_01_02_425006	36	27	many	many	JJ
10_1101-2021_01_02_425006	36	28	computational	computational	JJ
10_1101-2021_01_02_425006	36	29	studies	study	NNS
10_1101-2021_01_02_425006	36	30	have	have	VBP
10_1101-2021_01_02_425006	36	31	been	be	VBN
10_1101-2021_01_02_425006	36	32	carried	carry	VBN
10_1101-2021_01_02_425006	36	33	out	out	RP
10_1101-2021_01_02_425006	36	34	to	to	TO
10_1101-2021_01_02_425006	36	35	predict	predict	VB
10_1101-2021_01_02_425006	36	36	ATUs	atu	NNS
10_1101-2021_01_02_425006	36	37	in	in	IN
10_1101-2021_01_02_425006	36	38	bacteria	bacteria	NNS
10_1101-2021_01_02_425006	36	39	,	,	,
10_1101-2021_01_02_425006	36	40	which	which	WDT
10_1101-2021_01_02_425006	36	41	57	57	CD
10_1101-2021_01_02_425006	36	42	have	have	VBP
10_1101-2021_01_02_425006	36	43	provided	provide	VBN
10_1101-2021_01_02_425006	36	44	some	some	DT
10_1101-2021_01_02_425006	36	45	preliminary	preliminary	JJ
10_1101-2021_01_02_425006	36	46	studies	study	NNS
10_1101-2021_01_02_425006	36	47	for	for	IN
10_1101-2021_01_02_425006	36	48	ATU	ATU	NNP
10_1101-2021_01_02_425006	36	49	prediction	prediction	NN
10_1101-2021_01_02_425006	36	50	.	.	.
10_1101-2021_01_02_425006	37	1	Several	several	JJ
10_1101-2021_01_02_425006	37	2	public	public	JJ
10_1101-2021_01_02_425006	37	3	databases	database	NNS
10_1101-2021_01_02_425006	37	4	,	,	,
10_1101-2021_01_02_425006	37	5	such	such	JJ
10_1101-2021_01_02_425006	37	6	as	as	IN
10_1101-2021_01_02_425006	37	7	58	58	CD
10_1101-2021_01_02_425006	37	8	RegulonDB	regulondb	NN
10_1101-2021_01_02_425006	37	9	(	(	-LRB-
10_1101-2021_01_02_425006	37	10	19	19	CD
10_1101-2021_01_02_425006	37	11	)	)	-RRB-
10_1101-2021_01_02_425006	37	12	,	,	,
10_1101-2021_01_02_425006	37	13	DBTBS(20	DBTBS(20	NNP
10_1101-2021_01_02_425006	37	14	)	)	-RRB-
10_1101-2021_01_02_425006	37	15	,	,	,
10_1101-2021_01_02_425006	37	16	MicrobesOnline	MicrobesOnline	NNP
10_1101-2021_01_02_425006	37	17	(	(	-LRB-
10_1101-2021_01_02_425006	37	18	21	21	CD
10_1101-2021_01_02_425006	37	19	)	)	-RRB-
10_1101-2021_01_02_425006	37	20	,	,	,
10_1101-2021_01_02_425006	37	21	DOOR	DOOR	NNP
10_1101-2021_01_02_425006	37	22	(	(	-LRB-
10_1101-2021_01_02_425006	37	23	22	22	CD
10_1101-2021_01_02_425006	37	24	,	,	,
10_1101-2021_01_02_425006	37	25	23	23	CD
10_1101-2021_01_02_425006	37	26	)	)	-RRB-
10_1101-2021_01_02_425006	37	27	,	,	,
10_1101-2021_01_02_425006	37	28	OperomeDB	OperomeDB	NNP
10_1101-2021_01_02_425006	37	29	(	(	-LRB-
10_1101-2021_01_02_425006	37	30	24	24	CD
10_1101-2021_01_02_425006	37	31	)	)	-RRB-
10_1101-2021_01_02_425006	37	32	,	,	,
10_1101-2021_01_02_425006	37	33	DMINDA	DMINDA	NNP
10_1101-2021_01_02_425006	37	34	2.0	2.0	CD
10_1101-2021_01_02_425006	37	35	59	59	CD
10_1101-2021_01_02_425006	37	36	(	(	-LRB-
10_1101-2021_01_02_425006	37	37	25	25	CD
10_1101-2021_01_02_425006	37	38	)	)	-RRB-
10_1101-2021_01_02_425006	37	39	,	,	,
10_1101-2021_01_02_425006	37	40	and	and	CC
10_1101-2021_01_02_425006	37	41	ProOpDB	ProOpDB	NNP
10_1101-2021_01_02_425006	37	42	(	(	-LRB-
10_1101-2021_01_02_425006	37	43	26	26	CD
10_1101-2021_01_02_425006	37	44	)	)	-RRB-
10_1101-2021_01_02_425006	37	45	,	,	,
10_1101-2021_01_02_425006	37	46	provide	provide	VB
10_1101-2021_01_02_425006	37	47	various	various	JJ
10_1101-2021_01_02_425006	37	48	levels	level	NNS
10_1101-2021_01_02_425006	37	49	of	of	IN
10_1101-2021_01_02_425006	37	50	operon	operon	NNP
10_1101-2021_01_02_425006	37	51	information	information	NN
10_1101-2021_01_02_425006	37	52	and	and	CC
10_1101-2021_01_02_425006	37	53	small	small	JJ
10_1101-2021_01_02_425006	37	54	amounts	amount	NNS
10_1101-2021_01_02_425006	37	55	of	of	IN
10_1101-2021_01_02_425006	37	56	ATU	ATU	NNP
10_1101-2021_01_02_425006	37	57	60	60	CD
10_1101-2021_01_02_425006	37	58	information	information	NN
10_1101-2021_01_02_425006	37	59	.	.	.
10_1101-2021_01_02_425006	38	1	However	however	RB
10_1101-2021_01_02_425006	38	2	,	,	,
10_1101-2021_01_02_425006	38	3	these	these	DT
10_1101-2021_01_02_425006	38	4	databases	database	NNS
10_1101-2021_01_02_425006	38	5	can	can	MD
10_1101-2021_01_02_425006	38	6	not	not	RB
10_1101-2021_01_02_425006	38	7	provide	provide	VB
10_1101-2021_01_02_425006	38	8	genome	genome	NN
10_1101-2021_01_02_425006	38	9	-	-	HYPH
10_1101-2021_01_02_425006	38	10	scale	scale	NN
10_1101-2021_01_02_425006	38	11	ATU	ATU	NNP
10_1101-2021_01_02_425006	38	12	information	information	NN
10_1101-2021_01_02_425006	38	13	under	under	IN
10_1101-2021_01_02_425006	38	14	specific	specific	JJ
10_1101-2021_01_02_425006	38	15	61	61	CD
10_1101-2021_01_02_425006	38	16	conditions	condition	NNS
10_1101-2021_01_02_425006	38	17	.	.	.
10_1101-2021_01_02_425006	39	1	Some	some	DT
10_1101-2021_01_02_425006	39	2	computational	computational	JJ
10_1101-2021_01_02_425006	39	3	studies	study	NNS
10_1101-2021_01_02_425006	39	4	,	,	,
10_1101-2021_01_02_425006	39	5	including	include	VBG
10_1101-2021_01_02_425006	39	6	Rockhopper	Rockhopper	NNP
10_1101-2021_01_02_425006	39	7	(	(	-LRB-
10_1101-2021_01_02_425006	39	8	27	27	CD
10_1101-2021_01_02_425006	39	9	)	)	-RRB-
10_1101-2021_01_02_425006	39	10	,	,	,
10_1101-2021_01_02_425006	39	11	SeqTU	SeqTU	NNP
10_1101-2021_01_02_425006	39	12	(	(	-LRB-
10_1101-2021_01_02_425006	39	13	4	4	CD
10_1101-2021_01_02_425006	39	14	,	,	,
10_1101-2021_01_02_425006	39	15	28	28	CD
10_1101-2021_01_02_425006	39	16	)	)	-RRB-
10_1101-2021_01_02_425006	39	17	,	,	,
10_1101-2021_01_02_425006	39	18	BAC-62	BAC-62	NNP
10_1101-2021_01_02_425006	39	19	BROWSER(29	browser(29	ADD
10_1101-2021_01_02_425006	39	20	)	)	-RRB-
10_1101-2021_01_02_425006	39	21	,	,	,
10_1101-2021_01_02_425006	39	22	rSeqTU	rseqtu	CD
10_1101-2021_01_02_425006	39	23	(	(	-LRB-
10_1101-2021_01_02_425006	39	24	5	5	CD
10_1101-2021_01_02_425006	39	25	)	)	-RRB-
10_1101-2021_01_02_425006	39	26	,	,	,
10_1101-2021_01_02_425006	39	27	and	and	CC
10_1101-2021_01_02_425006	39	28	Operon	Operon	NNP
10_1101-2021_01_02_425006	39	29	-	-	HYPH
10_1101-2021_01_02_425006	39	30	mapper	mapper	NNP
10_1101-2021_01_02_425006	39	31	(	(	-LRB-
10_1101-2021_01_02_425006	39	32	30	30	CD
10_1101-2021_01_02_425006	39	33	)	)	-RRB-
10_1101-2021_01_02_425006	39	34	,	,	,
10_1101-2021_01_02_425006	39	35	utilize	utilize	VB
10_1101-2021_01_02_425006	39	36	machine	machine	NN
10_1101-2021_01_02_425006	39	37	learning	learning	NN
10_1101-2021_01_02_425006	39	38	and	and	CC
10_1101-2021_01_02_425006	39	39	model	model	NN
10_1101-2021_01_02_425006	39	40	integration	integration	NN
10_1101-2021_01_02_425006	39	41	63	63	CD
10_1101-2021_01_02_425006	39	42	methods	method	NNS
10_1101-2021_01_02_425006	39	43	based	base	VBN
10_1101-2021_01_02_425006	39	44	on	on	IN
10_1101-2021_01_02_425006	39	45	genomic	genomic	JJ
10_1101-2021_01_02_425006	39	46	information	information	NN
10_1101-2021_01_02_425006	39	47	and	and	CC
10_1101-2021_01_02_425006	39	48	gene	gene	NN
10_1101-2021_01_02_425006	39	49	expression	expression	NN
10_1101-2021_01_02_425006	39	50	profiles	profile	NNS
10_1101-2021_01_02_425006	39	51	to	to	TO
10_1101-2021_01_02_425006	39	52	identify	identify	VB
10_1101-2021_01_02_425006	39	53	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	39	54	transcription	transcription	NN
10_1101-2021_01_02_425006	39	55	64	64	CD
10_1101-2021_01_02_425006	39	56	architecture	architecture	NN
10_1101-2021_01_02_425006	39	57	.	.	.
10_1101-2021_01_02_425006	40	1	However	however	RB
10_1101-2021_01_02_425006	40	2	,	,	,
10_1101-2021_01_02_425006	40	3	these	these	DT
10_1101-2021_01_02_425006	40	4	works	work	NNS
10_1101-2021_01_02_425006	40	5	still	still	RB
10_1101-2021_01_02_425006	40	6	can	can	MD
10_1101-2021_01_02_425006	40	7	not	not	RB
10_1101-2021_01_02_425006	40	8	solve	solve	VB
10_1101-2021_01_02_425006	40	9	the	the	DT
10_1101-2021_01_02_425006	40	10	dynamic	dynamic	JJ
10_1101-2021_01_02_425006	40	11	patterns	pattern	NNS
10_1101-2021_01_02_425006	40	12	and	and	CC
10_1101-2021_01_02_425006	40	13	overlapping	overlap	VBG
10_1101-2021_01_02_425006	40	14	nature	nature	NN
10_1101-2021_01_02_425006	40	15	of	of	IN
10_1101-2021_01_02_425006	40	16	65	65	CD
10_1101-2021_01_02_425006	40	17	ATUs	atu	NNS
10_1101-2021_01_02_425006	40	18	.	.	.
10_1101-2021_01_02_425006	41	1	66	66	CD
10_1101-2021_01_02_425006	41	2	Here	here	RB
10_1101-2021_01_02_425006	41	3	,	,	,
10_1101-2021_01_02_425006	41	4	we	-PRON-	PRP
10_1101-2021_01_02_425006	41	5	present	present	VBP
10_1101-2021_01_02_425006	41	6	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	41	7	,	,	,
10_1101-2021_01_02_425006	41	8	a	a	DT
10_1101-2021_01_02_425006	41	9	novel	novel	JJ
10_1101-2021_01_02_425006	41	10	computational	computational	JJ
10_1101-2021_01_02_425006	41	11	method	method	NN
10_1101-2021_01_02_425006	41	12	for	for	IN
10_1101-2021_01_02_425006	41	13	genome	genome	NN
10_1101-2021_01_02_425006	41	14	-	-	HYPH
10_1101-2021_01_02_425006	41	15	scale	scale	NN
10_1101-2021_01_02_425006	41	16	ATU	ATU	NNP
10_1101-2021_01_02_425006	41	17	prediction	prediction	NN
10_1101-2021_01_02_425006	41	18	by	by	IN
10_1101-2021_01_02_425006	41	19	67	67	CD
10_1101-2021_01_02_425006	41	20	analyzing	analyze	VBG
10_1101-2021_01_02_425006	41	21	next-	next-	JJ
10_1101-2021_01_02_425006	41	22	and	and	CC
10_1101-2021_01_02_425006	41	23	third	third	JJ
10_1101-2021_01_02_425006	41	24	-	-	HYPH
10_1101-2021_01_02_425006	41	25	generation	generation	NN
10_1101-2021_01_02_425006	41	26	RNA	RNA	NNP
10_1101-2021_01_02_425006	41	27	-	-	HYPH
10_1101-2021_01_02_425006	41	28	Seq	seq	NN
10_1101-2021_01_02_425006	41	29	data	datum	NNS
10_1101-2021_01_02_425006	41	30	(	(	-LRB-
10_1101-2021_01_02_425006	41	31	Fig	fig	NN
10_1101-2021_01_02_425006	41	32	.	.	.
10_1101-2021_01_02_425006	42	1	1	1	CD
10_1101-2021_01_02_425006	42	2	and	and	CC
10_1101-2021_01_02_425006	42	3	table	table	NN
10_1101-2021_01_02_425006	42	4	S1	S1	NNS
10_1101-2021_01_02_425006	42	5	)	)	-RRB-
10_1101-2021_01_02_425006	42	6	.	.	.
10_1101-2021_01_02_425006	43	1	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	43	2	utilizes	utilize	VBZ
10_1101-2021_01_02_425006	43	3	a	a	DT
10_1101-2021_01_02_425006	43	4	convex	convex	NNP
10_1101-2021_01_02_425006	43	5	68	68	CD
10_1101-2021_01_02_425006	43	6	quadratic	quadratic	JJ
10_1101-2021_01_02_425006	43	7	programming	programming	NN
10_1101-2021_01_02_425006	43	8	model	model	NN
10_1101-2021_01_02_425006	43	9	(	(	-LRB-
10_1101-2021_01_02_425006	43	10	CQP	CQP	NNP
10_1101-2021_01_02_425006	43	11	)	)	-RRB-
10_1101-2021_01_02_425006	43	12	and	and	CC
10_1101-2021_01_02_425006	43	13	aims	aim	VBZ
10_1101-2021_01_02_425006	43	14	to	to	TO
10_1101-2021_01_02_425006	43	15	provide	provide	VB
10_1101-2021_01_02_425006	43	16	the	the	DT
10_1101-2021_01_02_425006	43	17	optimum	optimum	JJ
10_1101-2021_01_02_425006	43	18	expression	expression	NN
10_1101-2021_01_02_425006	43	19	combination	combination	NN
10_1101-2021_01_02_425006	43	20	of	of	IN
10_1101-2021_01_02_425006	43	21	all	all	DT
10_1101-2021_01_02_425006	43	22	of	of	IN
10_1101-2021_01_02_425006	43	23	69	69	CD
10_1101-2021_01_02_425006	43	24	the	the	DT
10_1101-2021_01_02_425006	43	25	to	to	TO
10_1101-2021_01_02_425006	43	26	-	-	HYPH
10_1101-2021_01_02_425006	43	27	be	be	VB
10_1101-2021_01_02_425006	43	28	-	-	HYPH
10_1101-2021_01_02_425006	43	29	identified	identify	VBN
10_1101-2021_01_02_425006	43	30	ATUs	atu	NNS
10_1101-2021_01_02_425006	43	31	.	.	.
10_1101-2021_01_02_425006	44	1	Specifically	specifically	RB
10_1101-2021_01_02_425006	44	2	,	,	,
10_1101-2021_01_02_425006	44	3	CQP	CQP	NNP
10_1101-2021_01_02_425006	44	4	minimizes	minimize	VBZ
10_1101-2021_01_02_425006	44	5	the	the	DT
10_1101-2021_01_02_425006	44	6	squared	squared	JJ
10_1101-2021_01_02_425006	44	7	error	error	NN
10_1101-2021_01_02_425006	44	8	between	between	IN
10_1101-2021_01_02_425006	44	9	the	the	DT
10_1101-2021_01_02_425006	44	10	predicted	predict	VBN
10_1101-2021_01_02_425006	44	11	70	70	CD
10_1101-2021_01_02_425006	44	12	expression	expression	NN
10_1101-2021_01_02_425006	44	13	level	level	NN
10_1101-2021_01_02_425006	44	14	of	of	IN
10_1101-2021_01_02_425006	44	15	ATUs	atu	NNS
10_1101-2021_01_02_425006	44	16	and	and	CC
10_1101-2021_01_02_425006	44	17	the	the	DT
10_1101-2021_01_02_425006	44	18	actual	actual	JJ
10_1101-2021_01_02_425006	44	19	expression	expression	NN
10_1101-2021_01_02_425006	44	20	levels	level	NNS
10_1101-2021_01_02_425006	44	21	in	in	IN
10_1101-2021_01_02_425006	44	22	genetic	genetic	JJ
10_1101-2021_01_02_425006	44	23	and	and	CC
10_1101-2021_01_02_425006	44	24	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	44	25	regions	region	NNS
10_1101-2021_01_02_425006	44	26	.	.	.
10_1101-2021_01_02_425006	45	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	45	2	is	be	VBZ
10_1101-2021_01_02_425006	45	3	71	71	CD
10_1101-2021_01_02_425006	45	4	noteworthy	noteworthy	JJ
10_1101-2021_01_02_425006	45	5	that	that	IN
10_1101-2021_01_02_425006	45	6	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	45	7	also	also	RB
10_1101-2021_01_02_425006	45	8	utilizes	utilize	VBZ
10_1101-2021_01_02_425006	45	9	the	the	DT
10_1101-2021_01_02_425006	45	10	information	information	NN
10_1101-2021_01_02_425006	45	11	about	about	IN
10_1101-2021_01_02_425006	45	12	the	the	DT
10_1101-2021_01_02_425006	45	13	bias	bias	NN
10_1101-2021_01_02_425006	45	14	rate	rate	NN
10_1101-2021_01_02_425006	45	15	function	function	NN
10_1101-2021_01_02_425006	45	16	in	in	IN
10_1101-2021_01_02_425006	45	17	modeling	model	VBG
10_1101-2021_01_02_425006	45	18	non-72	non-72	JJ
10_1101-2021_01_02_425006	45	19	uniform	uniform	NN
10_1101-2021_01_02_425006	45	20	read	read	VBD
10_1101-2021_01_02_425006	45	21	distribution	distribution	NN
10_1101-2021_01_02_425006	45	22	as	as	IN
10_1101-2021_01_02_425006	45	23	the	the	DT
10_1101-2021_01_02_425006	45	24	linear	linear	JJ
10_1101-2021_01_02_425006	45	25	constraints	constraint	NNS
10_1101-2021_01_02_425006	45	26	of	of	IN
10_1101-2021_01_02_425006	45	27	CQP	CQP	NNP
10_1101-2021_01_02_425006	45	28	to	to	TO
10_1101-2021_01_02_425006	45	29	profile	profile	VB
10_1101-2021_01_02_425006	45	30	the	the	DT
10_1101-2021_01_02_425006	45	31	complexity	complexity	NN
10_1101-2021_01_02_425006	45	32	of	of	IN
10_1101-2021_01_02_425006	45	33	the	the	DT
10_1101-2021_01_02_425006	45	34	ATU	ATU	NNP
10_1101-2021_01_02_425006	45	35	73	73	CD
10_1101-2021_01_02_425006	45	36	architecture	architecture	NN
10_1101-2021_01_02_425006	45	37	.	.	.
10_1101-2021_01_02_425006	46	1	Overall	overall	RB
10_1101-2021_01_02_425006	46	2	,	,	,
10_1101-2021_01_02_425006	46	3	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	46	4	provides	provide	VBZ
10_1101-2021_01_02_425006	46	5	a	a	DT
10_1101-2021_01_02_425006	46	6	generalized	generalize	VBN
10_1101-2021_01_02_425006	46	7	framework	framework	NN
10_1101-2021_01_02_425006	46	8	for	for	IN
10_1101-2021_01_02_425006	46	9	the	the	DT
10_1101-2021_01_02_425006	46	10	inference	inference	NN
10_1101-2021_01_02_425006	46	11	of	of	IN
10_1101-2021_01_02_425006	46	12	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	46	13	based	base	VBN
10_1101-2021_01_02_425006	46	14	on	on	IN
10_1101-2021_01_02_425006	46	15	74	74	CD
10_1101-2021_01_02_425006	46	16	next	next	JJ
10_1101-2021_01_02_425006	46	17	-	-	HYPH
10_1101-2021_01_02_425006	46	18	generation	generation	NN
10_1101-2021_01_02_425006	46	19	RNA	RNA	NNP
10_1101-2021_01_02_425006	46	20	-	-	HYPH
10_1101-2021_01_02_425006	46	21	Seq	Seq	NNP
10_1101-2021_01_02_425006	46	22	data	datum	NNS
10_1101-2021_01_02_425006	46	23	collected	collect	VBN
10_1101-2021_01_02_425006	46	24	under	under	IN
10_1101-2021_01_02_425006	46	25	multiple	multiple	JJ
10_1101-2021_01_02_425006	46	26	conditions	condition	NNS
10_1101-2021_01_02_425006	46	27	and	and	CC
10_1101-2021_01_02_425006	46	28	can	can	MD
10_1101-2021_01_02_425006	46	29	be	be	VB
10_1101-2021_01_02_425006	46	30	easily	easily	RB
10_1101-2021_01_02_425006	46	31	applied	apply	VBN
10_1101-2021_01_02_425006	46	32	to	to	IN
10_1101-2021_01_02_425006	46	33	any	any	DT
10_1101-2021_01_02_425006	46	34	75	75	CD
10_1101-2021_01_02_425006	46	35	.CC	.CC	,
10_1101-2021_01_02_425006	46	36	-	-	HYPH
10_1101-2021_01_02_425006	46	37	BY	by	IN
10_1101-2021_01_02_425006	46	38	-	-	HYPH
10_1101-2021_01_02_425006	46	39	NC	NC	NNP
10_1101-2021_01_02_425006	46	40	-	-	HYPH
10_1101-2021_01_02_425006	46	41	ND	ND	NNP
10_1101-2021_01_02_425006	46	42	4.0	4.0	CD
10_1101-2021_01_02_425006	46	43	International	International	NNP
10_1101-2021_01_02_425006	46	44	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	46	45	under	under	IN
10_1101-2021_01_02_425006	46	46	a	a	DT
10_1101-2021_01_02_425006	46	47	(	(	-LRB-
10_1101-2021_01_02_425006	46	48	which	which	WDT
10_1101-2021_01_02_425006	46	49	was	be	VBD
10_1101-2021_01_02_425006	46	50	not	not	RB
10_1101-2021_01_02_425006	46	51	certified	certify	VBN
10_1101-2021_01_02_425006	46	52	by	by	IN
10_1101-2021_01_02_425006	46	53	peer	peer	NN
10_1101-2021_01_02_425006	46	54	review	review	NN
10_1101-2021_01_02_425006	46	55	)	)	-RRB-
10_1101-2021_01_02_425006	46	56	is	be	VBZ
10_1101-2021_01_02_425006	46	57	the	the	DT
10_1101-2021_01_02_425006	46	58	author	author	NN
10_1101-2021_01_02_425006	46	59	/	/	SYM
10_1101-2021_01_02_425006	46	60	funder	funder	NN
10_1101-2021_01_02_425006	46	61	,	,	,
10_1101-2021_01_02_425006	46	62	who	who	WP
10_1101-2021_01_02_425006	46	63	has	have	VBZ
10_1101-2021_01_02_425006	46	64	granted	grant	VBN
10_1101-2021_01_02_425006	46	65	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	46	66	a	a	DT
10_1101-2021_01_02_425006	46	67	license	license	NN
10_1101-2021_01_02_425006	46	68	to	to	TO
10_1101-2021_01_02_425006	46	69	display	display	VB
10_1101-2021_01_02_425006	46	70	the	the	DT
10_1101-2021_01_02_425006	46	71	preprint	preprint	NN
10_1101-2021_01_02_425006	46	72	in	in	IN
10_1101-2021_01_02_425006	46	73	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	46	74	.	.	.
10_1101-2021_01_02_425006	47	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	47	2	is	be	VBZ
10_1101-2021_01_02_425006	47	3	made	make	VBN
10_1101-2021_01_02_425006	47	4	The	the	DT
10_1101-2021_01_02_425006	47	5	copyright	copyright	NN
10_1101-2021_01_02_425006	47	6	holder	holder	NN
10_1101-2021_01_02_425006	47	7	for	for	IN
10_1101-2021_01_02_425006	47	8	this	this	DT
10_1101-2021_01_02_425006	47	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	47	10	version	version	NN
10_1101-2021_01_02_425006	47	11	posted	post	VBD
10_1101-2021_01_02_425006	47	12	January	January	NNP
10_1101-2021_01_02_425006	47	13	6	6	CD
10_1101-2021_01_02_425006	47	14	,	,	,
10_1101-2021_01_02_425006	47	15	2021	2021	CD
10_1101-2021_01_02_425006	47	16	.	.	.
10_1101-2021_01_02_425006	47	17	;	;	:
10_1101-2021_01_02_425006	47	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	47	19	:	:	:
10_1101-2021_01_02_425006	47	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	47	21	preprint	preprint	NN
10_1101-2021_01_02_425006	47	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	47	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	47	24	5	5	CD
10_1101-2021_01_02_425006	47	25	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	47	26	organism	organism	NN
10_1101-2021_01_02_425006	47	27	to	to	TO
10_1101-2021_01_02_425006	47	28	identify	identify	VB
10_1101-2021_01_02_425006	47	29	the	the	DT
10_1101-2021_01_02_425006	47	30	ATU	ATU	NNP
10_1101-2021_01_02_425006	47	31	architecture	architecture	NN
10_1101-2021_01_02_425006	47	32	and	and	CC
10_1101-2021_01_02_425006	47	33	construct	construct	VB
10_1101-2021_01_02_425006	47	34	a	a	DT
10_1101-2021_01_02_425006	47	35	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	47	36	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	47	37	network	network	NN
10_1101-2021_01_02_425006	47	38	.	.	.
10_1101-2021_01_02_425006	48	1	76	76	CD
10_1101-2021_01_02_425006	48	2	Please	please	UH
10_1101-2021_01_02_425006	48	3	place	place	VB
10_1101-2021_01_02_425006	48	4	Fig	Fig	NNP
10_1101-2021_01_02_425006	48	5	.	.	.
10_1101-2021_01_02_425006	49	1	1	1	CD
10_1101-2021_01_02_425006	49	2	here	here	RB
10_1101-2021_01_02_425006	49	3	.	.	.
10_1101-2021_01_02_425006	50	1	77	77	CD
10_1101-2021_01_02_425006	50	2	MATERIALS	material	NNS
10_1101-2021_01_02_425006	50	3	AND	and	CC
10_1101-2021_01_02_425006	50	4	METHODS	METHODS	NNP
10_1101-2021_01_02_425006	50	5	78	78	CD
10_1101-2021_01_02_425006	50	6	Data	Data	NNP
10_1101-2021_01_02_425006	50	7	collection	collection	NN
10_1101-2021_01_02_425006	50	8	79	79	CD
10_1101-2021_01_02_425006	50	9	The	the	DT
10_1101-2021_01_02_425006	50	10	two	two	CD
10_1101-2021_01_02_425006	50	11	Cappable	Cappable	NNP
10_1101-2021_01_02_425006	50	12	RNA	RNA	NNP
10_1101-2021_01_02_425006	50	13	-	-	HYPH
10_1101-2021_01_02_425006	50	14	Seq	Seq	NNP
10_1101-2021_01_02_425006	50	15	datasets	dataset	NNS
10_1101-2021_01_02_425006	50	16	used	use	VBN
10_1101-2021_01_02_425006	50	17	in	in	IN
10_1101-2021_01_02_425006	50	18	this	this	DT
10_1101-2021_01_02_425006	50	19	study	study	NN
10_1101-2021_01_02_425006	50	20	,	,	,
10_1101-2021_01_02_425006	50	21	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	50	22	and	and	CC
10_1101-2021_01_02_425006	50	23	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	50	24	,	,	,
10_1101-2021_01_02_425006	50	25	were	be	VBD
10_1101-2021_01_02_425006	50	26	80	80	CD
10_1101-2021_01_02_425006	50	27	obtained	obtain	VBN
10_1101-2021_01_02_425006	50	28	from	from	IN
10_1101-2021_01_02_425006	50	29	E.	E.	NNP
10_1101-2021_01_02_425006	50	30	coli	coli	NNS
10_1101-2021_01_02_425006	50	31	grown	grow	VBN
10_1101-2021_01_02_425006	50	32	under	under	IN
10_1101-2021_01_02_425006	50	33	two	two	CD
10_1101-2021_01_02_425006	50	34	different	different	JJ
10_1101-2021_01_02_425006	50	35	conditions	condition	NNS
10_1101-2021_01_02_425006	50	36	:	:	:
10_1101-2021_01_02_425006	50	37	M9	M9	NNP
10_1101-2021_01_02_425006	50	38	minimal	minimal	JJ
10_1101-2021_01_02_425006	50	39	medium	medium	NN
10_1101-2021_01_02_425006	50	40	and	and	CC
10_1101-2021_01_02_425006	50	41	Rich	rich	JJ
10_1101-2021_01_02_425006	50	42	medium	medium	NN
10_1101-2021_01_02_425006	50	43	,	,	,
10_1101-2021_01_02_425006	50	44	81	81	CD
10_1101-2021_01_02_425006	50	45	respectively	respectively	RB
10_1101-2021_01_02_425006	50	46	(	(	-LRB-
10_1101-2021_01_02_425006	50	47	6	6	CD
10_1101-2021_01_02_425006	50	48	)	)	-RRB-
10_1101-2021_01_02_425006	50	49	.	.	.
10_1101-2021_01_02_425006	51	1	The	the	DT
10_1101-2021_01_02_425006	51	2	full	full	JJ
10_1101-2021_01_02_425006	51	3	-	-	HYPH
10_1101-2021_01_02_425006	51	4	length	length	NN
10_1101-2021_01_02_425006	51	5	primary	primary	JJ
10_1101-2021_01_02_425006	51	6	transcripts	transcript	NNS
10_1101-2021_01_02_425006	51	7	were	be	VBD
10_1101-2021_01_02_425006	51	8	enriched	enrich	VBN
10_1101-2021_01_02_425006	51	9	as	as	IN
10_1101-2021_01_02_425006	51	10	described	describe	VBN
10_1101-2021_01_02_425006	51	11	in	in	IN
10_1101-2021_01_02_425006	51	12	(	(	-LRB-
10_1101-2021_01_02_425006	51	13	6	6	CD
10_1101-2021_01_02_425006	51	14	)	)	-RRB-
10_1101-2021_01_02_425006	51	15	with	with	IN
10_1101-2021_01_02_425006	51	16	modifications	modification	NNS
10_1101-2021_01_02_425006	51	17	82	82	CD
10_1101-2021_01_02_425006	51	18	to	to	TO
10_1101-2021_01_02_425006	51	19	be	be	VB
10_1101-2021_01_02_425006	51	20	adapted	adapt	VBN
10_1101-2021_01_02_425006	51	21	to	to	IN
10_1101-2021_01_02_425006	51	22	Illumina	Illumina	NNP
10_1101-2021_01_02_425006	51	23	sequencing	sequencing	NN
10_1101-2021_01_02_425006	51	24	.	.	.
10_1101-2021_01_02_425006	52	1	The	the	DT
10_1101-2021_01_02_425006	52	2	capping	cap	VBG
10_1101-2021_01_02_425006	52	3	and	and	CC
10_1101-2021_01_02_425006	52	4	polyA	polyA	NNP
10_1101-2021_01_02_425006	52	5	tailing	tailing	NN
10_1101-2021_01_02_425006	52	6	were	be	VBD
10_1101-2021_01_02_425006	52	7	performed	perform	VBN
10_1101-2021_01_02_425006	52	8	as	as	IN
10_1101-2021_01_02_425006	52	9	described	describe	VBN
10_1101-2021_01_02_425006	52	10	in	in	IN
10_1101-2021_01_02_425006	52	11	(	(	-LRB-
10_1101-2021_01_02_425006	52	12	6	6	CD
10_1101-2021_01_02_425006	52	13	)	)	-RRB-
10_1101-2021_01_02_425006	52	14	.	.	.
10_1101-2021_01_02_425006	53	1	83	83	CD
10_1101-2021_01_02_425006	53	2	The	the	DT
10_1101-2021_01_02_425006	53	3	capped	cap	VBN
10_1101-2021_01_02_425006	53	4	RNA	RNA	NNP
10_1101-2021_01_02_425006	53	5	was	be	VBD
10_1101-2021_01_02_425006	53	6	enriched	enrich	VBN
10_1101-2021_01_02_425006	53	7	using	use	VBG
10_1101-2021_01_02_425006	53	8	hydrophilic	hydrophilic	JJ
10_1101-2021_01_02_425006	53	9	streptavidin	streptavidin	NNS
10_1101-2021_01_02_425006	53	10	magnetic	magnetic	JJ
10_1101-2021_01_02_425006	53	11	beads	bead	NNS
10_1101-2021_01_02_425006	53	12	(	(	-LRB-
10_1101-2021_01_02_425006	53	13	New	New	NNP
10_1101-2021_01_02_425006	53	14	England	England	NNP
10_1101-2021_01_02_425006	53	15	Biolabs	Biolabs	NNP
10_1101-2021_01_02_425006	53	16	)	)	-RRB-
10_1101-2021_01_02_425006	53	17	84	84	CD
10_1101-2021_01_02_425006	53	18	and	and	CC
10_1101-2021_01_02_425006	53	19	eluted	elute	VBN
10_1101-2021_01_02_425006	53	20	with	with	IN
10_1101-2021_01_02_425006	53	21	Biotin	Biotin	NNP
10_1101-2021_01_02_425006	53	22	using	use	VBG
10_1101-2021_01_02_425006	53	23	the	the	DT
10_1101-2021_01_02_425006	53	24	same	same	JJ
10_1101-2021_01_02_425006	53	25	condition	condition	NN
10_1101-2021_01_02_425006	53	26	(	(	-LRB-
10_1101-2021_01_02_425006	53	27	6	6	CD
10_1101-2021_01_02_425006	53	28	)	)	-RRB-
10_1101-2021_01_02_425006	53	29	.	.	.
10_1101-2021_01_02_425006	54	1	Differently	differently	RB
10_1101-2021_01_02_425006	54	2	,	,	,
10_1101-2021_01_02_425006	54	3	the	the	DT
10_1101-2021_01_02_425006	54	4	eluted	elute	VBN
10_1101-2021_01_02_425006	54	5	RNA	RNA	NNP
10_1101-2021_01_02_425006	54	6	was	be	VBD
10_1101-2021_01_02_425006	54	7	enriched	enrich	VBN
10_1101-2021_01_02_425006	54	8	once	once	RB
10_1101-2021_01_02_425006	54	9	85	85	CD
10_1101-2021_01_02_425006	54	10	more	more	RBR
10_1101-2021_01_02_425006	54	11	using	use	VBG
10_1101-2021_01_02_425006	54	12	streptavidin	streptavidin	NNP
10_1101-2021_01_02_425006	54	13	beads	bead	NNS
10_1101-2021_01_02_425006	54	14	to	to	TO
10_1101-2021_01_02_425006	54	15	further	far	RBR
10_1101-2021_01_02_425006	54	16	remove	remove	VB
10_1101-2021_01_02_425006	54	17	processed	process	VBN
10_1101-2021_01_02_425006	54	18	RNA	RNA	NNP
10_1101-2021_01_02_425006	54	19	(	(	-LRB-
10_1101-2021_01_02_425006	54	20	e.g.	e.g.	RB
10_1101-2021_01_02_425006	54	21	,	,	,
10_1101-2021_01_02_425006	54	22	rRNA	rrna	CD
10_1101-2021_01_02_425006	54	23	)	)	-RRB-
10_1101-2021_01_02_425006	54	24	.	.	.
10_1101-2021_01_02_425006	55	1	Subsequently	subsequently	RB
10_1101-2021_01_02_425006	55	2	,	,	,
10_1101-2021_01_02_425006	55	3	the	the	DT
10_1101-2021_01_02_425006	55	4	eluted	elute	VBN
10_1101-2021_01_02_425006	55	5	86	86	CD
10_1101-2021_01_02_425006	55	6	RNA	RNA	NNP
10_1101-2021_01_02_425006	55	7	was	be	VBD
10_1101-2021_01_02_425006	55	8	used	use	VBN
10_1101-2021_01_02_425006	55	9	for	for	IN
10_1101-2021_01_02_425006	55	10	library	library	NN
10_1101-2021_01_02_425006	55	11	preparation	preparation	NN
10_1101-2021_01_02_425006	55	12	using	use	VBG
10_1101-2021_01_02_425006	55	13	NEBNext	nebnext	JJ
10_1101-2021_01_02_425006	55	14	Ultra	Ultra	NNP
10_1101-2021_01_02_425006	55	15	II	II	NNP
10_1101-2021_01_02_425006	55	16	directional	directional	JJ
10_1101-2021_01_02_425006	55	17	RNA	RNA	NNP
10_1101-2021_01_02_425006	55	18	library	library	NN
10_1101-2021_01_02_425006	55	19	prep	prep	NN
10_1101-2021_01_02_425006	55	20	kit	kit	NNP
10_1101-2021_01_02_425006	55	21	(	(	-LRB-
10_1101-2021_01_02_425006	55	22	E7760	E7760	NNP
10_1101-2021_01_02_425006	55	23	)	)	-RRB-
10_1101-2021_01_02_425006	55	24	.	.	.
10_1101-2021_01_02_425006	56	1	87	87	CD
10_1101-2021_01_02_425006	56	2	Sequencing	Sequencing	NNP
10_1101-2021_01_02_425006	56	3	was	be	VBD
10_1101-2021_01_02_425006	56	4	performed	perform	VBN
10_1101-2021_01_02_425006	56	5	on	on	IN
10_1101-2021_01_02_425006	56	6	the	the	DT
10_1101-2021_01_02_425006	56	7	Illumina	Illumina	NNP
10_1101-2021_01_02_425006	56	8	Miseq	Miseq	NNP
10_1101-2021_01_02_425006	56	9	system	system	NN
10_1101-2021_01_02_425006	56	10	(	(	-LRB-
10_1101-2021_01_02_425006	56	11	paired	pair	VBN
10_1101-2021_01_02_425006	56	12	-	-	HYPH
10_1101-2021_01_02_425006	56	13	end	end	NN
10_1101-2021_01_02_425006	56	14	,	,	,
10_1101-2021_01_02_425006	56	15	100bp	100bp	NNP
10_1101-2021_01_02_425006	56	16	)	)	-RRB-
10_1101-2021_01_02_425006	56	17	.	.	.
10_1101-2021_01_02_425006	57	1	All	all	DT
10_1101-2021_01_02_425006	57	2	reads	read	NNS
10_1101-2021_01_02_425006	57	3	were	be	VBD
10_1101-2021_01_02_425006	57	4	mapped	map	VBN
10_1101-2021_01_02_425006	57	5	to	to	IN
10_1101-2021_01_02_425006	57	6	88	88	CD
10_1101-2021_01_02_425006	57	7	the	the	DT
10_1101-2021_01_02_425006	57	8	E.	E.	NNP
10_1101-2021_01_02_425006	57	9	coli	coli	NNS
10_1101-2021_01_02_425006	57	10	genome	genome	NN
10_1101-2021_01_02_425006	57	11	using	use	VBG
10_1101-2021_01_02_425006	57	12	Burrows	Burrows	NNP
10_1101-2021_01_02_425006	57	13	-	-	HYPH
10_1101-2021_01_02_425006	57	14	Wheeler	Wheeler	NNP
10_1101-2021_01_02_425006	57	15	Aligner	Aligner	NNP
10_1101-2021_01_02_425006	57	16	(	(	-LRB-
10_1101-2021_01_02_425006	57	17	BWA	BWA	NNP
10_1101-2021_01_02_425006	57	18	)	)	-RRB-
10_1101-2021_01_02_425006	57	19	with	with	IN
10_1101-2021_01_02_425006	57	20	the	the	DT
10_1101-2021_01_02_425006	57	21	default	default	NN
10_1101-2021_01_02_425006	57	22	parameters	parameter	NNS
10_1101-2021_01_02_425006	57	23	(	(	-LRB-
10_1101-2021_01_02_425006	57	24	31	31	CD
10_1101-2021_01_02_425006	57	25	)	)	-RRB-
10_1101-2021_01_02_425006	57	26	.	.	.
10_1101-2021_01_02_425006	58	1	Read	read	VB
10_1101-2021_01_02_425006	58	2	89	89	CD
10_1101-2021_01_02_425006	58	3	alignment	alignment	NN
10_1101-2021_01_02_425006	58	4	and	and	CC
10_1101-2021_01_02_425006	58	5	other	other	JJ
10_1101-2021_01_02_425006	58	6	computational	computational	JJ
10_1101-2021_01_02_425006	58	7	analyses	analysis	NNS
10_1101-2021_01_02_425006	58	8	were	be	VBD
10_1101-2021_01_02_425006	58	9	carried	carry	VBN
10_1101-2021_01_02_425006	58	10	out	out	RP
10_1101-2021_01_02_425006	58	11	using	use	VBG
10_1101-2021_01_02_425006	58	12	the	the	DT
10_1101-2021_01_02_425006	58	13	E.	E.	NNP
10_1101-2021_01_02_425006	58	14	coli	coli	NNS
10_1101-2021_01_02_425006	58	15	genome	genome	VBP
10_1101-2021_01_02_425006	58	16	NC_000913.3	nc_000913.3	RB
10_1101-2021_01_02_425006	58	17	,	,	,
10_1101-2021_01_02_425006	58	18	90	90	CD
10_1101-2021_01_02_425006	58	19	and	and	CC
10_1101-2021_01_02_425006	58	20	the	the	DT
10_1101-2021_01_02_425006	58	21	corresponding	correspond	VBG
10_1101-2021_01_02_425006	58	22	gene	gene	NN
10_1101-2021_01_02_425006	58	23	annotations	annotation	NNS
10_1101-2021_01_02_425006	58	24	(	(	-LRB-
10_1101-2021_01_02_425006	58	25	GCF_000005845.2_ASM584v2_genomic.gff	GCF_000005845.2_ASM584v2_genomic.gff	NNP
10_1101-2021_01_02_425006	58	26	)	)	-RRB-
10_1101-2021_01_02_425006	58	27	were	be	VBD
10_1101-2021_01_02_425006	58	28	91	91	CD
10_1101-2021_01_02_425006	58	29	downloaded	download	VBN
10_1101-2021_01_02_425006	58	30	from	from	IN
10_1101-2021_01_02_425006	58	31	NCBI	NCBI	NNP
10_1101-2021_01_02_425006	58	32	.	.	.
10_1101-2021_01_02_425006	59	1	Two	two	CD
10_1101-2021_01_02_425006	59	2	experimentally	experimentally	RB
10_1101-2021_01_02_425006	59	3	verified	verify	VBN
10_1101-2021_01_02_425006	59	4	ATU	ATU	NNP
10_1101-2021_01_02_425006	59	5	datasets	dataset	NNS
10_1101-2021_01_02_425006	59	6	,	,	,
10_1101-2021_01_02_425006	59	7	SMRT_M9Enrich	SMRT_M9Enrich	NNP
10_1101-2021_01_02_425006	59	8	and	and	CC
10_1101-2021_01_02_425006	59	9	92	92	CD
10_1101-2021_01_02_425006	59	10	SMRT_RiEnrich	smrt_rienrich	CD
10_1101-2021_01_02_425006	59	11	,	,	,
10_1101-2021_01_02_425006	59	12	were	be	VBD
10_1101-2021_01_02_425006	59	13	used	use	VBN
10_1101-2021_01_02_425006	59	14	as	as	IN
10_1101-2021_01_02_425006	59	15	the	the	DT
10_1101-2021_01_02_425006	59	16	benchmark	benchmark	JJ
10_1101-2021_01_02_425006	59	17	data	datum	NNS
10_1101-2021_01_02_425006	59	18	to	to	TO
10_1101-2021_01_02_425006	59	19	evaluate	evaluate	VB
10_1101-2021_01_02_425006	59	20	the	the	DT
10_1101-2021_01_02_425006	59	21	predicted	predict	VBN
10_1101-2021_01_02_425006	59	22	ATUs	atu	NNS
10_1101-2021_01_02_425006	59	23	,	,	,
10_1101-2021_01_02_425006	59	24	which	which	WDT
10_1101-2021_01_02_425006	59	25	were	be	VBD
10_1101-2021_01_02_425006	59	26	93	93	CD
10_1101-2021_01_02_425006	59	27	.CC	.CC	,
10_1101-2021_01_02_425006	59	28	-	-	HYPH
10_1101-2021_01_02_425006	59	29	BY	by	IN
10_1101-2021_01_02_425006	59	30	-	-	HYPH
10_1101-2021_01_02_425006	59	31	NC	NC	NNP
10_1101-2021_01_02_425006	59	32	-	-	HYPH
10_1101-2021_01_02_425006	59	33	ND	ND	NNP
10_1101-2021_01_02_425006	59	34	4.0	4.0	CD
10_1101-2021_01_02_425006	59	35	International	International	NNP
10_1101-2021_01_02_425006	59	36	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	59	37	under	under	IN
10_1101-2021_01_02_425006	59	38	a	a	DT
10_1101-2021_01_02_425006	59	39	(	(	-LRB-
10_1101-2021_01_02_425006	59	40	which	which	WDT
10_1101-2021_01_02_425006	59	41	was	be	VBD
10_1101-2021_01_02_425006	59	42	not	not	RB
10_1101-2021_01_02_425006	59	43	certified	certify	VBN
10_1101-2021_01_02_425006	59	44	by	by	IN
10_1101-2021_01_02_425006	59	45	peer	peer	NN
10_1101-2021_01_02_425006	59	46	review	review	NN
10_1101-2021_01_02_425006	59	47	)	)	-RRB-
10_1101-2021_01_02_425006	59	48	is	be	VBZ
10_1101-2021_01_02_425006	59	49	the	the	DT
10_1101-2021_01_02_425006	59	50	author	author	NN
10_1101-2021_01_02_425006	59	51	/	/	SYM
10_1101-2021_01_02_425006	59	52	funder	funder	NN
10_1101-2021_01_02_425006	59	53	,	,	,
10_1101-2021_01_02_425006	59	54	who	who	WP
10_1101-2021_01_02_425006	59	55	has	have	VBZ
10_1101-2021_01_02_425006	59	56	granted	grant	VBN
10_1101-2021_01_02_425006	59	57	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	59	58	a	a	DT
10_1101-2021_01_02_425006	59	59	license	license	NN
10_1101-2021_01_02_425006	59	60	to	to	TO
10_1101-2021_01_02_425006	59	61	display	display	VB
10_1101-2021_01_02_425006	59	62	the	the	DT
10_1101-2021_01_02_425006	59	63	preprint	preprint	NN
10_1101-2021_01_02_425006	59	64	in	in	IN
10_1101-2021_01_02_425006	59	65	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	59	66	.	.	.
10_1101-2021_01_02_425006	60	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	60	2	is	be	VBZ
10_1101-2021_01_02_425006	60	3	made	make	VBN
10_1101-2021_01_02_425006	60	4	The	the	DT
10_1101-2021_01_02_425006	60	5	copyright	copyright	NN
10_1101-2021_01_02_425006	60	6	holder	holder	NN
10_1101-2021_01_02_425006	60	7	for	for	IN
10_1101-2021_01_02_425006	60	8	this	this	DT
10_1101-2021_01_02_425006	60	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	60	10	version	version	NN
10_1101-2021_01_02_425006	60	11	posted	post	VBD
10_1101-2021_01_02_425006	60	12	January	January	NNP
10_1101-2021_01_02_425006	60	13	6	6	CD
10_1101-2021_01_02_425006	60	14	,	,	,
10_1101-2021_01_02_425006	60	15	2021	2021	CD
10_1101-2021_01_02_425006	60	16	.	.	.
10_1101-2021_01_02_425006	60	17	;	;	:
10_1101-2021_01_02_425006	60	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	60	19	:	:	:
10_1101-2021_01_02_425006	60	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	60	21	preprint	preprint	NN
10_1101-2021_01_02_425006	60	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	60	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	60	24	6	6	CD
10_1101-2021_01_02_425006	60	25	generated	generate	VBN
10_1101-2021_01_02_425006	60	26	by	by	IN
10_1101-2021_01_02_425006	60	27	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	60	28	-	-	HYPH
10_1101-2021_01_02_425006	60	29	Cappable	cappable	JJ
10_1101-2021_01_02_425006	60	30	-	-	HYPH
10_1101-2021_01_02_425006	60	31	seq	seq	NN
10_1101-2021_01_02_425006	60	32	under	under	IN
10_1101-2021_01_02_425006	60	33	the	the	DT
10_1101-2021_01_02_425006	60	34	same	same	JJ
10_1101-2021_01_02_425006	60	35	conditions	condition	NNS
10_1101-2021_01_02_425006	60	36	as	as	IN
10_1101-2021_01_02_425006	60	37	the	the	DT
10_1101-2021_01_02_425006	60	38	Illumina	Illumina	NNP
10_1101-2021_01_02_425006	60	39	datasets	dataset	VBZ
10_1101-2021_01_02_425006	60	40	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	60	41	94	94	CD
10_1101-2021_01_02_425006	60	42	and	and	CC
10_1101-2021_01_02_425006	60	43	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	60	44	,	,	,
10_1101-2021_01_02_425006	60	45	respectively	respectively	RB
10_1101-2021_01_02_425006	60	46	(	(	-LRB-
10_1101-2021_01_02_425006	60	47	6	6	CD
10_1101-2021_01_02_425006	60	48	)	)	-RRB-
10_1101-2021_01_02_425006	60	49	.	.	.
10_1101-2021_01_02_425006	61	1	In	in	IN
10_1101-2021_01_02_425006	61	2	addition	addition	NN
10_1101-2021_01_02_425006	61	3	,	,	,
10_1101-2021_01_02_425006	61	4	the	the	DT
10_1101-2021_01_02_425006	61	5	ATUs	atu	NNS
10_1101-2021_01_02_425006	61	6	defined	define	VBN
10_1101-2021_01_02_425006	61	7	by	by	IN
10_1101-2021_01_02_425006	61	8	RegulonDB	regulondb	NN
10_1101-2021_01_02_425006	61	9	(	(	-LRB-
10_1101-2021_01_02_425006	61	10	19	19	CD
10_1101-2021_01_02_425006	61	11	)	)	-RRB-
10_1101-2021_01_02_425006	61	12	and	and	CC
10_1101-2021_01_02_425006	61	13	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	61	14	-	-	HYPH
10_1101-2021_01_02_425006	61	15	seq	seq	NNP
10_1101-2021_01_02_425006	61	16	(	(	-LRB-
10_1101-2021_01_02_425006	61	17	7	7	CD
10_1101-2021_01_02_425006	61	18	)	)	-RRB-
10_1101-2021_01_02_425006	61	19	95	95	CD
10_1101-2021_01_02_425006	61	20	were	be	VBD
10_1101-2021_01_02_425006	61	21	also	also	RB
10_1101-2021_01_02_425006	61	22	used	use	VBN
10_1101-2021_01_02_425006	61	23	as	as	IN
10_1101-2021_01_02_425006	61	24	additional	additional	JJ
10_1101-2021_01_02_425006	61	25	evaluation	evaluation	NN
10_1101-2021_01_02_425006	61	26	data	datum	NNS
10_1101-2021_01_02_425006	61	27	in	in	IN
10_1101-2021_01_02_425006	61	28	our	-PRON-	PRP$
10_1101-2021_01_02_425006	61	29	study	study	NN
10_1101-2021_01_02_425006	61	30	.	.	.
10_1101-2021_01_02_425006	62	1	96	96	CD
10_1101-2021_01_02_425006	62	2	Calculation	calculation	NN
10_1101-2021_01_02_425006	62	3	of	of	IN
10_1101-2021_01_02_425006	62	4	the	the	DT
10_1101-2021_01_02_425006	62	5	expression	expression	NN
10_1101-2021_01_02_425006	62	6	values	value	NNS
10_1101-2021_01_02_425006	62	7	of	of	IN
10_1101-2021_01_02_425006	62	8	genetic	genetic	JJ
10_1101-2021_01_02_425006	62	9	and	and	CC
10_1101-2021_01_02_425006	62	10	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	62	11	regions	region	NNS
10_1101-2021_01_02_425006	62	12	97	97	CD
10_1101-2021_01_02_425006	62	13	After	after	IN
10_1101-2021_01_02_425006	62	14	the	the	DT
10_1101-2021_01_02_425006	62	15	RNA	RNA	NNP
10_1101-2021_01_02_425006	62	16	-	-	HYPH
10_1101-2021_01_02_425006	62	17	Seq	Seq	NNP
10_1101-2021_01_02_425006	62	18	reads	read	VBZ
10_1101-2021_01_02_425006	62	19	in	in	IN
10_1101-2021_01_02_425006	62	20	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	62	21	and	and	CC
10_1101-2021_01_02_425006	62	22	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	62	23	were	be	VBD
10_1101-2021_01_02_425006	62	24	mapped	map	VBN
10_1101-2021_01_02_425006	62	25	to	to	IN
10_1101-2021_01_02_425006	62	26	the	the	DT
10_1101-2021_01_02_425006	62	27	E.	E.	NNP
10_1101-2021_01_02_425006	62	28	coli	coli	NNS
10_1101-2021_01_02_425006	62	29	genome	genome	NNP
10_1101-2021_01_02_425006	62	30	using	use	VBG
10_1101-2021_01_02_425006	62	31	98	98	CD
10_1101-2021_01_02_425006	62	32	BWA	BWA	NNP
10_1101-2021_01_02_425006	62	33	,	,	,
10_1101-2021_01_02_425006	62	34	we	-PRON-	PRP
10_1101-2021_01_02_425006	62	35	determined	determine	VBD
10_1101-2021_01_02_425006	62	36	the	the	DT
10_1101-2021_01_02_425006	62	37	number	number	NN
10_1101-2021_01_02_425006	62	38	of	of	IN
10_1101-2021_01_02_425006	62	39	reads	read	NNS
10_1101-2021_01_02_425006	62	40	�	�	.
10_1101-2021_01_02_425006	62	41	(	(	-LRB-
10_1101-2021_01_02_425006	62	42	�	�	NNP
10_1101-2021_01_02_425006	62	43	)	)	-RRB-
10_1101-2021_01_02_425006	62	44	covering	cover	VBG
10_1101-2021_01_02_425006	62	45	each	each	DT
10_1101-2021_01_02_425006	62	46	genomic	genomic	JJ
10_1101-2021_01_02_425006	62	47	position	position	NN
10_1101-2021_01_02_425006	62	48	�	�	NNP
10_1101-2021_01_02_425006	62	49	.	.	.
10_1101-2021_01_02_425006	63	1	Suppose	suppose	VB
10_1101-2021_01_02_425006	63	2	that	that	IN
10_1101-2021_01_02_425006	63	3	�	�	NNP
10_1101-2021_01_02_425006	63	4	�	�	NNP
10_1101-2021_01_02_425006	63	5	99	99	CD
10_1101-2021_01_02_425006	63	6	and	and	CC
10_1101-2021_01_02_425006	63	7	�	�	NNP
10_1101-2021_01_02_425006	63	8	�	�	NNP
10_1101-2021_01_02_425006	63	9	�	�	NNS
10_1101-2021_01_02_425006	63	10	�	�	NNS
10_1101-2021_01_02_425006	63	11	are	be	VBP
10_1101-2021_01_02_425006	63	12	two	two	CD
10_1101-2021_01_02_425006	63	13	consecutive	consecutive	JJ
10_1101-2021_01_02_425006	63	14	genes	gene	NNS
10_1101-2021_01_02_425006	63	15	on	on	IN
10_1101-2021_01_02_425006	63	16	the	the	DT
10_1101-2021_01_02_425006	63	17	same	same	JJ
10_1101-2021_01_02_425006	63	18	strand	strand	NN
10_1101-2021_01_02_425006	63	19	;	;	:
10_1101-2021_01_02_425006	63	20	we	-PRON-	PRP
10_1101-2021_01_02_425006	63	21	denote	denote	VBP
10_1101-2021_01_02_425006	63	22	the	the	DT
10_1101-2021_01_02_425006	63	23	expression	expression	NN
10_1101-2021_01_02_425006	63	24	value	value	NN
10_1101-2021_01_02_425006	63	25	of	of	IN
10_1101-2021_01_02_425006	63	26	�	�	NNP
10_1101-2021_01_02_425006	63	27	�	�	NNP
10_1101-2021_01_02_425006	63	28	as	as	IN
10_1101-2021_01_02_425006	63	29	�	�	NNP
10_1101-2021_01_02_425006	63	30	�	�	NNP
10_1101-2021_01_02_425006	63	31	100	100	CD
10_1101-2021_01_02_425006	63	32	and	and	CC
10_1101-2021_01_02_425006	63	33	the	the	DT
10_1101-2021_01_02_425006	63	34	expression	expression	NN
10_1101-2021_01_02_425006	63	35	value	value	NN
10_1101-2021_01_02_425006	63	36	of	of	IN
10_1101-2021_01_02_425006	63	37	the	the	DT
10_1101-2021_01_02_425006	63	38	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	63	39	region	region	NN
10_1101-2021_01_02_425006	63	40	between	between	IN
10_1101-2021_01_02_425006	63	41	genes	gene	NNS
10_1101-2021_01_02_425006	63	42	�	�	NNPS
10_1101-2021_01_02_425006	63	43	�	�	NNP
10_1101-2021_01_02_425006	63	44	and	and	CC
10_1101-2021_01_02_425006	63	45	�	�	NNP
10_1101-2021_01_02_425006	63	46	�	�	NNP
10_1101-2021_01_02_425006	63	47	�	�	NNS
10_1101-2021_01_02_425006	63	48	�	�	,
10_1101-2021_01_02_425006	63	49	as	as	IN
10_1101-2021_01_02_425006	63	50	�	�	NNP
10_1101-2021_01_02_425006	63	51	�	�	NNP
10_1101-2021_01_02_425006	63	52	,	,	,
10_1101-2021_01_02_425006	63	53	�	�	NNP
10_1101-2021_01_02_425006	63	54	�	�	NNP
10_1101-2021_01_02_425006	63	55	�	�	NNP
10_1101-2021_01_02_425006	63	56	.	.	.
10_1101-2021_01_02_425006	64	1	Then	then	RB
10_1101-2021_01_02_425006	64	2	,	,	,
10_1101-2021_01_02_425006	64	3	the	the	DT
10_1101-2021_01_02_425006	64	4	101	101	CD
10_1101-2021_01_02_425006	64	5	calculation	calculation	NN
10_1101-2021_01_02_425006	64	6	of	of	IN
10_1101-2021_01_02_425006	64	7	�	�	NNP
10_1101-2021_01_02_425006	64	8	�	�	NNP
10_1101-2021_01_02_425006	64	9	and	and	CC
10_1101-2021_01_02_425006	64	10	�	�	NNP
10_1101-2021_01_02_425006	64	11	�	�	NNP
10_1101-2021_01_02_425006	64	12	,	,	,
10_1101-2021_01_02_425006	64	13	�	�	NNP
10_1101-2021_01_02_425006	64	14	�	�	NNP
10_1101-2021_01_02_425006	64	15	�	�	NNP
10_1101-2021_01_02_425006	64	16	is	be	VBZ
10_1101-2021_01_02_425006	64	17	given	give	VBN
10_1101-2021_01_02_425006	64	18	by	by	IN
10_1101-2021_01_02_425006	64	19	:	:	:
10_1101-2021_01_02_425006	64	20	102	102	CD
10_1101-2021_01_02_425006	64	21	�	�	NNS
10_1101-2021_01_02_425006	64	22	�	�	ADD
10_1101-2021_01_02_425006	64	23	=	=	NFP
10_1101-2021_01_02_425006	64	24	∑	∑	.
10_1101-2021_01_02_425006	64	25	�	�	NNP
10_1101-2021_01_02_425006	64	26	(	(	-LRB-
10_1101-2021_01_02_425006	64	27	�	�	NNP
10_1101-2021_01_02_425006	64	28	)	)	-RRB-
10_1101-2021_01_02_425006	64	29	�	�	VBZ
10_1101-2021_01_02_425006	64	30	∈	∈	JJ
10_1101-2021_01_02_425006	64	31	�	�	NNS
10_1101-2021_01_02_425006	64	32	�	�	JJ
10_1101-2021_01_02_425006	64	33	|	|	NNP
10_1101-2021_01_02_425006	64	34	�	�	NNP
10_1101-2021_01_02_425006	64	35	�	�	NNP
10_1101-2021_01_02_425006	64	36	|	|	NNS
10_1101-2021_01_02_425006	64	37	(	(	-LRB-
10_1101-2021_01_02_425006	64	38	1	1	CD
10_1101-2021_01_02_425006	64	39	)	)	-RRB-
10_1101-2021_01_02_425006	64	40	�	�	NNP
10_1101-2021_01_02_425006	64	41	�	�	NNP
10_1101-2021_01_02_425006	64	42	,	,	,
10_1101-2021_01_02_425006	64	43	�	�	NNP
10_1101-2021_01_02_425006	64	44	�	�	NNP
10_1101-2021_01_02_425006	64	45	�	�	NNP
10_1101-2021_01_02_425006	64	46	=	=	SYM
10_1101-2021_01_02_425006	64	47	∑	∑	.
10_1101-2021_01_02_425006	64	48	�	�	NNP
10_1101-2021_01_02_425006	64	49	(	(	-LRB-
10_1101-2021_01_02_425006	64	50	�	�	NNP
10_1101-2021_01_02_425006	64	51	)	)	-RRB-
10_1101-2021_01_02_425006	64	52	�	�	VBZ
10_1101-2021_01_02_425006	64	53	∈	∈	JJ
10_1101-2021_01_02_425006	64	54	�	�	NNS
10_1101-2021_01_02_425006	64	55	�	�	NNS
10_1101-2021_01_02_425006	64	56	,	,	,
10_1101-2021_01_02_425006	64	57	�	�	NNP
10_1101-2021_01_02_425006	64	58	�	�	NNP
10_1101-2021_01_02_425006	64	59	�	�	JJ
10_1101-2021_01_02_425006	64	60	|	|	NNP
10_1101-2021_01_02_425006	64	61	�	�	NNP
10_1101-2021_01_02_425006	64	62	�	�	NNP
10_1101-2021_01_02_425006	64	63	,	,	,
10_1101-2021_01_02_425006	64	64	�	�	NNP
10_1101-2021_01_02_425006	64	65	�	�	NNP
10_1101-2021_01_02_425006	64	66	�	�	NNS
10_1101-2021_01_02_425006	64	67	|	|	NN
10_1101-2021_01_02_425006	64	68	(	(	-LRB-
10_1101-2021_01_02_425006	64	69	2	2	CD
10_1101-2021_01_02_425006	64	70	)	)	-RRB-
10_1101-2021_01_02_425006	64	71	where	where	WRB
10_1101-2021_01_02_425006	64	72	�	�	.
10_1101-2021_01_02_425006	64	73	∈	∈	IN
10_1101-2021_01_02_425006	64	74	�	�	NNS
10_1101-2021_01_02_425006	64	75	�	�	NNP
10_1101-2021_01_02_425006	64	76	denotes	denote	VBZ
10_1101-2021_01_02_425006	64	77	that	that	IN
10_1101-2021_01_02_425006	64	78	genomic	genomic	JJ
10_1101-2021_01_02_425006	64	79	position	position	NN
10_1101-2021_01_02_425006	64	80	�	�	NNP
10_1101-2021_01_02_425006	64	81	is	be	VBZ
10_1101-2021_01_02_425006	64	82	on	on	IN
10_1101-2021_01_02_425006	64	83	the	the	DT
10_1101-2021_01_02_425006	64	84	gene	gene	NN
10_1101-2021_01_02_425006	64	85	�	�	NNP
10_1101-2021_01_02_425006	64	86	�	�	NNP
10_1101-2021_01_02_425006	64	87	and	and	CC
10_1101-2021_01_02_425006	64	88	|	|	NNP
10_1101-2021_01_02_425006	64	89	�	�	NNP
10_1101-2021_01_02_425006	64	90	�	�	NNP
10_1101-2021_01_02_425006	64	91	|	|	NNP
10_1101-2021_01_02_425006	64	92	denotes	denote	VBZ
10_1101-2021_01_02_425006	64	93	the	the	DT
10_1101-2021_01_02_425006	64	94	genomic	genomic	JJ
10_1101-2021_01_02_425006	64	95	103	103	CD
10_1101-2021_01_02_425006	64	96	length	length	NN
10_1101-2021_01_02_425006	64	97	of	of	IN
10_1101-2021_01_02_425006	64	98	�	�	NNP
10_1101-2021_01_02_425006	64	99	�	�	NNP
10_1101-2021_01_02_425006	64	100	.	.	.
10_1101-2021_01_02_425006	65	1	104	104	CD
10_1101-2021_01_02_425006	65	2	Modeling	model	VBG
10_1101-2021_01_02_425006	65	3	non	non	JJ
10_1101-2021_01_02_425006	65	4	-	-	JJ
10_1101-2021_01_02_425006	65	5	uniform	uniform	JJ
10_1101-2021_01_02_425006	65	6	read	read	VBD
10_1101-2021_01_02_425006	65	7	distribution	distribution	NN
10_1101-2021_01_02_425006	65	8	along	along	IN
10_1101-2021_01_02_425006	65	9	mRNA	mRNA	NNP
10_1101-2021_01_02_425006	65	10	transcripts	transcript	NNS
10_1101-2021_01_02_425006	65	11	105	105	CD
10_1101-2021_01_02_425006	65	12	We	-PRON-	PRP
10_1101-2021_01_02_425006	65	13	introduced	introduce	VBD
10_1101-2021_01_02_425006	65	14	the	the	DT
10_1101-2021_01_02_425006	65	15	bias	bias	NN
10_1101-2021_01_02_425006	65	16	rate	rate	NN
10_1101-2021_01_02_425006	65	17	function	function	NN
10_1101-2021_01_02_425006	65	18	,	,	,
10_1101-2021_01_02_425006	65	19	which	which	WDT
10_1101-2021_01_02_425006	65	20	is	be	VBZ
10_1101-2021_01_02_425006	65	21	similar	similar	JJ
10_1101-2021_01_02_425006	65	22	to	to	IN
10_1101-2021_01_02_425006	65	23	the	the	DT
10_1101-2021_01_02_425006	65	24	bias	bias	NN
10_1101-2021_01_02_425006	65	25	curves	curve	NNS
10_1101-2021_01_02_425006	65	26	in	in	IN
10_1101-2021_01_02_425006	65	27	the	the	DT
10_1101-2021_01_02_425006	65	28	work	work	NN
10_1101-2021_01_02_425006	65	29	of	of	IN
10_1101-2021_01_02_425006	65	30	Wu	Wu	NNP
10_1101-2021_01_02_425006	65	31	et	et	NNP
10_1101-2021_01_02_425006	65	32	al	al	NNP
10_1101-2021_01_02_425006	65	33	.	.	.
10_1101-2021_01_02_425006	66	1	(	(	-LRB-
10_1101-2021_01_02_425006	66	2	32	32	CD
10_1101-2021_01_02_425006	66	3	)	)	-RRB-
10_1101-2021_01_02_425006	66	4	,	,	,
10_1101-2021_01_02_425006	66	5	to	to	IN
10_1101-2021_01_02_425006	66	6	106	106	CD
10_1101-2021_01_02_425006	66	7	address	address	NN
10_1101-2021_01_02_425006	66	8	the	the	DT
10_1101-2021_01_02_425006	66	9	non	non	JJ
10_1101-2021_01_02_425006	66	10	-	-	JJ
10_1101-2021_01_02_425006	66	11	uniform	uniform	JJ
10_1101-2021_01_02_425006	66	12	distribution	distribution	NN
10_1101-2021_01_02_425006	66	13	of	of	IN
10_1101-2021_01_02_425006	66	14	the	the	DT
10_1101-2021_01_02_425006	66	15	RNA	RNA	NNP
10_1101-2021_01_02_425006	66	16	-	-	HYPH
10_1101-2021_01_02_425006	66	17	Seq	Seq	NNP
10_1101-2021_01_02_425006	66	18	reads	read	VBZ
10_1101-2021_01_02_425006	66	19	along	along	IN
10_1101-2021_01_02_425006	66	20	mRNA	mRNA	NNP
10_1101-2021_01_02_425006	66	21	transcripts	transcript	NNS
10_1101-2021_01_02_425006	66	22	(	(	-LRB-
10_1101-2021_01_02_425006	66	23	32	32	CD
10_1101-2021_01_02_425006	66	24	-	-	SYM
10_1101-2021_01_02_425006	66	25	35	35	CD
10_1101-2021_01_02_425006	66	26	)	)	-RRB-
10_1101-2021_01_02_425006	66	27	.	.	.
10_1101-2021_01_02_425006	67	1	The	the	DT
10_1101-2021_01_02_425006	67	2	bias	bias	NN
10_1101-2021_01_02_425006	67	3	107	107	CD
10_1101-2021_01_02_425006	67	4	function	function	NN
10_1101-2021_01_02_425006	67	5	reflects	reflect	VBZ
10_1101-2021_01_02_425006	67	6	the	the	DT
10_1101-2021_01_02_425006	67	7	relative	relative	JJ
10_1101-2021_01_02_425006	67	8	read	read	VBP
10_1101-2021_01_02_425006	67	9	distribution	distribution	NN
10_1101-2021_01_02_425006	67	10	bias	bias	NN
10_1101-2021_01_02_425006	67	11	from	from	IN
10_1101-2021_01_02_425006	67	12	the	the	DT
10_1101-2021_01_02_425006	67	13	3	3	CD
10_1101-2021_01_02_425006	67	14	’	'	''
10_1101-2021_01_02_425006	67	15	end	end	NN
10_1101-2021_01_02_425006	67	16	to	to	IN
10_1101-2021_01_02_425006	67	17	the	the	DT
10_1101-2021_01_02_425006	67	18	5	5	CD
10_1101-2021_01_02_425006	67	19	’	'	''
10_1101-2021_01_02_425006	67	20	end	end	NN
10_1101-2021_01_02_425006	67	21	of	of	IN
10_1101-2021_01_02_425006	67	22	an	an	DT
10_1101-2021_01_02_425006	67	23	mRNA	mrna	NN
10_1101-2021_01_02_425006	67	24	transcript	transcript	NN
10_1101-2021_01_02_425006	67	25	.	.	.
10_1101-2021_01_02_425006	68	1	108	108	CD
10_1101-2021_01_02_425006	68	2	.CC	.CC	:
10_1101-2021_01_02_425006	68	3	-	-	HYPH
10_1101-2021_01_02_425006	68	4	BY	by	IN
10_1101-2021_01_02_425006	68	5	-	-	HYPH
10_1101-2021_01_02_425006	68	6	NC	NC	NNP
10_1101-2021_01_02_425006	68	7	-	-	HYPH
10_1101-2021_01_02_425006	68	8	ND	ND	NNP
10_1101-2021_01_02_425006	68	9	4.0	4.0	CD
10_1101-2021_01_02_425006	68	10	International	International	NNP
10_1101-2021_01_02_425006	68	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	68	12	under	under	IN
10_1101-2021_01_02_425006	68	13	a	a	DT
10_1101-2021_01_02_425006	68	14	(	(	-LRB-
10_1101-2021_01_02_425006	68	15	which	which	WDT
10_1101-2021_01_02_425006	68	16	was	be	VBD
10_1101-2021_01_02_425006	68	17	not	not	RB
10_1101-2021_01_02_425006	68	18	certified	certify	VBN
10_1101-2021_01_02_425006	68	19	by	by	IN
10_1101-2021_01_02_425006	68	20	peer	peer	NN
10_1101-2021_01_02_425006	68	21	review	review	NN
10_1101-2021_01_02_425006	68	22	)	)	-RRB-
10_1101-2021_01_02_425006	68	23	is	be	VBZ
10_1101-2021_01_02_425006	68	24	the	the	DT
10_1101-2021_01_02_425006	68	25	author	author	NN
10_1101-2021_01_02_425006	68	26	/	/	SYM
10_1101-2021_01_02_425006	68	27	funder	funder	NN
10_1101-2021_01_02_425006	68	28	,	,	,
10_1101-2021_01_02_425006	68	29	who	who	WP
10_1101-2021_01_02_425006	68	30	has	have	VBZ
10_1101-2021_01_02_425006	68	31	granted	grant	VBN
10_1101-2021_01_02_425006	68	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	68	33	a	a	DT
10_1101-2021_01_02_425006	68	34	license	license	NN
10_1101-2021_01_02_425006	68	35	to	to	TO
10_1101-2021_01_02_425006	68	36	display	display	VB
10_1101-2021_01_02_425006	68	37	the	the	DT
10_1101-2021_01_02_425006	68	38	preprint	preprint	NN
10_1101-2021_01_02_425006	68	39	in	in	IN
10_1101-2021_01_02_425006	68	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	68	41	.	.	.
10_1101-2021_01_02_425006	69	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	69	2	is	be	VBZ
10_1101-2021_01_02_425006	69	3	made	make	VBN
10_1101-2021_01_02_425006	69	4	The	the	DT
10_1101-2021_01_02_425006	69	5	copyright	copyright	NN
10_1101-2021_01_02_425006	69	6	holder	holder	NN
10_1101-2021_01_02_425006	69	7	for	for	IN
10_1101-2021_01_02_425006	69	8	this	this	DT
10_1101-2021_01_02_425006	69	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	69	10	version	version	NN
10_1101-2021_01_02_425006	69	11	posted	post	VBD
10_1101-2021_01_02_425006	69	12	January	January	NNP
10_1101-2021_01_02_425006	69	13	6	6	CD
10_1101-2021_01_02_425006	69	14	,	,	,
10_1101-2021_01_02_425006	69	15	2021	2021	CD
10_1101-2021_01_02_425006	69	16	.	.	.
10_1101-2021_01_02_425006	69	17	;	;	:
10_1101-2021_01_02_425006	69	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	69	19	:	:	:
10_1101-2021_01_02_425006	69	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	69	21	preprint	preprint	NN
10_1101-2021_01_02_425006	69	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	69	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	69	24	7	7	CD
10_1101-2021_01_02_425006	69	25	We	-PRON-	PRP
10_1101-2021_01_02_425006	69	26	assumed	assume	VBD
10_1101-2021_01_02_425006	69	27	that	that	IN
10_1101-2021_01_02_425006	69	28	the	the	DT
10_1101-2021_01_02_425006	69	29	maximum	maximum	JJ
10_1101-2021_01_02_425006	69	30	read	read	JJ
10_1101-2021_01_02_425006	69	31	coverage	coverage	NN
10_1101-2021_01_02_425006	69	32	of	of	IN
10_1101-2021_01_02_425006	69	33	all	all	PDT
10_1101-2021_01_02_425006	69	34	the	the	DT
10_1101-2021_01_02_425006	69	35	genomic	genomic	JJ
10_1101-2021_01_02_425006	69	36	positions	position	NNS
10_1101-2021_01_02_425006	69	37	of	of	IN
10_1101-2021_01_02_425006	69	38	an	an	DT
10_1101-2021_01_02_425006	69	39	mRNA	mrna	NN
10_1101-2021_01_02_425006	69	40	transcript	transcript	NN
10_1101-2021_01_02_425006	69	41	is	be	VBZ
10_1101-2021_01_02_425006	69	42	the	the	DT
10_1101-2021_01_02_425006	69	43	109	109	CD
10_1101-2021_01_02_425006	69	44	expression	expression	NN
10_1101-2021_01_02_425006	69	45	level	level	NN
10_1101-2021_01_02_425006	69	46	without	without	IN
10_1101-2021_01_02_425006	69	47	bias	bias	NN
10_1101-2021_01_02_425006	69	48	.	.	.
10_1101-2021_01_02_425006	70	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	70	2	is	be	VBZ
10_1101-2021_01_02_425006	70	3	noteworthy	noteworthy	JJ
10_1101-2021_01_02_425006	70	4	that	that	IN
10_1101-2021_01_02_425006	70	5	a	a	DT
10_1101-2021_01_02_425006	70	6	single	single	JJ
10_1101-2021_01_02_425006	70	7	gene	gene	NN
10_1101-2021_01_02_425006	70	8	mRNA	mrna	NN
10_1101-2021_01_02_425006	70	9	transcript	transcript	NN
10_1101-2021_01_02_425006	70	10	with	with	IN
10_1101-2021_01_02_425006	70	11	no	no	DT
10_1101-2021_01_02_425006	70	12	shared	shared	JJ
10_1101-2021_01_02_425006	70	13	gene	gene	NN
10_1101-2021_01_02_425006	70	14	110	110	CD
10_1101-2021_01_02_425006	70	15	among	among	IN
10_1101-2021_01_02_425006	70	16	different	different	JJ
10_1101-2021_01_02_425006	70	17	mRNA	mRNA	NNS
10_1101-2021_01_02_425006	70	18	transcripts	transcript	NNS
10_1101-2021_01_02_425006	70	19	can	can	MD
10_1101-2021_01_02_425006	70	20	serve	serve	VB
10_1101-2021_01_02_425006	70	21	as	as	IN
10_1101-2021_01_02_425006	70	22	the	the	DT
10_1101-2021_01_02_425006	70	23	ideal	ideal	JJ
10_1101-2021_01_02_425006	70	24	template	template	NN
10_1101-2021_01_02_425006	70	25	for	for	IN
10_1101-2021_01_02_425006	70	26	modeling	model	VBG
10_1101-2021_01_02_425006	70	27	non	non	JJ
10_1101-2021_01_02_425006	70	28	-	-	JJ
10_1101-2021_01_02_425006	70	29	uniform	uniform	JJ
10_1101-2021_01_02_425006	70	30	read	read	VBD
10_1101-2021_01_02_425006	70	31	111	111	CD
10_1101-2021_01_02_425006	70	32	distribution	distribution	NN
10_1101-2021_01_02_425006	70	33	along	along	IN
10_1101-2021_01_02_425006	70	34	mRNA	mRNA	NNP
10_1101-2021_01_02_425006	70	35	transcripts	transcript	NNS
10_1101-2021_01_02_425006	70	36	.	.	.
10_1101-2021_01_02_425006	71	1	The	the	DT
10_1101-2021_01_02_425006	71	2	specific	specific	JJ
10_1101-2021_01_02_425006	71	3	steps	step	NNS
10_1101-2021_01_02_425006	71	4	of	of	IN
10_1101-2021_01_02_425006	71	5	modeling	model	VBG
10_1101-2021_01_02_425006	71	6	non	non	JJ
10_1101-2021_01_02_425006	71	7	-	-	JJ
10_1101-2021_01_02_425006	71	8	uniform	uniform	JJ
10_1101-2021_01_02_425006	71	9	read	read	NN
10_1101-2021_01_02_425006	71	10	distribution	distribution	NN
10_1101-2021_01_02_425006	71	11	are	be	VBP
10_1101-2021_01_02_425006	71	12	112	112	CD
10_1101-2021_01_02_425006	71	13	detailed	detail	VBN
10_1101-2021_01_02_425006	71	14	as	as	IN
10_1101-2021_01_02_425006	71	15	follows	follow	VBZ
10_1101-2021_01_02_425006	71	16	:	:	:
10_1101-2021_01_02_425006	71	17	113	113	CD
10_1101-2021_01_02_425006	71	18	Step	step	NN
10_1101-2021_01_02_425006	71	19	1	1	CD
10_1101-2021_01_02_425006	71	20	:	:	:
10_1101-2021_01_02_425006	71	21	Single	single	JJ
10_1101-2021_01_02_425006	71	22	Gene	gene	NN
10_1101-2021_01_02_425006	71	23	mRNA	mrna	NN
10_1101-2021_01_02_425006	71	24	Transcript	Transcript	NNP
10_1101-2021_01_02_425006	71	25	Selection	Selection	NNP
10_1101-2021_01_02_425006	71	26	.	.	.
10_1101-2021_01_02_425006	72	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	72	2	selected	select	VBD
10_1101-2021_01_02_425006	72	3	single	single	JJ
10_1101-2021_01_02_425006	72	4	gene	gene	NN
10_1101-2021_01_02_425006	72	5	mRNA	mrna	NN
10_1101-2021_01_02_425006	72	6	transcripts	transcript	NNS
10_1101-2021_01_02_425006	72	7	from	from	IN
10_1101-2021_01_02_425006	72	8	the	the	DT
10_1101-2021_01_02_425006	72	9	114	114	CD
10_1101-2021_01_02_425006	72	10	evaluation	evaluation	NN
10_1101-2021_01_02_425006	72	11	data	datum	NNS
10_1101-2021_01_02_425006	72	12	and	and	CC
10_1101-2021_01_02_425006	72	13	plotted	plot	VBD
10_1101-2021_01_02_425006	72	14	their	-PRON-	PRP$
10_1101-2021_01_02_425006	72	15	expression	expression	NN
10_1101-2021_01_02_425006	72	16	distributions	distribution	NNS
10_1101-2021_01_02_425006	72	17	.	.	.
10_1101-2021_01_02_425006	73	1	Specifically	specifically	RB
10_1101-2021_01_02_425006	73	2	,	,	,
10_1101-2021_01_02_425006	73	3	12	12	CD
10_1101-2021_01_02_425006	73	4	groups	group	NNS
10_1101-2021_01_02_425006	73	5	of	of	IN
10_1101-2021_01_02_425006	73	6	single	single	JJ
10_1101-2021_01_02_425006	73	7	gene	gene	NN
10_1101-2021_01_02_425006	73	8	mRNA	mrna	CD
10_1101-2021_01_02_425006	73	9	115	115	CD
10_1101-2021_01_02_425006	73	10	transcripts	transcript	NNS
10_1101-2021_01_02_425006	73	11	with	with	IN
10_1101-2021_01_02_425006	73	12	lengths	length	NNS
10_1101-2021_01_02_425006	73	13	ranging	range	VBG
10_1101-2021_01_02_425006	73	14	from	from	IN
10_1101-2021_01_02_425006	73	15	300	300	CD
10_1101-2021_01_02_425006	73	16	to	to	IN
10_1101-2021_01_02_425006	73	17	1,500	1,500	CD
10_1101-2021_01_02_425006	73	18	bp	bp	NN
10_1101-2021_01_02_425006	73	19	were	be	VBD
10_1101-2021_01_02_425006	73	20	selected	select	VBN
10_1101-2021_01_02_425006	73	21	from	from	IN
10_1101-2021_01_02_425006	73	22	the	the	DT
10_1101-2021_01_02_425006	73	23	evaluation	evaluation	NN
10_1101-2021_01_02_425006	73	24	data	datum	NNS
10_1101-2021_01_02_425006	73	25	(	(	-LRB-
10_1101-2021_01_02_425006	73	26	more	more	JJR
10_1101-2021_01_02_425006	73	27	116	116	CD
10_1101-2021_01_02_425006	73	28	details	detail	NNS
10_1101-2021_01_02_425006	73	29	are	be	VBP
10_1101-2021_01_02_425006	73	30	given	give	VBN
10_1101-2021_01_02_425006	73	31	in	in	IN
10_1101-2021_01_02_425006	73	32	method	method	NN
10_1101-2021_01_02_425006	73	33	S1	S1	NNP
10_1101-2021_01_02_425006	73	34	)	)	-RRB-
10_1101-2021_01_02_425006	73	35	,	,	,
10_1101-2021_01_02_425006	73	36	and	and	CC
10_1101-2021_01_02_425006	73	37	each	each	DT
10_1101-2021_01_02_425006	73	38	group	group	NN
10_1101-2021_01_02_425006	73	39	had	have	VBD
10_1101-2021_01_02_425006	73	40	ten	ten	CD
10_1101-2021_01_02_425006	73	41	randomly	randomly	RB
10_1101-2021_01_02_425006	73	42	chosen	choose	VBN
10_1101-2021_01_02_425006	73	43	mRNA	mRNA	NNS
10_1101-2021_01_02_425006	73	44	transcripts	transcript	NNS
10_1101-2021_01_02_425006	73	45	.	.	.
10_1101-2021_01_02_425006	74	1	Apparent	apparent	JJ
10_1101-2021_01_02_425006	74	2	117	117	CD
10_1101-2021_01_02_425006	74	3	decline	decline	NN
10_1101-2021_01_02_425006	74	4	trends	trend	NNS
10_1101-2021_01_02_425006	74	5	appeared	appear	VBD
10_1101-2021_01_02_425006	74	6	in	in	IN
10_1101-2021_01_02_425006	74	7	the	the	DT
10_1101-2021_01_02_425006	74	8	single	single	JJ
10_1101-2021_01_02_425006	74	9	gene	gene	NN
10_1101-2021_01_02_425006	74	10	mRNA	mrna	NN
10_1101-2021_01_02_425006	74	11	transcripts	transcript	NNS
10_1101-2021_01_02_425006	74	12	with	with	IN
10_1101-2021_01_02_425006	74	13	long	long	JJ
10_1101-2021_01_02_425006	74	14	lengths	length	NNS
10_1101-2021_01_02_425006	74	15	,	,	,
10_1101-2021_01_02_425006	74	16	ranging	range	VBG
10_1101-2021_01_02_425006	74	17	from	from	IN
10_1101-2021_01_02_425006	74	18	1,100	1,100	CD
10_1101-2021_01_02_425006	74	19	to	to	TO
10_1101-2021_01_02_425006	74	20	118	118	CD
10_1101-2021_01_02_425006	74	21	1,500	1,500	CD
10_1101-2021_01_02_425006	74	22	bp	bp	NNS
10_1101-2021_01_02_425006	74	23	(	(	-LRB-
10_1101-2021_01_02_425006	74	24	fig	fig	NN
10_1101-2021_01_02_425006	74	25	.	.	.
10_1101-2021_01_02_425006	75	1	S2	s2	NN
10_1101-2021_01_02_425006	75	2	)	)	-RRB-
10_1101-2021_01_02_425006	75	3	.	.	.
10_1101-2021_01_02_425006	76	1	The	the	DT
10_1101-2021_01_02_425006	76	2	reason	reason	NN
10_1101-2021_01_02_425006	76	3	for	for	IN
10_1101-2021_01_02_425006	76	4	this	this	DT
10_1101-2021_01_02_425006	76	5	phenomenon	phenomenon	NN
10_1101-2021_01_02_425006	76	6	may	may	MD
10_1101-2021_01_02_425006	76	7	be	be	VB
10_1101-2021_01_02_425006	76	8	that	that	IN
10_1101-2021_01_02_425006	76	9	the	the	DT
10_1101-2021_01_02_425006	76	10	incomplete	incomplete	JJ
10_1101-2021_01_02_425006	76	11	transcription	transcription	NN
10_1101-2021_01_02_425006	76	12	and	and	CC
10_1101-2021_01_02_425006	76	13	3	3	CD
10_1101-2021_01_02_425006	76	14	’	'	''
10_1101-2021_01_02_425006	76	15	end	end	VB
10_1101-2021_01_02_425006	76	16	119	119	CD
10_1101-2021_01_02_425006	76	17	degradation	degradation	NN
10_1101-2021_01_02_425006	76	18	or	or	CC
10_1101-2021_01_02_425006	76	19	processing	processing	NN
10_1101-2021_01_02_425006	76	20	induce	induce	VBP
10_1101-2021_01_02_425006	76	21	the	the	DT
10_1101-2021_01_02_425006	76	22	enrichment	enrichment	NN
10_1101-2021_01_02_425006	76	23	of	of	IN
10_1101-2021_01_02_425006	76	24	signal	signal	NN
10_1101-2021_01_02_425006	76	25	at	at	IN
10_1101-2021_01_02_425006	76	26	5	5	CD
10_1101-2021_01_02_425006	76	27	’	'	''
10_1101-2021_01_02_425006	76	28	end	end	NN
10_1101-2021_01_02_425006	76	29	of	of	IN
10_1101-2021_01_02_425006	76	30	the	the	DT
10_1101-2021_01_02_425006	76	31	mRNA	mrna	NN
10_1101-2021_01_02_425006	76	32	transcripts	transcript	NNS
10_1101-2021_01_02_425006	76	33	with	with	IN
10_1101-2021_01_02_425006	76	34	long	long	JJ
10_1101-2021_01_02_425006	76	35	120	120	CD
10_1101-2021_01_02_425006	76	36	lengths	length	NNS
10_1101-2021_01_02_425006	76	37	(	(	-LRB-
10_1101-2021_01_02_425006	76	38	36	36	CD
10_1101-2021_01_02_425006	76	39	,	,	,
10_1101-2021_01_02_425006	76	40	37	37	CD
10_1101-2021_01_02_425006	76	41	)	)	-RRB-
10_1101-2021_01_02_425006	76	42	.	.	.
10_1101-2021_01_02_425006	77	1	Finally	finally	RB
10_1101-2021_01_02_425006	77	2	,	,	,
10_1101-2021_01_02_425006	77	3	we	-PRON-	PRP
10_1101-2021_01_02_425006	77	4	plotted	plot	VBD
10_1101-2021_01_02_425006	77	5	the	the	DT
10_1101-2021_01_02_425006	77	6	expression	expression	NN
10_1101-2021_01_02_425006	77	7	distribution	distribution	NN
10_1101-2021_01_02_425006	77	8	of	of	IN
10_1101-2021_01_02_425006	77	9	single	single	JJ
10_1101-2021_01_02_425006	77	10	gene	gene	NN
10_1101-2021_01_02_425006	77	11	mRNA	mrna	NN
10_1101-2021_01_02_425006	77	12	transcripts	transcript	NNS
10_1101-2021_01_02_425006	77	13	with	with	IN
10_1101-2021_01_02_425006	77	14	121	121	CD
10_1101-2021_01_02_425006	77	15	lengths	length	NNS
10_1101-2021_01_02_425006	77	16	ranging	range	VBG
10_1101-2021_01_02_425006	77	17	from	from	IN
10_1101-2021_01_02_425006	77	18	1,100	1,100	CD
10_1101-2021_01_02_425006	77	19	to	to	IN
10_1101-2021_01_02_425006	77	20	1,500	1,500	CD
10_1101-2021_01_02_425006	77	21	bp	bp	NN
10_1101-2021_01_02_425006	77	22	.	.	.
10_1101-2021_01_02_425006	78	1	122	122	CD
10_1101-2021_01_02_425006	78	2	Step	step	NN
10_1101-2021_01_02_425006	78	3	2	2	CD
10_1101-2021_01_02_425006	78	4	:	:	:
10_1101-2021_01_02_425006	78	5	Acquiring	acquire	VBG
10_1101-2021_01_02_425006	78	6	the	the	DT
10_1101-2021_01_02_425006	78	7	Bias	Bias	NNP
10_1101-2021_01_02_425006	78	8	Rate	Rate	NNP
10_1101-2021_01_02_425006	78	9	Function	Function	NNP
10_1101-2021_01_02_425006	78	10	.	.	.
10_1101-2021_01_02_425006	79	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	79	2	applied	apply	VBD
10_1101-2021_01_02_425006	79	3	nonlinear	nonlinear	JJ
10_1101-2021_01_02_425006	79	4	regression	regression	NN
10_1101-2021_01_02_425006	79	5	to	to	IN
10_1101-2021_01_02_425006	79	6	the	the	DT
10_1101-2021_01_02_425006	79	7	expression	expression	NN
10_1101-2021_01_02_425006	79	8	123	123	CD
10_1101-2021_01_02_425006	79	9	distribution	distribution	NN
10_1101-2021_01_02_425006	79	10	of	of	IN
10_1101-2021_01_02_425006	79	11	the	the	DT
10_1101-2021_01_02_425006	79	12	selected	select	VBN
10_1101-2021_01_02_425006	79	13	single	single	JJ
10_1101-2021_01_02_425006	79	14	gene	gene	NN
10_1101-2021_01_02_425006	79	15	mRNA	mrna	NN
10_1101-2021_01_02_425006	79	16	transcripts	transcript	NNS
10_1101-2021_01_02_425006	79	17	and	and	CC
10_1101-2021_01_02_425006	79	18	acquired	acquire	VBD
10_1101-2021_01_02_425006	79	19	the	the	DT
10_1101-2021_01_02_425006	79	20	hypothetical	hypothetical	JJ
10_1101-2021_01_02_425006	79	21	function	function	NN
10_1101-2021_01_02_425006	79	22	�	�	.
10_1101-2021_01_02_425006	79	23	(	(	-LRB-
10_1101-2021_01_02_425006	79	24	�	�	NNP
10_1101-2021_01_02_425006	79	25	)	)	-RRB-
10_1101-2021_01_02_425006	79	26	.	.	.
10_1101-2021_01_02_425006	80	1	124	124	CD
10_1101-2021_01_02_425006	80	2	Specifically	specifically	RB
10_1101-2021_01_02_425006	80	3	,	,	,
10_1101-2021_01_02_425006	80	4	the	the	DT
10_1101-2021_01_02_425006	80	5	�	�	NNP
10_1101-2021_01_02_425006	80	6	axis	axis	JJ
10_1101-2021_01_02_425006	80	7	and	and	CC
10_1101-2021_01_02_425006	80	8	�	�	JJ
10_1101-2021_01_02_425006	80	9	axis	axis	RB
10_1101-2021_01_02_425006	80	10	of	of	IN
10_1101-2021_01_02_425006	80	11	the	the	DT
10_1101-2021_01_02_425006	80	12	expression	expression	NN
10_1101-2021_01_02_425006	80	13	distribution	distribution	NN
10_1101-2021_01_02_425006	80	14	were	be	VBD
10_1101-2021_01_02_425006	80	15	converted	convert	VBN
10_1101-2021_01_02_425006	80	16	to	to	IN
10_1101-2021_01_02_425006	80	17	the	the	DT
10_1101-2021_01_02_425006	80	18	distance	distance	NN
10_1101-2021_01_02_425006	80	19	from	from	IN
10_1101-2021_01_02_425006	80	20	125	125	CD
10_1101-2021_01_02_425006	80	21	the	the	DT
10_1101-2021_01_02_425006	80	22	3	3	CD
10_1101-2021_01_02_425006	80	23	’	'	''
10_1101-2021_01_02_425006	80	24	end	end	NN
10_1101-2021_01_02_425006	80	25	of	of	IN
10_1101-2021_01_02_425006	80	26	an	an	DT
10_1101-2021_01_02_425006	80	27	mRNA	mrna	NN
10_1101-2021_01_02_425006	80	28	transcript	transcript	NN
10_1101-2021_01_02_425006	80	29	and	and	CC
10_1101-2021_01_02_425006	80	30	the	the	DT
10_1101-2021_01_02_425006	80	31	bias	bias	NN
10_1101-2021_01_02_425006	80	32	rate	rate	NN
10_1101-2021_01_02_425006	80	33	of	of	IN
10_1101-2021_01_02_425006	80	34	read	read	VBN
10_1101-2021_01_02_425006	80	35	distribution	distribution	NN
10_1101-2021_01_02_425006	80	36	,	,	,
10_1101-2021_01_02_425006	80	37	respectively	respectively	RB
10_1101-2021_01_02_425006	80	38	.	.	.
10_1101-2021_01_02_425006	81	1	To	to	TO
10_1101-2021_01_02_425006	81	2	apply	apply	VB
10_1101-2021_01_02_425006	81	3	nonlinear	nonlinear	JJ
10_1101-2021_01_02_425006	81	4	126	126	CD
10_1101-2021_01_02_425006	81	5	regression	regression	NN
10_1101-2021_01_02_425006	81	6	to	to	IN
10_1101-2021_01_02_425006	81	7	single	single	JJ
10_1101-2021_01_02_425006	81	8	gene	gene	NN
10_1101-2021_01_02_425006	81	9	mRNA	mrna	NN
10_1101-2021_01_02_425006	81	10	transcripts	transcript	NNS
10_1101-2021_01_02_425006	81	11	with	with	IN
10_1101-2021_01_02_425006	81	12	different	different	JJ
10_1101-2021_01_02_425006	81	13	lengths	length	NNS
10_1101-2021_01_02_425006	81	14	,	,	,
10_1101-2021_01_02_425006	81	15	normalization	normalization	NN
10_1101-2021_01_02_425006	81	16	was	be	VBD
10_1101-2021_01_02_425006	81	17	also	also	RB
10_1101-2021_01_02_425006	81	18	implemented	implement	VBN
10_1101-2021_01_02_425006	81	19	127	127	CD
10_1101-2021_01_02_425006	81	20	.CC	.CC	,
10_1101-2021_01_02_425006	81	21	-	-	HYPH
10_1101-2021_01_02_425006	81	22	BY	by	IN
10_1101-2021_01_02_425006	81	23	-	-	HYPH
10_1101-2021_01_02_425006	81	24	NC	NC	NNP
10_1101-2021_01_02_425006	81	25	-	-	HYPH
10_1101-2021_01_02_425006	81	26	ND	ND	NNP
10_1101-2021_01_02_425006	81	27	4.0	4.0	CD
10_1101-2021_01_02_425006	81	28	International	International	NNP
10_1101-2021_01_02_425006	81	29	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	81	30	under	under	IN
10_1101-2021_01_02_425006	81	31	a	a	DT
10_1101-2021_01_02_425006	81	32	(	(	-LRB-
10_1101-2021_01_02_425006	81	33	which	which	WDT
10_1101-2021_01_02_425006	81	34	was	be	VBD
10_1101-2021_01_02_425006	81	35	not	not	RB
10_1101-2021_01_02_425006	81	36	certified	certify	VBN
10_1101-2021_01_02_425006	81	37	by	by	IN
10_1101-2021_01_02_425006	81	38	peer	peer	NN
10_1101-2021_01_02_425006	81	39	review	review	NN
10_1101-2021_01_02_425006	81	40	)	)	-RRB-
10_1101-2021_01_02_425006	81	41	is	be	VBZ
10_1101-2021_01_02_425006	81	42	the	the	DT
10_1101-2021_01_02_425006	81	43	author	author	NN
10_1101-2021_01_02_425006	81	44	/	/	SYM
10_1101-2021_01_02_425006	81	45	funder	funder	NN
10_1101-2021_01_02_425006	81	46	,	,	,
10_1101-2021_01_02_425006	81	47	who	who	WP
10_1101-2021_01_02_425006	81	48	has	have	VBZ
10_1101-2021_01_02_425006	81	49	granted	grant	VBN
10_1101-2021_01_02_425006	81	50	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	81	51	a	a	DT
10_1101-2021_01_02_425006	81	52	license	license	NN
10_1101-2021_01_02_425006	81	53	to	to	TO
10_1101-2021_01_02_425006	81	54	display	display	VB
10_1101-2021_01_02_425006	81	55	the	the	DT
10_1101-2021_01_02_425006	81	56	preprint	preprint	NN
10_1101-2021_01_02_425006	81	57	in	in	IN
10_1101-2021_01_02_425006	81	58	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	81	59	.	.	.
10_1101-2021_01_02_425006	82	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	82	2	is	be	VBZ
10_1101-2021_01_02_425006	82	3	made	make	VBN
10_1101-2021_01_02_425006	82	4	The	the	DT
10_1101-2021_01_02_425006	82	5	copyright	copyright	NN
10_1101-2021_01_02_425006	82	6	holder	holder	NN
10_1101-2021_01_02_425006	82	7	for	for	IN
10_1101-2021_01_02_425006	82	8	this	this	DT
10_1101-2021_01_02_425006	82	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	82	10	version	version	NN
10_1101-2021_01_02_425006	82	11	posted	post	VBD
10_1101-2021_01_02_425006	82	12	January	January	NNP
10_1101-2021_01_02_425006	82	13	6	6	CD
10_1101-2021_01_02_425006	82	14	,	,	,
10_1101-2021_01_02_425006	82	15	2021	2021	CD
10_1101-2021_01_02_425006	82	16	.	.	.
10_1101-2021_01_02_425006	82	17	;	;	:
10_1101-2021_01_02_425006	82	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	82	19	:	:	:
10_1101-2021_01_02_425006	82	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	82	21	preprint	preprint	NN
10_1101-2021_01_02_425006	82	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	82	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	82	24	8	8	CD
10_1101-2021_01_02_425006	82	25	on	on	IN
10_1101-2021_01_02_425006	82	26	�	�	NNP
10_1101-2021_01_02_425006	82	27	.	.	.
10_1101-2021_01_02_425006	83	1	Here	here	RB
10_1101-2021_01_02_425006	83	2	,	,	,
10_1101-2021_01_02_425006	83	3	�	�	NNP
10_1101-2021_01_02_425006	83	4	=	=	NFP
10_1101-2021_01_02_425006	83	5	(	(	-LRB-
10_1101-2021_01_02_425006	83	6	�	�	NNP
10_1101-2021_01_02_425006	83	7	�	�	NNP
10_1101-2021_01_02_425006	83	8	,	,	,
10_1101-2021_01_02_425006	83	9	�	�	NNP
10_1101-2021_01_02_425006	83	10	�	�	NNP
10_1101-2021_01_02_425006	83	11	,	,	,
10_1101-2021_01_02_425006	83	12	…	…	NFP
10_1101-2021_01_02_425006	83	13	,	,	,
10_1101-2021_01_02_425006	83	14	�	�	NNP
10_1101-2021_01_02_425006	83	15	�	�	NNP
10_1101-2021_01_02_425006	83	16	)	)	-RRB-
10_1101-2021_01_02_425006	83	17	and	and	CC
10_1101-2021_01_02_425006	83	18	�	�	NNPS
10_1101-2021_01_02_425006	83	19	=	=	NFP
10_1101-2021_01_02_425006	83	20	(	(	-LRB-
10_1101-2021_01_02_425006	83	21	�	�	NNP
10_1101-2021_01_02_425006	83	22	�	�	NNP
10_1101-2021_01_02_425006	83	23	,	,	,
10_1101-2021_01_02_425006	83	24	�	�	NNP
10_1101-2021_01_02_425006	83	25	�	�	NNP
10_1101-2021_01_02_425006	83	26	,	,	,
10_1101-2021_01_02_425006	83	27	…	…	NFP
10_1101-2021_01_02_425006	83	28	,	,	,
10_1101-2021_01_02_425006	83	29	�	�	NNP
10_1101-2021_01_02_425006	83	30	�	�	NNP
10_1101-2021_01_02_425006	83	31	)	)	-RRB-
10_1101-2021_01_02_425006	83	32	are	be	VBP
10_1101-2021_01_02_425006	83	33	defined	define	VBN
10_1101-2021_01_02_425006	83	34	by	by	IN
10_1101-2021_01_02_425006	83	35	:	:	:
10_1101-2021_01_02_425006	83	36	128	128	CD
10_1101-2021_01_02_425006	83	37	�	�	NNS
10_1101-2021_01_02_425006	83	38	�	�	ADD
10_1101-2021_01_02_425006	83	39	=	=	NFP
10_1101-2021_01_02_425006	83	40	⎩	⎩	CD
10_1101-2021_01_02_425006	83	41	⎨	⎨	NNP
10_1101-2021_01_02_425006	83	42	⎧	⎧	NNP
10_1101-2021_01_02_425006	83	43	�	�	,
10_1101-2021_01_02_425006	83	44	�	�	NNS
10_1101-2021_01_02_425006	83	45	−	−	NNP
10_1101-2021_01_02_425006	83	46	�	�	VBZ
10_1101-2021_01_02_425006	83	47	�	�	NN
10_1101-2021_01_02_425006	83	48	�	�	NNS
10_1101-2021_01_02_425006	83	49	�	�	VBZ
10_1101-2021_01_02_425006	83	50	�	�	VBZ
10_1101-2021_01_02_425006	83	51	�	�	VBZ
10_1101-2021_01_02_425006	83	52	�	�	VBZ
10_1101-2021_01_02_425006	83	53	�	�	VBZ
10_1101-2021_01_02_425006	83	54	�	�	NNS
10_1101-2021_01_02_425006	83	55	�	�	NNS
10_1101-2021_01_02_425006	83	56	−	−	NNP
10_1101-2021_01_02_425006	83	57	�	�	NNP
10_1101-2021_01_02_425006	83	58	�	�	NNP
10_1101-2021_01_02_425006	83	59	×	×	CD
10_1101-2021_01_02_425006	83	60	10	10	CD
10_1101-2021_01_02_425006	83	61	�	�	NNS
10_1101-2021_01_02_425006	83	62	,	,	,
10_1101-2021_01_02_425006	83	63	�	�	NNP
10_1101-2021_01_02_425006	83	64	�	�	ADD
10_1101-2021_01_02_425006	83	65	�	�	VBZ
10_1101-2021_01_02_425006	83	66	�	�	VBZ
10_1101-2021_01_02_425006	83	67	�	�	VBZ
10_1101-2021_01_02_425006	83	68	�	�	VBZ
10_1101-2021_01_02_425006	83	69	�	�	VBZ
10_1101-2021_01_02_425006	83	70	�	�	NNS
10_1101-2021_01_02_425006	83	71	�	�	NNS
10_1101-2021_01_02_425006	83	72	−	−	NNP
10_1101-2021_01_02_425006	83	73	�	�	VBZ
10_1101-2021_01_02_425006	83	74	�	�	NN
10_1101-2021_01_02_425006	83	75	�	�	NNS
10_1101-2021_01_02_425006	83	76	�	�	JJ
10_1101-2021_01_02_425006	83	77	�	�	NNS
10_1101-2021_01_02_425006	83	78	�	�	NNS
10_1101-2021_01_02_425006	83	79	−	−	NNP
10_1101-2021_01_02_425006	83	80	�	�	NNP
10_1101-2021_01_02_425006	83	81	�	�	NNP
10_1101-2021_01_02_425006	83	82	×	×	CD
10_1101-2021_01_02_425006	83	83	10	10	CD
10_1101-2021_01_02_425006	83	84	�	�	NNS
10_1101-2021_01_02_425006	83	85	,	,	,
10_1101-2021_01_02_425006	83	86	�	�	NNP
10_1101-2021_01_02_425006	83	87	�	�	ADD
10_1101-2021_01_02_425006	83	88	�	�	VBZ
10_1101-2021_01_02_425006	83	89	�	�	VBZ
10_1101-2021_01_02_425006	83	90	�	�	JJ
10_1101-2021_01_02_425006	83	91	�	�	NNS
10_1101-2021_01_02_425006	83	92	�	�	NNP
10_1101-2021_01_02_425006	83	93	(	(	-LRB-
10_1101-2021_01_02_425006	83	94	3	3	LS
10_1101-2021_01_02_425006	83	95	)	)	-RRB-
10_1101-2021_01_02_425006	83	96	�	�	ADD
10_1101-2021_01_02_425006	83	97	�	�	NNP
10_1101-2021_01_02_425006	83	98	=	=	NFP
10_1101-2021_01_02_425006	83	99	⎩	⎩	NNP
10_1101-2021_01_02_425006	83	100	⎪	⎪	NNP
10_1101-2021_01_02_425006	83	101	⎨	⎨	NNP
10_1101-2021_01_02_425006	83	102	⎪	⎪	NNP
10_1101-2021_01_02_425006	83	103	⎧	⎧	XX
10_1101-2021_01_02_425006	83	104	�	�	NNP
10_1101-2021_01_02_425006	83	105	(	(	-LRB-
10_1101-2021_01_02_425006	83	106	�	�	NNP
10_1101-2021_01_02_425006	83	107	�	�	JJ
10_1101-2021_01_02_425006	83	108	�	�	NNS
10_1101-2021_01_02_425006	83	109	�	�	JJ
10_1101-2021_01_02_425006	83	110	�	�	NNS
10_1101-2021_01_02_425006	83	111	�	�	NN
10_1101-2021_01_02_425006	83	112	)	)	-RRB-
10_1101-2021_01_02_425006	83	113	�	�	NNP
10_1101-2021_01_02_425006	83	114	�	�	NNP
10_1101-2021_01_02_425006	83	115	�	�	NNP
10_1101-2021_01_02_425006	83	116	�	�	NNP
10_1101-2021_01_02_425006	83	117	,	,	,
10_1101-2021_01_02_425006	83	118	�	�	NNP
10_1101-2021_01_02_425006	83	119	�	�	ADD
10_1101-2021_01_02_425006	83	120	�	�	VBZ
10_1101-2021_01_02_425006	83	121	�	�	VBZ
10_1101-2021_01_02_425006	83	122	�	�	VBZ
10_1101-2021_01_02_425006	83	123	�	�	JJ
10_1101-2021_01_02_425006	83	124	�	�	NNS
10_1101-2021_01_02_425006	83	125	�	�	.
10_1101-2021_01_02_425006	83	126	(	(	-LRB-
10_1101-2021_01_02_425006	83	127	�	�	NNP
10_1101-2021_01_02_425006	83	128	�	�	NNP
10_1101-2021_01_02_425006	83	129	)	)	-RRB-
10_1101-2021_01_02_425006	83	130	�	�	NNP
10_1101-2021_01_02_425006	83	131	�	�	NNP
10_1101-2021_01_02_425006	83	132	�	�	NNP
10_1101-2021_01_02_425006	83	133	�	�	NNP
10_1101-2021_01_02_425006	83	134	,	,	,
10_1101-2021_01_02_425006	83	135	�	�	NNP
10_1101-2021_01_02_425006	83	136	�	�	ADD
10_1101-2021_01_02_425006	83	137	�	�	VBZ
10_1101-2021_01_02_425006	83	138	�	�	VBZ
10_1101-2021_01_02_425006	83	139	�	�	JJ
10_1101-2021_01_02_425006	83	140	�	�	NNS
10_1101-2021_01_02_425006	83	141	�	�	NNP
10_1101-2021_01_02_425006	83	142	(	(	-LRB-
10_1101-2021_01_02_425006	83	143	4	4	LS
10_1101-2021_01_02_425006	83	144	)	)	-RRB-
10_1101-2021_01_02_425006	83	145	where	where	WRB
10_1101-2021_01_02_425006	83	146	�	�	NNP
10_1101-2021_01_02_425006	83	147	denotes	denote	VBZ
10_1101-2021_01_02_425006	83	148	the	the	DT
10_1101-2021_01_02_425006	83	149	number	number	NN
10_1101-2021_01_02_425006	83	150	of	of	IN
10_1101-2021_01_02_425006	83	151	genomic	genomic	JJ
10_1101-2021_01_02_425006	83	152	positions	position	NNS
10_1101-2021_01_02_425006	83	153	on	on	IN
10_1101-2021_01_02_425006	83	154	an	an	DT
10_1101-2021_01_02_425006	83	155	mRNA	mrna	NN
10_1101-2021_01_02_425006	83	156	transcript	transcript	NN
10_1101-2021_01_02_425006	83	157	;	;	:
10_1101-2021_01_02_425006	83	158	�	�	ADD
10_1101-2021_01_02_425006	83	159	=	=	NFP
10_1101-2021_01_02_425006	83	160	(	(	-LRB-
10_1101-2021_01_02_425006	83	161	�	�	NNP
10_1101-2021_01_02_425006	83	162	�	�	NNP
10_1101-2021_01_02_425006	83	163	,	,	,
10_1101-2021_01_02_425006	83	164	�	�	NNP
10_1101-2021_01_02_425006	83	165	�	�	NNP
10_1101-2021_01_02_425006	83	166	,	,	,
10_1101-2021_01_02_425006	83	167	…	…	NFP
10_1101-2021_01_02_425006	83	168	,	,	,
10_1101-2021_01_02_425006	83	169	�	�	NNP
10_1101-2021_01_02_425006	83	170	�	�	NNP
10_1101-2021_01_02_425006	83	171	)	)	-RRB-
10_1101-2021_01_02_425006	83	172	denotes	denote	VBZ
10_1101-2021_01_02_425006	83	173	129	129	CD
10_1101-2021_01_02_425006	83	174	the	the	DT
10_1101-2021_01_02_425006	83	175	genomic	genomic	JJ
10_1101-2021_01_02_425006	83	176	positions	position	NNS
10_1101-2021_01_02_425006	83	177	on	on	IN
10_1101-2021_01_02_425006	83	178	an	an	DT
10_1101-2021_01_02_425006	83	179	mRNA	mrna	NN
10_1101-2021_01_02_425006	83	180	transcript	transcript	NN
10_1101-2021_01_02_425006	83	181	;	;	:
10_1101-2021_01_02_425006	83	182	�	�	NNP
10_1101-2021_01_02_425006	83	183	�	�	,
10_1101-2021_01_02_425006	83	184	�	�	NNS
10_1101-2021_01_02_425006	83	185	�	�	NNP
10_1101-2021_01_02_425006	83	186	=	=	VBZ
10_1101-2021_01_02_425006	83	187	�	�	NNP
10_1101-2021_01_02_425006	83	188	�	�	NNP
10_1101-2021_01_02_425006	83	189	;	;	:
10_1101-2021_01_02_425006	83	190	�	�	NNP
10_1101-2021_01_02_425006	83	191	(	(	-LRB-
10_1101-2021_01_02_425006	83	192	�	�	NNP
10_1101-2021_01_02_425006	83	193	�	�	NNP
10_1101-2021_01_02_425006	83	194	)	)	-RRB-
10_1101-2021_01_02_425006	83	195	denotes	denote	VBZ
10_1101-2021_01_02_425006	83	196	the	the	DT
10_1101-2021_01_02_425006	83	197	expression	expression	NN
10_1101-2021_01_02_425006	83	198	level	level	NN
10_1101-2021_01_02_425006	83	199	of	of	IN
10_1101-2021_01_02_425006	83	200	the	the	DT
10_1101-2021_01_02_425006	83	201	130	130	CD
10_1101-2021_01_02_425006	83	202	genomic	genomic	JJ
10_1101-2021_01_02_425006	83	203	position	position	NN
10_1101-2021_01_02_425006	83	204	�	�	NNP
10_1101-2021_01_02_425006	83	205	�	�	NNP
10_1101-2021_01_02_425006	83	206	,	,	,
10_1101-2021_01_02_425006	83	207	i.e.	i.e.	FW
10_1101-2021_01_02_425006	83	208	,	,	,
10_1101-2021_01_02_425006	83	209	the	the	DT
10_1101-2021_01_02_425006	83	210	number	number	NN
10_1101-2021_01_02_425006	83	211	of	of	IN
10_1101-2021_01_02_425006	83	212	reads	read	NNS
10_1101-2021_01_02_425006	83	213	covering	cover	VBG
10_1101-2021_01_02_425006	83	214	the	the	DT
10_1101-2021_01_02_425006	83	215	genomic	genomic	JJ
10_1101-2021_01_02_425006	83	216	position	position	NN
10_1101-2021_01_02_425006	83	217	�	�	ADD
10_1101-2021_01_02_425006	83	218	�	�	NNP
10_1101-2021_01_02_425006	83	219	;	;	,
10_1101-2021_01_02_425006	83	220	and	and	CC
10_1101-2021_01_02_425006	83	221	�	�	JJ
10_1101-2021_01_02_425006	83	222	�	�	NNP
10_1101-2021_01_02_425006	83	223	�	�	NNP
10_1101-2021_01_02_425006	83	224	�	�	NNP
10_1101-2021_01_02_425006	83	225	denotes	denote	VBZ
10_1101-2021_01_02_425006	83	226	the	the	DT
10_1101-2021_01_02_425006	83	227	131	131	CD
10_1101-2021_01_02_425006	83	228	expression	expression	NN
10_1101-2021_01_02_425006	83	229	level	level	NN
10_1101-2021_01_02_425006	83	230	without	without	IN
10_1101-2021_01_02_425006	83	231	bias	bias	NN
10_1101-2021_01_02_425006	83	232	in	in	IN
10_1101-2021_01_02_425006	83	233	an	an	DT
10_1101-2021_01_02_425006	83	234	mRNA	mrna	NN
10_1101-2021_01_02_425006	83	235	transcript	transcript	NN
10_1101-2021_01_02_425006	83	236	,	,	,
10_1101-2021_01_02_425006	83	237	which	which	WDT
10_1101-2021_01_02_425006	83	238	is	be	VBZ
10_1101-2021_01_02_425006	83	239	calculated	calculate	VBN
10_1101-2021_01_02_425006	83	240	as	as	IN
10_1101-2021_01_02_425006	83	241	�	�	NNP
10_1101-2021_01_02_425006	83	242	�	�	ADD
10_1101-2021_01_02_425006	83	243	�	�	,
10_1101-2021_01_02_425006	83	244	{	{	-LRB-
10_1101-2021_01_02_425006	83	245	�	�	NNP
10_1101-2021_01_02_425006	83	246	(	(	-LRB-
10_1101-2021_01_02_425006	83	247	�	�	NNP
10_1101-2021_01_02_425006	83	248	�	�	NNP
10_1101-2021_01_02_425006	83	249	)	)	-RRB-
10_1101-2021_01_02_425006	83	250	}	}	-RRB-
10_1101-2021_01_02_425006	83	251	,	,	,
10_1101-2021_01_02_425006	83	252	1	1	CD
10_1101-2021_01_02_425006	83	253	≤	≤	NN
10_1101-2021_01_02_425006	83	254	�	�	NNP
10_1101-2021_01_02_425006	83	255	≤	≤	NN
10_1101-2021_01_02_425006	83	256	�	�	NNP
10_1101-2021_01_02_425006	83	257	.	.	.
10_1101-2021_01_02_425006	84	1	132	132	CD
10_1101-2021_01_02_425006	84	2	We	-PRON-	PRP
10_1101-2021_01_02_425006	84	3	used	use	VBD
10_1101-2021_01_02_425006	84	4	the	the	DT
10_1101-2021_01_02_425006	84	5	function	function	NN
10_1101-2021_01_02_425006	84	6	nls	nls	JJ
10_1101-2021_01_02_425006	84	7	in	in	IN
10_1101-2021_01_02_425006	84	8	R	R	NNP
10_1101-2021_01_02_425006	84	9	to	to	TO
10_1101-2021_01_02_425006	84	10	acquire	acquire	VB
10_1101-2021_01_02_425006	84	11	the	the	DT
10_1101-2021_01_02_425006	84	12	hypothetical	hypothetical	JJ
10_1101-2021_01_02_425006	84	13	function	function	NN
10_1101-2021_01_02_425006	84	14	�	�	.
10_1101-2021_01_02_425006	84	15	(	(	-LRB-
10_1101-2021_01_02_425006	84	16	�	�	NNP
10_1101-2021_01_02_425006	84	17	)	)	-RRB-
10_1101-2021_01_02_425006	84	18	.	.	.
10_1101-2021_01_02_425006	85	1	133	133	CD
10_1101-2021_01_02_425006	85	2	Step	step	NN
10_1101-2021_01_02_425006	85	3	3	3	CD
10_1101-2021_01_02_425006	85	4	:	:	:
10_1101-2021_01_02_425006	85	5	Constructing	construct	VBG
10_1101-2021_01_02_425006	85	6	Bias	Bias	NNP
10_1101-2021_01_02_425006	85	7	Rate	Rate	NNP
10_1101-2021_01_02_425006	85	8	Vectors	Vectors	NNPS
10_1101-2021_01_02_425006	85	9	.	.	.
10_1101-2021_01_02_425006	86	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	86	2	constructed	construct	VBD
10_1101-2021_01_02_425006	86	3	a	a	DT
10_1101-2021_01_02_425006	86	4	genetic	genetic	JJ
10_1101-2021_01_02_425006	86	5	or	or	CC
10_1101-2021_01_02_425006	86	6	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	86	7	region	region	NN
10_1101-2021_01_02_425006	86	8	bias	bias	NN
10_1101-2021_01_02_425006	86	9	rate	rate	NN
10_1101-2021_01_02_425006	86	10	vector	vector	NN
10_1101-2021_01_02_425006	86	11	134	134	CD
10_1101-2021_01_02_425006	86	12	for	for	IN
10_1101-2021_01_02_425006	86	13	each	each	DT
10_1101-2021_01_02_425006	86	14	mRNA	mrna	NN
10_1101-2021_01_02_425006	86	15	transcript	transcript	NN
10_1101-2021_01_02_425006	86	16	by	by	IN
10_1101-2021_01_02_425006	86	17	calculating	calculate	VBG
10_1101-2021_01_02_425006	86	18	the	the	DT
10_1101-2021_01_02_425006	86	19	bias	bias	NN
10_1101-2021_01_02_425006	86	20	rate	rate	NN
10_1101-2021_01_02_425006	86	21	of	of	IN
10_1101-2021_01_02_425006	86	22	all	all	DT
10_1101-2021_01_02_425006	86	23	of	of	IN
10_1101-2021_01_02_425006	86	24	its	-PRON-	PRP$
10_1101-2021_01_02_425006	86	25	component	component	NN
10_1101-2021_01_02_425006	86	26	genetic	genetic	JJ
10_1101-2021_01_02_425006	86	27	or	or	CC
10_1101-2021_01_02_425006	86	28	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	86	29	135	135	CD
10_1101-2021_01_02_425006	86	30	regions	region	NNS
10_1101-2021_01_02_425006	86	31	.	.	.
10_1101-2021_01_02_425006	87	1	The	the	DT
10_1101-2021_01_02_425006	87	2	bias	bias	NN
10_1101-2021_01_02_425006	87	3	rate	rate	NN
10_1101-2021_01_02_425006	87	4	of	of	IN
10_1101-2021_01_02_425006	87	5	a	a	DT
10_1101-2021_01_02_425006	87	6	genetic	genetic	JJ
10_1101-2021_01_02_425006	87	7	or	or	CC
10_1101-2021_01_02_425006	87	8	an	an	DT
10_1101-2021_01_02_425006	87	9	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	87	10	region	region	NN
10_1101-2021_01_02_425006	87	11	is	be	VBZ
10_1101-2021_01_02_425006	87	12	the	the	DT
10_1101-2021_01_02_425006	87	13	average	average	JJ
10_1101-2021_01_02_425006	87	14	bias	bias	NN
10_1101-2021_01_02_425006	87	15	rate	rate	NN
10_1101-2021_01_02_425006	87	16	of	of	IN
10_1101-2021_01_02_425006	87	17	all	all	PDT
10_1101-2021_01_02_425006	87	18	the	the	DT
10_1101-2021_01_02_425006	87	19	genomic	genomic	JJ
10_1101-2021_01_02_425006	87	20	136	136	CD
10_1101-2021_01_02_425006	87	21	positions	position	NNS
10_1101-2021_01_02_425006	87	22	that	that	IN
10_1101-2021_01_02_425006	87	23	it	-PRON-	PRP
10_1101-2021_01_02_425006	87	24	contains	contain	VBZ
10_1101-2021_01_02_425006	87	25	.	.	.
10_1101-2021_01_02_425006	88	1	Considering	consider	VBG
10_1101-2021_01_02_425006	88	2	an	an	DT
10_1101-2021_01_02_425006	88	3	mRNA	mrna	NN
10_1101-2021_01_02_425006	88	4	transcript	transcript	NN
10_1101-2021_01_02_425006	88	5	�	�	NNP
10_1101-2021_01_02_425006	88	6	and	and	CC
10_1101-2021_01_02_425006	88	7	its	-PRON-	PRP$
10_1101-2021_01_02_425006	88	8	component	component	NN
10_1101-2021_01_02_425006	88	9	gene	gene	NN
10_1101-2021_01_02_425006	88	10	set	set	VBD
10_1101-2021_01_02_425006	88	11	137	137	CD
10_1101-2021_01_02_425006	88	12	{	{	-LRB-
10_1101-2021_01_02_425006	88	13	�	�	NNP
10_1101-2021_01_02_425006	88	14	�	�	NNP
10_1101-2021_01_02_425006	88	15	,	,	,
10_1101-2021_01_02_425006	88	16	�	�	NNP
10_1101-2021_01_02_425006	88	17	�	�	NNP
10_1101-2021_01_02_425006	88	18	,	,	,
10_1101-2021_01_02_425006	88	19	…	…	NFP
10_1101-2021_01_02_425006	88	20	,	,	,
10_1101-2021_01_02_425006	88	21	�	�	NNP
10_1101-2021_01_02_425006	88	22	�	�	.
10_1101-2021_01_02_425006	88	23	}	}	-RRB-
10_1101-2021_01_02_425006	88	24	(	(	-LRB-
10_1101-2021_01_02_425006	88	25	the	the	DT
10_1101-2021_01_02_425006	88	26	details	detail	NNS
10_1101-2021_01_02_425006	88	27	of	of	IN
10_1101-2021_01_02_425006	88	28	the	the	DT
10_1101-2021_01_02_425006	88	29	gene	gene	NN
10_1101-2021_01_02_425006	88	30	labels	label	NNS
10_1101-2021_01_02_425006	88	31	are	be	VBP
10_1101-2021_01_02_425006	88	32	described	describe	VBN
10_1101-2021_01_02_425006	88	33	in	in	IN
10_1101-2021_01_02_425006	88	34	method	method	NNP
10_1101-2021_01_02_425006	88	35	S2	S2	NNP
10_1101-2021_01_02_425006	88	36	)	)	-RRB-
10_1101-2021_01_02_425006	88	37	,	,	,
10_1101-2021_01_02_425006	88	38	we	-PRON-	PRP
10_1101-2021_01_02_425006	88	39	denoted	denote	VBD
10_1101-2021_01_02_425006	88	40	the	the	DT
10_1101-2021_01_02_425006	88	41	genetic	genetic	JJ
10_1101-2021_01_02_425006	88	42	138	138	CD
10_1101-2021_01_02_425006	88	43	region	region	NN
10_1101-2021_01_02_425006	88	44	bias	bias	NN
10_1101-2021_01_02_425006	88	45	rate	rate	NN
10_1101-2021_01_02_425006	88	46	vector	vector	NN
10_1101-2021_01_02_425006	88	47	as	as	IN
10_1101-2021_01_02_425006	88	48	�	�	NNP
10_1101-2021_01_02_425006	88	49	=	=	NFP
10_1101-2021_01_02_425006	88	50	(	(	-LRB-
10_1101-2021_01_02_425006	88	51	�	�	NNP
10_1101-2021_01_02_425006	88	52	�	�	NNP
10_1101-2021_01_02_425006	88	53	,	,	,
10_1101-2021_01_02_425006	88	54	�	�	NNP
10_1101-2021_01_02_425006	88	55	�	�	NNP
10_1101-2021_01_02_425006	88	56	,	,	,
10_1101-2021_01_02_425006	88	57	…	…	NFP
10_1101-2021_01_02_425006	88	58	,	,	,
10_1101-2021_01_02_425006	88	59	�	�	NNP
10_1101-2021_01_02_425006	88	60	�	�	NNP
10_1101-2021_01_02_425006	88	61	)	)	-RRB-
10_1101-2021_01_02_425006	88	62	,	,	,
10_1101-2021_01_02_425006	88	63	which	which	WDT
10_1101-2021_01_02_425006	88	64	was	be	VBD
10_1101-2021_01_02_425006	88	65	calculated	calculate	VBN
10_1101-2021_01_02_425006	88	66	using	use	VBG
10_1101-2021_01_02_425006	88	67	the	the	DT
10_1101-2021_01_02_425006	88	68	formula	formula	NN
10_1101-2021_01_02_425006	88	69	:	:	:
10_1101-2021_01_02_425006	88	70	139	139	CD
10_1101-2021_01_02_425006	88	71	�	�	NNP
10_1101-2021_01_02_425006	88	72	�	�	NNP
10_1101-2021_01_02_425006	88	73	=	=	SYM
10_1101-2021_01_02_425006	88	74	⎩	⎩	NNP
10_1101-2021_01_02_425006	88	75	⎪	⎪	NNP
10_1101-2021_01_02_425006	88	76	⎨	⎨	NNP
10_1101-2021_01_02_425006	88	77	⎪	⎪	NNP
10_1101-2021_01_02_425006	88	78	⎧	⎧	NNP
10_1101-2021_01_02_425006	88	79	∑	∑	.
10_1101-2021_01_02_425006	88	80	�	�	NNP
10_1101-2021_01_02_425006	88	81	(	(	-LRB-
10_1101-2021_01_02_425006	88	82	�	�	NNP
10_1101-2021_01_02_425006	88	83	�	�	NNP
10_1101-2021_01_02_425006	88	84	)	)	-RRB-
10_1101-2021_01_02_425006	88	85	�	�	NNP
10_1101-2021_01_02_425006	88	86	�	�	ADD
10_1101-2021_01_02_425006	88	87	�	�	VBZ
10_1101-2021_01_02_425006	88	88	�	�	VBZ
10_1101-2021_01_02_425006	88	89	�	�	VBZ
10_1101-2021_01_02_425006	88	90	�	�	VBZ
10_1101-2021_01_02_425006	88	91	�	�	VBZ
10_1101-2021_01_02_425006	88	92	�	�	VBZ
10_1101-2021_01_02_425006	88	93	�	�	VBZ
10_1101-2021_01_02_425006	88	94	�	�	VBZ
10_1101-2021_01_02_425006	88	95	�	�	VBZ
10_1101-2021_01_02_425006	88	96	�	�	VBZ
10_1101-2021_01_02_425006	88	97	�	�	VBZ
10_1101-2021_01_02_425006	88	98	�	�	VBZ
10_1101-2021_01_02_425006	88	99	�	�	VBZ
10_1101-2021_01_02_425006	88	100	�	�	VBZ
10_1101-2021_01_02_425006	88	101	�	�	VBZ
10_1101-2021_01_02_425006	88	102	�	�	VBZ
10_1101-2021_01_02_425006	88	103	�	�	VBZ
10_1101-2021_01_02_425006	88	104	�	�	NNS
10_1101-2021_01_02_425006	88	105	�	�	NNS
10_1101-2021_01_02_425006	88	106	−	−	NNP
10_1101-2021_01_02_425006	88	107	�	�	VBZ
10_1101-2021_01_02_425006	88	108	�	�	NN
10_1101-2021_01_02_425006	88	109	�	�	NNS
10_1101-2021_01_02_425006	88	110	�	�	VBZ
10_1101-2021_01_02_425006	88	111	�	�	JJ
10_1101-2021_01_02_425006	88	112	�	�	NNS
10_1101-2021_01_02_425006	88	113	�	�	NN
10_1101-2021_01_02_425006	88	114	+	+	CC
10_1101-2021_01_02_425006	88	115	1	1	CD
10_1101-2021_01_02_425006	88	116	,	,	,
10_1101-2021_01_02_425006	88	117	�	�	NNP
10_1101-2021_01_02_425006	88	118	�	�	ADD
10_1101-2021_01_02_425006	88	119	�	�	VBZ
10_1101-2021_01_02_425006	88	120	�	�	VBZ
10_1101-2021_01_02_425006	88	121	�	�	NN
10_1101-2021_01_02_425006	88	122	�	�	NNS
10_1101-2021_01_02_425006	88	123	�	�	NNP
10_1101-2021_01_02_425006	88	124	∑	∑	.
10_1101-2021_01_02_425006	88	125	�	�	NNP
10_1101-2021_01_02_425006	88	126	(	(	-LRB-
10_1101-2021_01_02_425006	88	127	�	�	NNP
10_1101-2021_01_02_425006	88	128	�	�	NNP
10_1101-2021_01_02_425006	88	129	)	)	-RRB-
10_1101-2021_01_02_425006	88	130	�	�	NNP
10_1101-2021_01_02_425006	88	131	�	�	ADD
10_1101-2021_01_02_425006	88	132	�	�	VBZ
10_1101-2021_01_02_425006	88	133	�	�	VBZ
10_1101-2021_01_02_425006	88	134	�	�	VBZ
10_1101-2021_01_02_425006	88	135	�	�	VBZ
10_1101-2021_01_02_425006	88	136	�	�	VBZ
10_1101-2021_01_02_425006	88	137	�	�	NNS
10_1101-2021_01_02_425006	88	138	�	�	NNS
10_1101-2021_01_02_425006	88	139	−	−	NNP
10_1101-2021_01_02_425006	88	140	�	�	NNP
10_1101-2021_01_02_425006	88	141	�	�	NNP
10_1101-2021_01_02_425006	88	142	�	�	NN
10_1101-2021_01_02_425006	88	143	+	+	CC
10_1101-2021_01_02_425006	88	144	1	1	CD
10_1101-2021_01_02_425006	88	145	,	,	,
10_1101-2021_01_02_425006	88	146	�	�	NNP
10_1101-2021_01_02_425006	88	147	�	�	ADD
10_1101-2021_01_02_425006	88	148	�	�	VBZ
10_1101-2021_01_02_425006	88	149	�	�	VBZ
10_1101-2021_01_02_425006	88	150	�	�	JJ
10_1101-2021_01_02_425006	88	151	�	�	NNS
10_1101-2021_01_02_425006	88	152	�	�	NNP
10_1101-2021_01_02_425006	88	153	(	(	-LRB-
10_1101-2021_01_02_425006	88	154	5	5	CD
10_1101-2021_01_02_425006	88	155	)	)	-RRB-
10_1101-2021_01_02_425006	88	156	.CC	.CC	:
10_1101-2021_01_02_425006	88	157	-	-	:
10_1101-2021_01_02_425006	88	158	BY	by	IN
10_1101-2021_01_02_425006	88	159	-	-	HYPH
10_1101-2021_01_02_425006	88	160	NC	NC	NNP
10_1101-2021_01_02_425006	88	161	-	-	HYPH
10_1101-2021_01_02_425006	88	162	ND	ND	NNP
10_1101-2021_01_02_425006	88	163	4.0	4.0	CD
10_1101-2021_01_02_425006	88	164	International	International	NNP
10_1101-2021_01_02_425006	88	165	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	88	166	under	under	IN
10_1101-2021_01_02_425006	88	167	a	a	DT
10_1101-2021_01_02_425006	88	168	(	(	-LRB-
10_1101-2021_01_02_425006	88	169	which	which	WDT
10_1101-2021_01_02_425006	88	170	was	be	VBD
10_1101-2021_01_02_425006	88	171	not	not	RB
10_1101-2021_01_02_425006	88	172	certified	certify	VBN
10_1101-2021_01_02_425006	88	173	by	by	IN
10_1101-2021_01_02_425006	88	174	peer	peer	NN
10_1101-2021_01_02_425006	88	175	review	review	NN
10_1101-2021_01_02_425006	88	176	)	)	-RRB-
10_1101-2021_01_02_425006	88	177	is	be	VBZ
10_1101-2021_01_02_425006	88	178	the	the	DT
10_1101-2021_01_02_425006	88	179	author	author	NN
10_1101-2021_01_02_425006	88	180	/	/	SYM
10_1101-2021_01_02_425006	88	181	funder	funder	NN
10_1101-2021_01_02_425006	88	182	,	,	,
10_1101-2021_01_02_425006	88	183	who	who	WP
10_1101-2021_01_02_425006	88	184	has	have	VBZ
10_1101-2021_01_02_425006	88	185	granted	grant	VBN
10_1101-2021_01_02_425006	88	186	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	88	187	a	a	DT
10_1101-2021_01_02_425006	88	188	license	license	NN
10_1101-2021_01_02_425006	88	189	to	to	TO
10_1101-2021_01_02_425006	88	190	display	display	VB
10_1101-2021_01_02_425006	88	191	the	the	DT
10_1101-2021_01_02_425006	88	192	preprint	preprint	NN
10_1101-2021_01_02_425006	88	193	in	in	IN
10_1101-2021_01_02_425006	88	194	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	88	195	.	.	.
10_1101-2021_01_02_425006	89	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	89	2	is	be	VBZ
10_1101-2021_01_02_425006	89	3	made	make	VBN
10_1101-2021_01_02_425006	89	4	The	the	DT
10_1101-2021_01_02_425006	89	5	copyright	copyright	NN
10_1101-2021_01_02_425006	89	6	holder	holder	NN
10_1101-2021_01_02_425006	89	7	for	for	IN
10_1101-2021_01_02_425006	89	8	this	this	DT
10_1101-2021_01_02_425006	89	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	89	10	version	version	NN
10_1101-2021_01_02_425006	89	11	posted	post	VBD
10_1101-2021_01_02_425006	89	12	January	January	NNP
10_1101-2021_01_02_425006	89	13	6	6	CD
10_1101-2021_01_02_425006	89	14	,	,	,
10_1101-2021_01_02_425006	89	15	2021	2021	CD
10_1101-2021_01_02_425006	89	16	.	.	.
10_1101-2021_01_02_425006	89	17	;	;	:
10_1101-2021_01_02_425006	89	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	89	19	:	:	:
10_1101-2021_01_02_425006	89	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	89	21	preprint	preprint	NN
10_1101-2021_01_02_425006	89	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	89	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	89	24	9	9	CD
10_1101-2021_01_02_425006	89	25	where	where	WRB
10_1101-2021_01_02_425006	89	26	�	�	NNP
10_1101-2021_01_02_425006	89	27	denotes	denote	VBZ
10_1101-2021_01_02_425006	89	28	the	the	DT
10_1101-2021_01_02_425006	89	29	number	number	NN
10_1101-2021_01_02_425006	89	30	of	of	IN
10_1101-2021_01_02_425006	89	31	genomic	genomic	JJ
10_1101-2021_01_02_425006	89	32	positions	position	NNS
10_1101-2021_01_02_425006	89	33	on	on	IN
10_1101-2021_01_02_425006	89	34	�	�	NNP
10_1101-2021_01_02_425006	89	35	;	;	,
10_1101-2021_01_02_425006	89	36	�	�	NNP
10_1101-2021_01_02_425006	89	37	�	�	NNP
10_1101-2021_01_02_425006	89	38	denotes	denote	VBZ
10_1101-2021_01_02_425006	89	39	the	the	DT
10_1101-2021_01_02_425006	89	40	bias	bias	NN
10_1101-2021_01_02_425006	89	41	rate	rate	NN
10_1101-2021_01_02_425006	89	42	of	of	IN
10_1101-2021_01_02_425006	89	43	�	�	NNP
10_1101-2021_01_02_425006	89	44	�	�	NNP
10_1101-2021_01_02_425006	89	45	for	for	IN
10_1101-2021_01_02_425006	89	46	�	�	NNP
10_1101-2021_01_02_425006	89	47	;	;	,
10_1101-2021_01_02_425006	89	48	and	and	CC
10_1101-2021_01_02_425006	89	49	140	140	CD
10_1101-2021_01_02_425006	89	50	�	�	NNS
10_1101-2021_01_02_425006	89	51	�	�	NNS
10_1101-2021_01_02_425006	89	52	=	=	NFP
10_1101-2021_01_02_425006	89	53	(	(	-LRB-
10_1101-2021_01_02_425006	89	54	�	�	NNP
10_1101-2021_01_02_425006	89	55	�	�	NNP
10_1101-2021_01_02_425006	89	56	�	�	NNP
10_1101-2021_01_02_425006	89	57	,	,	,
10_1101-2021_01_02_425006	89	58	�	�	NNP
10_1101-2021_01_02_425006	89	59	�	�	NNP
10_1101-2021_01_02_425006	89	60	�	�	NNP
10_1101-2021_01_02_425006	89	61	,	,	,
10_1101-2021_01_02_425006	89	62	�	�	NNP
10_1101-2021_01_02_425006	89	63	�	�	NNP
10_1101-2021_01_02_425006	89	64	�	�	NNP
10_1101-2021_01_02_425006	89	65	,	,	,
10_1101-2021_01_02_425006	89	66	�	�	NNP
10_1101-2021_01_02_425006	89	67	�	�	NNP
10_1101-2021_01_02_425006	89	68	�	�	NNP
10_1101-2021_01_02_425006	89	69	,	,	,
10_1101-2021_01_02_425006	89	70	…	…	NFP
10_1101-2021_01_02_425006	89	71	,	,	,
10_1101-2021_01_02_425006	89	72	�	�	NNP
10_1101-2021_01_02_425006	89	73	�	�	NNP
10_1101-2021_01_02_425006	89	74	�	�	NNP
10_1101-2021_01_02_425006	89	75	,	,	,
10_1101-2021_01_02_425006	89	76	�	�	NNP
10_1101-2021_01_02_425006	89	77	�	�	NNP
10_1101-2021_01_02_425006	89	78	�	�	NNP
10_1101-2021_01_02_425006	89	79	)	)	-RRB-
10_1101-2021_01_02_425006	89	80	is	be	VBZ
10_1101-2021_01_02_425006	89	81	the	the	DT
10_1101-2021_01_02_425006	89	82	range	range	NN
10_1101-2021_01_02_425006	89	83	of	of	IN
10_1101-2021_01_02_425006	89	84	the	the	DT
10_1101-2021_01_02_425006	89	85	genomic	genomic	JJ
10_1101-2021_01_02_425006	89	86	positions	position	NNS
10_1101-2021_01_02_425006	89	87	of	of	IN
10_1101-2021_01_02_425006	89	88	{	{	-LRB-
10_1101-2021_01_02_425006	89	89	�	�	NNP
10_1101-2021_01_02_425006	89	90	�	�	NNP
10_1101-2021_01_02_425006	89	91	,	,	,
10_1101-2021_01_02_425006	89	92	�	�	NNP
10_1101-2021_01_02_425006	89	93	�	�	NNP
10_1101-2021_01_02_425006	89	94	,	,	,
10_1101-2021_01_02_425006	89	95	…	…	NFP
10_1101-2021_01_02_425006	89	96	,	,	,
10_1101-2021_01_02_425006	89	97	�	�	NNP
10_1101-2021_01_02_425006	89	98	�	�	NNP
10_1101-2021_01_02_425006	89	99	}	}	-RRB-
10_1101-2021_01_02_425006	89	100	,	,	,
10_1101-2021_01_02_425006	89	101	while	while	IN
10_1101-2021_01_02_425006	89	102	the	the	DT
10_1101-2021_01_02_425006	89	103	141	141	CD
10_1101-2021_01_02_425006	89	104	range	range	NN
10_1101-2021_01_02_425006	89	105	of	of	IN
10_1101-2021_01_02_425006	89	106	the	the	DT
10_1101-2021_01_02_425006	89	107	genomic	genomic	JJ
10_1101-2021_01_02_425006	89	108	positions	position	NNS
10_1101-2021_01_02_425006	89	109	of	of	IN
10_1101-2021_01_02_425006	89	110	�	�	NNP
10_1101-2021_01_02_425006	89	111	�	�	NNP
10_1101-2021_01_02_425006	89	112	is	be	VBZ
10_1101-2021_01_02_425006	89	113	[	[	-LRB-
10_1101-2021_01_02_425006	89	114	�	�	NNP
10_1101-2021_01_02_425006	89	115	�	�	NNP
10_1101-2021_01_02_425006	89	116	�	�	NNP
10_1101-2021_01_02_425006	89	117	,	,	,
10_1101-2021_01_02_425006	89	118	�	�	NNP
10_1101-2021_01_02_425006	89	119	�	�	NNP
10_1101-2021_01_02_425006	89	120	�	�	NNP
10_1101-2021_01_02_425006	89	121	]	]	-RRB-
10_1101-2021_01_02_425006	89	122	,	,	,
10_1101-2021_01_02_425006	89	123	1	1	CD
10_1101-2021_01_02_425006	89	124	≤	≤	NN
10_1101-2021_01_02_425006	89	125	�	�	NNP
10_1101-2021_01_02_425006	89	126	≤	≤	NN
10_1101-2021_01_02_425006	89	127	�	�	NNP
10_1101-2021_01_02_425006	89	128	.	.	.
10_1101-2021_01_02_425006	90	1	Similarly	similarly	RB
10_1101-2021_01_02_425006	90	2	,	,	,
10_1101-2021_01_02_425006	90	3	the	the	DT
10_1101-2021_01_02_425006	90	4	calculation	calculation	NN
10_1101-2021_01_02_425006	90	5	of	of	IN
10_1101-2021_01_02_425006	90	6	the	the	DT
10_1101-2021_01_02_425006	90	7	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	90	8	142	142	CD
10_1101-2021_01_02_425006	90	9	region	region	NN
10_1101-2021_01_02_425006	90	10	bias	bias	NN
10_1101-2021_01_02_425006	90	11	rate	rate	NN
10_1101-2021_01_02_425006	90	12	vector	vector	NN
10_1101-2021_01_02_425006	90	13	�	�	,
10_1101-2021_01_02_425006	90	14	=	=	NFP
10_1101-2021_01_02_425006	90	15	(	(	-LRB-
10_1101-2021_01_02_425006	90	16	�	�	NNP
10_1101-2021_01_02_425006	90	17	�	�	NNP
10_1101-2021_01_02_425006	90	18	,	,	,
10_1101-2021_01_02_425006	90	19	�	�	NNP
10_1101-2021_01_02_425006	90	20	�	�	NNP
10_1101-2021_01_02_425006	90	21	,	,	,
10_1101-2021_01_02_425006	90	22	…	…	NFP
10_1101-2021_01_02_425006	90	23	,	,	,
10_1101-2021_01_02_425006	90	24	�	�	NNP
10_1101-2021_01_02_425006	90	25	�	�	ADD
10_1101-2021_01_02_425006	90	26	�	�	NNP
10_1101-2021_01_02_425006	90	27	�	�	NNP
10_1101-2021_01_02_425006	90	28	)	)	-RRB-
10_1101-2021_01_02_425006	90	29	is	be	VBZ
10_1101-2021_01_02_425006	90	30	provided	provide	VBN
10_1101-2021_01_02_425006	90	31	in	in	IN
10_1101-2021_01_02_425006	90	32	method	method	NNP
10_1101-2021_01_02_425006	90	33	S3	S3	NNP
10_1101-2021_01_02_425006	90	34	.	.	.
10_1101-2021_01_02_425006	91	1	143	143	CD
10_1101-2021_01_02_425006	91	2	Modification	Modification	NNP
10_1101-2021_01_02_425006	91	3	of	of	IN
10_1101-2021_01_02_425006	91	4	maximal	maximal	JJ
10_1101-2021_01_02_425006	91	5	ATU	ATU	NNP
10_1101-2021_01_02_425006	91	6	clusters	cluster	NNS
10_1101-2021_01_02_425006	91	7	144	144	CD
10_1101-2021_01_02_425006	91	8	A	a	DT
10_1101-2021_01_02_425006	91	9	maximal	maximal	JJ
10_1101-2021_01_02_425006	91	10	ATU	ATU	NNP
10_1101-2021_01_02_425006	91	11	cluster	cluster	NN
10_1101-2021_01_02_425006	91	12	is	be	VBZ
10_1101-2021_01_02_425006	91	13	defined	define	VBN
10_1101-2021_01_02_425006	91	14	as	as	IN
10_1101-2021_01_02_425006	91	15	a	a	DT
10_1101-2021_01_02_425006	91	16	maximal	maximal	JJ
10_1101-2021_01_02_425006	91	17	consecutive	consecutive	JJ
10_1101-2021_01_02_425006	91	18	gene	gene	NN
10_1101-2021_01_02_425006	91	19	set	set	VBD
10_1101-2021_01_02_425006	91	20	such	such	JJ
10_1101-2021_01_02_425006	91	21	that	that	IN
10_1101-2021_01_02_425006	91	22	each	each	DT
10_1101-2021_01_02_425006	91	23	pair	pair	NN
10_1101-2021_01_02_425006	91	24	of	of	IN
10_1101-2021_01_02_425006	91	25	its	-PRON-	PRP$
10_1101-2021_01_02_425006	91	26	145	145	CD
10_1101-2021_01_02_425006	91	27	consecutive	consecutive	JJ
10_1101-2021_01_02_425006	91	28	genes	gene	NNS
10_1101-2021_01_02_425006	91	29	can	can	MD
10_1101-2021_01_02_425006	91	30	be	be	VB
10_1101-2021_01_02_425006	91	31	covered	cover	VBN
10_1101-2021_01_02_425006	91	32	by	by	IN
10_1101-2021_01_02_425006	91	33	at	at	RB
10_1101-2021_01_02_425006	91	34	least	least	RBS
10_1101-2021_01_02_425006	91	35	one	one	CD
10_1101-2021_01_02_425006	91	36	ATU	ATU	NNP
10_1101-2021_01_02_425006	91	37	.	.	.
10_1101-2021_01_02_425006	92	1	Similar	similar	JJ
10_1101-2021_01_02_425006	92	2	to	to	IN
10_1101-2021_01_02_425006	92	3	ATUs	atu	NNS
10_1101-2021_01_02_425006	92	4	,	,	,
10_1101-2021_01_02_425006	92	5	maximal	maximal	JJ
10_1101-2021_01_02_425006	92	6	ATU	ATU	NNP
10_1101-2021_01_02_425006	92	7	clusters	cluster	NNS
10_1101-2021_01_02_425006	92	8	are	be	VBP
10_1101-2021_01_02_425006	92	9	also	also	RB
10_1101-2021_01_02_425006	92	10	146	146	CD
10_1101-2021_01_02_425006	92	11	dynamically	dynamically	RB
10_1101-2021_01_02_425006	92	12	composed	compose	VBN
10_1101-2021_01_02_425006	92	13	under	under	IN
10_1101-2021_01_02_425006	92	14	different	different	JJ
10_1101-2021_01_02_425006	92	15	conditions	condition	NNS
10_1101-2021_01_02_425006	92	16	or	or	CC
10_1101-2021_01_02_425006	92	17	environmental	environmental	JJ
10_1101-2021_01_02_425006	92	18	stimuli	stimulus	NNS
10_1101-2021_01_02_425006	92	19	in	in	IN
10_1101-2021_01_02_425006	92	20	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	92	21	genomes	genome	NNS
10_1101-2021_01_02_425006	92	22	(	(	-LRB-
10_1101-2021_01_02_425006	92	23	5	5	CD
10_1101-2021_01_02_425006	92	24	,	,	,
10_1101-2021_01_02_425006	92	25	38	38	CD
10_1101-2021_01_02_425006	92	26	)	)	-RRB-
10_1101-2021_01_02_425006	92	27	.	.	.
10_1101-2021_01_02_425006	93	1	147	147	CD
10_1101-2021_01_02_425006	93	2	Such	such	PDT
10_1101-2021_01_02_425006	93	3	a	a	DT
10_1101-2021_01_02_425006	93	4	maximal	maximal	JJ
10_1101-2021_01_02_425006	93	5	ATU	atu	NN
10_1101-2021_01_02_425006	93	6	cluster	cluster	NN
10_1101-2021_01_02_425006	93	7	can	can	MD
10_1101-2021_01_02_425006	93	8	be	be	VB
10_1101-2021_01_02_425006	93	9	used	use	VBN
10_1101-2021_01_02_425006	93	10	as	as	IN
10_1101-2021_01_02_425006	93	11	an	an	DT
10_1101-2021_01_02_425006	93	12	independent	independent	JJ
10_1101-2021_01_02_425006	93	13	genomic	genomic	JJ
10_1101-2021_01_02_425006	93	14	region	region	NN
10_1101-2021_01_02_425006	93	15	for	for	IN
10_1101-2021_01_02_425006	93	16	ATU	ATU	NNP
10_1101-2021_01_02_425006	93	17	prediction	prediction	NN
10_1101-2021_01_02_425006	93	18	,	,	,
10_1101-2021_01_02_425006	93	19	which	which	WDT
10_1101-2021_01_02_425006	93	20	148	148	CD
10_1101-2021_01_02_425006	93	21	alleviates	alleviate	VBZ
10_1101-2021_01_02_425006	93	22	the	the	DT
10_1101-2021_01_02_425006	93	23	difficulty	difficulty	NN
10_1101-2021_01_02_425006	93	24	in	in	IN
10_1101-2021_01_02_425006	93	25	computationally	computationally	RB
10_1101-2021_01_02_425006	93	26	predicting	predict	VBG
10_1101-2021_01_02_425006	93	27	ATUs	atu	NNS
10_1101-2021_01_02_425006	93	28	at	at	IN
10_1101-2021_01_02_425006	93	29	the	the	DT
10_1101-2021_01_02_425006	93	30	genome	genome	JJ
10_1101-2021_01_02_425006	93	31	scale	scale	NN
10_1101-2021_01_02_425006	93	32	.	.	.
10_1101-2021_01_02_425006	94	1	The	the	DT
10_1101-2021_01_02_425006	94	2	output	output	NN
10_1101-2021_01_02_425006	94	3	of	of	IN
10_1101-2021_01_02_425006	94	4	our	-PRON-	PRP$
10_1101-2021_01_02_425006	94	5	in-149	in-149	NNP
10_1101-2021_01_02_425006	94	6	house	house	NN
10_1101-2021_01_02_425006	94	7	tool	tool	NN
10_1101-2021_01_02_425006	94	8	rSeqTU	rseqtu	PRP
10_1101-2021_01_02_425006	94	9	can	can	MD
10_1101-2021_01_02_425006	94	10	serve	serve	VB
10_1101-2021_01_02_425006	94	11	as	as	IN
10_1101-2021_01_02_425006	94	12	the	the	DT
10_1101-2021_01_02_425006	94	13	maximal	maximal	JJ
10_1101-2021_01_02_425006	94	14	ATU	ATU	NNP
10_1101-2021_01_02_425006	94	15	cluster	cluster	NN
10_1101-2021_01_02_425006	94	16	data	datum	NNS
10_1101-2021_01_02_425006	94	17	,	,	,
10_1101-2021_01_02_425006	94	18	which	which	WDT
10_1101-2021_01_02_425006	94	19	lays	lay	VBZ
10_1101-2021_01_02_425006	94	20	a	a	DT
10_1101-2021_01_02_425006	94	21	solid	solid	JJ
10_1101-2021_01_02_425006	94	22	foundation	foundation	NN
10_1101-2021_01_02_425006	94	23	for	for	IN
10_1101-2021_01_02_425006	94	24	ATU	ATU	NNP
10_1101-2021_01_02_425006	94	25	150	150	CD
10_1101-2021_01_02_425006	94	26	prediction	prediction	NN
10_1101-2021_01_02_425006	94	27	(	(	-LRB-
10_1101-2021_01_02_425006	94	28	5	5	CD
10_1101-2021_01_02_425006	94	29	)	)	-RRB-
10_1101-2021_01_02_425006	94	30	.	.	.
10_1101-2021_01_02_425006	95	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	95	2	modified	modify	VBD
10_1101-2021_01_02_425006	95	3	the	the	DT
10_1101-2021_01_02_425006	95	4	maximal	maximal	JJ
10_1101-2021_01_02_425006	95	5	ATU	ATU	NNP
10_1101-2021_01_02_425006	95	6	clusters	cluster	NNS
10_1101-2021_01_02_425006	95	7	from	from	IN
10_1101-2021_01_02_425006	95	8	rSeqTU	rseqtu	CD
10_1101-2021_01_02_425006	95	9	:	:	:
10_1101-2021_01_02_425006	95	10	(	(	-LRB-
10_1101-2021_01_02_425006	95	11	i	i	NN
10_1101-2021_01_02_425006	95	12	)	)	-RRB-
10_1101-2021_01_02_425006	95	13	two	two	CD
10_1101-2021_01_02_425006	95	14	maximal	maximal	JJ
10_1101-2021_01_02_425006	95	15	ATU	ATU	NNP
10_1101-2021_01_02_425006	95	16	clusters	cluster	NNS
10_1101-2021_01_02_425006	95	17	with	with	IN
10_1101-2021_01_02_425006	95	18	151	151	CD
10_1101-2021_01_02_425006	95	19	distances	distance	NNS
10_1101-2021_01_02_425006	95	20	less	less	JJR
10_1101-2021_01_02_425006	95	21	than	than	IN
10_1101-2021_01_02_425006	95	22	40	40	CD
10_1101-2021_01_02_425006	95	23	bp	bp	NN
10_1101-2021_01_02_425006	95	24	were	be	VBD
10_1101-2021_01_02_425006	95	25	combined	combine	VBN
10_1101-2021_01_02_425006	95	26	into	into	IN
10_1101-2021_01_02_425006	95	27	one	one	CD
10_1101-2021_01_02_425006	95	28	cluster	cluster	NN
10_1101-2021_01_02_425006	95	29	and	and	CC
10_1101-2021_01_02_425006	95	30	(	(	-LRB-
10_1101-2021_01_02_425006	95	31	ii	ii	NN
10_1101-2021_01_02_425006	95	32	)	)	-RRB-
10_1101-2021_01_02_425006	95	33	a	a	DT
10_1101-2021_01_02_425006	95	34	maximal	maximal	JJ
10_1101-2021_01_02_425006	95	35	ATU	ATU	NNP
10_1101-2021_01_02_425006	95	36	cluster	cluster	NN
10_1101-2021_01_02_425006	95	37	was	be	VBD
10_1101-2021_01_02_425006	95	38	split	split	VBN
10_1101-2021_01_02_425006	95	39	at	at	IN
10_1101-2021_01_02_425006	95	40	the	the	DT
10_1101-2021_01_02_425006	95	41	152	152	CD
10_1101-2021_01_02_425006	95	42	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	95	43	region	region	NN
10_1101-2021_01_02_425006	95	44	where	where	WRB
10_1101-2021_01_02_425006	95	45	the	the	DT
10_1101-2021_01_02_425006	95	46	opposite	opposite	JJ
10_1101-2021_01_02_425006	95	47	-	-	HYPH
10_1101-2021_01_02_425006	95	48	strand	strand	NN
10_1101-2021_01_02_425006	95	49	genes	gene	NNS
10_1101-2021_01_02_425006	95	50	were	be	VBD
10_1101-2021_01_02_425006	95	51	located	locate	VBN
10_1101-2021_01_02_425006	95	52	.	.	.
10_1101-2021_01_02_425006	96	1	In	in	IN
10_1101-2021_01_02_425006	96	2	addition	addition	NN
10_1101-2021_01_02_425006	96	3	,	,	,
10_1101-2021_01_02_425006	96	4	we	-PRON-	PRP
10_1101-2021_01_02_425006	96	5	selected	select	VBD
10_1101-2021_01_02_425006	96	6	the	the	DT
10_1101-2021_01_02_425006	96	7	maximal	maximal	JJ
10_1101-2021_01_02_425006	96	8	153	153	CD
10_1101-2021_01_02_425006	96	9	ATU	ATU	NNP
10_1101-2021_01_02_425006	96	10	clusters	cluster	NNS
10_1101-2021_01_02_425006	96	11	with	with	IN
10_1101-2021_01_02_425006	96	12	expression	expression	NN
10_1101-2021_01_02_425006	96	13	values	value	NNS
10_1101-2021_01_02_425006	96	14	over	over	IN
10_1101-2021_01_02_425006	96	15	ten	ten	CD
10_1101-2021_01_02_425006	96	16	(	(	-LRB-
10_1101-2021_01_02_425006	96	17	see	see	VB
10_1101-2021_01_02_425006	96	18	the	the	DT
10_1101-2021_01_02_425006	96	19	details	detail	NNS
10_1101-2021_01_02_425006	96	20	in	in	IN
10_1101-2021_01_02_425006	96	21	method	method	NNP
10_1101-2021_01_02_425006	96	22	S4	S4	NNP
10_1101-2021_01_02_425006	96	23	)	)	-RRB-
10_1101-2021_01_02_425006	96	24	,	,	,
10_1101-2021_01_02_425006	96	25	according	accord	VBG
10_1101-2021_01_02_425006	96	26	to	to	IN
10_1101-2021_01_02_425006	96	27	the	the	DT
10_1101-2021_01_02_425006	96	28	study	study	NN
10_1101-2021_01_02_425006	96	29	of	of	IN
10_1101-2021_01_02_425006	96	30	154	154	CD
10_1101-2021_01_02_425006	96	31	Etwiller	Etwiller	NNP
10_1101-2021_01_02_425006	96	32	et	et	NNP
10_1101-2021_01_02_425006	96	33	al	al	NNP
10_1101-2021_01_02_425006	96	34	.	.	.
10_1101-2021_01_02_425006	97	1	(	(	-LRB-
10_1101-2021_01_02_425006	97	2	13	13	CD
10_1101-2021_01_02_425006	97	3	)	)	-RRB-
10_1101-2021_01_02_425006	97	4	.	.	.
10_1101-2021_01_02_425006	98	1	155	155	CD
10_1101-2021_01_02_425006	98	2	The	the	DT
10_1101-2021_01_02_425006	98	3	mathematical	mathematical	JJ
10_1101-2021_01_02_425006	98	4	programming	programming	NN
10_1101-2021_01_02_425006	98	5	model	model	NN
10_1101-2021_01_02_425006	98	6	for	for	IN
10_1101-2021_01_02_425006	98	7	ATU	ATU	NNP
10_1101-2021_01_02_425006	98	8	prediction	prediction	NN
10_1101-2021_01_02_425006	98	9	156	156	CD
10_1101-2021_01_02_425006	98	10	The	the	DT
10_1101-2021_01_02_425006	98	11	predicted	predicted	JJ
10_1101-2021_01_02_425006	98	12	ATU	ATU	NNP
10_1101-2021_01_02_425006	98	13	expression	expression	NN
10_1101-2021_01_02_425006	98	14	profile	profile	NN
10_1101-2021_01_02_425006	98	15	should	should	MD
10_1101-2021_01_02_425006	98	16	be	be	VB
10_1101-2021_01_02_425006	98	17	consistent	consistent	JJ
10_1101-2021_01_02_425006	98	18	with	with	IN
10_1101-2021_01_02_425006	98	19	the	the	DT
10_1101-2021_01_02_425006	98	20	observed	observed	JJ
10_1101-2021_01_02_425006	98	21	expression	expression	NN
10_1101-2021_01_02_425006	98	22	profiles	profile	NNS
10_1101-2021_01_02_425006	98	23	of	of	IN
10_1101-2021_01_02_425006	98	24	the	the	DT
10_1101-2021_01_02_425006	98	25	157	157	CD
10_1101-2021_01_02_425006	98	26	.CC	.CC	:
10_1101-2021_01_02_425006	98	27	-	-	HYPH
10_1101-2021_01_02_425006	98	28	BY	by	IN
10_1101-2021_01_02_425006	98	29	-	-	HYPH
10_1101-2021_01_02_425006	98	30	NC	NC	NNP
10_1101-2021_01_02_425006	98	31	-	-	HYPH
10_1101-2021_01_02_425006	98	32	ND	ND	NNP
10_1101-2021_01_02_425006	98	33	4.0	4.0	CD
10_1101-2021_01_02_425006	98	34	International	International	NNP
10_1101-2021_01_02_425006	98	35	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	98	36	under	under	IN
10_1101-2021_01_02_425006	98	37	a	a	DT
10_1101-2021_01_02_425006	98	38	(	(	-LRB-
10_1101-2021_01_02_425006	98	39	which	which	WDT
10_1101-2021_01_02_425006	98	40	was	be	VBD
10_1101-2021_01_02_425006	98	41	not	not	RB
10_1101-2021_01_02_425006	98	42	certified	certify	VBN
10_1101-2021_01_02_425006	98	43	by	by	IN
10_1101-2021_01_02_425006	98	44	peer	peer	NN
10_1101-2021_01_02_425006	98	45	review	review	NN
10_1101-2021_01_02_425006	98	46	)	)	-RRB-
10_1101-2021_01_02_425006	98	47	is	be	VBZ
10_1101-2021_01_02_425006	98	48	the	the	DT
10_1101-2021_01_02_425006	98	49	author	author	NN
10_1101-2021_01_02_425006	98	50	/	/	SYM
10_1101-2021_01_02_425006	98	51	funder	funder	NN
10_1101-2021_01_02_425006	98	52	,	,	,
10_1101-2021_01_02_425006	98	53	who	who	WP
10_1101-2021_01_02_425006	98	54	has	have	VBZ
10_1101-2021_01_02_425006	98	55	granted	grant	VBN
10_1101-2021_01_02_425006	98	56	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	98	57	a	a	DT
10_1101-2021_01_02_425006	98	58	license	license	NN
10_1101-2021_01_02_425006	98	59	to	to	TO
10_1101-2021_01_02_425006	98	60	display	display	VB
10_1101-2021_01_02_425006	98	61	the	the	DT
10_1101-2021_01_02_425006	98	62	preprint	preprint	NN
10_1101-2021_01_02_425006	98	63	in	in	IN
10_1101-2021_01_02_425006	98	64	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	98	65	.	.	.
10_1101-2021_01_02_425006	99	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	99	2	is	be	VBZ
10_1101-2021_01_02_425006	99	3	made	make	VBN
10_1101-2021_01_02_425006	99	4	The	the	DT
10_1101-2021_01_02_425006	99	5	copyright	copyright	NN
10_1101-2021_01_02_425006	99	6	holder	holder	NN
10_1101-2021_01_02_425006	99	7	for	for	IN
10_1101-2021_01_02_425006	99	8	this	this	DT
10_1101-2021_01_02_425006	99	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	99	10	version	version	NN
10_1101-2021_01_02_425006	99	11	posted	post	VBD
10_1101-2021_01_02_425006	99	12	January	January	NNP
10_1101-2021_01_02_425006	99	13	6	6	CD
10_1101-2021_01_02_425006	99	14	,	,	,
10_1101-2021_01_02_425006	99	15	2021	2021	CD
10_1101-2021_01_02_425006	99	16	.	.	.
10_1101-2021_01_02_425006	99	17	;	;	:
10_1101-2021_01_02_425006	99	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	99	19	:	:	:
10_1101-2021_01_02_425006	99	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	99	21	preprint	preprint	NN
10_1101-2021_01_02_425006	99	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	99	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	99	24	10	10	CD
10_1101-2021_01_02_425006	99	25	genetic	genetic	JJ
10_1101-2021_01_02_425006	99	26	and	and	CC
10_1101-2021_01_02_425006	99	27	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	99	28	regions	region	NNS
10_1101-2021_01_02_425006	99	29	.	.	.
10_1101-2021_01_02_425006	100	1	Therefore	therefore	RB
10_1101-2021_01_02_425006	100	2	,	,	,
10_1101-2021_01_02_425006	100	3	the	the	DT
10_1101-2021_01_02_425006	100	4	prediction	prediction	NN
10_1101-2021_01_02_425006	100	5	of	of	IN
10_1101-2021_01_02_425006	100	6	the	the	DT
10_1101-2021_01_02_425006	100	7	ATU	ATU	NNP
10_1101-2021_01_02_425006	100	8	profiles	profile	NNS
10_1101-2021_01_02_425006	100	9	can	can	MD
10_1101-2021_01_02_425006	100	10	be	be	VB
10_1101-2021_01_02_425006	100	11	modeled	model	VBN
10_1101-2021_01_02_425006	100	12	as	as	IN
10_1101-2021_01_02_425006	100	13	an	an	DT
10_1101-2021_01_02_425006	100	14	158	158	CD
10_1101-2021_01_02_425006	100	15	optimization	optimization	NN
10_1101-2021_01_02_425006	100	16	problem	problem	NN
10_1101-2021_01_02_425006	100	17	,	,	,
10_1101-2021_01_02_425006	100	18	which	which	WDT
10_1101-2021_01_02_425006	100	19	seeks	seek	VBZ
10_1101-2021_01_02_425006	100	20	an	an	DT
10_1101-2021_01_02_425006	100	21	optimum	optimum	JJ
10_1101-2021_01_02_425006	100	22	expression	expression	NN
10_1101-2021_01_02_425006	100	23	combination	combination	NN
10_1101-2021_01_02_425006	100	24	of	of	IN
10_1101-2021_01_02_425006	100	25	all	all	DT
10_1101-2021_01_02_425006	100	26	of	of	IN
10_1101-2021_01_02_425006	100	27	the	the	DT
10_1101-2021_01_02_425006	100	28	to	to	TO
10_1101-2021_01_02_425006	100	29	-	-	HYPH
10_1101-2021_01_02_425006	100	30	be	be	VB
10_1101-2021_01_02_425006	100	31	-	-	HYPH
10_1101-2021_01_02_425006	100	32	identified	identify	VBN
10_1101-2021_01_02_425006	100	33	159	159	CD
10_1101-2021_01_02_425006	100	34	ATUs	atu	NNS
10_1101-2021_01_02_425006	100	35	to	to	TO
10_1101-2021_01_02_425006	100	36	minimize	minimize	VB
10_1101-2021_01_02_425006	100	37	the	the	DT
10_1101-2021_01_02_425006	100	38	gap	gap	NN
10_1101-2021_01_02_425006	100	39	between	between	IN
10_1101-2021_01_02_425006	100	40	the	the	DT
10_1101-2021_01_02_425006	100	41	predicted	predict	VBN
10_1101-2021_01_02_425006	100	42	ATUs	atu	NNS
10_1101-2021_01_02_425006	100	43	and	and	CC
10_1101-2021_01_02_425006	100	44	the	the	DT
10_1101-2021_01_02_425006	100	45	observed	observe	VBN
10_1101-2021_01_02_425006	100	46	genetic	genetic	JJ
10_1101-2021_01_02_425006	100	47	and	and	CC
10_1101-2021_01_02_425006	100	48	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	100	49	region	region	NN
10_1101-2021_01_02_425006	100	50	160	160	CD
10_1101-2021_01_02_425006	100	51	expression	expression	NN
10_1101-2021_01_02_425006	100	52	profiles	profile	NNS
10_1101-2021_01_02_425006	100	53	.	.	.
10_1101-2021_01_02_425006	101	1	Here	here	RB
10_1101-2021_01_02_425006	101	2	,	,	,
10_1101-2021_01_02_425006	101	3	a	a	DT
10_1101-2021_01_02_425006	101	4	convex	convex	NNP
10_1101-2021_01_02_425006	101	5	quadratic	quadratic	NNP
10_1101-2021_01_02_425006	101	6	programming	programming	NN
10_1101-2021_01_02_425006	101	7	model	model	NN
10_1101-2021_01_02_425006	101	8	was	be	VBD
10_1101-2021_01_02_425006	101	9	built	build	VBN
10_1101-2021_01_02_425006	101	10	to	to	TO
10_1101-2021_01_02_425006	101	11	solve	solve	VB
10_1101-2021_01_02_425006	101	12	this	this	DT
10_1101-2021_01_02_425006	101	13	optimization	optimization	NN
10_1101-2021_01_02_425006	101	14	161	161	CD
10_1101-2021_01_02_425006	101	15	problem	problem	NN
10_1101-2021_01_02_425006	101	16	.	.	.
10_1101-2021_01_02_425006	102	1	162	162	CD
10_1101-2021_01_02_425006	102	2	We	-PRON-	PRP
10_1101-2021_01_02_425006	102	3	denoted	denote	VBD
10_1101-2021_01_02_425006	102	4	a	a	DT
10_1101-2021_01_02_425006	102	5	maximal	maximal	JJ
10_1101-2021_01_02_425006	102	6	ATU	ATU	NNP
10_1101-2021_01_02_425006	102	7	cluster	cluster	NN
10_1101-2021_01_02_425006	102	8	as	as	IN
10_1101-2021_01_02_425006	102	9	�	�	NNP
10_1101-2021_01_02_425006	102	10	,	,	,
10_1101-2021_01_02_425006	102	11	assuming	assume	VBG
10_1101-2021_01_02_425006	102	12	that	that	IN
10_1101-2021_01_02_425006	102	13	it	-PRON-	PRP
10_1101-2021_01_02_425006	102	14	contains	contain	VBZ
10_1101-2021_01_02_425006	102	15	the	the	DT
10_1101-2021_01_02_425006	102	16	consecutive	consecutive	JJ
10_1101-2021_01_02_425006	102	17	genes	gene	NNS
10_1101-2021_01_02_425006	102	18	163	163	CD
10_1101-2021_01_02_425006	102	19	{	{	-LRB-
10_1101-2021_01_02_425006	102	20	�	�	NNP
10_1101-2021_01_02_425006	102	21	�	�	NNP
10_1101-2021_01_02_425006	102	22	,	,	,
10_1101-2021_01_02_425006	102	23	…	…	NFP
10_1101-2021_01_02_425006	102	24	,	,	,
10_1101-2021_01_02_425006	102	25	�	�	NNP
10_1101-2021_01_02_425006	102	26	�	�	NNP
10_1101-2021_01_02_425006	102	27	}	}	-RRB-
10_1101-2021_01_02_425006	102	28	,	,	,
10_1101-2021_01_02_425006	102	29	and	and	CC
10_1101-2021_01_02_425006	102	30	the	the	DT
10_1101-2021_01_02_425006	102	31	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	102	32	regions	region	NNS
10_1101-2021_01_02_425006	102	33	of	of	IN
10_1101-2021_01_02_425006	102	34	these	these	DT
10_1101-2021_01_02_425006	102	35	genes	gene	NNS
10_1101-2021_01_02_425006	102	36	are	be	VBP
10_1101-2021_01_02_425006	102	37	{	{	-LRB-
10_1101-2021_01_02_425006	102	38	�	�	NNP
10_1101-2021_01_02_425006	102	39	�	�	NNP
10_1101-2021_01_02_425006	102	40	,	,	,
10_1101-2021_01_02_425006	102	41	�	�	NNP
10_1101-2021_01_02_425006	102	42	,	,	,
10_1101-2021_01_02_425006	102	43	…	…	NFP
10_1101-2021_01_02_425006	102	44	,	,	,
10_1101-2021_01_02_425006	102	45	�	�	NNP
10_1101-2021_01_02_425006	102	46	�	�	NNP
10_1101-2021_01_02_425006	102	47	�	�	NNP
10_1101-2021_01_02_425006	102	48	�	�	NNP
10_1101-2021_01_02_425006	102	49	,	,	,
10_1101-2021_01_02_425006	102	50	�	�	NNP
10_1101-2021_01_02_425006	102	51	}	}	-RRB-
10_1101-2021_01_02_425006	102	52	.	.	.
10_1101-2021_01_02_425006	103	1	The	the	DT
10_1101-2021_01_02_425006	103	2	size	size	NN
10_1101-2021_01_02_425006	103	3	of	of	IN
10_1101-2021_01_02_425006	103	4	�	�	NNP
10_1101-2021_01_02_425006	103	5	is	be	VBZ
10_1101-2021_01_02_425006	103	6	defined	define	VBN
10_1101-2021_01_02_425006	103	7	as	as	IN
10_1101-2021_01_02_425006	103	8	164	164	CD
10_1101-2021_01_02_425006	103	9	the	the	DT
10_1101-2021_01_02_425006	103	10	number	number	NN
10_1101-2021_01_02_425006	103	11	of	of	IN
10_1101-2021_01_02_425006	103	12	its	-PRON-	PRP$
10_1101-2021_01_02_425006	103	13	component	component	NN
10_1101-2021_01_02_425006	103	14	genes	gene	NNS
10_1101-2021_01_02_425006	103	15	�	�	NNP
10_1101-2021_01_02_425006	103	16	.	.	.
10_1101-2021_01_02_425006	104	1	Theoretically	theoretically	RB
10_1101-2021_01_02_425006	104	2	,	,	,
10_1101-2021_01_02_425006	104	3	there	there	EX
10_1101-2021_01_02_425006	104	4	are	be	VBP
10_1101-2021_01_02_425006	104	5	�	�	,
10_1101-2021_01_02_425006	104	6	×	×	NFP
10_1101-2021_01_02_425006	104	7	(	(	-LRB-
10_1101-2021_01_02_425006	104	8	�	�	NNP
10_1101-2021_01_02_425006	104	9	�	�	NNP
10_1101-2021_01_02_425006	104	10	�	�	NNP
10_1101-2021_01_02_425006	104	11	)	)	-RRB-
10_1101-2021_01_02_425006	104	12	�	�	.
10_1101-2021_01_02_425006	104	13	ATUs	atu	NNS
10_1101-2021_01_02_425006	104	14	for	for	IN
10_1101-2021_01_02_425006	104	15	�	�	NNP
10_1101-2021_01_02_425006	104	16	,	,	,
10_1101-2021_01_02_425006	104	17	and	and	CC
10_1101-2021_01_02_425006	104	18	an	an	DT
10_1101-2021_01_02_425006	104	19	ATU	ATU	NNP
10_1101-2021_01_02_425006	104	20	with	with	IN
10_1101-2021_01_02_425006	104	21	165	165	CD
10_1101-2021_01_02_425006	104	22	consecutive	consecutive	JJ
10_1101-2021_01_02_425006	104	23	genes	gene	NNS
10_1101-2021_01_02_425006	104	24	{	{	-LRB-
10_1101-2021_01_02_425006	104	25	�	�	NNP
10_1101-2021_01_02_425006	104	26	�	�	NNP
10_1101-2021_01_02_425006	104	27	,	,	,
10_1101-2021_01_02_425006	104	28	�	�	NNP
10_1101-2021_01_02_425006	104	29	�	�	NNP
10_1101-2021_01_02_425006	104	30	�	�	NNP
10_1101-2021_01_02_425006	104	31	�	�	NNP
10_1101-2021_01_02_425006	104	32	,	,	,
10_1101-2021_01_02_425006	104	33	…	…	NFP
10_1101-2021_01_02_425006	104	34	,	,	,
10_1101-2021_01_02_425006	104	35	�	�	NNP
10_1101-2021_01_02_425006	104	36	�	�	.
10_1101-2021_01_02_425006	104	37	}	}	-RRB-
10_1101-2021_01_02_425006	104	38	is	be	VBZ
10_1101-2021_01_02_425006	104	39	denoted	denote	VBN
10_1101-2021_01_02_425006	104	40	as	as	IN
10_1101-2021_01_02_425006	104	41	�	�	NNP
10_1101-2021_01_02_425006	104	42	�	�	NNP
10_1101-2021_01_02_425006	104	43	,	,	,
10_1101-2021_01_02_425006	104	44	�	�	NNP
10_1101-2021_01_02_425006	104	45	;	;	:
10_1101-2021_01_02_425006	104	46	the	the	DT
10_1101-2021_01_02_425006	104	47	corresponding	corresponding	JJ
10_1101-2021_01_02_425006	104	48	expression	expression	NN
10_1101-2021_01_02_425006	104	49	value	value	NN
10_1101-2021_01_02_425006	104	50	is	be	VBZ
10_1101-2021_01_02_425006	104	51	�	�	NNP
10_1101-2021_01_02_425006	104	52	�	�	NNP
10_1101-2021_01_02_425006	104	53	,	,	,
10_1101-2021_01_02_425006	104	54	�	�	NNP
10_1101-2021_01_02_425006	104	55	,	,	,
10_1101-2021_01_02_425006	104	56	1	1	CD
10_1101-2021_01_02_425006	104	57	≤166	≤166	NN
10_1101-2021_01_02_425006	104	58	�	�	NNP
10_1101-2021_01_02_425006	104	59	≤	≤	NNP
10_1101-2021_01_02_425006	104	60	�	�	NNP
10_1101-2021_01_02_425006	104	61	≤	≤	NN
10_1101-2021_01_02_425006	104	62	�	�	NNP
10_1101-2021_01_02_425006	104	63	.	.	.
10_1101-2021_01_02_425006	105	1	167	167	CD
10_1101-2021_01_02_425006	105	2	For	for	IN
10_1101-2021_01_02_425006	105	3	the	the	DT
10_1101-2021_01_02_425006	105	4	component	component	NN
10_1101-2021_01_02_425006	105	5	gene	gene	NN
10_1101-2021_01_02_425006	105	6	�	�	NNP
10_1101-2021_01_02_425006	105	7	�	�	NNP
10_1101-2021_01_02_425006	105	8	of	of	IN
10_1101-2021_01_02_425006	105	9	�	�	NNP
10_1101-2021_01_02_425006	105	10	,	,	,
10_1101-2021_01_02_425006	105	11	the	the	DT
10_1101-2021_01_02_425006	105	12	gap	gap	NN
10_1101-2021_01_02_425006	105	13	between	between	IN
10_1101-2021_01_02_425006	105	14	the	the	DT
10_1101-2021_01_02_425006	105	15	gene	gene	NN
10_1101-2021_01_02_425006	105	16	expression	expression	NN
10_1101-2021_01_02_425006	105	17	value	value	NN
10_1101-2021_01_02_425006	105	18	�	�	.
10_1101-2021_01_02_425006	105	19	�	�	NNP
10_1101-2021_01_02_425006	105	20	and	and	CC
10_1101-2021_01_02_425006	105	21	the	the	DT
10_1101-2021_01_02_425006	105	22	sum	sum	NN
10_1101-2021_01_02_425006	105	23	of	of	IN
10_1101-2021_01_02_425006	105	24	the	the	DT
10_1101-2021_01_02_425006	105	25	168	168	CD
10_1101-2021_01_02_425006	105	26	expression	expression	NN
10_1101-2021_01_02_425006	105	27	level	level	NN
10_1101-2021_01_02_425006	105	28	of	of	IN
10_1101-2021_01_02_425006	105	29	the	the	DT
10_1101-2021_01_02_425006	105	30	ATUs	atu	NNS
10_1101-2021_01_02_425006	105	31	containing	contain	VBG
10_1101-2021_01_02_425006	105	32	it	-PRON-	PRP
10_1101-2021_01_02_425006	105	33	is	be	VBZ
10_1101-2021_01_02_425006	105	34	denoted	denote	VBN
10_1101-2021_01_02_425006	105	35	as	as	IN
10_1101-2021_01_02_425006	105	36	�	�	NNP
10_1101-2021_01_02_425006	105	37	�	�	NNP
10_1101-2021_01_02_425006	105	38	,	,	,
10_1101-2021_01_02_425006	105	39	which	which	WDT
10_1101-2021_01_02_425006	105	40	provides	provide	VBZ
10_1101-2021_01_02_425006	105	41	the	the	DT
10_1101-2021_01_02_425006	105	42	first	first	JJ
10_1101-2021_01_02_425006	105	43	�	�	NNP
10_1101-2021_01_02_425006	105	44	equality	equality	NN
10_1101-2021_01_02_425006	105	45	169	169	CD
10_1101-2021_01_02_425006	105	46	constraints	constraint	NNS
10_1101-2021_01_02_425006	105	47	in	in	IN
10_1101-2021_01_02_425006	105	48	our	-PRON-	PRP$
10_1101-2021_01_02_425006	105	49	mathematical	mathematical	JJ
10_1101-2021_01_02_425006	105	50	programming	programming	NN
10_1101-2021_01_02_425006	105	51	model	model	NN
10_1101-2021_01_02_425006	105	52	,	,	,
10_1101-2021_01_02_425006	105	53	�	�	NNP
10_1101-2021_01_02_425006	105	54	=	=	SYM
10_1101-2021_01_02_425006	105	55	1,2	1,2	CD
10_1101-2021_01_02_425006	105	56	,	,	,
10_1101-2021_01_02_425006	105	57	…	…	NFP
10_1101-2021_01_02_425006	105	58	,	,	,
10_1101-2021_01_02_425006	105	59	�	�	NNP
10_1101-2021_01_02_425006	105	60	.	.	.
10_1101-2021_01_02_425006	106	1	Similarly	similarly	RB
10_1101-2021_01_02_425006	106	2	,	,	,
10_1101-2021_01_02_425006	106	3	for	for	IN
10_1101-2021_01_02_425006	106	4	the	the	DT
10_1101-2021_01_02_425006	106	5	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	106	6	region	region	NN
10_1101-2021_01_02_425006	106	7	170	170	CD
10_1101-2021_01_02_425006	106	8	�	�	NNP
10_1101-2021_01_02_425006	106	9	�	�	NNP
10_1101-2021_01_02_425006	106	10	,	,	,
10_1101-2021_01_02_425006	106	11	�	�	NNP
10_1101-2021_01_02_425006	106	12	�	�	NNS
10_1101-2021_01_02_425006	106	13	�	�	NN
10_1101-2021_01_02_425006	106	14	of	of	IN
10_1101-2021_01_02_425006	106	15	�	�	NNP
10_1101-2021_01_02_425006	106	16	,	,	,
10_1101-2021_01_02_425006	106	17	the	the	DT
10_1101-2021_01_02_425006	106	18	gap	gap	NN
10_1101-2021_01_02_425006	106	19	between	between	IN
10_1101-2021_01_02_425006	106	20	the	the	DT
10_1101-2021_01_02_425006	106	21	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	106	22	region	region	NN
10_1101-2021_01_02_425006	106	23	expression	expression	NN
10_1101-2021_01_02_425006	106	24	value	value	NN
10_1101-2021_01_02_425006	106	25	�	�	NNP
10_1101-2021_01_02_425006	106	26	�	�	NNP
10_1101-2021_01_02_425006	106	27	,	,	,
10_1101-2021_01_02_425006	106	28	�	�	NNP
10_1101-2021_01_02_425006	106	29	�	�	NNP
10_1101-2021_01_02_425006	106	30	�	�	NNP
10_1101-2021_01_02_425006	106	31	and	and	CC
10_1101-2021_01_02_425006	106	32	the	the	DT
10_1101-2021_01_02_425006	106	33	sum	sum	NN
10_1101-2021_01_02_425006	106	34	of	of	IN
10_1101-2021_01_02_425006	106	35	the	the	DT
10_1101-2021_01_02_425006	106	36	171	171	CD
10_1101-2021_01_02_425006	106	37	expression	expression	NN
10_1101-2021_01_02_425006	106	38	level	level	NN
10_1101-2021_01_02_425006	106	39	of	of	IN
10_1101-2021_01_02_425006	106	40	the	the	DT
10_1101-2021_01_02_425006	106	41	ATUs	atu	NNS
10_1101-2021_01_02_425006	106	42	containing	contain	VBG
10_1101-2021_01_02_425006	106	43	it	-PRON-	PRP
10_1101-2021_01_02_425006	106	44	is	be	VBZ
10_1101-2021_01_02_425006	106	45	denoted	denote	VBN
10_1101-2021_01_02_425006	106	46	as	as	IN
10_1101-2021_01_02_425006	106	47	�	�	NNP
10_1101-2021_01_02_425006	106	48	�	�	NNP
10_1101-2021_01_02_425006	106	49	,	,	,
10_1101-2021_01_02_425006	106	50	providing	provide	VBG
10_1101-2021_01_02_425006	106	51	the	the	DT
10_1101-2021_01_02_425006	106	52	last	last	JJ
10_1101-2021_01_02_425006	106	53	�	�	NNP
10_1101-2021_01_02_425006	106	54	−	−	NNP
10_1101-2021_01_02_425006	106	55	1	1	CD
10_1101-2021_01_02_425006	106	56	equality	equality	NN
10_1101-2021_01_02_425006	106	57	172	172	CD
10_1101-2021_01_02_425006	106	58	constraints	constraint	NNS
10_1101-2021_01_02_425006	106	59	in	in	IN
10_1101-2021_01_02_425006	106	60	our	-PRON-	PRP$
10_1101-2021_01_02_425006	106	61	mathematical	mathematical	JJ
10_1101-2021_01_02_425006	106	62	programming	programming	NN
10_1101-2021_01_02_425006	106	63	model	model	NN
10_1101-2021_01_02_425006	106	64	,	,	,
10_1101-2021_01_02_425006	106	65	�	�	NNP
10_1101-2021_01_02_425006	106	66	=	=	SYM
10_1101-2021_01_02_425006	106	67	1,2	1,2	CD
10_1101-2021_01_02_425006	106	68	,	,	,
10_1101-2021_01_02_425006	106	69	…	…	NFP
10_1101-2021_01_02_425006	106	70	,	,	,
10_1101-2021_01_02_425006	106	71	�	�	NNP
10_1101-2021_01_02_425006	106	72	−	−	NNP
10_1101-2021_01_02_425006	106	73	1	1	CD
10_1101-2021_01_02_425006	106	74	.	.	.
10_1101-2021_01_02_425006	107	1	173	173	CD
10_1101-2021_01_02_425006	107	2	The	the	DT
10_1101-2021_01_02_425006	107	3	goal	goal	NN
10_1101-2021_01_02_425006	107	4	of	of	IN
10_1101-2021_01_02_425006	107	5	our	-PRON-	PRP$
10_1101-2021_01_02_425006	107	6	mathematical	mathematical	JJ
10_1101-2021_01_02_425006	107	7	programming	programming	NN
10_1101-2021_01_02_425006	107	8	model	model	NN
10_1101-2021_01_02_425006	107	9	is	be	VBZ
10_1101-2021_01_02_425006	107	10	to	to	TO
10_1101-2021_01_02_425006	107	11	minimize	minimize	VB
10_1101-2021_01_02_425006	107	12	the	the	DT
10_1101-2021_01_02_425006	107	13	square	square	NN
10_1101-2021_01_02_425006	107	14	of	of	IN
10_1101-2021_01_02_425006	107	15	�	�	NNP
10_1101-2021_01_02_425006	107	16	=	=	SYM
10_1101-2021_01_02_425006	107	17	174	174	CD
10_1101-2021_01_02_425006	107	18	(	(	-LRB-
10_1101-2021_01_02_425006	107	19	�	�	NNP
10_1101-2021_01_02_425006	107	20	�	�	NNP
10_1101-2021_01_02_425006	107	21	,	,	,
10_1101-2021_01_02_425006	107	22	�	�	NNP
10_1101-2021_01_02_425006	107	23	�	�	NNP
10_1101-2021_01_02_425006	107	24	,	,	,
10_1101-2021_01_02_425006	107	25	…	…	NFP
10_1101-2021_01_02_425006	107	26	,	,	,
10_1101-2021_01_02_425006	107	27	�	�	NNP
10_1101-2021_01_02_425006	107	28	�	�	NNP
10_1101-2021_01_02_425006	107	29	,	,	,
10_1101-2021_01_02_425006	107	30	�	�	NNP
10_1101-2021_01_02_425006	107	31	�	�	NNP
10_1101-2021_01_02_425006	107	32	,	,	,
10_1101-2021_01_02_425006	107	33	…	…	NFP
10_1101-2021_01_02_425006	107	34	,	,	,
10_1101-2021_01_02_425006	107	35	�	�	NNP
10_1101-2021_01_02_425006	107	36	�	�	ADD
10_1101-2021_01_02_425006	107	37	�	�	NNP
10_1101-2021_01_02_425006	107	38	�	�	NNP
10_1101-2021_01_02_425006	107	39	)	)	-RRB-
10_1101-2021_01_02_425006	107	40	,	,	,
10_1101-2021_01_02_425006	107	41	as	as	IN
10_1101-2021_01_02_425006	107	42	the	the	DT
10_1101-2021_01_02_425006	107	43	combination	combination	NN
10_1101-2021_01_02_425006	107	44	of	of	IN
10_1101-2021_01_02_425006	107	45	�	�	NNP
10_1101-2021_01_02_425006	107	46	�	�	NNP
10_1101-2021_01_02_425006	107	47	,	,	,
10_1101-2021_01_02_425006	107	48	�	�	NNP
10_1101-2021_01_02_425006	107	49	with	with	IN
10_1101-2021_01_02_425006	107	50	a	a	DT
10_1101-2021_01_02_425006	107	51	minimal	minimal	JJ
10_1101-2021_01_02_425006	107	52	value	value	NN
10_1101-2021_01_02_425006	107	53	of	of	IN
10_1101-2021_01_02_425006	107	54	�	�	NNP
10_1101-2021_01_02_425006	107	55	�	�	NNP
10_1101-2021_01_02_425006	107	56	�	�	NNP
10_1101-2021_01_02_425006	107	57	is	be	VBZ
10_1101-2021_01_02_425006	107	58	corresponding	correspond	VBG
10_1101-2021_01_02_425006	107	59	to	to	IN
10_1101-2021_01_02_425006	107	60	175	175	CD
10_1101-2021_01_02_425006	107	61	an	an	DT
10_1101-2021_01_02_425006	107	62	optimum	optimum	JJ
10_1101-2021_01_02_425006	107	63	expression	expression	NN
10_1101-2021_01_02_425006	107	64	combination	combination	NN
10_1101-2021_01_02_425006	107	65	of	of	IN
10_1101-2021_01_02_425006	107	66	all	all	DT
10_1101-2021_01_02_425006	107	67	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	107	68	�	�	NNPS
10_1101-2021_01_02_425006	107	69	�	�	NNP
10_1101-2021_01_02_425006	107	70	,	,	,
10_1101-2021_01_02_425006	107	71	�	�	NNP
10_1101-2021_01_02_425006	107	72	for	for	IN
10_1101-2021_01_02_425006	107	73	�	�	NNP
10_1101-2021_01_02_425006	107	74	,	,	,
10_1101-2021_01_02_425006	107	75	1	1	CD
10_1101-2021_01_02_425006	107	76	≤	≤	NN
10_1101-2021_01_02_425006	107	77	�	�	NNP
10_1101-2021_01_02_425006	107	78	≤	≤	NNP
10_1101-2021_01_02_425006	107	79	�	�	NNP
10_1101-2021_01_02_425006	107	80	≤	≤	NN
10_1101-2021_01_02_425006	107	81	�	�	NNP
10_1101-2021_01_02_425006	107	82	.	.	.
10_1101-2021_01_02_425006	108	1	Additionally	additionally	RB
10_1101-2021_01_02_425006	108	2	,	,	,
10_1101-2021_01_02_425006	108	3	to	to	TO
10_1101-2021_01_02_425006	108	4	control	control	VB
10_1101-2021_01_02_425006	108	5	the	the	DT
10_1101-2021_01_02_425006	108	6	176	176	CD
10_1101-2021_01_02_425006	108	7	.CC	.CC	:
10_1101-2021_01_02_425006	108	8	-	-	HYPH
10_1101-2021_01_02_425006	108	9	BY	by	IN
10_1101-2021_01_02_425006	108	10	-	-	HYPH
10_1101-2021_01_02_425006	108	11	NC	NC	NNP
10_1101-2021_01_02_425006	108	12	-	-	HYPH
10_1101-2021_01_02_425006	108	13	ND	ND	NNP
10_1101-2021_01_02_425006	108	14	4.0	4.0	CD
10_1101-2021_01_02_425006	108	15	International	International	NNP
10_1101-2021_01_02_425006	108	16	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	108	17	under	under	IN
10_1101-2021_01_02_425006	108	18	a	a	DT
10_1101-2021_01_02_425006	108	19	(	(	-LRB-
10_1101-2021_01_02_425006	108	20	which	which	WDT
10_1101-2021_01_02_425006	108	21	was	be	VBD
10_1101-2021_01_02_425006	108	22	not	not	RB
10_1101-2021_01_02_425006	108	23	certified	certify	VBN
10_1101-2021_01_02_425006	108	24	by	by	IN
10_1101-2021_01_02_425006	108	25	peer	peer	NN
10_1101-2021_01_02_425006	108	26	review	review	NN
10_1101-2021_01_02_425006	108	27	)	)	-RRB-
10_1101-2021_01_02_425006	108	28	is	be	VBZ
10_1101-2021_01_02_425006	108	29	the	the	DT
10_1101-2021_01_02_425006	108	30	author	author	NN
10_1101-2021_01_02_425006	108	31	/	/	SYM
10_1101-2021_01_02_425006	108	32	funder	funder	NN
10_1101-2021_01_02_425006	108	33	,	,	,
10_1101-2021_01_02_425006	108	34	who	who	WP
10_1101-2021_01_02_425006	108	35	has	have	VBZ
10_1101-2021_01_02_425006	108	36	granted	grant	VBN
10_1101-2021_01_02_425006	108	37	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	108	38	a	a	DT
10_1101-2021_01_02_425006	108	39	license	license	NN
10_1101-2021_01_02_425006	108	40	to	to	TO
10_1101-2021_01_02_425006	108	41	display	display	VB
10_1101-2021_01_02_425006	108	42	the	the	DT
10_1101-2021_01_02_425006	108	43	preprint	preprint	NN
10_1101-2021_01_02_425006	108	44	in	in	IN
10_1101-2021_01_02_425006	108	45	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	108	46	.	.	.
10_1101-2021_01_02_425006	109	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	109	2	is	be	VBZ
10_1101-2021_01_02_425006	109	3	made	make	VBN
10_1101-2021_01_02_425006	109	4	The	the	DT
10_1101-2021_01_02_425006	109	5	copyright	copyright	NN
10_1101-2021_01_02_425006	109	6	holder	holder	NN
10_1101-2021_01_02_425006	109	7	for	for	IN
10_1101-2021_01_02_425006	109	8	this	this	DT
10_1101-2021_01_02_425006	109	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	109	10	version	version	NN
10_1101-2021_01_02_425006	109	11	posted	post	VBD
10_1101-2021_01_02_425006	109	12	January	January	NNP
10_1101-2021_01_02_425006	109	13	6	6	CD
10_1101-2021_01_02_425006	109	14	,	,	,
10_1101-2021_01_02_425006	109	15	2021	2021	CD
10_1101-2021_01_02_425006	109	16	.	.	.
10_1101-2021_01_02_425006	109	17	;	;	:
10_1101-2021_01_02_425006	109	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	109	19	:	:	:
10_1101-2021_01_02_425006	109	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	109	21	preprint	preprint	NN
10_1101-2021_01_02_425006	109	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	109	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	109	24	11	11	CD
10_1101-2021_01_02_425006	109	25	number	number	NN
10_1101-2021_01_02_425006	109	26	of	of	IN
10_1101-2021_01_02_425006	109	27	optimal	optimal	JJ
10_1101-2021_01_02_425006	109	28	solutions	solution	NNS
10_1101-2021_01_02_425006	109	29	and	and	CC
10_1101-2021_01_02_425006	109	30	reduce	reduce	VB
10_1101-2021_01_02_425006	109	31	the	the	DT
10_1101-2021_01_02_425006	109	32	false	false	JJ
10_1101-2021_01_02_425006	109	33	-	-	HYPH
10_1101-2021_01_02_425006	109	34	positive	positive	JJ
10_1101-2021_01_02_425006	109	35	errors	error	NNS
10_1101-2021_01_02_425006	109	36	,	,	,
10_1101-2021_01_02_425006	109	37	we	-PRON-	PRP
10_1101-2021_01_02_425006	109	38	added	add	VBD
10_1101-2021_01_02_425006	109	39	an	an	DT
10_1101-2021_01_02_425006	109	40	�	�	NNP
10_1101-2021_01_02_425006	109	41	�	�	JJ
10_1101-2021_01_02_425006	109	42	regularization	regularization	NN
10_1101-2021_01_02_425006	109	43	�	�	.
10_1101-2021_01_02_425006	109	44	||	||	NNP
10_1101-2021_01_02_425006	109	45	�	�	JJ
10_1101-2021_01_02_425006	109	46	||	||	ADD
10_1101-2021_01_02_425006	109	47	�	�	NNP
10_1101-2021_01_02_425006	109	48	177	177	CD
10_1101-2021_01_02_425006	109	49	to	to	IN
10_1101-2021_01_02_425006	109	50	�	�	ADD
10_1101-2021_01_02_425006	109	51	�	�	NNP
10_1101-2021_01_02_425006	109	52	�	�	NNP
10_1101-2021_01_02_425006	109	53	with	with	IN
10_1101-2021_01_02_425006	109	54	�	�	NNP
10_1101-2021_01_02_425006	109	55	�	�	NNP
10_1101-2021_01_02_425006	109	56	,	,	,
10_1101-2021_01_02_425006	109	57	�	�	NNP
10_1101-2021_01_02_425006	109	58	≥	≥	NN
10_1101-2021_01_02_425006	109	59	0	0	CD
10_1101-2021_01_02_425006	109	60	,	,	,
10_1101-2021_01_02_425006	109	61	which	which	WDT
10_1101-2021_01_02_425006	109	62	is	be	VBZ
10_1101-2021_01_02_425006	109	63	a	a	DT
10_1101-2021_01_02_425006	109	64	linear	linear	JJ
10_1101-2021_01_02_425006	109	65	function	function	NN
10_1101-2021_01_02_425006	109	66	.	.	.
10_1101-2021_01_02_425006	110	1	Because	because	IN
10_1101-2021_01_02_425006	110	2	of	of	IN
10_1101-2021_01_02_425006	110	3	the	the	DT
10_1101-2021_01_02_425006	110	4	variant	variant	JJ
10_1101-2021_01_02_425006	110	5	expression	expression	NN
10_1101-2021_01_02_425006	110	6	level	level	NN
10_1101-2021_01_02_425006	110	7	of	of	IN
10_1101-2021_01_02_425006	110	8	different	different	JJ
10_1101-2021_01_02_425006	110	9	178	178	CD
10_1101-2021_01_02_425006	110	10	maximal	maximal	JJ
10_1101-2021_01_02_425006	110	11	ATU	ATU	NNP
10_1101-2021_01_02_425006	110	12	clusters	cluster	NNS
10_1101-2021_01_02_425006	110	13	,	,	,
10_1101-2021_01_02_425006	110	14	we	-PRON-	PRP
10_1101-2021_01_02_425006	110	15	used	use	VBD
10_1101-2021_01_02_425006	110	16	the	the	DT
10_1101-2021_01_02_425006	110	17	expression	expression	NN
10_1101-2021_01_02_425006	110	18	value	value	NN
10_1101-2021_01_02_425006	110	19	of	of	IN
10_1101-2021_01_02_425006	110	20	�	�	NNP
10_1101-2021_01_02_425006	110	21	as	as	IN
10_1101-2021_01_02_425006	110	22	�	�	NNP
10_1101-2021_01_02_425006	110	23	.	.	.
10_1101-2021_01_02_425006	111	1	In	in	IN
10_1101-2021_01_02_425006	111	2	total	total	NN
10_1101-2021_01_02_425006	111	3	,	,	,
10_1101-2021_01_02_425006	111	4	the	the	DT
10_1101-2021_01_02_425006	111	5	convex	convex	NNP
10_1101-2021_01_02_425006	111	6	quadratic	quadratic	NNP
10_1101-2021_01_02_425006	111	7	179	179	CD
10_1101-2021_01_02_425006	111	8	programming	programming	NN
10_1101-2021_01_02_425006	111	9	model	model	NN
10_1101-2021_01_02_425006	111	10	with	with	IN
10_1101-2021_01_02_425006	111	11	unknown	unknown	JJ
10_1101-2021_01_02_425006	111	12	variables	variable	NNS
10_1101-2021_01_02_425006	111	13	(	(	-LRB-
10_1101-2021_01_02_425006	111	14	�	�	NNP
10_1101-2021_01_02_425006	111	15	,	,	,
10_1101-2021_01_02_425006	111	16	�	�	NNP
10_1101-2021_01_02_425006	111	17	)	)	-RRB-
10_1101-2021_01_02_425006	111	18	is	be	VBZ
10_1101-2021_01_02_425006	111	19	shown	show	VBN
10_1101-2021_01_02_425006	111	20	as	as	IN
10_1101-2021_01_02_425006	111	21	follows	follow	VBZ
10_1101-2021_01_02_425006	111	22	:	:	:
10_1101-2021_01_02_425006	111	23	180	180	CD
10_1101-2021_01_02_425006	111	24	�	�	NNS
10_1101-2021_01_02_425006	111	25	�	�	,
10_1101-2021_01_02_425006	111	26	�	�	JJ
10_1101-2021_01_02_425006	111	27	�	�	JJ
10_1101-2021_01_02_425006	111	28	�	�	NNS
10_1101-2021_01_02_425006	111	29	�	�	NN
10_1101-2021_01_02_425006	111	30	+	+	SYM
10_1101-2021_01_02_425006	111	31	�	�	NNS
10_1101-2021_01_02_425006	111	32	||	||	NNP
10_1101-2021_01_02_425006	111	33	�	�	,
10_1101-2021_01_02_425006	111	34	||	||	ADD
10_1101-2021_01_02_425006	111	35	�	�	NNP
10_1101-2021_01_02_425006	111	36	�	�	NNP
10_1101-2021_01_02_425006	111	37	.	.	.
10_1101-2021_01_02_425006	112	1	�	�	NNP
10_1101-2021_01_02_425006	112	2	.	.	.
10_1101-2021_01_02_425006	113	1	∑	∑	NFP
10_1101-2021_01_02_425006	113	2	∑	∑	.
10_1101-2021_01_02_425006	113	3	�	�	NNP
10_1101-2021_01_02_425006	113	4	�	�	NNP
10_1101-2021_01_02_425006	113	5	,	,	,
10_1101-2021_01_02_425006	113	6	�	�	NNP
10_1101-2021_01_02_425006	113	7	�	�	NNP
10_1101-2021_01_02_425006	113	8	�	�	NNP
10_1101-2021_01_02_425006	113	9	,	,	,
10_1101-2021_01_02_425006	113	10	�	�	NNP
10_1101-2021_01_02_425006	113	11	�	�	ADD
10_1101-2021_01_02_425006	113	12	�	�	VBZ
10_1101-2021_01_02_425006	113	13	�	�	VBZ
10_1101-2021_01_02_425006	113	14	�	�	VBZ
10_1101-2021_01_02_425006	113	15	�	�	VBZ
10_1101-2021_01_02_425006	113	16	�	�	JJ
10_1101-2021_01_02_425006	113	17	�	�	NNS
10_1101-2021_01_02_425006	113	18	�	�	NNP
10_1101-2021_01_02_425006	113	19	=	=	VBZ
10_1101-2021_01_02_425006	113	20	�	�	NNP
10_1101-2021_01_02_425006	113	21	�	�	NNP
10_1101-2021_01_02_425006	113	22	+	+	SYM
10_1101-2021_01_02_425006	113	23	�	�	NNS
10_1101-2021_01_02_425006	113	24	�	�	NNP
10_1101-2021_01_02_425006	113	25	�	�	NNS
10_1101-2021_01_02_425006	113	26	=	=	SYM
10_1101-2021_01_02_425006	113	27	1,2	1,2	CD
10_1101-2021_01_02_425006	113	28	,	,	,
10_1101-2021_01_02_425006	113	29	…	…	NFP
10_1101-2021_01_02_425006	113	30	,	,	,
10_1101-2021_01_02_425006	113	31	�	�	NNP
10_1101-2021_01_02_425006	113	32	∑	∑	.
10_1101-2021_01_02_425006	113	33	∑	∑	.
10_1101-2021_01_02_425006	113	34	�	�	NNP
10_1101-2021_01_02_425006	113	35	�	�	NNP
10_1101-2021_01_02_425006	113	36	,	,	,
10_1101-2021_01_02_425006	113	37	�	�	NNP
10_1101-2021_01_02_425006	113	38	�	�	ADD
10_1101-2021_01_02_425006	113	39	�	�	JJ
10_1101-2021_01_02_425006	113	40	�	�	NNP
10_1101-2021_01_02_425006	113	41	�	�	NNP
10_1101-2021_01_02_425006	113	42	,	,	,
10_1101-2021_01_02_425006	113	43	�	�	NNP
10_1101-2021_01_02_425006	113	44	�	�	ADD
10_1101-2021_01_02_425006	113	45	�	�	VBZ
10_1101-2021_01_02_425006	113	46	�	�	VBZ
10_1101-2021_01_02_425006	113	47	�	�	VBZ
10_1101-2021_01_02_425006	113	48	�	�	VBZ
10_1101-2021_01_02_425006	113	49	�	�	VBZ
10_1101-2021_01_02_425006	113	50	�	�	VBZ
10_1101-2021_01_02_425006	113	51	�	�	JJ
10_1101-2021_01_02_425006	113	52	�	�	NNS
10_1101-2021_01_02_425006	113	53	�	�	NNP
10_1101-2021_01_02_425006	113	54	=	=	VBZ
10_1101-2021_01_02_425006	113	55	�	�	NNP
10_1101-2021_01_02_425006	113	56	�	�	NNP
10_1101-2021_01_02_425006	113	57	,	,	,
10_1101-2021_01_02_425006	113	58	�	�	NNP
10_1101-2021_01_02_425006	113	59	�	�	NNP
10_1101-2021_01_02_425006	113	60	�	�	NN
10_1101-2021_01_02_425006	113	61	+	+	CC
10_1101-2021_01_02_425006	113	62	�	�	NNS
10_1101-2021_01_02_425006	113	63	�	�	NNP
10_1101-2021_01_02_425006	113	64	�	�	NNS
10_1101-2021_01_02_425006	113	65	=	=	SYM
10_1101-2021_01_02_425006	113	66	1,2	1,2	CD
10_1101-2021_01_02_425006	113	67	,	,	,
10_1101-2021_01_02_425006	113	68	…	…	NFP
10_1101-2021_01_02_425006	113	69	,	,	,
10_1101-2021_01_02_425006	113	70	�	�	NNP
10_1101-2021_01_02_425006	113	71	−	−	NNP
10_1101-2021_01_02_425006	113	72	1	1	CD
10_1101-2021_01_02_425006	113	73	�	�	NNS
10_1101-2021_01_02_425006	113	74	=	=	SYM
10_1101-2021_01_02_425006	113	75	�	�	NNP
10_1101-2021_01_02_425006	113	76	�	�	NNP
10_1101-2021_01_02_425006	113	77	�	�	NNP
10_1101-2021_01_02_425006	113	78	,	,	,
10_1101-2021_01_02_425006	113	79	�	�	NNP
10_1101-2021_01_02_425006	113	80	�	�	NNP
10_1101-2021_01_02_425006	113	81	,	,	,
10_1101-2021_01_02_425006	113	82	�	�	NNP
10_1101-2021_01_02_425006	113	83	�	�	NNP
10_1101-2021_01_02_425006	113	84	,	,	,
10_1101-2021_01_02_425006	113	85	�	�	NNP
10_1101-2021_01_02_425006	113	86	≥	≥	CD
10_1101-2021_01_02_425006	113	87	0	0	CD
10_1101-2021_01_02_425006	113	88	1	1	CD
10_1101-2021_01_02_425006	113	89	≤	≤	NN
10_1101-2021_01_02_425006	113	90	�	�	NNP
10_1101-2021_01_02_425006	113	91	≤	≤	NNP
10_1101-2021_01_02_425006	113	92	�	�	NNP
10_1101-2021_01_02_425006	113	93	≤	≤	NN
10_1101-2021_01_02_425006	113	94	�	�	NNS
10_1101-2021_01_02_425006	113	95	�	�	ADD
10_1101-2021_01_02_425006	113	96	=	=	NFP
10_1101-2021_01_02_425006	113	97	(	(	-LRB-
10_1101-2021_01_02_425006	113	98	�	�	NNP
10_1101-2021_01_02_425006	113	99	�	�	NNP
10_1101-2021_01_02_425006	113	100	,	,	,
10_1101-2021_01_02_425006	113	101	�	�	NNP
10_1101-2021_01_02_425006	113	102	�	�	NNP
10_1101-2021_01_02_425006	113	103	,	,	,
10_1101-2021_01_02_425006	113	104	…	…	NFP
10_1101-2021_01_02_425006	113	105	,	,	,
10_1101-2021_01_02_425006	113	106	�	�	NNP
10_1101-2021_01_02_425006	113	107	�	�	NNP
10_1101-2021_01_02_425006	113	108	,	,	,
10_1101-2021_01_02_425006	113	109	�	�	NNP
10_1101-2021_01_02_425006	113	110	�	�	NNP
10_1101-2021_01_02_425006	113	111	,	,	,
10_1101-2021_01_02_425006	113	112	…	…	NFP
10_1101-2021_01_02_425006	113	113	,	,	,
10_1101-2021_01_02_425006	113	114	�	�	NNP
10_1101-2021_01_02_425006	113	115	�	�	ADD
10_1101-2021_01_02_425006	113	116	�	�	NNP
10_1101-2021_01_02_425006	113	117	�	�	NNP
10_1101-2021_01_02_425006	113	118	)	)	-RRB-
10_1101-2021_01_02_425006	113	119	(	(	-LRB-
10_1101-2021_01_02_425006	113	120	6	6	CD
10_1101-2021_01_02_425006	113	121	)	)	-RRB-
10_1101-2021_01_02_425006	113	122	where	where	WRB
10_1101-2021_01_02_425006	113	123	�	�	NNP
10_1101-2021_01_02_425006	113	124	=	=	NFP
10_1101-2021_01_02_425006	113	125	(	(	-LRB-
10_1101-2021_01_02_425006	113	126	�	�	NNP
10_1101-2021_01_02_425006	113	127	�	�	NNP
10_1101-2021_01_02_425006	113	128	,	,	,
10_1101-2021_01_02_425006	113	129	�	�	NNP
10_1101-2021_01_02_425006	113	130	)	)	-RRB-
10_1101-2021_01_02_425006	113	131	is	be	VBZ
10_1101-2021_01_02_425006	113	132	the	the	DT
10_1101-2021_01_02_425006	113	133	genetic	genetic	JJ
10_1101-2021_01_02_425006	113	134	region	region	NN
10_1101-2021_01_02_425006	113	135	bias	bias	NN
10_1101-2021_01_02_425006	113	136	rate	rate	NN
10_1101-2021_01_02_425006	113	137	vector	vector	NN
10_1101-2021_01_02_425006	113	138	for	for	IN
10_1101-2021_01_02_425006	113	139	�	�	NNP
10_1101-2021_01_02_425006	113	140	,	,	,
10_1101-2021_01_02_425006	113	141	�	�	NNP
10_1101-2021_01_02_425006	113	142	�	�	NNP
10_1101-2021_01_02_425006	113	143	,	,	,
10_1101-2021_01_02_425006	113	144	�	�	NNP
10_1101-2021_01_02_425006	113	145	is	be	VBZ
10_1101-2021_01_02_425006	113	146	the	the	DT
10_1101-2021_01_02_425006	113	147	bias	bias	NN
10_1101-2021_01_02_425006	113	148	rate	rate	NN
10_1101-2021_01_02_425006	113	149	of	of	IN
10_1101-2021_01_02_425006	113	150	gene	gene	NN
10_1101-2021_01_02_425006	113	151	�	�	NNP
10_1101-2021_01_02_425006	113	152	�	�	NNP
10_1101-2021_01_02_425006	113	153	for	for	IN
10_1101-2021_01_02_425006	113	154	ATU	ATU	NNP
10_1101-2021_01_02_425006	113	155	181	181	CD
10_1101-2021_01_02_425006	113	156	�	�	NNP
10_1101-2021_01_02_425006	113	157	�	�	NNP
10_1101-2021_01_02_425006	113	158	,	,	,
10_1101-2021_01_02_425006	113	159	�	�	NNP
10_1101-2021_01_02_425006	113	160	,	,	,
10_1101-2021_01_02_425006	113	161	1	1	CD
10_1101-2021_01_02_425006	113	162	≤	≤	NN
10_1101-2021_01_02_425006	113	163	�	�	NNP
10_1101-2021_01_02_425006	113	164	≤	≤	NNP
10_1101-2021_01_02_425006	113	165	�	�	NNP
10_1101-2021_01_02_425006	113	166	≤	≤	NN
10_1101-2021_01_02_425006	113	167	�	�	NNP
10_1101-2021_01_02_425006	113	168	，	，	,
10_1101-2021_01_02_425006	113	169	�	�	NNP
10_1101-2021_01_02_425006	113	170	≤	≤	CC
10_1101-2021_01_02_425006	113	171	�	�	NNP
10_1101-2021_01_02_425006	113	172	≤	≤	NNP
10_1101-2021_01_02_425006	113	173	�	�	NNP
10_1101-2021_01_02_425006	113	174	,	,	,
10_1101-2021_01_02_425006	113	175	�	�	NNP
10_1101-2021_01_02_425006	113	176	=	=	NFP
10_1101-2021_01_02_425006	113	177	(	(	-LRB-
10_1101-2021_01_02_425006	113	178	�	�	NNP
10_1101-2021_01_02_425006	113	179	�	�	NNP
10_1101-2021_01_02_425006	113	180	,	,	,
10_1101-2021_01_02_425006	113	181	�	�	NNP
10_1101-2021_01_02_425006	113	182	)	)	-RRB-
10_1101-2021_01_02_425006	113	183	is	be	VBZ
10_1101-2021_01_02_425006	113	184	the	the	DT
10_1101-2021_01_02_425006	113	185	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	113	186	region	region	NN
10_1101-2021_01_02_425006	113	187	bias	bias	NN
10_1101-2021_01_02_425006	113	188	rate	rate	NN
10_1101-2021_01_02_425006	113	189	vector	vector	NN
10_1101-2021_01_02_425006	113	190	for	for	IN
10_1101-2021_01_02_425006	113	191	�	�	NNP
10_1101-2021_01_02_425006	113	192	,	,	,
10_1101-2021_01_02_425006	113	193	and	and	CC
10_1101-2021_01_02_425006	113	194	�	�	NNP
10_1101-2021_01_02_425006	113	195	�	�	NNP
10_1101-2021_01_02_425006	113	196	,	,	,
10_1101-2021_01_02_425006	113	197	�	�	NNP
10_1101-2021_01_02_425006	113	198	182	182	CD
10_1101-2021_01_02_425006	113	199	is	be	VBZ
10_1101-2021_01_02_425006	113	200	the	the	DT
10_1101-2021_01_02_425006	113	201	bias	bias	NN
10_1101-2021_01_02_425006	113	202	rate	rate	NN
10_1101-2021_01_02_425006	113	203	of	of	IN
10_1101-2021_01_02_425006	113	204	the	the	DT
10_1101-2021_01_02_425006	113	205	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	113	206	region	region	NN
10_1101-2021_01_02_425006	113	207	�	�	.
10_1101-2021_01_02_425006	113	208	�	�	JJ
10_1101-2021_01_02_425006	113	209	�	�	NNP
10_1101-2021_01_02_425006	113	210	�	�	NNP
10_1101-2021_01_02_425006	113	211	,	,	,
10_1101-2021_01_02_425006	113	212	�	�	NNP
10_1101-2021_01_02_425006	113	213	for	for	IN
10_1101-2021_01_02_425006	113	214	ATU	ATU	NNP
10_1101-2021_01_02_425006	113	215	�	�	NNP
10_1101-2021_01_02_425006	113	216	�	�	NNP
10_1101-2021_01_02_425006	113	217	,	,	,
10_1101-2021_01_02_425006	113	218	�	�	NNP
10_1101-2021_01_02_425006	113	219	,	,	,
10_1101-2021_01_02_425006	113	220	1	1	CD
10_1101-2021_01_02_425006	113	221	≤	≤	NN
10_1101-2021_01_02_425006	113	222	�	�	NNP
10_1101-2021_01_02_425006	113	223	<	<	XX
10_1101-2021_01_02_425006	113	224	�	�	NNP
10_1101-2021_01_02_425006	113	225	≤	≤	JJ
10_1101-2021_01_02_425006	113	226	�	�	NNP
10_1101-2021_01_02_425006	113	227	，	，	,
10_1101-2021_01_02_425006	113	228	�	�	NNP
10_1101-2021_01_02_425006	113	229	≤	≤	CC
10_1101-2021_01_02_425006	113	230	�	�	NNP
10_1101-2021_01_02_425006	113	231	≤	≤	NN
10_1101-2021_01_02_425006	113	232	�	�	NNP
10_1101-2021_01_02_425006	113	233	(	(	-LRB-
10_1101-2021_01_02_425006	113	234	see	see	VB
10_1101-2021_01_02_425006	113	235	the	the	DT
10_1101-2021_01_02_425006	113	236	183	183	CD
10_1101-2021_01_02_425006	113	237	details	detail	NNS
10_1101-2021_01_02_425006	113	238	in	in	IN
10_1101-2021_01_02_425006	113	239	method	method	NNP
10_1101-2021_01_02_425006	113	240	S5	S5	NNP
10_1101-2021_01_02_425006	113	241	)	)	-RRB-
10_1101-2021_01_02_425006	113	242	.	.	.
10_1101-2021_01_02_425006	114	1	184	184	CD
10_1101-2021_01_02_425006	114	2	Two	two	CD
10_1101-2021_01_02_425006	114	3	evaluation	evaluation	NN
10_1101-2021_01_02_425006	114	4	methods	method	NNS
10_1101-2021_01_02_425006	114	5	for	for	IN
10_1101-2021_01_02_425006	114	6	ATU	ATU	NNP
10_1101-2021_01_02_425006	114	7	prediction	prediction	NN
10_1101-2021_01_02_425006	114	8	185	185	CD
10_1101-2021_01_02_425006	114	9	In	in	IN
10_1101-2021_01_02_425006	114	10	the	the	DT
10_1101-2021_01_02_425006	114	11	first	first	JJ
10_1101-2021_01_02_425006	114	12	evaluation	evaluation	NN
10_1101-2021_01_02_425006	114	13	method	method	NN
10_1101-2021_01_02_425006	114	14	,	,	,
10_1101-2021_01_02_425006	114	15	precision	precision	NN
10_1101-2021_01_02_425006	114	16	and	and	CC
10_1101-2021_01_02_425006	114	17	recall	recall	NN
10_1101-2021_01_02_425006	114	18	were	be	VBD
10_1101-2021_01_02_425006	114	19	defined	define	VBN
10_1101-2021_01_02_425006	114	20	based	base	VBN
10_1101-2021_01_02_425006	114	21	on	on	IN
10_1101-2021_01_02_425006	114	22	perfect	perfect	JJ
10_1101-2021_01_02_425006	114	23	matching	matching	NN
10_1101-2021_01_02_425006	114	24	(	(	-LRB-
10_1101-2021_01_02_425006	114	25	Eqs	Eqs	NNP
10_1101-2021_01_02_425006	114	26	.	.	.
10_1101-2021_01_02_425006	115	1	7	7	LS
10_1101-2021_01_02_425006	115	2	)	)	-RRB-
10_1101-2021_01_02_425006	115	3	.	.	.
10_1101-2021_01_02_425006	116	1	186	186	CD
10_1101-2021_01_02_425006	116	2	Perfect	perfect	JJ
10_1101-2021_01_02_425006	116	3	matching	matching	NN
10_1101-2021_01_02_425006	116	4	of	of	IN
10_1101-2021_01_02_425006	116	5	two	two	CD
10_1101-2021_01_02_425006	116	6	ATUs	atu	NNS
10_1101-2021_01_02_425006	116	7	means	mean	VBZ
10_1101-2021_01_02_425006	116	8	that	that	IN
10_1101-2021_01_02_425006	116	9	all	all	DT
10_1101-2021_01_02_425006	116	10	of	of	IN
10_1101-2021_01_02_425006	116	11	their	-PRON-	PRP$
10_1101-2021_01_02_425006	116	12	component	component	NN
10_1101-2021_01_02_425006	116	13	genes	gene	NNS
10_1101-2021_01_02_425006	116	14	are	be	VBP
10_1101-2021_01_02_425006	116	15	the	the	DT
10_1101-2021_01_02_425006	116	16	same	same	JJ
10_1101-2021_01_02_425006	116	17	.	.	.
10_1101-2021_01_02_425006	117	1	Here	here	RB
10_1101-2021_01_02_425006	117	2	,	,	,
10_1101-2021_01_02_425006	117	3	the	the	DT
10_1101-2021_01_02_425006	117	4	true	true	JJ
10_1101-2021_01_02_425006	117	5	187	187	CD
10_1101-2021_01_02_425006	117	6	positives	positive	NNS
10_1101-2021_01_02_425006	117	7	(	(	-LRB-
10_1101-2021_01_02_425006	117	8	�	�	NNP
10_1101-2021_01_02_425006	117	9	�	�	NNP
10_1101-2021_01_02_425006	117	10	)	)	-RRB-
10_1101-2021_01_02_425006	117	11	are	be	VBP
10_1101-2021_01_02_425006	117	12	the	the	DT
10_1101-2021_01_02_425006	117	13	number	number	NN
10_1101-2021_01_02_425006	117	14	of	of	IN
10_1101-2021_01_02_425006	117	15	predicted	predict	VBN
10_1101-2021_01_02_425006	117	16	ATUs	atu	NNS
10_1101-2021_01_02_425006	117	17	with	with	IN
10_1101-2021_01_02_425006	117	18	the	the	DT
10_1101-2021_01_02_425006	117	19	same	same	JJ
10_1101-2021_01_02_425006	117	20	component	component	NN
10_1101-2021_01_02_425006	117	21	genes	gene	NNS
10_1101-2021_01_02_425006	117	22	as	as	IN
10_1101-2021_01_02_425006	117	23	an	an	DT
10_1101-2021_01_02_425006	117	24	ATU	ATU	NNP
10_1101-2021_01_02_425006	117	25	in	in	IN
10_1101-2021_01_02_425006	117	26	the	the	DT
10_1101-2021_01_02_425006	117	27	188	188	CD
10_1101-2021_01_02_425006	117	28	evaluation	evaluation	NN
10_1101-2021_01_02_425006	117	29	data	datum	NNS
10_1101-2021_01_02_425006	117	30	;	;	:
10_1101-2021_01_02_425006	117	31	the	the	DT
10_1101-2021_01_02_425006	117	32	false	false	JJ
10_1101-2021_01_02_425006	117	33	positives	positive	NNS
10_1101-2021_01_02_425006	117	34	(	(	-LRB-
10_1101-2021_01_02_425006	117	35	�	�	NNP
10_1101-2021_01_02_425006	117	36	�	�	NNP
10_1101-2021_01_02_425006	117	37	)	)	-RRB-
10_1101-2021_01_02_425006	117	38	are	be	VBP
10_1101-2021_01_02_425006	117	39	the	the	DT
10_1101-2021_01_02_425006	117	40	number	number	NN
10_1101-2021_01_02_425006	117	41	of	of	IN
10_1101-2021_01_02_425006	117	42	predicted	predict	VBN
10_1101-2021_01_02_425006	117	43	ATUs	atu	NNS
10_1101-2021_01_02_425006	117	44	that	that	WDT
10_1101-2021_01_02_425006	117	45	do	do	VBP
10_1101-2021_01_02_425006	117	46	not	not	RB
10_1101-2021_01_02_425006	117	47	exist	exist	VB
10_1101-2021_01_02_425006	117	48	in	in	IN
10_1101-2021_01_02_425006	117	49	the	the	DT
10_1101-2021_01_02_425006	117	50	189	189	CD
10_1101-2021_01_02_425006	117	51	.CC	.CC	NFP
10_1101-2021_01_02_425006	117	52	-	-	HYPH
10_1101-2021_01_02_425006	117	53	BY	by	IN
10_1101-2021_01_02_425006	117	54	-	-	HYPH
10_1101-2021_01_02_425006	117	55	NC	NC	NNP
10_1101-2021_01_02_425006	117	56	-	-	HYPH
10_1101-2021_01_02_425006	117	57	ND	ND	NNP
10_1101-2021_01_02_425006	117	58	4.0	4.0	CD
10_1101-2021_01_02_425006	117	59	International	International	NNP
10_1101-2021_01_02_425006	117	60	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	117	61	under	under	IN
10_1101-2021_01_02_425006	117	62	a	a	DT
10_1101-2021_01_02_425006	117	63	(	(	-LRB-
10_1101-2021_01_02_425006	117	64	which	which	WDT
10_1101-2021_01_02_425006	117	65	was	be	VBD
10_1101-2021_01_02_425006	117	66	not	not	RB
10_1101-2021_01_02_425006	117	67	certified	certify	VBN
10_1101-2021_01_02_425006	117	68	by	by	IN
10_1101-2021_01_02_425006	117	69	peer	peer	NN
10_1101-2021_01_02_425006	117	70	review	review	NN
10_1101-2021_01_02_425006	117	71	)	)	-RRB-
10_1101-2021_01_02_425006	117	72	is	be	VBZ
10_1101-2021_01_02_425006	117	73	the	the	DT
10_1101-2021_01_02_425006	117	74	author	author	NN
10_1101-2021_01_02_425006	117	75	/	/	SYM
10_1101-2021_01_02_425006	117	76	funder	funder	NN
10_1101-2021_01_02_425006	117	77	,	,	,
10_1101-2021_01_02_425006	117	78	who	who	WP
10_1101-2021_01_02_425006	117	79	has	have	VBZ
10_1101-2021_01_02_425006	117	80	granted	grant	VBN
10_1101-2021_01_02_425006	117	81	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	117	82	a	a	DT
10_1101-2021_01_02_425006	117	83	license	license	NN
10_1101-2021_01_02_425006	117	84	to	to	TO
10_1101-2021_01_02_425006	117	85	display	display	VB
10_1101-2021_01_02_425006	117	86	the	the	DT
10_1101-2021_01_02_425006	117	87	preprint	preprint	NN
10_1101-2021_01_02_425006	117	88	in	in	IN
10_1101-2021_01_02_425006	117	89	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	117	90	.	.	.
10_1101-2021_01_02_425006	118	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	118	2	is	be	VBZ
10_1101-2021_01_02_425006	118	3	made	make	VBN
10_1101-2021_01_02_425006	118	4	The	the	DT
10_1101-2021_01_02_425006	118	5	copyright	copyright	NN
10_1101-2021_01_02_425006	118	6	holder	holder	NN
10_1101-2021_01_02_425006	118	7	for	for	IN
10_1101-2021_01_02_425006	118	8	this	this	DT
10_1101-2021_01_02_425006	118	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	118	10	version	version	NN
10_1101-2021_01_02_425006	118	11	posted	post	VBD
10_1101-2021_01_02_425006	118	12	January	January	NNP
10_1101-2021_01_02_425006	118	13	6	6	CD
10_1101-2021_01_02_425006	118	14	,	,	,
10_1101-2021_01_02_425006	118	15	2021	2021	CD
10_1101-2021_01_02_425006	118	16	.	.	.
10_1101-2021_01_02_425006	118	17	;	;	:
10_1101-2021_01_02_425006	118	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	118	19	:	:	:
10_1101-2021_01_02_425006	118	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	118	21	preprint	preprint	NN
10_1101-2021_01_02_425006	118	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	118	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	118	24	12	12	CD
10_1101-2021_01_02_425006	118	25	evaluation	evaluation	NN
10_1101-2021_01_02_425006	118	26	data	datum	NNS
10_1101-2021_01_02_425006	118	27	;	;	:
10_1101-2021_01_02_425006	118	28	the	the	DT
10_1101-2021_01_02_425006	118	29	false	false	JJ
10_1101-2021_01_02_425006	118	30	negatives	negative	NNS
10_1101-2021_01_02_425006	118	31	(	(	-LRB-
10_1101-2021_01_02_425006	118	32	�	�	NNP
10_1101-2021_01_02_425006	118	33	�	�	NNP
10_1101-2021_01_02_425006	118	34	)	)	-RRB-
10_1101-2021_01_02_425006	118	35	are	be	VBP
10_1101-2021_01_02_425006	118	36	the	the	DT
10_1101-2021_01_02_425006	118	37	number	number	NN
10_1101-2021_01_02_425006	118	38	of	of	IN
10_1101-2021_01_02_425006	118	39	ATUs	atu	NNS
10_1101-2021_01_02_425006	118	40	that	that	WDT
10_1101-2021_01_02_425006	118	41	appear	appear	VBP
10_1101-2021_01_02_425006	118	42	in	in	IN
10_1101-2021_01_02_425006	118	43	the	the	DT
10_1101-2021_01_02_425006	118	44	evaluation	evaluation	NN
10_1101-2021_01_02_425006	118	45	data	datum	NNS
10_1101-2021_01_02_425006	118	46	but	but	CC
10_1101-2021_01_02_425006	118	47	190	190	CD
10_1101-2021_01_02_425006	118	48	not	not	RB
10_1101-2021_01_02_425006	118	49	in	in	IN
10_1101-2021_01_02_425006	118	50	the	the	DT
10_1101-2021_01_02_425006	118	51	prediction	prediction	NN
10_1101-2021_01_02_425006	118	52	results	result	NNS
10_1101-2021_01_02_425006	118	53	of	of	IN
10_1101-2021_01_02_425006	118	54	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	118	55	.	.	.
10_1101-2021_01_02_425006	119	1	191	191	CD
10_1101-2021_01_02_425006	119	2	�	�	NNS
10_1101-2021_01_02_425006	119	3	�	�	,
10_1101-2021_01_02_425006	119	4	�	�	NNS
10_1101-2021_01_02_425006	119	5	�	�	VBZ
10_1101-2021_01_02_425006	119	6	�	�	VBZ
10_1101-2021_01_02_425006	119	7	�	�	VBZ
10_1101-2021_01_02_425006	119	8	�	�	JJ
10_1101-2021_01_02_425006	119	9	�	�	NNS
10_1101-2021_01_02_425006	119	10	�	�	NNP
10_1101-2021_01_02_425006	119	11	=	=	VBZ
10_1101-2021_01_02_425006	119	12	�	�	ADD
10_1101-2021_01_02_425006	119	13	�	�	VBZ
10_1101-2021_01_02_425006	119	14	�	�	NNS
10_1101-2021_01_02_425006	119	15	�	�	NN
10_1101-2021_01_02_425006	119	16	+	+	CC
10_1101-2021_01_02_425006	119	17	�	�	NNS
10_1101-2021_01_02_425006	119	18	�	�	NNS
10_1101-2021_01_02_425006	119	19	�	�	NNS
10_1101-2021_01_02_425006	119	20	�	�	VBZ
10_1101-2021_01_02_425006	119	21	�	�	VBZ
10_1101-2021_01_02_425006	119	22	�	�	JJ
10_1101-2021_01_02_425006	119	23	�	�	NNS
10_1101-2021_01_02_425006	119	24	�	�	NNP
10_1101-2021_01_02_425006	119	25	=	=	VBZ
10_1101-2021_01_02_425006	119	26	�	�	ADD
10_1101-2021_01_02_425006	119	27	�	�	VBZ
10_1101-2021_01_02_425006	119	28	�	�	NNS
10_1101-2021_01_02_425006	119	29	�	�	NN
10_1101-2021_01_02_425006	119	30	+	+	SYM
10_1101-2021_01_02_425006	119	31	�	�	NNS
10_1101-2021_01_02_425006	119	32	�	�	NNP
10_1101-2021_01_02_425006	119	33	(	(	-LRB-
10_1101-2021_01_02_425006	119	34	7	7	CD
10_1101-2021_01_02_425006	119	35	)	)	-RRB-
10_1101-2021_01_02_425006	119	36	In	in	IN
10_1101-2021_01_02_425006	119	37	the	the	DT
10_1101-2021_01_02_425006	119	38	second	second	JJ
10_1101-2021_01_02_425006	119	39	evaluation	evaluation	NN
10_1101-2021_01_02_425006	119	40	method	method	NN
10_1101-2021_01_02_425006	119	41	,	,	,
10_1101-2021_01_02_425006	119	42	precision	precision	NN
10_1101-2021_01_02_425006	119	43	and	and	CC
10_1101-2021_01_02_425006	119	44	recall	recall	NN
10_1101-2021_01_02_425006	119	45	were	be	VBD
10_1101-2021_01_02_425006	119	46	defined	define	VBN
10_1101-2021_01_02_425006	119	47	based	base	VBN
10_1101-2021_01_02_425006	119	48	on	on	IN
10_1101-2021_01_02_425006	119	49	relaxed	relaxed	JJ
10_1101-2021_01_02_425006	119	50	matching	matching	NN
10_1101-2021_01_02_425006	119	51	,	,	,
10_1101-2021_01_02_425006	119	52	which	which	WDT
10_1101-2021_01_02_425006	119	53	192	192	CD
10_1101-2021_01_02_425006	119	54	is	be	VBZ
10_1101-2021_01_02_425006	119	55	measured	measure	VBN
10_1101-2021_01_02_425006	119	56	by	by	IN
10_1101-2021_01_02_425006	119	57	the	the	DT
10_1101-2021_01_02_425006	119	58	similarity	similarity	NN
10_1101-2021_01_02_425006	119	59	of	of	IN
10_1101-2021_01_02_425006	119	60	two	two	CD
10_1101-2021_01_02_425006	119	61	ATUs	atu	NNS
10_1101-2021_01_02_425006	119	62	.	.	.
10_1101-2021_01_02_425006	120	1	Assuming	assume	VBG
10_1101-2021_01_02_425006	120	2	that	that	IN
10_1101-2021_01_02_425006	120	3	an	an	DT
10_1101-2021_01_02_425006	120	4	ATU	ATU	NNP
10_1101-2021_01_02_425006	120	5	�	�	NNP
10_1101-2021_01_02_425006	120	6	is	be	VBZ
10_1101-2021_01_02_425006	120	7	in	in	IN
10_1101-2021_01_02_425006	120	8	one	one	CD
10_1101-2021_01_02_425006	120	9	of	of	IN
10_1101-2021_01_02_425006	120	10	two	two	CD
10_1101-2021_01_02_425006	120	11	datasets	dataset	NNS
10_1101-2021_01_02_425006	120	12	(	(	-LRB-
10_1101-2021_01_02_425006	120	13	the	the	DT
10_1101-2021_01_02_425006	120	14	193	193	CD
10_1101-2021_01_02_425006	120	15	predicted	predict	VBN
10_1101-2021_01_02_425006	120	16	ATU	ATU	NNP
10_1101-2021_01_02_425006	120	17	dataset	dataset	NN
10_1101-2021_01_02_425006	120	18	and	and	CC
10_1101-2021_01_02_425006	120	19	evaluated	evaluate	VBD
10_1101-2021_01_02_425006	120	20	ATU	ATU	NNP
10_1101-2021_01_02_425006	120	21	dataset	dataset	NN
10_1101-2021_01_02_425006	120	22	)	)	-RRB-
10_1101-2021_01_02_425006	120	23	,	,	,
10_1101-2021_01_02_425006	120	24	the	the	DT
10_1101-2021_01_02_425006	120	25	definition	definition	NN
10_1101-2021_01_02_425006	120	26	and	and	CC
10_1101-2021_01_02_425006	120	27	calculation	calculation	NN
10_1101-2021_01_02_425006	120	28	of	of	IN
10_1101-2021_01_02_425006	120	29	the	the	DT
10_1101-2021_01_02_425006	120	30	similarity	similarity	NN
10_1101-2021_01_02_425006	120	31	of	of	IN
10_1101-2021_01_02_425006	120	32	�	�	NNP
10_1101-2021_01_02_425006	120	33	194	194	CD
10_1101-2021_01_02_425006	120	34	are	be	VBP
10_1101-2021_01_02_425006	120	35	shown	show	VBN
10_1101-2021_01_02_425006	120	36	in	in	IN
10_1101-2021_01_02_425006	120	37	the	the	DT
10_1101-2021_01_02_425006	120	38	following	follow	VBG
10_1101-2021_01_02_425006	120	39	three	three	CD
10_1101-2021_01_02_425006	120	40	cases	case	NNS
10_1101-2021_01_02_425006	120	41	:	:	:
10_1101-2021_01_02_425006	120	42	195	195	CD
10_1101-2021_01_02_425006	120	43	Case	case	NN
10_1101-2021_01_02_425006	120	44	1	1	CD
10_1101-2021_01_02_425006	120	45	:	:	:
10_1101-2021_01_02_425006	120	46	If	if	IN
10_1101-2021_01_02_425006	120	47	�	�	NNP
10_1101-2021_01_02_425006	120	48	shares	share	VBZ
10_1101-2021_01_02_425006	120	49	boundary	boundary	JJ
10_1101-2021_01_02_425006	120	50	genes	gene	NNS
10_1101-2021_01_02_425006	120	51	at	at	IN
10_1101-2021_01_02_425006	120	52	both	both	DT
10_1101-2021_01_02_425006	120	53	ends	end	NNS
10_1101-2021_01_02_425006	120	54	of	of	IN
10_1101-2021_01_02_425006	120	55	an	an	DT
10_1101-2021_01_02_425006	120	56	ATU	ATU	NNP
10_1101-2021_01_02_425006	120	57	in	in	IN
10_1101-2021_01_02_425006	120	58	the	the	DT
10_1101-2021_01_02_425006	120	59	other	other	JJ
10_1101-2021_01_02_425006	120	60	dataset	dataset	NN
10_1101-2021_01_02_425006	120	61	,	,	,
10_1101-2021_01_02_425006	120	62	i.e.	i.e.	FW
10_1101-2021_01_02_425006	120	63	,	,	,
10_1101-2021_01_02_425006	120	64	all	all	DT
10_1101-2021_01_02_425006	120	65	component	component	VBP
10_1101-2021_01_02_425006	120	66	196	196	CD
10_1101-2021_01_02_425006	120	67	genes	gene	NNS
10_1101-2021_01_02_425006	120	68	of	of	IN
10_1101-2021_01_02_425006	120	69	�	�	NNP
10_1101-2021_01_02_425006	120	70	are	be	VBP
10_1101-2021_01_02_425006	120	71	the	the	DT
10_1101-2021_01_02_425006	120	72	same	same	JJ
10_1101-2021_01_02_425006	120	73	as	as	IN
10_1101-2021_01_02_425006	120	74	one	one	CD
10_1101-2021_01_02_425006	120	75	in	in	IN
10_1101-2021_01_02_425006	120	76	the	the	DT
10_1101-2021_01_02_425006	120	77	other	other	JJ
10_1101-2021_01_02_425006	120	78	dataset	dataset	NN
10_1101-2021_01_02_425006	120	79	,	,	,
10_1101-2021_01_02_425006	120	80	then	then	RB
10_1101-2021_01_02_425006	120	81	�	�	ADD
10_1101-2021_01_02_425006	120	82	�	�	ADD
10_1101-2021_01_02_425006	120	83	�	�	VBZ
10_1101-2021_01_02_425006	120	84	�	�	VBZ
10_1101-2021_01_02_425006	120	85	�	�	VBZ
10_1101-2021_01_02_425006	120	86	�	�	VBZ
10_1101-2021_01_02_425006	120	87	�	�	VBZ
10_1101-2021_01_02_425006	120	88	�	�	JJ
10_1101-2021_01_02_425006	120	89	�	�	NNS
10_1101-2021_01_02_425006	120	90	�	�	NNP
10_1101-2021_01_02_425006	120	91	(	(	-LRB-
10_1101-2021_01_02_425006	120	92	�	�	NNP
10_1101-2021_01_02_425006	120	93	)	)	-RRB-
10_1101-2021_01_02_425006	120	94	=	=	NFP
10_1101-2021_01_02_425006	120	95	1	1	CD
10_1101-2021_01_02_425006	120	96	.	.	.
10_1101-2021_01_02_425006	121	1	197	197	CD
10_1101-2021_01_02_425006	121	2	Case	case	NN
10_1101-2021_01_02_425006	121	3	2	2	CD
10_1101-2021_01_02_425006	121	4	:	:	:
10_1101-2021_01_02_425006	121	5	If	if	IN
10_1101-2021_01_02_425006	121	6	�	�	NNP
10_1101-2021_01_02_425006	121	7	shares	share	NNS
10_1101-2021_01_02_425006	121	8	exactly	exactly	RB
10_1101-2021_01_02_425006	121	9	one	one	CD
10_1101-2021_01_02_425006	121	10	boundary	boundary	JJ
10_1101-2021_01_02_425006	121	11	gene	gene	NN
10_1101-2021_01_02_425006	121	12	of	of	IN
10_1101-2021_01_02_425006	121	13	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	121	14	in	in	IN
10_1101-2021_01_02_425006	121	15	the	the	DT
10_1101-2021_01_02_425006	121	16	other	other	JJ
10_1101-2021_01_02_425006	121	17	dataset	dataset	NN
10_1101-2021_01_02_425006	121	18	,	,	,
10_1101-2021_01_02_425006	121	19	then	then	RB
10_1101-2021_01_02_425006	121	20	we	-PRON-	PRP
10_1101-2021_01_02_425006	121	21	denote	denote	VBP
10_1101-2021_01_02_425006	121	22	�	�	NNP
10_1101-2021_01_02_425006	121	23	�	�	NNP
10_1101-2021_01_02_425006	121	24	as	as	IN
10_1101-2021_01_02_425006	121	25	198	198	CD
10_1101-2021_01_02_425006	121	26	the	the	DT
10_1101-2021_01_02_425006	121	27	ATUs	atu	NNS
10_1101-2021_01_02_425006	121	28	in	in	IN
10_1101-2021_01_02_425006	121	29	the	the	DT
10_1101-2021_01_02_425006	121	30	other	other	JJ
10_1101-2021_01_02_425006	121	31	dataset	dataset	NN
10_1101-2021_01_02_425006	121	32	that	that	WDT
10_1101-2021_01_02_425006	121	33	share	share	VBP
10_1101-2021_01_02_425006	121	34	the	the	DT
10_1101-2021_01_02_425006	121	35	5’-end	5’-end	CD
10_1101-2021_01_02_425006	121	36	gene	gene	NN
10_1101-2021_01_02_425006	121	37	with	with	IN
10_1101-2021_01_02_425006	121	38	�	�	NNP
10_1101-2021_01_02_425006	121	39	and	and	CC
10_1101-2021_01_02_425006	121	40	denoted	denote	VBD
10_1101-2021_01_02_425006	121	41	�	�	NNP
10_1101-2021_01_02_425006	121	42	�	�	NNP
10_1101-2021_01_02_425006	121	43	as	as	IN
10_1101-2021_01_02_425006	121	44	the	the	DT
10_1101-2021_01_02_425006	121	45	ATUs	atu	NNS
10_1101-2021_01_02_425006	121	46	in	in	IN
10_1101-2021_01_02_425006	121	47	the	the	DT
10_1101-2021_01_02_425006	121	48	199	199	CD
10_1101-2021_01_02_425006	121	49	other	other	JJ
10_1101-2021_01_02_425006	121	50	dataset	dataset	NN
10_1101-2021_01_02_425006	121	51	that	that	WDT
10_1101-2021_01_02_425006	121	52	share	share	VBP
10_1101-2021_01_02_425006	121	53	the	the	DT
10_1101-2021_01_02_425006	121	54	3’-end	3’-end	CD
10_1101-2021_01_02_425006	121	55	gene	gene	NN
10_1101-2021_01_02_425006	121	56	with	with	IN
10_1101-2021_01_02_425006	121	57	�	�	NNP
10_1101-2021_01_02_425006	121	58	,	,	,
10_1101-2021_01_02_425006	121	59	�	�	NNP
10_1101-2021_01_02_425006	121	60	�	�	NNP
10_1101-2021_01_02_425006	121	61	∩	∩	NN
10_1101-2021_01_02_425006	121	62	�	�	NNP
10_1101-2021_01_02_425006	121	63	�	�	NNP
10_1101-2021_01_02_425006	121	64	=	=	SYM
10_1101-2021_01_02_425006	121	65	∅	∅	NNP
10_1101-2021_01_02_425006	121	66	,	,	,
10_1101-2021_01_02_425006	121	67	one	one	CD
10_1101-2021_01_02_425006	121	68	of	of	IN
10_1101-2021_01_02_425006	121	69	�	�	NNP
10_1101-2021_01_02_425006	121	70	�	�	NNP
10_1101-2021_01_02_425006	121	71	and	and	CC
10_1101-2021_01_02_425006	121	72	�	�	NNP
10_1101-2021_01_02_425006	121	73	�	�	NNP
10_1101-2021_01_02_425006	121	74	can	can	MD
10_1101-2021_01_02_425006	121	75	be	be	VB
10_1101-2021_01_02_425006	121	76	empty	empty	JJ
10_1101-2021_01_02_425006	121	77	.	.	.
10_1101-2021_01_02_425006	122	1	Then	then	RB
10_1101-2021_01_02_425006	122	2	,	,	,
10_1101-2021_01_02_425006	122	3	200	200	CD
10_1101-2021_01_02_425006	122	4	�	�	NNS
10_1101-2021_01_02_425006	122	5	�	�	JJ
10_1101-2021_01_02_425006	122	6	�	�	NNS
10_1101-2021_01_02_425006	122	7	�	�	VBZ
10_1101-2021_01_02_425006	122	8	�	�	VBZ
10_1101-2021_01_02_425006	122	9	�	�	VBZ
10_1101-2021_01_02_425006	122	10	�	�	VBZ
10_1101-2021_01_02_425006	122	11	�	�	JJ
10_1101-2021_01_02_425006	122	12	�	�	NNS
10_1101-2021_01_02_425006	122	13	�	�	NNP
10_1101-2021_01_02_425006	122	14	(	(	-LRB-
10_1101-2021_01_02_425006	122	15	�	�	NNP
10_1101-2021_01_02_425006	122	16	)	)	-RRB-
10_1101-2021_01_02_425006	122	17	=	=	NFP
10_1101-2021_01_02_425006	122	18	1	1	CD
10_1101-2021_01_02_425006	122	19	2	2	CD
10_1101-2021_01_02_425006	122	20	�	�	NNS
10_1101-2021_01_02_425006	122	21	�	�	JJ
10_1101-2021_01_02_425006	122	22	�	�	''
10_1101-2021_01_02_425006	122	23	�	�	NNS
10_1101-2021_01_02_425006	122	24	�	�	VBZ
10_1101-2021_01_02_425006	122	25	∈	∈	JJ
10_1101-2021_01_02_425006	122	26	�	�	NNS
10_1101-2021_01_02_425006	122	27	�	�	NNS
10_1101-2021_01_02_425006	122	28	�	�	,
10_1101-2021_01_02_425006	122	29	(	(	-LRB-
10_1101-2021_01_02_425006	122	30	�	�	NNP
10_1101-2021_01_02_425006	122	31	�	�	NNP
10_1101-2021_01_02_425006	122	32	)	)	-RRB-
10_1101-2021_01_02_425006	122	33	�	�	NNP
10_1101-2021_01_02_425006	122	34	(	(	-LRB-
10_1101-2021_01_02_425006	122	35	�	�	NNP
10_1101-2021_01_02_425006	122	36	�	�	NNP
10_1101-2021_01_02_425006	122	37	)	)	-RRB-
10_1101-2021_01_02_425006	122	38	+	+	CC
10_1101-2021_01_02_425006	122	39	1	1	CD
10_1101-2021_01_02_425006	122	40	2	2	CD
10_1101-2021_01_02_425006	122	41	�	�	NNS
10_1101-2021_01_02_425006	122	42	�	�	JJ
10_1101-2021_01_02_425006	122	43	�	�	''
10_1101-2021_01_02_425006	122	44	�	�	NNS
10_1101-2021_01_02_425006	122	45	�	�	VBZ
10_1101-2021_01_02_425006	122	46	∈	∈	JJ
10_1101-2021_01_02_425006	122	47	�	�	NNS
10_1101-2021_01_02_425006	122	48	�	�	NNS
10_1101-2021_01_02_425006	122	49	�	�	,
10_1101-2021_01_02_425006	122	50	(	(	-LRB-
10_1101-2021_01_02_425006	122	51	�	�	NNP
10_1101-2021_01_02_425006	122	52	�	�	NNP
10_1101-2021_01_02_425006	122	53	)	)	-RRB-
10_1101-2021_01_02_425006	122	54	�	�	NNP
10_1101-2021_01_02_425006	122	55	(	(	-LRB-
10_1101-2021_01_02_425006	122	56	�	�	NNP
10_1101-2021_01_02_425006	122	57	�	�	NNP
10_1101-2021_01_02_425006	122	58	)	)	-RRB-
10_1101-2021_01_02_425006	122	59	(	(	-LRB-
10_1101-2021_01_02_425006	122	60	8)	8)	CD
10_1101-2021_01_02_425006	122	61	where	where	WRB
10_1101-2021_01_02_425006	122	62	�	�	NNP
10_1101-2021_01_02_425006	122	63	(	(	-LRB-
10_1101-2021_01_02_425006	122	64	�	�	NNP
10_1101-2021_01_02_425006	122	65	�	�	NNP
10_1101-2021_01_02_425006	122	66	)	)	-RRB-
10_1101-2021_01_02_425006	122	67	is	be	VBZ
10_1101-2021_01_02_425006	122	68	the	the	DT
10_1101-2021_01_02_425006	122	69	number	number	NN
10_1101-2021_01_02_425006	122	70	of	of	IN
10_1101-2021_01_02_425006	122	71	shared	share	VBN
10_1101-2021_01_02_425006	122	72	genes	gene	NNS
10_1101-2021_01_02_425006	122	73	of	of	IN
10_1101-2021_01_02_425006	122	74	�	�	NNP
10_1101-2021_01_02_425006	122	75	and	and	CC
10_1101-2021_01_02_425006	122	76	�	�	NNP
10_1101-2021_01_02_425006	122	77	�	�	NNP
10_1101-2021_01_02_425006	122	78	and	and	CC
10_1101-2021_01_02_425006	122	79	�	�	NNP
10_1101-2021_01_02_425006	122	80	(	(	-LRB-
10_1101-2021_01_02_425006	122	81	�	�	NNP
10_1101-2021_01_02_425006	122	82	�	�	NNP
10_1101-2021_01_02_425006	122	83	)	)	-RRB-
10_1101-2021_01_02_425006	122	84	is	be	VBZ
10_1101-2021_01_02_425006	122	85	the	the	DT
10_1101-2021_01_02_425006	122	86	maximal	maximal	JJ
10_1101-2021_01_02_425006	122	87	size	size	NN
10_1101-2021_01_02_425006	122	88	of	of	IN
10_1101-2021_01_02_425006	122	89	�	�	NNP
10_1101-2021_01_02_425006	122	90	and	and	CC
10_1101-2021_01_02_425006	122	91	�	�	NNP
10_1101-2021_01_02_425006	122	92	�	�	NNP
10_1101-2021_01_02_425006	122	93	.	.	.
10_1101-2021_01_02_425006	123	1	201	201	CD
10_1101-2021_01_02_425006	123	2	Case	case	NN
10_1101-2021_01_02_425006	123	3	3	3	CD
10_1101-2021_01_02_425006	123	4	:	:	:
10_1101-2021_01_02_425006	123	5	If	if	IN
10_1101-2021_01_02_425006	123	6	�	�	NNP
10_1101-2021_01_02_425006	123	7	shares	share	NNS
10_1101-2021_01_02_425006	123	8	no	no	DT
10_1101-2021_01_02_425006	123	9	boundary	boundary	JJ
10_1101-2021_01_02_425006	123	10	genes	gene	NNS
10_1101-2021_01_02_425006	123	11	at	at	IN
10_1101-2021_01_02_425006	123	12	both	both	DT
10_1101-2021_01_02_425006	123	13	ends	end	NNS
10_1101-2021_01_02_425006	123	14	of	of	IN
10_1101-2021_01_02_425006	123	15	the	the	DT
10_1101-2021_01_02_425006	123	16	ATUs	atu	NNS
10_1101-2021_01_02_425006	123	17	in	in	IN
10_1101-2021_01_02_425006	123	18	the	the	DT
10_1101-2021_01_02_425006	123	19	other	other	JJ
10_1101-2021_01_02_425006	123	20	dataset	dataset	NN
10_1101-2021_01_02_425006	123	21	,	,	,
10_1101-2021_01_02_425006	123	22	then	then	RB
10_1101-2021_01_02_425006	123	23	202	202	CD
10_1101-2021_01_02_425006	123	24	�	�	NNS
10_1101-2021_01_02_425006	123	25	�	�	,
10_1101-2021_01_02_425006	123	26	�	�	,
10_1101-2021_01_02_425006	123	27	�	�	NNS
10_1101-2021_01_02_425006	123	28	�	�	VBZ
10_1101-2021_01_02_425006	123	29	�	�	VBZ
10_1101-2021_01_02_425006	123	30	�	�	VBZ
10_1101-2021_01_02_425006	123	31	�	�	JJ
10_1101-2021_01_02_425006	123	32	�	�	NNS
10_1101-2021_01_02_425006	123	33	�	�	NNP
10_1101-2021_01_02_425006	123	34	(	(	-LRB-
10_1101-2021_01_02_425006	123	35	�	�	NNP
10_1101-2021_01_02_425006	123	36	)	)	-RRB-
10_1101-2021_01_02_425006	123	37	=	=	NFP
10_1101-2021_01_02_425006	123	38	0	0	NFP
10_1101-2021_01_02_425006	123	39	.	.	.
10_1101-2021_01_02_425006	124	1	203	203	CD
10_1101-2021_01_02_425006	124	2	Finally	finally	RB
10_1101-2021_01_02_425006	124	3	,	,	,
10_1101-2021_01_02_425006	124	4	the	the	DT
10_1101-2021_01_02_425006	124	5	precision	precision	NN
10_1101-2021_01_02_425006	124	6	and	and	CC
10_1101-2021_01_02_425006	124	7	recall	recall	NN
10_1101-2021_01_02_425006	124	8	based	base	VBN
10_1101-2021_01_02_425006	124	9	on	on	IN
10_1101-2021_01_02_425006	124	10	relaxed	relaxed	JJ
10_1101-2021_01_02_425006	124	11	matching	matching	NN
10_1101-2021_01_02_425006	124	12	are	be	VBP
10_1101-2021_01_02_425006	124	13	calculated	calculate	VBN
10_1101-2021_01_02_425006	124	14	by	by	IN
10_1101-2021_01_02_425006	124	15	the	the	DT
10_1101-2021_01_02_425006	124	16	following	follow	VBG
10_1101-2021_01_02_425006	124	17	formula	formula	NN
10_1101-2021_01_02_425006	124	18	:	:	:
10_1101-2021_01_02_425006	124	19	204	204	CD
10_1101-2021_01_02_425006	124	20	�	�	NNS
10_1101-2021_01_02_425006	124	21	�	�	NNS
10_1101-2021_01_02_425006	124	22	�	�	JJ
10_1101-2021_01_02_425006	124	23	�	�	NNS
10_1101-2021_01_02_425006	124	24	�	�	VBZ
10_1101-2021_01_02_425006	124	25	�	�	VBZ
10_1101-2021_01_02_425006	124	26	�	�	JJ
10_1101-2021_01_02_425006	124	27	�	�	NNS
10_1101-2021_01_02_425006	124	28	�	�	NNP
10_1101-2021_01_02_425006	124	29	=	=	SYM
10_1101-2021_01_02_425006	124	30	∑	∑	.
10_1101-2021_01_02_425006	124	31	�	�	JJ
10_1101-2021_01_02_425006	124	32	�	�	ADD
10_1101-2021_01_02_425006	124	33	�	�	NNS
10_1101-2021_01_02_425006	124	34	�	�	VBZ
10_1101-2021_01_02_425006	124	35	�	�	VBZ
10_1101-2021_01_02_425006	124	36	�	�	VBZ
10_1101-2021_01_02_425006	124	37	�	�	VBZ
10_1101-2021_01_02_425006	124	38	�	�	JJ
10_1101-2021_01_02_425006	124	39	�	�	NNS
10_1101-2021_01_02_425006	124	40	�	�	NNP
10_1101-2021_01_02_425006	124	41	(	(	-LRB-
10_1101-2021_01_02_425006	124	42	�	�	NNP
10_1101-2021_01_02_425006	124	43	)	)	-RRB-
10_1101-2021_01_02_425006	124	44	�	�	VBZ
10_1101-2021_01_02_425006	124	45	∈	∈	JJ
10_1101-2021_01_02_425006	124	46	�	�	NNS
10_1101-2021_01_02_425006	124	47	�	�	NNS
10_1101-2021_01_02_425006	124	48	�	�	JJ
10_1101-2021_01_02_425006	124	49	�	�	NNS
10_1101-2021_01_02_425006	124	50	.CC	.CC	NFP
10_1101-2021_01_02_425006	124	51	-	-	:
10_1101-2021_01_02_425006	124	52	BY	by	IN
10_1101-2021_01_02_425006	124	53	-	-	HYPH
10_1101-2021_01_02_425006	124	54	NC	NC	NNP
10_1101-2021_01_02_425006	124	55	-	-	HYPH
10_1101-2021_01_02_425006	124	56	ND	ND	NNP
10_1101-2021_01_02_425006	124	57	4.0	4.0	CD
10_1101-2021_01_02_425006	124	58	International	International	NNP
10_1101-2021_01_02_425006	124	59	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	124	60	under	under	IN
10_1101-2021_01_02_425006	124	61	a	a	DT
10_1101-2021_01_02_425006	124	62	(	(	-LRB-
10_1101-2021_01_02_425006	124	63	which	which	WDT
10_1101-2021_01_02_425006	124	64	was	be	VBD
10_1101-2021_01_02_425006	124	65	not	not	RB
10_1101-2021_01_02_425006	124	66	certified	certify	VBN
10_1101-2021_01_02_425006	124	67	by	by	IN
10_1101-2021_01_02_425006	124	68	peer	peer	NN
10_1101-2021_01_02_425006	124	69	review	review	NN
10_1101-2021_01_02_425006	124	70	)	)	-RRB-
10_1101-2021_01_02_425006	124	71	is	be	VBZ
10_1101-2021_01_02_425006	124	72	the	the	DT
10_1101-2021_01_02_425006	124	73	author	author	NN
10_1101-2021_01_02_425006	124	74	/	/	SYM
10_1101-2021_01_02_425006	124	75	funder	funder	NN
10_1101-2021_01_02_425006	124	76	,	,	,
10_1101-2021_01_02_425006	124	77	who	who	WP
10_1101-2021_01_02_425006	124	78	has	have	VBZ
10_1101-2021_01_02_425006	124	79	granted	grant	VBN
10_1101-2021_01_02_425006	124	80	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	124	81	a	a	DT
10_1101-2021_01_02_425006	124	82	license	license	NN
10_1101-2021_01_02_425006	124	83	to	to	TO
10_1101-2021_01_02_425006	124	84	display	display	VB
10_1101-2021_01_02_425006	124	85	the	the	DT
10_1101-2021_01_02_425006	124	86	preprint	preprint	NN
10_1101-2021_01_02_425006	124	87	in	in	IN
10_1101-2021_01_02_425006	124	88	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	124	89	.	.	.
10_1101-2021_01_02_425006	125	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	125	2	is	be	VBZ
10_1101-2021_01_02_425006	125	3	made	make	VBN
10_1101-2021_01_02_425006	125	4	The	the	DT
10_1101-2021_01_02_425006	125	5	copyright	copyright	NN
10_1101-2021_01_02_425006	125	6	holder	holder	NN
10_1101-2021_01_02_425006	125	7	for	for	IN
10_1101-2021_01_02_425006	125	8	this	this	DT
10_1101-2021_01_02_425006	125	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	125	10	version	version	NN
10_1101-2021_01_02_425006	125	11	posted	post	VBD
10_1101-2021_01_02_425006	125	12	January	January	NNP
10_1101-2021_01_02_425006	125	13	6	6	CD
10_1101-2021_01_02_425006	125	14	,	,	,
10_1101-2021_01_02_425006	125	15	2021	2021	CD
10_1101-2021_01_02_425006	125	16	.	.	.
10_1101-2021_01_02_425006	125	17	;	;	:
10_1101-2021_01_02_425006	125	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	125	19	:	:	:
10_1101-2021_01_02_425006	125	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	125	21	preprint	preprint	NN
10_1101-2021_01_02_425006	125	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	125	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	125	24	13	13	CD
10_1101-2021_01_02_425006	125	25	�	�	NNS
10_1101-2021_01_02_425006	125	26	�	�	,
10_1101-2021_01_02_425006	125	27	�	�	NNS
10_1101-2021_01_02_425006	125	28	�	�	JJ
10_1101-2021_01_02_425006	125	29	�	�	NNS
10_1101-2021_01_02_425006	125	30	�	�	NNP
10_1101-2021_01_02_425006	125	31	=	=	SYM
10_1101-2021_01_02_425006	125	32	∑	∑	.
10_1101-2021_01_02_425006	125	33	�	�	JJ
10_1101-2021_01_02_425006	125	34	�	�	ADD
10_1101-2021_01_02_425006	125	35	�	�	NNS
10_1101-2021_01_02_425006	125	36	�	�	VBZ
10_1101-2021_01_02_425006	125	37	�	�	VBZ
10_1101-2021_01_02_425006	125	38	�	�	VBZ
10_1101-2021_01_02_425006	125	39	�	�	VBZ
10_1101-2021_01_02_425006	125	40	�	�	JJ
10_1101-2021_01_02_425006	125	41	�	�	NNS
10_1101-2021_01_02_425006	125	42	�	�	NNP
10_1101-2021_01_02_425006	125	43	(	(	-LRB-
10_1101-2021_01_02_425006	125	44	�	�	NNP
10_1101-2021_01_02_425006	125	45	)	)	-RRB-
10_1101-2021_01_02_425006	125	46	�	�	VBZ
10_1101-2021_01_02_425006	125	47	∈	∈	JJ
10_1101-2021_01_02_425006	125	48	�	�	NNS
10_1101-2021_01_02_425006	125	49	�	�	NNS
10_1101-2021_01_02_425006	125	50	�	�	NNS
10_1101-2021_01_02_425006	125	51	�	�	NNP
10_1101-2021_01_02_425006	125	52	(	(	-LRB-
10_1101-2021_01_02_425006	125	53	9	9	CD
10_1101-2021_01_02_425006	125	54	)	)	-RRB-
10_1101-2021_01_02_425006	125	55	where	where	WRB
10_1101-2021_01_02_425006	125	56	�	�	NNP
10_1101-2021_01_02_425006	125	57	�	�	NNP
10_1101-2021_01_02_425006	125	58	is	be	VBZ
10_1101-2021_01_02_425006	125	59	the	the	DT
10_1101-2021_01_02_425006	125	60	set	set	NN
10_1101-2021_01_02_425006	125	61	of	of	IN
10_1101-2021_01_02_425006	125	62	predicted	predict	VBN
10_1101-2021_01_02_425006	125	63	ATUs	atu	NNS
10_1101-2021_01_02_425006	125	64	,	,	,
10_1101-2021_01_02_425006	125	65	�	�	NNP
10_1101-2021_01_02_425006	125	66	�	�	NNP
10_1101-2021_01_02_425006	125	67	is	be	VBZ
10_1101-2021_01_02_425006	125	68	the	the	DT
10_1101-2021_01_02_425006	125	69	number	number	NN
10_1101-2021_01_02_425006	125	70	of	of	IN
10_1101-2021_01_02_425006	125	71	predicted	predict	VBN
10_1101-2021_01_02_425006	125	72	ATUs	atu	NNS
10_1101-2021_01_02_425006	125	73	,	,	,
10_1101-2021_01_02_425006	125	74	�	�	NNP
10_1101-2021_01_02_425006	125	75	�	�	NNP
10_1101-2021_01_02_425006	125	76	is	be	VBZ
10_1101-2021_01_02_425006	125	77	the	the	DT
10_1101-2021_01_02_425006	125	78	set	set	NN
10_1101-2021_01_02_425006	125	79	of	of	IN
10_1101-2021_01_02_425006	125	80	evaluated	evaluate	VBN
10_1101-2021_01_02_425006	125	81	205	205	CD
10_1101-2021_01_02_425006	125	82	ATUs	atu	NNS
10_1101-2021_01_02_425006	125	83	,	,	,
10_1101-2021_01_02_425006	125	84	and	and	CC
10_1101-2021_01_02_425006	125	85	�	�	NNP
10_1101-2021_01_02_425006	125	86	�	�	NNP
10_1101-2021_01_02_425006	125	87	is	be	VBZ
10_1101-2021_01_02_425006	125	88	the	the	DT
10_1101-2021_01_02_425006	125	89	number	number	NN
10_1101-2021_01_02_425006	125	90	of	of	IN
10_1101-2021_01_02_425006	125	91	evaluated	evaluated	JJ
10_1101-2021_01_02_425006	125	92	ATUs	atu	NNS
10_1101-2021_01_02_425006	125	93	.	.	.
10_1101-2021_01_02_425006	126	1	206	206	CD
10_1101-2021_01_02_425006	126	2	RESULTS	results	NN
10_1101-2021_01_02_425006	126	3	207	207	CD
10_1101-2021_01_02_425006	126	4	A	a	DT
10_1101-2021_01_02_425006	126	5	reliable	reliable	JJ
10_1101-2021_01_02_425006	126	6	bias	bias	NN
10_1101-2021_01_02_425006	126	7	rate	rate	NN
10_1101-2021_01_02_425006	126	8	function	function	NN
10_1101-2021_01_02_425006	126	9	is	be	VBZ
10_1101-2021_01_02_425006	126	10	acquired	acquire	VBN
10_1101-2021_01_02_425006	126	11	in	in	IN
10_1101-2021_01_02_425006	126	12	modeling	model	VBG
10_1101-2021_01_02_425006	126	13	non	non	JJ
10_1101-2021_01_02_425006	126	14	-	-	JJ
10_1101-2021_01_02_425006	126	15	uniform	uniform	JJ
10_1101-2021_01_02_425006	126	16	read	read	VB
10_1101-2021_01_02_425006	126	17	distribution	distribution	NN
10_1101-2021_01_02_425006	126	18	along	along	IN
10_1101-2021_01_02_425006	126	19	mRNA	mrna	IN
10_1101-2021_01_02_425006	126	20	208	208	CD
10_1101-2021_01_02_425006	126	21	transcripts	transcript	NNS
10_1101-2021_01_02_425006	126	22	209	209	CD
10_1101-2021_01_02_425006	126	23	To	to	TO
10_1101-2021_01_02_425006	126	24	ensure	ensure	VB
10_1101-2021_01_02_425006	126	25	the	the	DT
10_1101-2021_01_02_425006	126	26	reliability	reliability	NN
10_1101-2021_01_02_425006	126	27	of	of	IN
10_1101-2021_01_02_425006	126	28	the	the	DT
10_1101-2021_01_02_425006	126	29	bias	bias	NN
10_1101-2021_01_02_425006	126	30	rate	rate	NN
10_1101-2021_01_02_425006	126	31	function	function	NN
10_1101-2021_01_02_425006	126	32	in	in	IN
10_1101-2021_01_02_425006	126	33	modeling	model	VBG
10_1101-2021_01_02_425006	126	34	non	non	JJ
10_1101-2021_01_02_425006	126	35	-	-	JJ
10_1101-2021_01_02_425006	126	36	uniform	uniform	JJ
10_1101-2021_01_02_425006	126	37	read	read	VB
10_1101-2021_01_02_425006	126	38	distribution	distribution	NN
10_1101-2021_01_02_425006	126	39	,	,	,
10_1101-2021_01_02_425006	126	40	we	-PRON-	PRP
10_1101-2021_01_02_425006	126	41	selected	select	VBD
10_1101-2021_01_02_425006	126	42	210	210	CD
10_1101-2021_01_02_425006	126	43	four	four	CD
10_1101-2021_01_02_425006	126	44	single	single	JJ
10_1101-2021_01_02_425006	126	45	gene	gene	NN
10_1101-2021_01_02_425006	126	46	mRNA	mrna	NN
10_1101-2021_01_02_425006	126	47	transcript	transcript	NNP
10_1101-2021_01_02_425006	126	48	datasets	dataset	VBZ
10_1101-2021_01_02_425006	126	49	randomly	randomly	RB
10_1101-2021_01_02_425006	126	50	from	from	IN
10_1101-2021_01_02_425006	126	51	the	the	DT
10_1101-2021_01_02_425006	126	52	two	two	CD
10_1101-2021_01_02_425006	126	53	evaluation	evaluation	NN
10_1101-2021_01_02_425006	126	54	datasets	dataset	VBZ
10_1101-2021_01_02_425006	126	55	211	211	CD
10_1101-2021_01_02_425006	126	56	(	(	-LRB-
10_1101-2021_01_02_425006	126	57	SMRT_M9Enrich	SMRT_M9Enrich	NNP
10_1101-2021_01_02_425006	126	58	and	and	CC
10_1101-2021_01_02_425006	126	59	SMRT_RiEnrich	SMRT_RiEnrich	NNP
10_1101-2021_01_02_425006	126	60	)	)	-RRB-
10_1101-2021_01_02_425006	126	61	,	,	,
10_1101-2021_01_02_425006	126	62	named	name	VBN
10_1101-2021_01_02_425006	126	63	M9Enrich_1	M9Enrich_1	NNP
10_1101-2021_01_02_425006	126	64	,	,	,
10_1101-2021_01_02_425006	126	65	M9Enrich_2	M9Enrich_2	NNP
10_1101-2021_01_02_425006	126	66	,	,	,
10_1101-2021_01_02_425006	126	67	RiEnrich_1	RiEnrich_1	NNP
10_1101-2021_01_02_425006	126	68	,	,	,
10_1101-2021_01_02_425006	126	69	and	and	CC
10_1101-2021_01_02_425006	126	70	212	212	CD
10_1101-2021_01_02_425006	126	71	RiEnrich_2	RiEnrich_2	NNS
10_1101-2021_01_02_425006	126	72	.	.	.
10_1101-2021_01_02_425006	127	1	Four	four	CD
10_1101-2021_01_02_425006	127	2	bias	bias	NN
10_1101-2021_01_02_425006	127	3	rate	rate	NN
10_1101-2021_01_02_425006	127	4	functions	function	NNS
10_1101-2021_01_02_425006	127	5	,	,	,
10_1101-2021_01_02_425006	127	6	which	which	WDT
10_1101-2021_01_02_425006	127	7	are	be	VBP
10_1101-2021_01_02_425006	127	8	exponential	exponential	JJ
10_1101-2021_01_02_425006	127	9	functions	function	NNS
10_1101-2021_01_02_425006	127	10	,	,	,
10_1101-2021_01_02_425006	127	11	were	be	VBD
10_1101-2021_01_02_425006	127	12	generated	generate	VBN
10_1101-2021_01_02_425006	127	13	after	after	IN
10_1101-2021_01_02_425006	127	14	conducting	conduct	VBG
10_1101-2021_01_02_425006	127	15	213	213	CD
10_1101-2021_01_02_425006	127	16	nonlinear	nonlinear	JJ
10_1101-2021_01_02_425006	127	17	regression	regression	NN
10_1101-2021_01_02_425006	127	18	on	on	IN
10_1101-2021_01_02_425006	127	19	the	the	DT
10_1101-2021_01_02_425006	127	20	mRNA	mrna	NN
10_1101-2021_01_02_425006	127	21	transcripts	transcript	NNS
10_1101-2021_01_02_425006	127	22	across	across	IN
10_1101-2021_01_02_425006	127	23	these	these	DT
10_1101-2021_01_02_425006	127	24	four	four	CD
10_1101-2021_01_02_425006	127	25	datasets	dataset	NNS
10_1101-2021_01_02_425006	127	26	(	(	-LRB-
10_1101-2021_01_02_425006	127	27	Fig	fig	NN
10_1101-2021_01_02_425006	127	28	.	.	.
10_1101-2021_01_02_425006	128	1	2	2	LS
10_1101-2021_01_02_425006	128	2	)	)	-RRB-
10_1101-2021_01_02_425006	128	3	.	.	.
10_1101-2021_01_02_425006	129	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	129	2	found	find	VBD
10_1101-2021_01_02_425006	129	3	that	that	IN
10_1101-2021_01_02_425006	129	4	these	these	DT
10_1101-2021_01_02_425006	129	5	214	214	CD
10_1101-2021_01_02_425006	129	6	bias	bias	NN
10_1101-2021_01_02_425006	129	7	rate	rate	NN
10_1101-2021_01_02_425006	129	8	functions	function	NNS
10_1101-2021_01_02_425006	129	9	were	be	VBD
10_1101-2021_01_02_425006	129	10	similar	similar	JJ
10_1101-2021_01_02_425006	129	11	(	(	-LRB-
10_1101-2021_01_02_425006	129	12	�	�	NNP
10_1101-2021_01_02_425006	129	13	�	�	NNP
10_1101-2021_01_02_425006	129	14	>	>	XX
10_1101-2021_01_02_425006	129	15	0.998	0.998	CD
10_1101-2021_01_02_425006	129	16	)	)	-RRB-
10_1101-2021_01_02_425006	129	17	when	when	WRB
10_1101-2021_01_02_425006	129	18	we	-PRON-	PRP
10_1101-2021_01_02_425006	129	19	evaluated	evaluate	VBD
10_1101-2021_01_02_425006	129	20	the	the	DT
10_1101-2021_01_02_425006	129	21	R	r	JJ
10_1101-2021_01_02_425006	129	22	-	-	HYPH
10_1101-2021_01_02_425006	129	23	square	square	NN
10_1101-2021_01_02_425006	129	24	statistic	statistic	NN
10_1101-2021_01_02_425006	129	25	(	(	-LRB-
10_1101-2021_01_02_425006	129	26	for	for	IN
10_1101-2021_01_02_425006	129	27	more	more	JJR
10_1101-2021_01_02_425006	129	28	215	215	CD
10_1101-2021_01_02_425006	129	29	details	detail	NNS
10_1101-2021_01_02_425006	129	30	,	,	,
10_1101-2021_01_02_425006	129	31	see	see	VB
10_1101-2021_01_02_425006	129	32	method	method	NN
10_1101-2021_01_02_425006	129	33	S6	s6	NN
10_1101-2021_01_02_425006	129	34	and	and	CC
10_1101-2021_01_02_425006	129	35	table	table	NN
10_1101-2021_01_02_425006	129	36	S2	S2	NNP
10_1101-2021_01_02_425006	129	37	)	)	-RRB-
10_1101-2021_01_02_425006	129	38	.	.	.
10_1101-2021_01_02_425006	130	1	The	the	DT
10_1101-2021_01_02_425006	130	2	similarity	similarity	NN
10_1101-2021_01_02_425006	130	3	of	of	IN
10_1101-2021_01_02_425006	130	4	the	the	DT
10_1101-2021_01_02_425006	130	5	four	four	CD
10_1101-2021_01_02_425006	130	6	bias	bias	NN
10_1101-2021_01_02_425006	130	7	rate	rate	NN
10_1101-2021_01_02_425006	130	8	functions	function	NNS
10_1101-2021_01_02_425006	130	9	indicated	indicate	VBD
10_1101-2021_01_02_425006	130	10	that	that	IN
10_1101-2021_01_02_425006	130	11	the	the	DT
10_1101-2021_01_02_425006	130	12	216	216	CD
10_1101-2021_01_02_425006	130	13	selection	selection	NN
10_1101-2021_01_02_425006	130	14	of	of	IN
10_1101-2021_01_02_425006	130	15	the	the	DT
10_1101-2021_01_02_425006	130	16	single	single	JJ
10_1101-2021_01_02_425006	130	17	gene	gene	NN
10_1101-2021_01_02_425006	130	18	mRNA	mrna	NN
10_1101-2021_01_02_425006	130	19	transcript	transcript	NNP
10_1101-2021_01_02_425006	130	20	datasets	datasets	NNPS
10_1101-2021_01_02_425006	130	21	had	have	VBD
10_1101-2021_01_02_425006	130	22	little	little	JJ
10_1101-2021_01_02_425006	130	23	impact	impact	NN
10_1101-2021_01_02_425006	130	24	on	on	IN
10_1101-2021_01_02_425006	130	25	modeling	model	VBG
10_1101-2021_01_02_425006	130	26	non	non	JJ
10_1101-2021_01_02_425006	130	27	-	-	JJ
10_1101-2021_01_02_425006	130	28	uniform	uniform	JJ
10_1101-2021_01_02_425006	130	29	read	read	VBD
10_1101-2021_01_02_425006	130	30	217	217	CD
10_1101-2021_01_02_425006	130	31	distribution	distribution	NN
10_1101-2021_01_02_425006	130	32	along	along	IN
10_1101-2021_01_02_425006	130	33	mRNA	mRNA	NNS
10_1101-2021_01_02_425006	130	34	transcripts	transcript	NNS
10_1101-2021_01_02_425006	130	35	,	,	,
10_1101-2021_01_02_425006	130	36	implying	imply	VBG
10_1101-2021_01_02_425006	130	37	the	the	DT
10_1101-2021_01_02_425006	130	38	universal	universal	JJ
10_1101-2021_01_02_425006	130	39	common	common	JJ
10_1101-2021_01_02_425006	130	40	non	non	JJ
10_1101-2021_01_02_425006	130	41	-	-	JJ
10_1101-2021_01_02_425006	130	42	uniform	uniform	JJ
10_1101-2021_01_02_425006	130	43	read	read	VBD
10_1101-2021_01_02_425006	130	44	distribution	distribution	NN
10_1101-2021_01_02_425006	130	45	of	of	IN
10_1101-2021_01_02_425006	130	46	218	218	CD
10_1101-2021_01_02_425006	130	47	different	different	JJ
10_1101-2021_01_02_425006	130	48	mRNA	mRNA	NNS
10_1101-2021_01_02_425006	130	49	transcripts	transcript	NNS
10_1101-2021_01_02_425006	130	50	of	of	IN
10_1101-2021_01_02_425006	130	51	E.	E.	NNP
10_1101-2021_01_02_425006	130	52	coli	coli	NNS
10_1101-2021_01_02_425006	130	53	.	.	.
10_1101-2021_01_02_425006	131	1	Specifically	specifically	RB
10_1101-2021_01_02_425006	131	2	,	,	,
10_1101-2021_01_02_425006	131	3	we	-PRON-	PRP
10_1101-2021_01_02_425006	131	4	used	use	VBD
10_1101-2021_01_02_425006	131	5	the	the	DT
10_1101-2021_01_02_425006	131	6	average	average	NN
10_1101-2021_01_02_425006	131	7	of	of	IN
10_1101-2021_01_02_425006	131	8	these	these	DT
10_1101-2021_01_02_425006	131	9	four	four	CD
10_1101-2021_01_02_425006	131	10	coefficients	coefficient	NNS
10_1101-2021_01_02_425006	131	11	as	as	IN
10_1101-2021_01_02_425006	131	12	the	the	DT
10_1101-2021_01_02_425006	131	13	219	219	CD
10_1101-2021_01_02_425006	131	14	final	final	JJ
10_1101-2021_01_02_425006	131	15	coefficients	coefficient	NNS
10_1101-2021_01_02_425006	131	16	of	of	IN
10_1101-2021_01_02_425006	131	17	the	the	DT
10_1101-2021_01_02_425006	131	18	exponential	exponential	JJ
10_1101-2021_01_02_425006	131	19	function	function	NN
10_1101-2021_01_02_425006	131	20	,	,	,
10_1101-2021_01_02_425006	131	21	which	which	WDT
10_1101-2021_01_02_425006	131	22	was	be	VBD
10_1101-2021_01_02_425006	131	23	�	�	NNP
10_1101-2021_01_02_425006	131	24	(	(	-LRB-
10_1101-2021_01_02_425006	131	25	�	�	NNP
10_1101-2021_01_02_425006	131	26	)	)	-RRB-
10_1101-2021_01_02_425006	131	27	=	=	NFP
10_1101-2021_01_02_425006	131	28	�	�	ADD
10_1101-2021_01_02_425006	131	29	�	�	,
10_1101-2021_01_02_425006	131	30	�	�	NNS
10_1101-2021_01_02_425006	131	31	�	�	NN
10_1101-2021_01_02_425006	131	32	with	with	IN
10_1101-2021_01_02_425006	131	33	�	�	NNP
10_1101-2021_01_02_425006	131	34	=	=	SYM
10_1101-2021_01_02_425006	131	35	0.256	0.256	CD
10_1101-2021_01_02_425006	131	36	and	and	CC
10_1101-2021_01_02_425006	131	37	�	�	NNP
10_1101-2021_01_02_425006	131	38	=	=	SYM
10_1101-2021_01_02_425006	131	39	220	220	CD
10_1101-2021_01_02_425006	131	40	0.00128	0.00128	CD
10_1101-2021_01_02_425006	131	41	.	.	.
10_1101-2021_01_02_425006	132	1	221	221	CD
10_1101-2021_01_02_425006	132	2	.CC	.CC	:
10_1101-2021_01_02_425006	132	3	-	-	HYPH
10_1101-2021_01_02_425006	132	4	BY	by	IN
10_1101-2021_01_02_425006	132	5	-	-	HYPH
10_1101-2021_01_02_425006	132	6	NC	NC	NNP
10_1101-2021_01_02_425006	132	7	-	-	HYPH
10_1101-2021_01_02_425006	132	8	ND	ND	NNP
10_1101-2021_01_02_425006	132	9	4.0	4.0	CD
10_1101-2021_01_02_425006	132	10	International	International	NNP
10_1101-2021_01_02_425006	132	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	132	12	under	under	IN
10_1101-2021_01_02_425006	132	13	a	a	DT
10_1101-2021_01_02_425006	132	14	(	(	-LRB-
10_1101-2021_01_02_425006	132	15	which	which	WDT
10_1101-2021_01_02_425006	132	16	was	be	VBD
10_1101-2021_01_02_425006	132	17	not	not	RB
10_1101-2021_01_02_425006	132	18	certified	certify	VBN
10_1101-2021_01_02_425006	132	19	by	by	IN
10_1101-2021_01_02_425006	132	20	peer	peer	NN
10_1101-2021_01_02_425006	132	21	review	review	NN
10_1101-2021_01_02_425006	132	22	)	)	-RRB-
10_1101-2021_01_02_425006	132	23	is	be	VBZ
10_1101-2021_01_02_425006	132	24	the	the	DT
10_1101-2021_01_02_425006	132	25	author	author	NN
10_1101-2021_01_02_425006	132	26	/	/	SYM
10_1101-2021_01_02_425006	132	27	funder	funder	NN
10_1101-2021_01_02_425006	132	28	,	,	,
10_1101-2021_01_02_425006	132	29	who	who	WP
10_1101-2021_01_02_425006	132	30	has	have	VBZ
10_1101-2021_01_02_425006	132	31	granted	grant	VBN
10_1101-2021_01_02_425006	132	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	132	33	a	a	DT
10_1101-2021_01_02_425006	132	34	license	license	NN
10_1101-2021_01_02_425006	132	35	to	to	TO
10_1101-2021_01_02_425006	132	36	display	display	VB
10_1101-2021_01_02_425006	132	37	the	the	DT
10_1101-2021_01_02_425006	132	38	preprint	preprint	NN
10_1101-2021_01_02_425006	132	39	in	in	IN
10_1101-2021_01_02_425006	132	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	132	41	.	.	.
10_1101-2021_01_02_425006	133	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	133	2	is	be	VBZ
10_1101-2021_01_02_425006	133	3	made	make	VBN
10_1101-2021_01_02_425006	133	4	The	the	DT
10_1101-2021_01_02_425006	133	5	copyright	copyright	NN
10_1101-2021_01_02_425006	133	6	holder	holder	NN
10_1101-2021_01_02_425006	133	7	for	for	IN
10_1101-2021_01_02_425006	133	8	this	this	DT
10_1101-2021_01_02_425006	133	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	133	10	version	version	NN
10_1101-2021_01_02_425006	133	11	posted	post	VBD
10_1101-2021_01_02_425006	133	12	January	January	NNP
10_1101-2021_01_02_425006	133	13	6	6	CD
10_1101-2021_01_02_425006	133	14	,	,	,
10_1101-2021_01_02_425006	133	15	2021	2021	CD
10_1101-2021_01_02_425006	133	16	.	.	.
10_1101-2021_01_02_425006	133	17	;	;	:
10_1101-2021_01_02_425006	133	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	133	19	:	:	:
10_1101-2021_01_02_425006	133	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	133	21	preprint	preprint	NN
10_1101-2021_01_02_425006	133	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	133	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	133	24	14	14	CD
10_1101-2021_01_02_425006	133	25	Please	please	UH
10_1101-2021_01_02_425006	133	26	place	place	VB
10_1101-2021_01_02_425006	133	27	Fig	Fig	NNP
10_1101-2021_01_02_425006	133	28	.	.	.
10_1101-2021_01_02_425006	134	1	2	2	CD
10_1101-2021_01_02_425006	134	2	here	here	RB
10_1101-2021_01_02_425006	134	3	.	.	.
10_1101-2021_01_02_425006	135	1	222	222	CD
10_1101-2021_01_02_425006	135	2	ATUs	atu	NNS
10_1101-2021_01_02_425006	135	3	predicted	predict	VBN
10_1101-2021_01_02_425006	135	4	by	by	IN
10_1101-2021_01_02_425006	135	5	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	135	6	reach	reach	VB
10_1101-2021_01_02_425006	135	7	precision	precision	NN
10_1101-2021_01_02_425006	135	8	and	and	CC
10_1101-2021_01_02_425006	135	9	recall	recall	NN
10_1101-2021_01_02_425006	135	10	over	over	IN
10_1101-2021_01_02_425006	135	11	0.64	0.64	CD
10_1101-2021_01_02_425006	135	12	223	223	CD
10_1101-2021_01_02_425006	135	13	The	the	DT
10_1101-2021_01_02_425006	135	14	performance	performance	NN
10_1101-2021_01_02_425006	135	15	evaluation	evaluation	NN
10_1101-2021_01_02_425006	135	16	was	be	VBD
10_1101-2021_01_02_425006	135	17	conducted	conduct	VBN
10_1101-2021_01_02_425006	135	18	by	by	IN
10_1101-2021_01_02_425006	135	19	comparing	compare	VBG
10_1101-2021_01_02_425006	135	20	the	the	DT
10_1101-2021_01_02_425006	135	21	predicted	predict	VBN
10_1101-2021_01_02_425006	135	22	ATUs	atu	NNS
10_1101-2021_01_02_425006	135	23	with	with	IN
10_1101-2021_01_02_425006	135	24	the	the	DT
10_1101-2021_01_02_425006	135	25	ATUs	atu	NNS
10_1101-2021_01_02_425006	135	26	in	in	IN
10_1101-2021_01_02_425006	135	27	224	224	CD
10_1101-2021_01_02_425006	135	28	SMRT_M9Enrich	SMRT_M9Enrich	NNP
10_1101-2021_01_02_425006	135	29	and	and	CC
10_1101-2021_01_02_425006	135	30	SMRT_RiEnrich	SMRT_RiEnrich	NNP
10_1101-2021_01_02_425006	135	31	,	,	,
10_1101-2021_01_02_425006	135	32	which	which	WDT
10_1101-2021_01_02_425006	135	33	were	be	VBD
10_1101-2021_01_02_425006	135	34	generated	generate	VBN
10_1101-2021_01_02_425006	135	35	based	base	VBN
10_1101-2021_01_02_425006	135	36	on	on	IN
10_1101-2021_01_02_425006	135	37	the	the	DT
10_1101-2021_01_02_425006	135	38	third	third	JJ
10_1101-2021_01_02_425006	135	39	-	-	HYPH
10_1101-2021_01_02_425006	135	40	generation	generation	NN
10_1101-2021_01_02_425006	135	41	sequencing	sequencing	NN
10_1101-2021_01_02_425006	135	42	225	225	CD
10_1101-2021_01_02_425006	135	43	and	and	CC
10_1101-2021_01_02_425006	135	44	are	be	VBP
10_1101-2021_01_02_425006	135	45	not	not	RB
10_1101-2021_01_02_425006	135	46	sensitive	sensitive	JJ
10_1101-2021_01_02_425006	135	47	to	to	IN
10_1101-2021_01_02_425006	135	48	transcripts	transcript	NNS
10_1101-2021_01_02_425006	135	49	with	with	IN
10_1101-2021_01_02_425006	135	50	low	low	JJ
10_1101-2021_01_02_425006	135	51	expression	expression	NN
10_1101-2021_01_02_425006	135	52	levels	level	NNS
10_1101-2021_01_02_425006	135	53	.	.	.
10_1101-2021_01_02_425006	136	1	For	for	IN
10_1101-2021_01_02_425006	136	2	a	a	DT
10_1101-2021_01_02_425006	136	3	more	more	RBR
10_1101-2021_01_02_425006	136	4	accurate	accurate	JJ
10_1101-2021_01_02_425006	136	5	and	and	CC
10_1101-2021_01_02_425006	136	6	fair	fair	JJ
10_1101-2021_01_02_425006	136	7	evaluation	evaluation	NN
10_1101-2021_01_02_425006	136	8	,	,	,
10_1101-2021_01_02_425006	136	9	226	226	CD
10_1101-2021_01_02_425006	136	10	maximal	maximal	JJ
10_1101-2021_01_02_425006	136	11	ATU	ATU	NNP
10_1101-2021_01_02_425006	136	12	clusters	cluster	NNS
10_1101-2021_01_02_425006	136	13	after	after	IN
10_1101-2021_01_02_425006	136	14	pre	pre	JJ
10_1101-2021_01_02_425006	136	15	-	-	NN
10_1101-2021_01_02_425006	136	16	selection	selection	NN
10_1101-2021_01_02_425006	136	17	were	be	VBD
10_1101-2021_01_02_425006	136	18	retained	retain	VBN
10_1101-2021_01_02_425006	136	19	in	in	IN
10_1101-2021_01_02_425006	136	20	the	the	DT
10_1101-2021_01_02_425006	136	21	subsequent	subsequent	JJ
10_1101-2021_01_02_425006	136	22	evaluations	evaluation	NNS
10_1101-2021_01_02_425006	136	23	(	(	-LRB-
10_1101-2021_01_02_425006	136	24	more	more	JJR
10_1101-2021_01_02_425006	136	25	details	detail	NNS
10_1101-2021_01_02_425006	136	26	227	227	CD
10_1101-2021_01_02_425006	136	27	about	about	IN
10_1101-2021_01_02_425006	136	28	the	the	DT
10_1101-2021_01_02_425006	136	29	pre	pre	JJ
10_1101-2021_01_02_425006	136	30	-	-	NN
10_1101-2021_01_02_425006	136	31	selection	selection	NN
10_1101-2021_01_02_425006	136	32	of	of	IN
10_1101-2021_01_02_425006	136	33	maximal	maximal	JJ
10_1101-2021_01_02_425006	136	34	ATU	ATU	NNP
10_1101-2021_01_02_425006	136	35	clusters	cluster	NNS
10_1101-2021_01_02_425006	136	36	can	can	MD
10_1101-2021_01_02_425006	136	37	be	be	VB
10_1101-2021_01_02_425006	136	38	seen	see	VBN
10_1101-2021_01_02_425006	136	39	in	in	IN
10_1101-2021_01_02_425006	136	40	method	method	NN
10_1101-2021_01_02_425006	136	41	S7	S7	NNP
10_1101-2021_01_02_425006	136	42	and	and	CC
10_1101-2021_01_02_425006	136	43	fig	fig	VBP
10_1101-2021_01_02_425006	136	44	.	.	.
10_1101-2021_01_02_425006	137	1	S3	S3	NNP
10_1101-2021_01_02_425006	137	2	)	)	-RRB-
10_1101-2021_01_02_425006	137	3	.	.	.
10_1101-2021_01_02_425006	138	1	228	228	CD
10_1101-2021_01_02_425006	138	2	The	the	DT
10_1101-2021_01_02_425006	138	3	precision	precision	NN
10_1101-2021_01_02_425006	138	4	and	and	CC
10_1101-2021_01_02_425006	138	5	recall	recall	NN
10_1101-2021_01_02_425006	138	6	of	of	IN
10_1101-2021_01_02_425006	138	7	the	the	DT
10_1101-2021_01_02_425006	138	8	predicted	predict	VBN
10_1101-2021_01_02_425006	138	9	ATUs	atu	NNS
10_1101-2021_01_02_425006	138	10	were	be	VBD
10_1101-2021_01_02_425006	138	11	calculated	calculate	VBN
10_1101-2021_01_02_425006	138	12	for	for	IN
10_1101-2021_01_02_425006	138	13	each	each	DT
10_1101-2021_01_02_425006	138	14	maximal	maximal	JJ
10_1101-2021_01_02_425006	138	15	ATU	ATU	NNP
10_1101-2021_01_02_425006	138	16	cluster	cluster	NN
10_1101-2021_01_02_425006	138	17	.	.	.
10_1101-2021_01_02_425006	139	1	By	by	IN
10_1101-2021_01_02_425006	139	2	229	229	CD
10_1101-2021_01_02_425006	139	3	considering	consider	VBG
10_1101-2021_01_02_425006	139	4	only	only	RB
10_1101-2021_01_02_425006	139	5	perfect	perfect	JJ
10_1101-2021_01_02_425006	139	6	matching	matching	NN
10_1101-2021_01_02_425006	139	7	,	,	,
10_1101-2021_01_02_425006	139	8	the	the	DT
10_1101-2021_01_02_425006	139	9	average	average	JJ
10_1101-2021_01_02_425006	139	10	precision	precision	NN
10_1101-2021_01_02_425006	139	11	and	and	CC
10_1101-2021_01_02_425006	139	12	recall	recall	NN
10_1101-2021_01_02_425006	139	13	were	be	VBD
10_1101-2021_01_02_425006	139	14	0.67	0.67	CD
10_1101-2021_01_02_425006	139	15	and	and	CC
10_1101-2021_01_02_425006	139	16	0.67	0.67	CD
10_1101-2021_01_02_425006	139	17	for	for	IN
10_1101-2021_01_02_425006	139	18	230	230	CD
10_1101-2021_01_02_425006	139	19	M9Enirch_Seq	m9enirch_seq	CD
10_1101-2021_01_02_425006	139	20	and	and	CC
10_1101-2021_01_02_425006	139	21	0.64	0.64	CD
10_1101-2021_01_02_425006	139	22	and	and	CC
10_1101-2021_01_02_425006	139	23	0.68	0.68	CD
10_1101-2021_01_02_425006	139	24	for	for	IN
10_1101-2021_01_02_425006	139	25	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	139	26	,	,	,
10_1101-2021_01_02_425006	139	27	respectively	respectively	RB
10_1101-2021_01_02_425006	139	28	.	.	.
10_1101-2021_01_02_425006	140	1	When	when	WRB
10_1101-2021_01_02_425006	140	2	using	use	VBG
10_1101-2021_01_02_425006	140	3	relaxed	relaxed	JJ
10_1101-2021_01_02_425006	140	4	matching	matching	NN
10_1101-2021_01_02_425006	140	5	,	,	,
10_1101-2021_01_02_425006	140	6	the	the	DT
10_1101-2021_01_02_425006	140	7	231	231	CD
10_1101-2021_01_02_425006	140	8	average	average	JJ
10_1101-2021_01_02_425006	140	9	precision	precision	NN
10_1101-2021_01_02_425006	140	10	and	and	CC
10_1101-2021_01_02_425006	140	11	recall	recall	NN
10_1101-2021_01_02_425006	140	12	increased	increase	VBD
10_1101-2021_01_02_425006	140	13	to	to	IN
10_1101-2021_01_02_425006	140	14	0.77	0.77	CD
10_1101-2021_01_02_425006	140	15	and	and	CC
10_1101-2021_01_02_425006	140	16	0.75	0.75	CD
10_1101-2021_01_02_425006	140	17	for	for	IN
10_1101-2021_01_02_425006	140	18	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	140	19	and	and	CC
10_1101-2021_01_02_425006	140	20	0.74	0.74	CD
10_1101-2021_01_02_425006	140	21	and	and	CC
10_1101-2021_01_02_425006	140	22	0.76	0.76	CD
10_1101-2021_01_02_425006	140	23	for	for	IN
10_1101-2021_01_02_425006	140	24	232	232	CD
10_1101-2021_01_02_425006	140	25	RiEnrich_Seq	rienrich_seq	NN
10_1101-2021_01_02_425006	140	26	,	,	,
10_1101-2021_01_02_425006	140	27	respectively	respectively	RB
10_1101-2021_01_02_425006	140	28	.	.	.
10_1101-2021_01_02_425006	141	1	The	the	DT
10_1101-2021_01_02_425006	141	2	statistics	statistic	NNS
10_1101-2021_01_02_425006	141	3	for	for	IN
10_1101-2021_01_02_425006	141	4	precision	precision	NN
10_1101-2021_01_02_425006	141	5	and	and	CC
10_1101-2021_01_02_425006	141	6	recall	recall	NN
10_1101-2021_01_02_425006	141	7	on	on	IN
10_1101-2021_01_02_425006	141	8	maximal	maximal	JJ
10_1101-2021_01_02_425006	141	9	ATU	ATU	NNP
10_1101-2021_01_02_425006	141	10	clusters	cluster	NNS
10_1101-2021_01_02_425006	141	11	with	with	IN
10_1101-2021_01_02_425006	141	12	233	233	CD
10_1101-2021_01_02_425006	141	13	different	different	JJ
10_1101-2021_01_02_425006	141	14	sizes	size	NNS
10_1101-2021_01_02_425006	141	15	,	,	,
10_1101-2021_01_02_425006	141	16	as	as	IN
10_1101-2021_01_02_425006	141	17	shown	show	VBN
10_1101-2021_01_02_425006	141	18	in	in	IN
10_1101-2021_01_02_425006	141	19	Fig	Fig	NNP
10_1101-2021_01_02_425006	141	20	.	.	.
10_1101-2021_01_02_425006	142	1	3A	3A	NNP
10_1101-2021_01_02_425006	142	2	and	and	CC
10_1101-2021_01_02_425006	142	3	fig	fig	NNP
10_1101-2021_01_02_425006	142	4	.	.	.
10_1101-2021_01_02_425006	143	1	S4A.	s4a.	NN
10_1101-2021_01_02_425006	144	1	These	these	DT
10_1101-2021_01_02_425006	144	2	results	result	NNS
10_1101-2021_01_02_425006	144	3	showed	show	VBD
10_1101-2021_01_02_425006	144	4	that	that	IN
10_1101-2021_01_02_425006	144	5	the	the	DT
10_1101-2021_01_02_425006	144	6	average	average	JJ
10_1101-2021_01_02_425006	144	7	precision	precision	NN
10_1101-2021_01_02_425006	144	8	and	and	CC
10_1101-2021_01_02_425006	144	9	234	234	CD
10_1101-2021_01_02_425006	144	10	recall	recall	NN
10_1101-2021_01_02_425006	144	11	were	be	VBD
10_1101-2021_01_02_425006	144	12	decreasing	decrease	VBG
10_1101-2021_01_02_425006	144	13	with	with	IN
10_1101-2021_01_02_425006	144	14	the	the	DT
10_1101-2021_01_02_425006	144	15	increasing	increase	VBG
10_1101-2021_01_02_425006	144	16	size	size	NN
10_1101-2021_01_02_425006	144	17	of	of	IN
10_1101-2021_01_02_425006	144	18	maximal	maximal	JJ
10_1101-2021_01_02_425006	144	19	ATU	ATU	NNP
10_1101-2021_01_02_425006	144	20	clusters	cluster	NNS
10_1101-2021_01_02_425006	144	21	(	(	-LRB-
10_1101-2021_01_02_425006	144	22	other	other	JJ
10_1101-2021_01_02_425006	144	23	than	than	IN
10_1101-2021_01_02_425006	144	24	several	several	JJ
10_1101-2021_01_02_425006	144	25	large	large	JJ
10_1101-2021_01_02_425006	144	26	size	size	NN
10_1101-2021_01_02_425006	144	27	235	235	CD
10_1101-2021_01_02_425006	144	28	ones	one	NNS
10_1101-2021_01_02_425006	144	29	due	due	JJ
10_1101-2021_01_02_425006	144	30	to	to	IN
10_1101-2021_01_02_425006	144	31	their	-PRON-	PRP$
10_1101-2021_01_02_425006	144	32	small	small	JJ
10_1101-2021_01_02_425006	144	33	number	number	NN
10_1101-2021_01_02_425006	144	34	of	of	IN
10_1101-2021_01_02_425006	144	35	counts	count	NNS
10_1101-2021_01_02_425006	144	36	)	)	-RRB-
10_1101-2021_01_02_425006	144	37	.	.	.
10_1101-2021_01_02_425006	145	1	The	the	DT
10_1101-2021_01_02_425006	145	2	results	result	NNS
10_1101-2021_01_02_425006	145	3	also	also	RB
10_1101-2021_01_02_425006	145	4	indicated	indicate	VBD
10_1101-2021_01_02_425006	145	5	that	that	IN
10_1101-2021_01_02_425006	145	6	the	the	DT
10_1101-2021_01_02_425006	145	7	evaluation	evaluation	NN
10_1101-2021_01_02_425006	145	8	results	result	NNS
10_1101-2021_01_02_425006	145	9	based	base	VBN
10_1101-2021_01_02_425006	145	10	on	on	IN
10_1101-2021_01_02_425006	145	11	236	236	CD
10_1101-2021_01_02_425006	145	12	relaxed	relaxed	JJ
10_1101-2021_01_02_425006	145	13	matching	matching	NN
10_1101-2021_01_02_425006	145	14	were	be	VBD
10_1101-2021_01_02_425006	145	15	significantly	significantly	RB
10_1101-2021_01_02_425006	145	16	higher	high	JJR
10_1101-2021_01_02_425006	145	17	than	than	IN
10_1101-2021_01_02_425006	145	18	those	those	DT
10_1101-2021_01_02_425006	145	19	based	base	VBN
10_1101-2021_01_02_425006	145	20	on	on	IN
10_1101-2021_01_02_425006	145	21	perfect	perfect	JJ
10_1101-2021_01_02_425006	145	22	matching	matching	NN
10_1101-2021_01_02_425006	145	23	across	across	IN
10_1101-2021_01_02_425006	145	24	different	different	JJ
10_1101-2021_01_02_425006	145	25	sizes	size	NNS
10_1101-2021_01_02_425006	145	26	.	.	.
10_1101-2021_01_02_425006	146	1	237	237	CD
10_1101-2021_01_02_425006	146	2	This	this	DT
10_1101-2021_01_02_425006	146	3	result	result	NN
10_1101-2021_01_02_425006	146	4	implied	imply	VBD
10_1101-2021_01_02_425006	146	5	that	that	IN
10_1101-2021_01_02_425006	146	6	the	the	DT
10_1101-2021_01_02_425006	146	7	incorrectly	incorrectly	RB
10_1101-2021_01_02_425006	146	8	predicted	predict	VBN
10_1101-2021_01_02_425006	146	9	ATUs	atu	NNS
10_1101-2021_01_02_425006	146	10	by	by	IN
10_1101-2021_01_02_425006	146	11	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	146	12	based	base	VBN
10_1101-2021_01_02_425006	146	13	on	on	IN
10_1101-2021_01_02_425006	146	14	perfect	perfect	JJ
10_1101-2021_01_02_425006	146	15	matching	matching	NN
10_1101-2021_01_02_425006	146	16	tended	tend	VBD
10_1101-2021_01_02_425006	146	17	to	to	IN
10_1101-2021_01_02_425006	146	18	238	238	CD
10_1101-2021_01_02_425006	146	19	have	have	VB
10_1101-2021_01_02_425006	146	20	strong	strong	JJ
10_1101-2021_01_02_425006	146	21	similarities	similarity	NNS
10_1101-2021_01_02_425006	146	22	with	with	IN
10_1101-2021_01_02_425006	146	23	the	the	DT
10_1101-2021_01_02_425006	146	24	ATUs	atu	NNS
10_1101-2021_01_02_425006	146	25	in	in	IN
10_1101-2021_01_02_425006	146	26	the	the	DT
10_1101-2021_01_02_425006	146	27	evaluation	evaluation	NN
10_1101-2021_01_02_425006	146	28	data	datum	NNS
10_1101-2021_01_02_425006	146	29	.	.	.
10_1101-2021_01_02_425006	147	1	In	in	IN
10_1101-2021_01_02_425006	147	2	addition	addition	NN
10_1101-2021_01_02_425006	147	3	,	,	,
10_1101-2021_01_02_425006	147	4	we	-PRON-	PRP
10_1101-2021_01_02_425006	147	5	also	also	RB
10_1101-2021_01_02_425006	147	6	found	find	VBD
10_1101-2021_01_02_425006	147	7	that	that	IN
10_1101-2021_01_02_425006	147	8	more	more	JJR
10_1101-2021_01_02_425006	147	9	than	than	IN
10_1101-2021_01_02_425006	147	10	a	a	DT
10_1101-2021_01_02_425006	147	11	239	239	CD
10_1101-2021_01_02_425006	147	12	quarter	quarter	NN
10_1101-2021_01_02_425006	147	13	of	of	IN
10_1101-2021_01_02_425006	147	14	the	the	DT
10_1101-2021_01_02_425006	147	15	incorrectly	incorrectly	RB
10_1101-2021_01_02_425006	147	16	predicted	predict	VBN
10_1101-2021_01_02_425006	147	17	ATUs	atu	NNS
10_1101-2021_01_02_425006	147	18	(	(	-LRB-
10_1101-2021_01_02_425006	147	19	25%/29	25%/29	CD
10_1101-2021_01_02_425006	147	20	%	%	NN
10_1101-2021_01_02_425006	147	21	for	for	IN
10_1101-2021_01_02_425006	147	22	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	147	23	/	/	SYM
10_1101-2021_01_02_425006	147	24	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	147	25	)	)	-RRB-
10_1101-2021_01_02_425006	147	26	by	by	IN
10_1101-2021_01_02_425006	147	27	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	147	28	240	240	CD
10_1101-2021_01_02_425006	147	29	.CC	.CC	:
10_1101-2021_01_02_425006	147	30	-	-	:
10_1101-2021_01_02_425006	147	31	BY	by	IN
10_1101-2021_01_02_425006	147	32	-	-	HYPH
10_1101-2021_01_02_425006	147	33	NC	NC	NNP
10_1101-2021_01_02_425006	147	34	-	-	HYPH
10_1101-2021_01_02_425006	147	35	ND	ND	NNP
10_1101-2021_01_02_425006	147	36	4.0	4.0	CD
10_1101-2021_01_02_425006	147	37	International	International	NNP
10_1101-2021_01_02_425006	147	38	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	147	39	under	under	IN
10_1101-2021_01_02_425006	147	40	a	a	DT
10_1101-2021_01_02_425006	147	41	(	(	-LRB-
10_1101-2021_01_02_425006	147	42	which	which	WDT
10_1101-2021_01_02_425006	147	43	was	be	VBD
10_1101-2021_01_02_425006	147	44	not	not	RB
10_1101-2021_01_02_425006	147	45	certified	certify	VBN
10_1101-2021_01_02_425006	147	46	by	by	IN
10_1101-2021_01_02_425006	147	47	peer	peer	NN
10_1101-2021_01_02_425006	147	48	review	review	NN
10_1101-2021_01_02_425006	147	49	)	)	-RRB-
10_1101-2021_01_02_425006	147	50	is	be	VBZ
10_1101-2021_01_02_425006	147	51	the	the	DT
10_1101-2021_01_02_425006	147	52	author	author	NN
10_1101-2021_01_02_425006	147	53	/	/	SYM
10_1101-2021_01_02_425006	147	54	funder	funder	NN
10_1101-2021_01_02_425006	147	55	,	,	,
10_1101-2021_01_02_425006	147	56	who	who	WP
10_1101-2021_01_02_425006	147	57	has	have	VBZ
10_1101-2021_01_02_425006	147	58	granted	grant	VBN
10_1101-2021_01_02_425006	147	59	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	147	60	a	a	DT
10_1101-2021_01_02_425006	147	61	license	license	NN
10_1101-2021_01_02_425006	147	62	to	to	TO
10_1101-2021_01_02_425006	147	63	display	display	VB
10_1101-2021_01_02_425006	147	64	the	the	DT
10_1101-2021_01_02_425006	147	65	preprint	preprint	NN
10_1101-2021_01_02_425006	147	66	in	in	IN
10_1101-2021_01_02_425006	147	67	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	147	68	.	.	.
10_1101-2021_01_02_425006	148	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	148	2	is	be	VBZ
10_1101-2021_01_02_425006	148	3	made	make	VBN
10_1101-2021_01_02_425006	148	4	The	the	DT
10_1101-2021_01_02_425006	148	5	copyright	copyright	NN
10_1101-2021_01_02_425006	148	6	holder	holder	NN
10_1101-2021_01_02_425006	148	7	for	for	IN
10_1101-2021_01_02_425006	148	8	this	this	DT
10_1101-2021_01_02_425006	148	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	148	10	version	version	NN
10_1101-2021_01_02_425006	148	11	posted	post	VBD
10_1101-2021_01_02_425006	148	12	January	January	NNP
10_1101-2021_01_02_425006	148	13	6	6	CD
10_1101-2021_01_02_425006	148	14	,	,	,
10_1101-2021_01_02_425006	148	15	2021	2021	CD
10_1101-2021_01_02_425006	148	16	.	.	.
10_1101-2021_01_02_425006	148	17	;	;	:
10_1101-2021_01_02_425006	148	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	148	19	:	:	:
10_1101-2021_01_02_425006	148	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	148	21	preprint	preprint	NN
10_1101-2021_01_02_425006	148	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	148	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	148	24	15	15	CD
10_1101-2021_01_02_425006	148	25	based	base	VBN
10_1101-2021_01_02_425006	148	26	on	on	IN
10_1101-2021_01_02_425006	148	27	perfect	perfect	JJ
10_1101-2021_01_02_425006	148	28	matching	matching	NN
10_1101-2021_01_02_425006	148	29	matched	match	VBN
10_1101-2021_01_02_425006	148	30	with	with	IN
10_1101-2021_01_02_425006	148	31	the	the	DT
10_1101-2021_01_02_425006	148	32	transcription	transcription	NN
10_1101-2021_01_02_425006	148	33	units	unit	NNS
10_1101-2021_01_02_425006	148	34	in	in	IN
10_1101-2021_01_02_425006	148	35	RegulonDB	RegulonDB	NNP
10_1101-2021_01_02_425006	148	36	(	(	-LRB-
10_1101-2021_01_02_425006	148	37	19	19	CD
10_1101-2021_01_02_425006	148	38	)	)	-RRB-
10_1101-2021_01_02_425006	148	39	.	.	.
10_1101-2021_01_02_425006	149	1	241	241	CD
10_1101-2021_01_02_425006	149	2	The	the	DT
10_1101-2021_01_02_425006	149	3	two	two	CD
10_1101-2021_01_02_425006	149	4	evaluation	evaluation	NN
10_1101-2021_01_02_425006	149	5	datasets	dataset	NNS
10_1101-2021_01_02_425006	149	6	(	(	-LRB-
10_1101-2021_01_02_425006	149	7	SMRT_M9Enrich	SMRT_M9Enrich	NNP
10_1101-2021_01_02_425006	149	8	and	and	CC
10_1101-2021_01_02_425006	149	9	SMRT_RiEnrich	smrt_rienrich	SYM
10_1101-2021_01_02_425006	149	10	)	)	-RRB-
10_1101-2021_01_02_425006	149	11	were	be	VBD
10_1101-2021_01_02_425006	149	12	both	both	DT
10_1101-2021_01_02_425006	149	13	from	from	IN
10_1101-2021_01_02_425006	149	14	SMRT-242	SMRT-242	NNP
10_1101-2021_01_02_425006	149	15	Cappable	cappable	JJ
10_1101-2021_01_02_425006	149	16	-	-	HYPH
10_1101-2021_01_02_425006	149	17	seq	seq	NN
10_1101-2021_01_02_425006	149	18	,	,	,
10_1101-2021_01_02_425006	149	19	while	while	IN
10_1101-2021_01_02_425006	149	20	one	one	CD
10_1101-2021_01_02_425006	149	21	of	of	IN
10_1101-2021_01_02_425006	149	22	the	the	DT
10_1101-2021_01_02_425006	149	23	processing	processing	NN
10_1101-2021_01_02_425006	149	24	steps	step	NNS
10_1101-2021_01_02_425006	149	25	of	of	IN
10_1101-2021_01_02_425006	149	26	the	the	DT
10_1101-2021_01_02_425006	149	27	technique	technique	NN
10_1101-2021_01_02_425006	149	28	filtered	filter	VBN
10_1101-2021_01_02_425006	149	29	RNA	RNA	NNP
10_1101-2021_01_02_425006	149	30	reads	read	VBZ
10_1101-2021_01_02_425006	149	31	smaller	small	JJR
10_1101-2021_01_02_425006	149	32	than	than	IN
10_1101-2021_01_02_425006	149	33	1,000	1,000	CD
10_1101-2021_01_02_425006	149	34	243	243	CD
10_1101-2021_01_02_425006	149	35	bp	bp	NNS
10_1101-2021_01_02_425006	149	36	(	(	-LRB-
10_1101-2021_01_02_425006	149	37	6	6	CD
10_1101-2021_01_02_425006	149	38	)	)	-RRB-
10_1101-2021_01_02_425006	149	39	,	,	,
10_1101-2021_01_02_425006	149	40	which	which	WDT
10_1101-2021_01_02_425006	149	41	indicated	indicate	VBD
10_1101-2021_01_02_425006	149	42	that	that	IN
10_1101-2021_01_02_425006	149	43	the	the	DT
10_1101-2021_01_02_425006	149	44	ATUs	atu	NNS
10_1101-2021_01_02_425006	149	45	in	in	IN
10_1101-2021_01_02_425006	149	46	these	these	DT
10_1101-2021_01_02_425006	149	47	two	two	CD
10_1101-2021_01_02_425006	149	48	evaluation	evaluation	NN
10_1101-2021_01_02_425006	149	49	datasets	dataset	NNS
10_1101-2021_01_02_425006	149	50	were	be	VBD
10_1101-2021_01_02_425006	149	51	not	not	RB
10_1101-2021_01_02_425006	149	52	comprehensive	comprehensive	JJ
10_1101-2021_01_02_425006	149	53	.	.	.
10_1101-2021_01_02_425006	150	1	To	to	IN
10_1101-2021_01_02_425006	150	2	244	244	CD
10_1101-2021_01_02_425006	150	3	address	address	NN
10_1101-2021_01_02_425006	150	4	this	this	DT
10_1101-2021_01_02_425006	150	5	issue	issue	NN
10_1101-2021_01_02_425006	150	6	,	,	,
10_1101-2021_01_02_425006	150	7	we	-PRON-	PRP
10_1101-2021_01_02_425006	150	8	enriched	enrich	VBD
10_1101-2021_01_02_425006	150	9	the	the	DT
10_1101-2021_01_02_425006	150	10	evaluation	evaluation	NN
10_1101-2021_01_02_425006	150	11	data	datum	NNS
10_1101-2021_01_02_425006	150	12	by	by	IN
10_1101-2021_01_02_425006	150	13	adding	add	VBG
10_1101-2021_01_02_425006	150	14	the	the	DT
10_1101-2021_01_02_425006	150	15	ATUs	atu	NNS
10_1101-2021_01_02_425006	150	16	defined	define	VBN
10_1101-2021_01_02_425006	150	17	by	by	IN
10_1101-2021_01_02_425006	150	18	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	150	19	-	-	HYPH
10_1101-2021_01_02_425006	150	20	seq	seq	NNP
10_1101-2021_01_02_425006	150	21	(	(	-LRB-
10_1101-2021_01_02_425006	150	22	7	7	CD
10_1101-2021_01_02_425006	150	23	)	)	-RRB-
10_1101-2021_01_02_425006	150	24	,	,	,
10_1101-2021_01_02_425006	150	25	as	as	IN
10_1101-2021_01_02_425006	150	26	245	245	CD
10_1101-2021_01_02_425006	150	27	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	150	28	-	-	HYPH
10_1101-2021_01_02_425006	150	29	seq	seq	NNP
10_1101-2021_01_02_425006	150	30	did	do	VBD
10_1101-2021_01_02_425006	150	31	not	not	RB
10_1101-2021_01_02_425006	150	32	introduce	introduce	VB
10_1101-2021_01_02_425006	150	33	any	any	DT
10_1101-2021_01_02_425006	150	34	filtering	filtering	NN
10_1101-2021_01_02_425006	150	35	based	base	VBN
10_1101-2021_01_02_425006	150	36	on	on	IN
10_1101-2021_01_02_425006	150	37	RNA	RNA	NNP
10_1101-2021_01_02_425006	150	38	size	size	NN
10_1101-2021_01_02_425006	150	39	.	.	.
10_1101-2021_01_02_425006	151	1	When	when	WRB
10_1101-2021_01_02_425006	151	2	we	-PRON-	PRP
10_1101-2021_01_02_425006	151	3	used	use	VBD
10_1101-2021_01_02_425006	151	4	the	the	DT
10_1101-2021_01_02_425006	151	5	new	new	JJ
10_1101-2021_01_02_425006	151	6	evaluation	evaluation	NN
10_1101-2021_01_02_425006	151	7	data	datum	NNS
10_1101-2021_01_02_425006	151	8	,	,	,
10_1101-2021_01_02_425006	151	9	the	the	DT
10_1101-2021_01_02_425006	151	10	246	246	CD
10_1101-2021_01_02_425006	151	11	ATUs	atu	NNS
10_1101-2021_01_02_425006	151	12	predicted	predict	VBN
10_1101-2021_01_02_425006	151	13	by	by	IN
10_1101-2021_01_02_425006	151	14	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	151	15	improved	improve	VBN
10_1101-2021_01_02_425006	151	16	by	by	IN
10_1101-2021_01_02_425006	151	17	15	15	CD
10_1101-2021_01_02_425006	151	18	%	%	NN
10_1101-2021_01_02_425006	151	19	(	(	-LRB-
10_1101-2021_01_02_425006	151	20	0.77	0.77	CD
10_1101-2021_01_02_425006	151	21	)	)	-RRB-
10_1101-2021_01_02_425006	151	22	and	and	CC
10_1101-2021_01_02_425006	151	23	19	19	CD
10_1101-2021_01_02_425006	151	24	%	%	NN
10_1101-2021_01_02_425006	151	25	(	(	-LRB-
10_1101-2021_01_02_425006	151	26	0.76	0.76	CD
10_1101-2021_01_02_425006	151	27	)	)	-RRB-
10_1101-2021_01_02_425006	151	28	in	in	IN
10_1101-2021_01_02_425006	151	29	terms	term	NNS
10_1101-2021_01_02_425006	151	30	of	of	IN
10_1101-2021_01_02_425006	151	31	the	the	DT
10_1101-2021_01_02_425006	151	32	average	average	JJ
10_1101-2021_01_02_425006	151	33	precision	precision	NN
10_1101-2021_01_02_425006	151	34	247	247	CD
10_1101-2021_01_02_425006	151	35	based	base	VBN
10_1101-2021_01_02_425006	151	36	on	on	IN
10_1101-2021_01_02_425006	151	37	perfect	perfect	JJ
10_1101-2021_01_02_425006	151	38	matching	matching	NN
10_1101-2021_01_02_425006	151	39	for	for	IN
10_1101-2021_01_02_425006	151	40	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	151	41	and	and	CC
10_1101-2021_01_02_425006	151	42	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	151	43	,	,	,
10_1101-2021_01_02_425006	151	44	respectively	respectively	RB
10_1101-2021_01_02_425006	151	45	,	,	,
10_1101-2021_01_02_425006	151	46	and	and	CC
10_1101-2021_01_02_425006	151	47	by	by	IN
10_1101-2021_01_02_425006	151	48	9	9	CD
10_1101-2021_01_02_425006	151	49	%	%	NN
10_1101-2021_01_02_425006	151	50	(	(	-LRB-
10_1101-2021_01_02_425006	151	51	0.84	0.84	CD
10_1101-2021_01_02_425006	151	52	)	)	-RRB-
10_1101-2021_01_02_425006	151	53	and	and	CC
10_1101-2021_01_02_425006	151	54	248	248	CD
10_1101-2021_01_02_425006	151	55	12	12	CD
10_1101-2021_01_02_425006	151	56	%	%	NN
10_1101-2021_01_02_425006	151	57	(	(	-LRB-
10_1101-2021_01_02_425006	151	58	0.83	0.83	CD
10_1101-2021_01_02_425006	151	59	)	)	-RRB-
10_1101-2021_01_02_425006	151	60	based	base	VBN
10_1101-2021_01_02_425006	151	61	on	on	IN
10_1101-2021_01_02_425006	151	62	relaxed	relaxed	JJ
10_1101-2021_01_02_425006	151	63	matching	matching	NN
10_1101-2021_01_02_425006	151	64	.	.	.
10_1101-2021_01_02_425006	152	1	The	the	DT
10_1101-2021_01_02_425006	152	2	statistics	statistic	NNS
10_1101-2021_01_02_425006	152	3	for	for	IN
10_1101-2021_01_02_425006	152	4	precision	precision	NN
10_1101-2021_01_02_425006	152	5	across	across	IN
10_1101-2021_01_02_425006	152	6	different	different	JJ
10_1101-2021_01_02_425006	152	7	sizes	size	NNS
10_1101-2021_01_02_425006	152	8	of	of	IN
10_1101-2021_01_02_425006	152	9	the	the	DT
10_1101-2021_01_02_425006	152	10	maximal	maximal	JJ
10_1101-2021_01_02_425006	152	11	249	249	CD
10_1101-2021_01_02_425006	152	12	ATU	ATU	NNP
10_1101-2021_01_02_425006	152	13	clusters	cluster	NNS
10_1101-2021_01_02_425006	152	14	are	be	VBP
10_1101-2021_01_02_425006	152	15	shown	show	VBN
10_1101-2021_01_02_425006	152	16	in	in	IN
10_1101-2021_01_02_425006	152	17	Fig	Fig	NNP
10_1101-2021_01_02_425006	152	18	.	.	.
10_1101-2021_01_02_425006	153	1	3B	3B	NNP
10_1101-2021_01_02_425006	153	2	and	and	CC
10_1101-2021_01_02_425006	153	3	fig	fig	VB
10_1101-2021_01_02_425006	153	4	.	.	.
10_1101-2021_01_02_425006	154	1	S4B	S4B	NNP
10_1101-2021_01_02_425006	154	2	,	,	,
10_1101-2021_01_02_425006	154	3	showing	show	VBG
10_1101-2021_01_02_425006	154	4	that	that	IN
10_1101-2021_01_02_425006	154	5	the	the	DT
10_1101-2021_01_02_425006	154	6	values	value	NNS
10_1101-2021_01_02_425006	154	7	of	of	IN
10_1101-2021_01_02_425006	154	8	precision	precision	NN
10_1101-2021_01_02_425006	154	9	based	base	VBN
10_1101-2021_01_02_425006	154	10	on	on	IN
10_1101-2021_01_02_425006	154	11	perfect	perfect	JJ
10_1101-2021_01_02_425006	154	12	250	250	CD
10_1101-2021_01_02_425006	154	13	matching	match	VBG
10_1101-2021_01_02_425006	154	14	were	be	VBD
10_1101-2021_01_02_425006	154	15	significantly	significantly	RB
10_1101-2021_01_02_425006	154	16	improved	improve	VBN
10_1101-2021_01_02_425006	154	17	across	across	IN
10_1101-2021_01_02_425006	154	18	different	different	JJ
10_1101-2021_01_02_425006	154	19	sizes	size	NNS
10_1101-2021_01_02_425006	154	20	of	of	IN
10_1101-2021_01_02_425006	154	21	maximal	maximal	JJ
10_1101-2021_01_02_425006	154	22	ATU	ATU	NNP
10_1101-2021_01_02_425006	154	23	clusters	cluster	NNS
10_1101-2021_01_02_425006	154	24	by	by	IN
10_1101-2021_01_02_425006	154	25	using	use	VBG
10_1101-2021_01_02_425006	154	26	the	the	DT
10_1101-2021_01_02_425006	154	27	251	251	CD
10_1101-2021_01_02_425006	154	28	evaluated	evaluate	VBN
10_1101-2021_01_02_425006	154	29	ATUs	atu	NNS
10_1101-2021_01_02_425006	154	30	from	from	IN
10_1101-2021_01_02_425006	154	31	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	154	32	-	-	HYPH
10_1101-2021_01_02_425006	154	33	Cappable	cappable	JJ
10_1101-2021_01_02_425006	154	34	-	-	HYPH
10_1101-2021_01_02_425006	154	35	seq	seq	NN
10_1101-2021_01_02_425006	154	36	and	and	CC
10_1101-2021_01_02_425006	154	37	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	154	38	-	-	HYPH
10_1101-2021_01_02_425006	154	39	seq	seq	NNP
10_1101-2021_01_02_425006	154	40	.	.	.
10_1101-2021_01_02_425006	155	1	This	this	DT
10_1101-2021_01_02_425006	155	2	result	result	NN
10_1101-2021_01_02_425006	155	3	suggested	suggest	VBD
10_1101-2021_01_02_425006	155	4	that	that	IN
10_1101-2021_01_02_425006	155	5	the	the	DT
10_1101-2021_01_02_425006	155	6	ATUs	atu	NNS
10_1101-2021_01_02_425006	155	7	we	-PRON-	PRP
10_1101-2021_01_02_425006	155	8	252	252	CD
10_1101-2021_01_02_425006	155	9	predicted	predict	VBD
10_1101-2021_01_02_425006	155	10	,	,	,
10_1101-2021_01_02_425006	155	11	which	which	WDT
10_1101-2021_01_02_425006	155	12	were	be	VBD
10_1101-2021_01_02_425006	155	13	not	not	RB
10_1101-2021_01_02_425006	155	14	in	in	IN
10_1101-2021_01_02_425006	155	15	SMRT_M9Enrich	SMRT_M9Enrich	NNP
10_1101-2021_01_02_425006	155	16	and	and	CC
10_1101-2021_01_02_425006	155	17	SMRT_RiEnrich	SMRT_RiEnrich	NNP
10_1101-2021_01_02_425006	155	18	,	,	,
10_1101-2021_01_02_425006	155	19	may	may	MD
10_1101-2021_01_02_425006	155	20	be	be	VB
10_1101-2021_01_02_425006	155	21	due	due	IN
10_1101-2021_01_02_425006	155	22	to	to	IN
10_1101-2021_01_02_425006	155	23	the	the	DT
10_1101-2021_01_02_425006	155	24	RNA	RNA	NNP
10_1101-2021_01_02_425006	155	25	length	length	NN
10_1101-2021_01_02_425006	155	26	253	253	CD
10_1101-2021_01_02_425006	155	27	selection	selection	NN
10_1101-2021_01_02_425006	155	28	of	of	IN
10_1101-2021_01_02_425006	155	29	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	155	30	-	-	HYPH
10_1101-2021_01_02_425006	155	31	Cappable	cappable	JJ
10_1101-2021_01_02_425006	155	32	-	-	HYPH
10_1101-2021_01_02_425006	155	33	seq	seq	NN
10_1101-2021_01_02_425006	155	34	.	.	.
10_1101-2021_01_02_425006	156	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	156	2	enriched	enrich	VBD
10_1101-2021_01_02_425006	156	3	the	the	DT
10_1101-2021_01_02_425006	156	4	evaluation	evaluation	NN
10_1101-2021_01_02_425006	156	5	data	datum	NNS
10_1101-2021_01_02_425006	156	6	by	by	IN
10_1101-2021_01_02_425006	156	7	adding	add	VBG
10_1101-2021_01_02_425006	156	8	the	the	DT
10_1101-2021_01_02_425006	156	9	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	156	10	in	in	IN
10_1101-2021_01_02_425006	156	11	RegulonDB	regulondb	NN
10_1101-2021_01_02_425006	156	12	254	254	CD
10_1101-2021_01_02_425006	156	13	(	(	-LRB-
10_1101-2021_01_02_425006	156	14	19	19	CD
10_1101-2021_01_02_425006	156	15	)	)	-RRB-
10_1101-2021_01_02_425006	156	16	and	and	CC
10_1101-2021_01_02_425006	156	17	also	also	RB
10_1101-2021_01_02_425006	156	18	found	find	VBD
10_1101-2021_01_02_425006	156	19	the	the	DT
10_1101-2021_01_02_425006	156	20	improvement	improvement	NN
10_1101-2021_01_02_425006	156	21	of	of	IN
10_1101-2021_01_02_425006	156	22	precision	precision	NN
10_1101-2021_01_02_425006	156	23	across	across	IN
10_1101-2021_01_02_425006	156	24	different	different	JJ
10_1101-2021_01_02_425006	156	25	sizes	size	NNS
10_1101-2021_01_02_425006	156	26	of	of	IN
10_1101-2021_01_02_425006	156	27	maximal	maximal	JJ
10_1101-2021_01_02_425006	156	28	ATU	ATU	NNP
10_1101-2021_01_02_425006	156	29	clusters	cluster	NNS
10_1101-2021_01_02_425006	156	30	for	for	IN
10_1101-2021_01_02_425006	156	31	255	255	CD
10_1101-2021_01_02_425006	156	32	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	156	33	and	and	CC
10_1101-2021_01_02_425006	156	34	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	156	35	(	(	-LRB-
10_1101-2021_01_02_425006	156	36	fig	fig	NN
10_1101-2021_01_02_425006	156	37	.	.	.
10_1101-2021_01_02_425006	157	1	S4C	S4C	NNP
10_1101-2021_01_02_425006	157	2	)	)	-RRB-
10_1101-2021_01_02_425006	157	3	.	.	.
10_1101-2021_01_02_425006	158	1	256	256	CD
10_1101-2021_01_02_425006	158	2	Furthermore	furthermore	RB
10_1101-2021_01_02_425006	158	3	,	,	,
10_1101-2021_01_02_425006	158	4	to	to	TO
10_1101-2021_01_02_425006	158	5	facilitate	facilitate	VB
10_1101-2021_01_02_425006	158	6	the	the	DT
10_1101-2021_01_02_425006	158	7	understanding	understanding	NN
10_1101-2021_01_02_425006	158	8	of	of	IN
10_1101-2021_01_02_425006	158	9	the	the	DT
10_1101-2021_01_02_425006	158	10	performance	performance	NN
10_1101-2021_01_02_425006	158	11	of	of	IN
10_1101-2021_01_02_425006	158	12	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	158	13	and	and	CC
10_1101-2021_01_02_425006	158	14	to	to	TO
10_1101-2021_01_02_425006	158	15	measure	measure	VB
10_1101-2021_01_02_425006	158	16	the	the	DT
10_1101-2021_01_02_425006	158	17	257	257	CD
10_1101-2021_01_02_425006	158	18	influence	influence	NN
10_1101-2021_01_02_425006	158	19	of	of	IN
10_1101-2021_01_02_425006	158	20	the	the	DT
10_1101-2021_01_02_425006	158	21	maximal	maximal	JJ
10_1101-2021_01_02_425006	158	22	ATU	ATU	NNP
10_1101-2021_01_02_425006	158	23	clusters	cluster	NNS
10_1101-2021_01_02_425006	158	24	from	from	IN
10_1101-2021_01_02_425006	158	25	rSeqTU	rseqtu	CD
10_1101-2021_01_02_425006	158	26	on	on	IN
10_1101-2021_01_02_425006	158	27	our	-PRON-	PRP$
10_1101-2021_01_02_425006	158	28	ATU	ATU	NNP
10_1101-2021_01_02_425006	158	29	prediction	prediction	NN
10_1101-2021_01_02_425006	158	30	method	method	NN
10_1101-2021_01_02_425006	158	31	,	,	,
10_1101-2021_01_02_425006	158	32	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	158	33	maximal	maximal	JJ
10_1101-2021_01_02_425006	158	34	258	258	CD
10_1101-2021_01_02_425006	158	35	ATU	ATU	NNP
10_1101-2021_01_02_425006	158	36	clusters	cluster	NNS
10_1101-2021_01_02_425006	158	37	collected	collect	VBN
10_1101-2021_01_02_425006	158	38	from	from	IN
10_1101-2021_01_02_425006	158	39	SMRT_M9Enrich	SMRT_M9Enrich	NNP
10_1101-2021_01_02_425006	158	40	and	and	CC
10_1101-2021_01_02_425006	158	41	SMRT_RiEnrich	SMRT_RiEnrich	NNP
10_1101-2021_01_02_425006	158	42	(	(	-LRB-
10_1101-2021_01_02_425006	158	43	for	for	IN
10_1101-2021_01_02_425006	158	44	more	more	JJR
10_1101-2021_01_02_425006	158	45	details	detail	NNS
10_1101-2021_01_02_425006	158	46	,	,	,
10_1101-2021_01_02_425006	158	47	see	see	VB
10_1101-2021_01_02_425006	158	48	method	method	NNP
10_1101-2021_01_02_425006	158	49	S8	S8	NNP
10_1101-2021_01_02_425006	158	50	)	)	-RRB-
10_1101-2021_01_02_425006	158	51	259	259	CD
10_1101-2021_01_02_425006	158	52	.CC	.CC	:
10_1101-2021_01_02_425006	158	53	-	-	HYPH
10_1101-2021_01_02_425006	158	54	BY	by	IN
10_1101-2021_01_02_425006	158	55	-	-	HYPH
10_1101-2021_01_02_425006	158	56	NC	NC	NNP
10_1101-2021_01_02_425006	158	57	-	-	HYPH
10_1101-2021_01_02_425006	158	58	ND	ND	NNP
10_1101-2021_01_02_425006	158	59	4.0	4.0	CD
10_1101-2021_01_02_425006	158	60	International	International	NNP
10_1101-2021_01_02_425006	158	61	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	158	62	under	under	IN
10_1101-2021_01_02_425006	158	63	a	a	DT
10_1101-2021_01_02_425006	158	64	(	(	-LRB-
10_1101-2021_01_02_425006	158	65	which	which	WDT
10_1101-2021_01_02_425006	158	66	was	be	VBD
10_1101-2021_01_02_425006	158	67	not	not	RB
10_1101-2021_01_02_425006	158	68	certified	certify	VBN
10_1101-2021_01_02_425006	158	69	by	by	IN
10_1101-2021_01_02_425006	158	70	peer	peer	NN
10_1101-2021_01_02_425006	158	71	review	review	NN
10_1101-2021_01_02_425006	158	72	)	)	-RRB-
10_1101-2021_01_02_425006	158	73	is	be	VBZ
10_1101-2021_01_02_425006	158	74	the	the	DT
10_1101-2021_01_02_425006	158	75	author	author	NN
10_1101-2021_01_02_425006	158	76	/	/	SYM
10_1101-2021_01_02_425006	158	77	funder	funder	NN
10_1101-2021_01_02_425006	158	78	,	,	,
10_1101-2021_01_02_425006	158	79	who	who	WP
10_1101-2021_01_02_425006	158	80	has	have	VBZ
10_1101-2021_01_02_425006	158	81	granted	grant	VBN
10_1101-2021_01_02_425006	158	82	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	158	83	a	a	DT
10_1101-2021_01_02_425006	158	84	license	license	NN
10_1101-2021_01_02_425006	158	85	to	to	TO
10_1101-2021_01_02_425006	158	86	display	display	VB
10_1101-2021_01_02_425006	158	87	the	the	DT
10_1101-2021_01_02_425006	158	88	preprint	preprint	NN
10_1101-2021_01_02_425006	158	89	in	in	IN
10_1101-2021_01_02_425006	158	90	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	158	91	.	.	.
10_1101-2021_01_02_425006	159	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	159	2	is	be	VBZ
10_1101-2021_01_02_425006	159	3	made	make	VBN
10_1101-2021_01_02_425006	159	4	The	the	DT
10_1101-2021_01_02_425006	159	5	copyright	copyright	NN
10_1101-2021_01_02_425006	159	6	holder	holder	NN
10_1101-2021_01_02_425006	159	7	for	for	IN
10_1101-2021_01_02_425006	159	8	this	this	DT
10_1101-2021_01_02_425006	159	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	159	10	version	version	NN
10_1101-2021_01_02_425006	159	11	posted	post	VBD
10_1101-2021_01_02_425006	159	12	January	January	NNP
10_1101-2021_01_02_425006	159	13	6	6	CD
10_1101-2021_01_02_425006	159	14	,	,	,
10_1101-2021_01_02_425006	159	15	2021	2021	CD
10_1101-2021_01_02_425006	159	16	.	.	.
10_1101-2021_01_02_425006	159	17	;	;	:
10_1101-2021_01_02_425006	159	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	159	19	:	:	:
10_1101-2021_01_02_425006	159	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	159	21	preprint	preprint	NN
10_1101-2021_01_02_425006	159	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	159	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	159	24	16	16	CD
10_1101-2021_01_02_425006	159	25	were	be	VBD
10_1101-2021_01_02_425006	159	26	applied	apply	VBN
10_1101-2021_01_02_425006	159	27	for	for	IN
10_1101-2021_01_02_425006	159	28	the	the	DT
10_1101-2021_01_02_425006	159	29	CQP	CQP	NNP
10_1101-2021_01_02_425006	159	30	in	in	IN
10_1101-2021_01_02_425006	159	31	two	two	CD
10_1101-2021_01_02_425006	159	32	conditions	condition	NNS
10_1101-2021_01_02_425006	159	33	(	(	-LRB-
10_1101-2021_01_02_425006	159	34	M9	M9	NNP
10_1101-2021_01_02_425006	159	35	minimal	minimal	JJ
10_1101-2021_01_02_425006	159	36	medium	medium	NN
10_1101-2021_01_02_425006	159	37	and	and	CC
10_1101-2021_01_02_425006	159	38	Rich	rich	JJ
10_1101-2021_01_02_425006	159	39	medium	medium	NN
10_1101-2021_01_02_425006	159	40	)	)	-RRB-
10_1101-2021_01_02_425006	159	41	.	.	.
10_1101-2021_01_02_425006	160	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	160	2	found	find	VBD
10_1101-2021_01_02_425006	160	3	that	that	IN
10_1101-2021_01_02_425006	160	4	260	260	CD
10_1101-2021_01_02_425006	160	5	precision	precision	NN
10_1101-2021_01_02_425006	160	6	and	and	CC
10_1101-2021_01_02_425006	160	7	recall	recall	NN
10_1101-2021_01_02_425006	160	8	increased	increase	VBD
10_1101-2021_01_02_425006	160	9	to	to	IN
10_1101-2021_01_02_425006	160	10	0.73	0.73	CD
10_1101-2021_01_02_425006	160	11	and	and	CC
10_1101-2021_01_02_425006	160	12	0.77	0.77	CD
10_1101-2021_01_02_425006	160	13	for	for	IN
10_1101-2021_01_02_425006	160	14	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	160	15	,	,	,
10_1101-2021_01_02_425006	160	16	respectively	respectively	RB
10_1101-2021_01_02_425006	160	17	,	,	,
10_1101-2021_01_02_425006	160	18	and	and	CC
10_1101-2021_01_02_425006	160	19	0.69	0.69	CD
10_1101-2021_01_02_425006	160	20	and	and	CC
10_1101-2021_01_02_425006	160	21	0.80	0.80	CD
10_1101-2021_01_02_425006	160	22	for	for	IN
10_1101-2021_01_02_425006	160	23	261	261	CD
10_1101-2021_01_02_425006	160	24	RiEnrich_Seq	rienrich_seq	NN
10_1101-2021_01_02_425006	160	25	based	base	VBN
10_1101-2021_01_02_425006	160	26	on	on	IN
10_1101-2021_01_02_425006	160	27	perfect	perfect	JJ
10_1101-2021_01_02_425006	160	28	matching	matching	NN
10_1101-2021_01_02_425006	160	29	(	(	-LRB-
10_1101-2021_01_02_425006	160	30	fig	fig	NN
10_1101-2021_01_02_425006	160	31	.	.	.
10_1101-2021_01_02_425006	161	1	S4D	S4D	NNP
10_1101-2021_01_02_425006	161	2	)	)	-RRB-
10_1101-2021_01_02_425006	161	3	.	.	.
10_1101-2021_01_02_425006	162	1	Additionally	additionally	RB
10_1101-2021_01_02_425006	162	2	,	,	,
10_1101-2021_01_02_425006	162	3	when	when	WRB
10_1101-2021_01_02_425006	162	4	using	use	VBG
10_1101-2021_01_02_425006	162	5	relaxed	relaxed	JJ
10_1101-2021_01_02_425006	162	6	matching	matching	NN
10_1101-2021_01_02_425006	162	7	,	,	,
10_1101-2021_01_02_425006	162	8	262	262	CD
10_1101-2021_01_02_425006	162	9	precision	precision	NN
10_1101-2021_01_02_425006	162	10	and	and	CC
10_1101-2021_01_02_425006	162	11	recall	recall	NN
10_1101-2021_01_02_425006	162	12	significantly	significantly	RB
10_1101-2021_01_02_425006	162	13	increased	increase	VBD
10_1101-2021_01_02_425006	162	14	to	to	IN
10_1101-2021_01_02_425006	162	15	0.82	0.82	CD
10_1101-2021_01_02_425006	162	16	and	and	CC
10_1101-2021_01_02_425006	162	17	0.84	0.84	CD
10_1101-2021_01_02_425006	162	18	for	for	IN
10_1101-2021_01_02_425006	162	19	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	162	20	,	,	,
10_1101-2021_01_02_425006	162	21	respectively	respectively	RB
10_1101-2021_01_02_425006	162	22	,	,	,
10_1101-2021_01_02_425006	162	23	and	and	CC
10_1101-2021_01_02_425006	162	24	0.79	0.79	CD
10_1101-2021_01_02_425006	162	25	263	263	CD
10_1101-2021_01_02_425006	162	26	and	and	CC
10_1101-2021_01_02_425006	162	27	0.86	0.86	CD
10_1101-2021_01_02_425006	162	28	for	for	IN
10_1101-2021_01_02_425006	162	29	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	162	30	(	(	-LRB-
10_1101-2021_01_02_425006	162	31	fig	fig	NN
10_1101-2021_01_02_425006	162	32	.	.	.
10_1101-2021_01_02_425006	163	1	S4D	S4D	NNP
10_1101-2021_01_02_425006	163	2	)	)	-RRB-
10_1101-2021_01_02_425006	163	3	.	.	.
10_1101-2021_01_02_425006	164	1	The	the	DT
10_1101-2021_01_02_425006	164	2	significantly	significantly	RB
10_1101-2021_01_02_425006	164	3	improved	improve	VBN
10_1101-2021_01_02_425006	164	4	results	result	NNS
10_1101-2021_01_02_425006	164	5	verified	verify	VBD
10_1101-2021_01_02_425006	164	6	the	the	DT
10_1101-2021_01_02_425006	164	7	ability	ability	NN
10_1101-2021_01_02_425006	164	8	of	of	IN
10_1101-2021_01_02_425006	164	9	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	164	10	264	264	CD
10_1101-2021_01_02_425006	164	11	to	to	TO
10_1101-2021_01_02_425006	164	12	accurately	accurately	RB
10_1101-2021_01_02_425006	164	13	predict	predict	VB
10_1101-2021_01_02_425006	164	14	ATU	ATU	NNP
10_1101-2021_01_02_425006	164	15	when	when	WRB
10_1101-2021_01_02_425006	164	16	giving	give	VBG
10_1101-2021_01_02_425006	164	17	more	more	RBR
10_1101-2021_01_02_425006	164	18	accurate	accurate	JJ
10_1101-2021_01_02_425006	164	19	maximal	maximal	JJ
10_1101-2021_01_02_425006	164	20	ATU	ATU	NNP
10_1101-2021_01_02_425006	164	21	clusters	cluster	NNS
10_1101-2021_01_02_425006	164	22	.	.	.
10_1101-2021_01_02_425006	165	1	In	in	IN
10_1101-2021_01_02_425006	165	2	addition	addition	NN
10_1101-2021_01_02_425006	165	3	,	,	,
10_1101-2021_01_02_425006	165	4	we	-PRON-	PRP
10_1101-2021_01_02_425006	165	5	found	find	VBD
10_1101-2021_01_02_425006	165	6	that	that	IN
10_1101-2021_01_02_425006	165	7	265	265	CD
10_1101-2021_01_02_425006	165	8	the	the	DT
10_1101-2021_01_02_425006	165	9	number	number	NN
10_1101-2021_01_02_425006	165	10	of	of	IN
10_1101-2021_01_02_425006	165	11	predicted	predict	VBN
10_1101-2021_01_02_425006	165	12	ATUs	atu	NNS
10_1101-2021_01_02_425006	165	13	and	and	CC
10_1101-2021_01_02_425006	165	14	the	the	DT
10_1101-2021_01_02_425006	165	15	evaluated	evaluate	VBN
10_1101-2021_01_02_425006	165	16	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	165	17	under	under	IN
10_1101-2021_01_02_425006	165	18	the	the	DT
10_1101-2021_01_02_425006	165	19	maximal	maximal	JJ
10_1101-2021_01_02_425006	165	20	ATU	ATU	NNP
10_1101-2021_01_02_425006	165	21	cluster	cluster	NN
10_1101-2021_01_02_425006	165	22	with	with	IN
10_1101-2021_01_02_425006	165	23	the	the	DT
10_1101-2021_01_02_425006	165	24	same	same	JJ
10_1101-2021_01_02_425006	165	25	266	266	CD
10_1101-2021_01_02_425006	165	26	size	size	NN
10_1101-2021_01_02_425006	165	27	were	be	VBD
10_1101-2021_01_02_425006	165	28	similar	similar	JJ
10_1101-2021_01_02_425006	165	29	except	except	IN
10_1101-2021_01_02_425006	165	30	for	for	IN
10_1101-2021_01_02_425006	165	31	the	the	DT
10_1101-2021_01_02_425006	165	32	maximal	maximal	JJ
10_1101-2021_01_02_425006	165	33	size	size	NN
10_1101-2021_01_02_425006	165	34	(	(	-LRB-
10_1101-2021_01_02_425006	165	35	Fig	fig	NN
10_1101-2021_01_02_425006	165	36	.	.	.
10_1101-2021_01_02_425006	166	1	3C	3c	NN
10_1101-2021_01_02_425006	166	2	)	)	-RRB-
10_1101-2021_01_02_425006	166	3	,	,	,
10_1101-2021_01_02_425006	166	4	and	and	CC
10_1101-2021_01_02_425006	166	5	they	-PRON-	PRP
10_1101-2021_01_02_425006	166	6	were	be	VBD
10_1101-2021_01_02_425006	166	7	far	far	RB
10_1101-2021_01_02_425006	166	8	less	less	JJR
10_1101-2021_01_02_425006	166	9	than	than	IN
10_1101-2021_01_02_425006	166	10	the	the	DT
10_1101-2021_01_02_425006	166	11	theoretical	theoretical	JJ
10_1101-2021_01_02_425006	166	12	267	267	CD
10_1101-2021_01_02_425006	166	13	number	number	NN
10_1101-2021_01_02_425006	166	14	,	,	,
10_1101-2021_01_02_425006	166	15	which	which	WDT
10_1101-2021_01_02_425006	166	16	indicated	indicate	VBD
10_1101-2021_01_02_425006	166	17	that	that	IN
10_1101-2021_01_02_425006	166	18	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	166	19	can	can	MD
10_1101-2021_01_02_425006	166	20	effectively	effectively	RB
10_1101-2021_01_02_425006	166	21	exclude	exclude	VB
10_1101-2021_01_02_425006	166	22	most	most	JJS
10_1101-2021_01_02_425006	166	23	of	of	IN
10_1101-2021_01_02_425006	166	24	the	the	DT
10_1101-2021_01_02_425006	166	25	incorrect	incorrect	JJ
10_1101-2021_01_02_425006	166	26	ATUs	atu	NNS
10_1101-2021_01_02_425006	166	27	.	.	.
10_1101-2021_01_02_425006	167	1	268	268	CD
10_1101-2021_01_02_425006	167	2	Please	please	UH
10_1101-2021_01_02_425006	167	3	place	place	VB
10_1101-2021_01_02_425006	167	4	Fig	Fig	NNP
10_1101-2021_01_02_425006	167	5	.	.	.
10_1101-2021_01_02_425006	168	1	3	3	CD
10_1101-2021_01_02_425006	168	2	here	here	RB
10_1101-2021_01_02_425006	168	3	.	.	.
10_1101-2021_01_02_425006	169	1	269	269	CD
10_1101-2021_01_02_425006	169	2	The	the	DT
10_1101-2021_01_02_425006	169	3	bias	bias	NN
10_1101-2021_01_02_425006	169	4	rate	rate	NN
10_1101-2021_01_02_425006	169	5	constraints	constraint	NNS
10_1101-2021_01_02_425006	169	6	efficiently	efficiently	RB
10_1101-2021_01_02_425006	169	7	improve	improve	VBP
10_1101-2021_01_02_425006	169	8	the	the	DT
10_1101-2021_01_02_425006	169	9	ability	ability	NN
10_1101-2021_01_02_425006	169	10	of	of	IN
10_1101-2021_01_02_425006	169	11	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	169	12	to	to	TO
10_1101-2021_01_02_425006	169	13	predict	predict	VB
10_1101-2021_01_02_425006	169	14	ATUs	atu	NNS
10_1101-2021_01_02_425006	169	15	270	270	CD
10_1101-2021_01_02_425006	169	16	We	-PRON-	PRP
10_1101-2021_01_02_425006	169	17	tried	try	VBD
10_1101-2021_01_02_425006	169	18	to	to	TO
10_1101-2021_01_02_425006	169	19	use	use	VB
10_1101-2021_01_02_425006	169	20	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	169	21	without	without	IN
10_1101-2021_01_02_425006	169	22	bias	bias	NN
10_1101-2021_01_02_425006	169	23	rate	rate	NN
10_1101-2021_01_02_425006	169	24	constraints	constraint	NNS
10_1101-2021_01_02_425006	169	25	to	to	TO
10_1101-2021_01_02_425006	169	26	predict	predict	VB
10_1101-2021_01_02_425006	169	27	the	the	DT
10_1101-2021_01_02_425006	169	28	ATUs	atu	NNS
10_1101-2021_01_02_425006	169	29	of	of	IN
10_1101-2021_01_02_425006	169	30	E.	E.	NNP
10_1101-2021_01_02_425006	169	31	coli	coli	NNS
10_1101-2021_01_02_425006	169	32	and	and	CC
10_1101-2021_01_02_425006	169	33	found	find	VBD
10_1101-2021_01_02_425006	169	34	that	that	IN
10_1101-2021_01_02_425006	169	35	its	-PRON-	PRP$
10_1101-2021_01_02_425006	169	36	271	271	CD
10_1101-2021_01_02_425006	169	37	performance	performance	NN
10_1101-2021_01_02_425006	169	38	significantly	significantly	RB
10_1101-2021_01_02_425006	169	39	decreased	decrease	VBD
10_1101-2021_01_02_425006	169	40	compared	compare	VBN
10_1101-2021_01_02_425006	169	41	with	with	IN
10_1101-2021_01_02_425006	169	42	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	169	43	(	(	-LRB-
10_1101-2021_01_02_425006	169	44	Fig	fig	NN
10_1101-2021_01_02_425006	169	45	.	.	.
10_1101-2021_01_02_425006	170	1	4	4	LS
10_1101-2021_01_02_425006	170	2	and	and	CC
10_1101-2021_01_02_425006	170	3	fig	fig	NN
10_1101-2021_01_02_425006	170	4	.	.	.
10_1101-2021_01_02_425006	171	1	S5	S5	NNP
10_1101-2021_01_02_425006	171	2	)	)	-RRB-
10_1101-2021_01_02_425006	171	3	.	.	.
10_1101-2021_01_02_425006	172	1	Specifically	specifically	RB
10_1101-2021_01_02_425006	172	2	,	,	,
10_1101-2021_01_02_425006	172	3	the	the	DT
10_1101-2021_01_02_425006	172	4	F-272	F-272	NNP
10_1101-2021_01_02_425006	172	5	score	score	NN
10_1101-2021_01_02_425006	172	6	of	of	IN
10_1101-2021_01_02_425006	172	7	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	172	8	without	without	IN
10_1101-2021_01_02_425006	172	9	bias	bias	NN
10_1101-2021_01_02_425006	172	10	rate	rate	NN
10_1101-2021_01_02_425006	172	11	constraints	constraint	NNS
10_1101-2021_01_02_425006	172	12	was	be	VBD
10_1101-2021_01_02_425006	172	13	0.69/0.68	0.69/0.68	RB
10_1101-2021_01_02_425006	172	14	based	base	VBN
10_1101-2021_01_02_425006	172	15	on	on	IN
10_1101-2021_01_02_425006	172	16	perfect	perfect	JJ
10_1101-2021_01_02_425006	172	17	matching	matching	NN
10_1101-2021_01_02_425006	172	18	for	for	IN
10_1101-2021_01_02_425006	172	19	273	273	CD
10_1101-2021_01_02_425006	172	20	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	172	21	/	/	SYM
10_1101-2021_01_02_425006	172	22	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	172	23	,	,	,
10_1101-2021_01_02_425006	172	24	compared	compare	VBN
10_1101-2021_01_02_425006	172	25	with	with	IN
10_1101-2021_01_02_425006	172	26	0.75/0.74	0.75/0.74	NNP
10_1101-2021_01_02_425006	172	27	for	for	IN
10_1101-2021_01_02_425006	172	28	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	172	29	.	.	.
10_1101-2021_01_02_425006	173	1	When	when	WRB
10_1101-2021_01_02_425006	173	2	using	use	VBG
10_1101-2021_01_02_425006	173	3	relaxed	relaxed	JJ
10_1101-2021_01_02_425006	173	4	matching	matching	NN
10_1101-2021_01_02_425006	173	5	,	,	,
10_1101-2021_01_02_425006	173	6	the	the	DT
10_1101-2021_01_02_425006	173	7	274	274	CD
10_1101-2021_01_02_425006	173	8	F	F	NNP
10_1101-2021_01_02_425006	173	9	-	-	HYPH
10_1101-2021_01_02_425006	173	10	score	score	NN
10_1101-2021_01_02_425006	173	11	of	of	IN
10_1101-2021_01_02_425006	173	12	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	173	13	without	without	IN
10_1101-2021_01_02_425006	173	14	bias	bias	NN
10_1101-2021_01_02_425006	173	15	rate	rate	NN
10_1101-2021_01_02_425006	173	16	constraints	constraint	NNS
10_1101-2021_01_02_425006	173	17	was	be	VBD
10_1101-2021_01_02_425006	173	18	0.79/0.78	0.79/0.78	NN
10_1101-2021_01_02_425006	173	19	for	for	IN
10_1101-2021_01_02_425006	173	20	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	173	21	/	/	SYM
10_1101-2021_01_02_425006	173	22	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	173	23	,	,	,
10_1101-2021_01_02_425006	173	24	275	275	CD
10_1101-2021_01_02_425006	173	25	compared	compare	VBN
10_1101-2021_01_02_425006	173	26	with	with	IN
10_1101-2021_01_02_425006	173	27	0.83/0.83	0.83/0.83	NNP
10_1101-2021_01_02_425006	173	28	for	for	IN
10_1101-2021_01_02_425006	173	29	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	173	30	.	.	.
10_1101-2021_01_02_425006	174	1	This	this	DT
10_1101-2021_01_02_425006	174	2	result	result	NN
10_1101-2021_01_02_425006	174	3	suggested	suggest	VBD
10_1101-2021_01_02_425006	174	4	that	that	IN
10_1101-2021_01_02_425006	174	5	the	the	DT
10_1101-2021_01_02_425006	174	6	bias	bias	NN
10_1101-2021_01_02_425006	174	7	rate	rate	NN
10_1101-2021_01_02_425006	174	8	constraints	constraint	NNS
10_1101-2021_01_02_425006	174	9	of	of	IN
10_1101-2021_01_02_425006	174	10	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	174	11	276	276	CD
10_1101-2021_01_02_425006	174	12	could	could	MD
10_1101-2021_01_02_425006	174	13	capture	capture	VB
10_1101-2021_01_02_425006	174	14	useful	useful	JJ
10_1101-2021_01_02_425006	174	15	information	information	NN
10_1101-2021_01_02_425006	174	16	about	about	IN
10_1101-2021_01_02_425006	174	17	the	the	DT
10_1101-2021_01_02_425006	174	18	non	non	JJ
10_1101-2021_01_02_425006	174	19	-	-	JJ
10_1101-2021_01_02_425006	174	20	uniform	uniform	JJ
10_1101-2021_01_02_425006	174	21	distribution	distribution	NN
10_1101-2021_01_02_425006	174	22	of	of	IN
10_1101-2021_01_02_425006	174	23	the	the	DT
10_1101-2021_01_02_425006	174	24	RNA	RNA	NNP
10_1101-2021_01_02_425006	174	25	-	-	HYPH
10_1101-2021_01_02_425006	174	26	Seq	Seq	NNP
10_1101-2021_01_02_425006	174	27	reads	read	VBZ
10_1101-2021_01_02_425006	174	28	along	along	IN
10_1101-2021_01_02_425006	174	29	the	the	DT
10_1101-2021_01_02_425006	174	30	277	277	CD
10_1101-2021_01_02_425006	174	31	.CC	.cc	SYM
10_1101-2021_01_02_425006	174	32	-	-	HYPH
10_1101-2021_01_02_425006	174	33	BY	by	IN
10_1101-2021_01_02_425006	174	34	-	-	HYPH
10_1101-2021_01_02_425006	174	35	NC	NC	NNP
10_1101-2021_01_02_425006	174	36	-	-	HYPH
10_1101-2021_01_02_425006	174	37	ND	ND	NNP
10_1101-2021_01_02_425006	174	38	4.0	4.0	CD
10_1101-2021_01_02_425006	174	39	International	International	NNP
10_1101-2021_01_02_425006	174	40	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	174	41	under	under	IN
10_1101-2021_01_02_425006	174	42	a	a	DT
10_1101-2021_01_02_425006	174	43	(	(	-LRB-
10_1101-2021_01_02_425006	174	44	which	which	WDT
10_1101-2021_01_02_425006	174	45	was	be	VBD
10_1101-2021_01_02_425006	174	46	not	not	RB
10_1101-2021_01_02_425006	174	47	certified	certify	VBN
10_1101-2021_01_02_425006	174	48	by	by	IN
10_1101-2021_01_02_425006	174	49	peer	peer	NN
10_1101-2021_01_02_425006	174	50	review	review	NN
10_1101-2021_01_02_425006	174	51	)	)	-RRB-
10_1101-2021_01_02_425006	174	52	is	be	VBZ
10_1101-2021_01_02_425006	174	53	the	the	DT
10_1101-2021_01_02_425006	174	54	author	author	NN
10_1101-2021_01_02_425006	174	55	/	/	SYM
10_1101-2021_01_02_425006	174	56	funder	funder	NN
10_1101-2021_01_02_425006	174	57	,	,	,
10_1101-2021_01_02_425006	174	58	who	who	WP
10_1101-2021_01_02_425006	174	59	has	have	VBZ
10_1101-2021_01_02_425006	174	60	granted	grant	VBN
10_1101-2021_01_02_425006	174	61	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	174	62	a	a	DT
10_1101-2021_01_02_425006	174	63	license	license	NN
10_1101-2021_01_02_425006	174	64	to	to	TO
10_1101-2021_01_02_425006	174	65	display	display	VB
10_1101-2021_01_02_425006	174	66	the	the	DT
10_1101-2021_01_02_425006	174	67	preprint	preprint	NN
10_1101-2021_01_02_425006	174	68	in	in	IN
10_1101-2021_01_02_425006	174	69	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	174	70	.	.	.
10_1101-2021_01_02_425006	175	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	175	2	is	be	VBZ
10_1101-2021_01_02_425006	175	3	made	make	VBN
10_1101-2021_01_02_425006	175	4	The	the	DT
10_1101-2021_01_02_425006	175	5	copyright	copyright	NN
10_1101-2021_01_02_425006	175	6	holder	holder	NN
10_1101-2021_01_02_425006	175	7	for	for	IN
10_1101-2021_01_02_425006	175	8	this	this	DT
10_1101-2021_01_02_425006	175	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	175	10	version	version	NN
10_1101-2021_01_02_425006	175	11	posted	post	VBD
10_1101-2021_01_02_425006	175	12	January	January	NNP
10_1101-2021_01_02_425006	175	13	6	6	CD
10_1101-2021_01_02_425006	175	14	,	,	,
10_1101-2021_01_02_425006	175	15	2021	2021	CD
10_1101-2021_01_02_425006	175	16	.	.	.
10_1101-2021_01_02_425006	175	17	;	;	:
10_1101-2021_01_02_425006	175	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	175	19	:	:	:
10_1101-2021_01_02_425006	175	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	175	21	preprint	preprint	NN
10_1101-2021_01_02_425006	175	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	175	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	175	24	17	17	CD
10_1101-2021_01_02_425006	175	25	mRNA	mrna	NN
10_1101-2021_01_02_425006	175	26	transcripts	transcript	NNS
10_1101-2021_01_02_425006	175	27	(	(	-LRB-
10_1101-2021_01_02_425006	175	28	32	32	CD
10_1101-2021_01_02_425006	175	29	-	-	SYM
10_1101-2021_01_02_425006	175	30	35	35	CD
10_1101-2021_01_02_425006	175	31	)	)	-RRB-
10_1101-2021_01_02_425006	175	32	and	and	CC
10_1101-2021_01_02_425006	175	33	then	then	RB
10_1101-2021_01_02_425006	175	34	efficiently	efficiently	RB
10_1101-2021_01_02_425006	175	35	improve	improve	VBP
10_1101-2021_01_02_425006	175	36	the	the	DT
10_1101-2021_01_02_425006	175	37	ability	ability	NN
10_1101-2021_01_02_425006	175	38	of	of	IN
10_1101-2021_01_02_425006	175	39	the	the	DT
10_1101-2021_01_02_425006	175	40	model	model	NN
10_1101-2021_01_02_425006	175	41	to	to	TO
10_1101-2021_01_02_425006	175	42	predict	predict	VB
10_1101-2021_01_02_425006	175	43	complex	complex	JJ
10_1101-2021_01_02_425006	175	44	278	278	CD
10_1101-2021_01_02_425006	175	45	ATUs	atu	NNS
10_1101-2021_01_02_425006	175	46	.	.	.
10_1101-2021_01_02_425006	176	1	279	279	CD
10_1101-2021_01_02_425006	176	2	Please	please	UH
10_1101-2021_01_02_425006	176	3	place	place	VB
10_1101-2021_01_02_425006	176	4	Fig	Fig	NNP
10_1101-2021_01_02_425006	176	5	.	.	.
10_1101-2021_01_02_425006	177	1	4	4	CD
10_1101-2021_01_02_425006	177	2	here	here	RB
10_1101-2021_01_02_425006	177	3	.	.	.
10_1101-2021_01_02_425006	178	1	280	280	CD
10_1101-2021_01_02_425006	178	2	ATUs	atu	NNS
10_1101-2021_01_02_425006	178	3	predicted	predict	VBN
10_1101-2021_01_02_425006	178	4	by	by	IN
10_1101-2021_01_02_425006	178	5	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	178	6	display	display	VB
10_1101-2021_01_02_425006	178	7	a	a	DT
10_1101-2021_01_02_425006	178	8	dynamic	dynamic	JJ
10_1101-2021_01_02_425006	178	9	composition	composition	NN
10_1101-2021_01_02_425006	178	10	and	and	CC
10_1101-2021_01_02_425006	178	11	overlapping	overlap	VBG
10_1101-2021_01_02_425006	178	12	nature	nature	NN
10_1101-2021_01_02_425006	178	13	281	281	CD
10_1101-2021_01_02_425006	178	14	A	a	DT
10_1101-2021_01_02_425006	178	15	total	total	NN
10_1101-2021_01_02_425006	178	16	of	of	IN
10_1101-2021_01_02_425006	178	17	2,973	2,973	CD
10_1101-2021_01_02_425006	178	18	distinct	distinct	JJ
10_1101-2021_01_02_425006	178	19	ATUs	atu	NNS
10_1101-2021_01_02_425006	178	20	were	be	VBD
10_1101-2021_01_02_425006	178	21	identified	identify	VBN
10_1101-2021_01_02_425006	178	22	in	in	IN
10_1101-2021_01_02_425006	178	23	M9	M9	NNP
10_1101-2021_01_02_425006	178	24	minimal	minimal	JJ
10_1101-2021_01_02_425006	178	25	medium	medium	NN
10_1101-2021_01_02_425006	178	26	,	,	,
10_1101-2021_01_02_425006	178	27	and	and	CC
10_1101-2021_01_02_425006	178	28	2,767	2,767	CD
10_1101-2021_01_02_425006	178	29	were	be	VBD
10_1101-2021_01_02_425006	178	30	identified	identify	VBN
10_1101-2021_01_02_425006	178	31	in	in	IN
10_1101-2021_01_02_425006	178	32	Rich	Rich	NNP
10_1101-2021_01_02_425006	178	33	282	282	CD
10_1101-2021_01_02_425006	178	34	medium	medium	NN
10_1101-2021_01_02_425006	178	35	.	.	.
10_1101-2021_01_02_425006	179	1	Among	among	IN
10_1101-2021_01_02_425006	179	2	them	-PRON-	PRP
10_1101-2021_01_02_425006	179	3	,	,	,
10_1101-2021_01_02_425006	179	4	there	there	EX
10_1101-2021_01_02_425006	179	5	were	be	VBD
10_1101-2021_01_02_425006	179	6	1,423/1,550	1,423/1,550	CD
10_1101-2021_01_02_425006	179	7	distinct	distinct	JJ
10_1101-2021_01_02_425006	179	8	ATUs	atu	NNS
10_1101-2021_01_02_425006	179	9	on	on	IN
10_1101-2021_01_02_425006	179	10	the	the	DT
10_1101-2021_01_02_425006	179	11	forward	forward	JJ
10_1101-2021_01_02_425006	179	12	strand	strand	NN
10_1101-2021_01_02_425006	179	13	and	and	CC
10_1101-2021_01_02_425006	179	14	1,323/1,444	1,323/1,444	NNP
10_1101-2021_01_02_425006	179	15	on	on	IN
10_1101-2021_01_02_425006	179	16	283	283	CD
10_1101-2021_01_02_425006	179	17	the	the	DT
10_1101-2021_01_02_425006	179	18	reverse	reverse	JJ
10_1101-2021_01_02_425006	179	19	strand	strand	NN
10_1101-2021_01_02_425006	179	20	for	for	IN
10_1101-2021_01_02_425006	179	21	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	179	22	/	/	SYM
10_1101-2021_01_02_425006	179	23	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	179	24	.	.	.
10_1101-2021_01_02_425006	180	1	Each	each	DT
10_1101-2021_01_02_425006	180	2	of	of	IN
10_1101-2021_01_02_425006	180	3	the	the	DT
10_1101-2021_01_02_425006	180	4	predicted	predict	VBN
10_1101-2021_01_02_425006	180	5	ATUs	atu	NNS
10_1101-2021_01_02_425006	180	6	was	be	VBD
10_1101-2021_01_02_425006	180	7	comprised	comprise	VBN
10_1101-2021_01_02_425006	180	8	of	of	IN
10_1101-2021_01_02_425006	180	9	an	an	DT
10_1101-2021_01_02_425006	180	10	284	284	CD
10_1101-2021_01_02_425006	180	11	average	average	NN
10_1101-2021_01_02_425006	180	12	of	of	IN
10_1101-2021_01_02_425006	180	13	2.59	2.59	CD
10_1101-2021_01_02_425006	180	14	genes	gene	NNS
10_1101-2021_01_02_425006	180	15	,	,	,
10_1101-2021_01_02_425006	180	16	with	with	IN
10_1101-2021_01_02_425006	180	17	the	the	DT
10_1101-2021_01_02_425006	180	18	largest	large	JJS
10_1101-2021_01_02_425006	180	19	ATU	atu	NN
10_1101-2021_01_02_425006	180	20	containing	contain	VBG
10_1101-2021_01_02_425006	180	21	28	28	CD
10_1101-2021_01_02_425006	180	22	genes	gene	NNS
10_1101-2021_01_02_425006	180	23	across	across	IN
10_1101-2021_01_02_425006	180	24	the	the	DT
10_1101-2021_01_02_425006	180	25	two	two	CD
10_1101-2021_01_02_425006	180	26	conditions	condition	NNS
10_1101-2021_01_02_425006	180	27	.	.	.
10_1101-2021_01_02_425006	181	1	The	the	DT
10_1101-2021_01_02_425006	181	2	285	285	CD
10_1101-2021_01_02_425006	181	3	distribution	distribution	NN
10_1101-2021_01_02_425006	181	4	of	of	IN
10_1101-2021_01_02_425006	181	5	the	the	DT
10_1101-2021_01_02_425006	181	6	size	size	NN
10_1101-2021_01_02_425006	181	7	of	of	IN
10_1101-2021_01_02_425006	181	8	the	the	DT
10_1101-2021_01_02_425006	181	9	predicted	predict	VBN
10_1101-2021_01_02_425006	181	10	ATUs	atu	NNS
10_1101-2021_01_02_425006	181	11	is	be	VBZ
10_1101-2021_01_02_425006	181	12	shown	show	VBN
10_1101-2021_01_02_425006	181	13	in	in	IN
10_1101-2021_01_02_425006	181	14	Fig	Fig	NNP
10_1101-2021_01_02_425006	181	15	.	.	.
10_1101-2021_01_02_425006	182	1	5A	5a	RB
10_1101-2021_01_02_425006	182	2	,	,	,
10_1101-2021_01_02_425006	182	3	from	from	IN
10_1101-2021_01_02_425006	182	4	which	which	WDT
10_1101-2021_01_02_425006	182	5	we	-PRON-	PRP
10_1101-2021_01_02_425006	182	6	can	can	MD
10_1101-2021_01_02_425006	182	7	see	see	VB
10_1101-2021_01_02_425006	182	8	that	that	IN
10_1101-2021_01_02_425006	182	9	the	the	DT
10_1101-2021_01_02_425006	182	10	286	286	CD
10_1101-2021_01_02_425006	182	11	majority	majority	NN
10_1101-2021_01_02_425006	182	12	of	of	IN
10_1101-2021_01_02_425006	182	13	ATUs	atu	NNS
10_1101-2021_01_02_425006	182	14	(	(	-LRB-
10_1101-2021_01_02_425006	182	15	more	more	JJR
10_1101-2021_01_02_425006	182	16	than	than	IN
10_1101-2021_01_02_425006	182	17	87	87	CD
10_1101-2021_01_02_425006	182	18	%	%	NN
10_1101-2021_01_02_425006	182	19	)	)	-RRB-
10_1101-2021_01_02_425006	182	20	contained	contain	VBD
10_1101-2021_01_02_425006	182	21	fewer	few	JJR
10_1101-2021_01_02_425006	182	22	than	than	IN
10_1101-2021_01_02_425006	182	23	five	five	CD
10_1101-2021_01_02_425006	182	24	genes	gene	NNS
10_1101-2021_01_02_425006	182	25	in	in	IN
10_1101-2021_01_02_425006	182	26	M9	M9	NNP
10_1101-2021_01_02_425006	182	27	minimal	minimal	JJ
10_1101-2021_01_02_425006	182	28	medium	medium	NN
10_1101-2021_01_02_425006	182	29	and	and	CC
10_1101-2021_01_02_425006	182	30	Rich	Rich	NNP
10_1101-2021_01_02_425006	182	31	287	287	CD
10_1101-2021_01_02_425006	182	32	medium	medium	NN
10_1101-2021_01_02_425006	182	33	.	.	.
10_1101-2021_01_02_425006	183	1	Approximately	approximately	RB
10_1101-2021_01_02_425006	183	2	41	41	CD
10_1101-2021_01_02_425006	183	3	%	%	NN
10_1101-2021_01_02_425006	183	4	of	of	IN
10_1101-2021_01_02_425006	183	5	the	the	DT
10_1101-2021_01_02_425006	183	6	genes	gene	NNS
10_1101-2021_01_02_425006	183	7	in	in	IN
10_1101-2021_01_02_425006	183	8	E.	E.	NNP
10_1101-2021_01_02_425006	183	9	coli	coli	NNS
10_1101-2021_01_02_425006	183	10	were	be	VBD
10_1101-2021_01_02_425006	183	11	contained	contain	VBN
10_1101-2021_01_02_425006	183	12	in	in	IN
10_1101-2021_01_02_425006	183	13	more	more	JJR
10_1101-2021_01_02_425006	183	14	than	than	IN
10_1101-2021_01_02_425006	183	15	one	one	CD
10_1101-2021_01_02_425006	183	16	ATU	ATU	NNP
10_1101-2021_01_02_425006	183	17	for	for	IN
10_1101-2021_01_02_425006	183	18	288	288	CD
10_1101-2021_01_02_425006	183	19	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	183	20	,	,	,
10_1101-2021_01_02_425006	183	21	compared	compare	VBN
10_1101-2021_01_02_425006	183	22	to	to	IN
10_1101-2021_01_02_425006	183	23	43	43	CD
10_1101-2021_01_02_425006	183	24	%	%	NN
10_1101-2021_01_02_425006	183	25	genes	gene	NNS
10_1101-2021_01_02_425006	183	26	for	for	IN
10_1101-2021_01_02_425006	183	27	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	183	28	,	,	,
10_1101-2021_01_02_425006	183	29	suggesting	suggest	VBG
10_1101-2021_01_02_425006	183	30	that	that	IN
10_1101-2021_01_02_425006	183	31	the	the	DT
10_1101-2021_01_02_425006	183	32	ATUs	atu	NNS
10_1101-2021_01_02_425006	183	33	in	in	IN
10_1101-2021_01_02_425006	183	34	a	a	DT
10_1101-2021_01_02_425006	183	35	maximal	maximal	JJ
10_1101-2021_01_02_425006	183	36	ATU	ATU	NNP
10_1101-2021_01_02_425006	183	37	289	289	CD
10_1101-2021_01_02_425006	183	38	cluster	cluster	NN
10_1101-2021_01_02_425006	183	39	generally	generally	RB
10_1101-2021_01_02_425006	183	40	overlapped	overlap	VBD
10_1101-2021_01_02_425006	183	41	with	with	IN
10_1101-2021_01_02_425006	183	42	each	each	DT
10_1101-2021_01_02_425006	183	43	other	other	JJ
10_1101-2021_01_02_425006	183	44	(	(	-LRB-
10_1101-2021_01_02_425006	183	45	Fig	fig	NN
10_1101-2021_01_02_425006	183	46	.	.	.
10_1101-2021_01_02_425006	184	1	5B	5b	JJ
10_1101-2021_01_02_425006	184	2	)	)	-RRB-
10_1101-2021_01_02_425006	184	3	.	.	.
10_1101-2021_01_02_425006	185	1	In	in	IN
10_1101-2021_01_02_425006	185	2	addition	addition	NN
10_1101-2021_01_02_425006	185	3	,	,	,
10_1101-2021_01_02_425006	185	4	there	there	EX
10_1101-2021_01_02_425006	185	5	were	be	VBD
10_1101-2021_01_02_425006	185	6	1,576	1,576	CD
10_1101-2021_01_02_425006	185	7	ATU	ATU	NNP
10_1101-2021_01_02_425006	185	8	maximal	maximal	JJ
10_1101-2021_01_02_425006	185	9	290	290	CD
10_1101-2021_01_02_425006	185	10	clusters	cluster	NNS
10_1101-2021_01_02_425006	185	11	for	for	IN
10_1101-2021_01_02_425006	185	12	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	185	13	and	and	CC
10_1101-2021_01_02_425006	185	14	1,512	1,512	CD
10_1101-2021_01_02_425006	185	15	ATU	ATU	NNP
10_1101-2021_01_02_425006	185	16	maximal	maximal	JJ
10_1101-2021_01_02_425006	185	17	clusters	cluster	NNS
10_1101-2021_01_02_425006	185	18	for	for	IN
10_1101-2021_01_02_425006	185	19	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	185	20	.	.	.
10_1101-2021_01_02_425006	186	1	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	186	2	identified	identify	VBD
10_1101-2021_01_02_425006	186	3	a	a	DT
10_1101-2021_01_02_425006	186	4	291	291	CD
10_1101-2021_01_02_425006	186	5	total	total	NN
10_1101-2021_01_02_425006	186	6	of	of	IN
10_1101-2021_01_02_425006	186	7	1,977	1,977	CD
10_1101-2021_01_02_425006	186	8	identical	identical	JJ
10_1101-2021_01_02_425006	186	9	ATUs	atu	NNS
10_1101-2021_01_02_425006	186	10	under	under	IN
10_1101-2021_01_02_425006	186	11	the	the	DT
10_1101-2021_01_02_425006	186	12	two	two	CD
10_1101-2021_01_02_425006	186	13	conditions	condition	NNS
10_1101-2021_01_02_425006	186	14	,	,	,
10_1101-2021_01_02_425006	186	15	whereas	whereas	IN
10_1101-2021_01_02_425006	186	16	there	there	EX
10_1101-2021_01_02_425006	186	17	were	be	VBD
10_1101-2021_01_02_425006	186	18	1,786	1,786	CD
10_1101-2021_01_02_425006	186	19	distinct	distinct	JJ
10_1101-2021_01_02_425006	186	20	ATUs	atu	NNS
10_1101-2021_01_02_425006	186	21	.	.	.
10_1101-2021_01_02_425006	187	1	Among	among	IN
10_1101-2021_01_02_425006	187	2	292	292	CD
10_1101-2021_01_02_425006	187	3	the	the	DT
10_1101-2021_01_02_425006	187	4	distinct	distinct	JJ
10_1101-2021_01_02_425006	187	5	ATUs	atu	NNS
10_1101-2021_01_02_425006	187	6	across	across	IN
10_1101-2021_01_02_425006	187	7	the	the	DT
10_1101-2021_01_02_425006	187	8	two	two	CD
10_1101-2021_01_02_425006	187	9	conditions	condition	NNS
10_1101-2021_01_02_425006	187	10	,	,	,
10_1101-2021_01_02_425006	187	11	394	394	CD
10_1101-2021_01_02_425006	187	12	ATUs	atu	NNS
10_1101-2021_01_02_425006	187	13	were	be	VBD
10_1101-2021_01_02_425006	187	14	from	from	IN
10_1101-2021_01_02_425006	187	15	the	the	DT
10_1101-2021_01_02_425006	187	16	same	same	JJ
10_1101-2021_01_02_425006	187	17	maximal	maximal	JJ
10_1101-2021_01_02_425006	187	18	ATU	ATU	NNP
10_1101-2021_01_02_425006	187	19	clusters	cluster	NNS
10_1101-2021_01_02_425006	187	20	in	in	IN
10_1101-2021_01_02_425006	187	21	the	the	DT
10_1101-2021_01_02_425006	187	22	293	293	CD
10_1101-2021_01_02_425006	187	23	two	two	CD
10_1101-2021_01_02_425006	187	24	maximal	maximal	JJ
10_1101-2021_01_02_425006	187	25	ATU	ATU	NNP
10_1101-2021_01_02_425006	187	26	cluster	cluster	NN
10_1101-2021_01_02_425006	187	27	datasets	dataset	NNS
10_1101-2021_01_02_425006	187	28	,	,	,
10_1101-2021_01_02_425006	187	29	and	and	CC
10_1101-2021_01_02_425006	187	30	the	the	DT
10_1101-2021_01_02_425006	187	31	rest	rest	NN
10_1101-2021_01_02_425006	187	32	were	be	VBD
10_1101-2021_01_02_425006	187	33	from	from	IN
10_1101-2021_01_02_425006	187	34	different	different	JJ
10_1101-2021_01_02_425006	187	35	maximal	maximal	JJ
10_1101-2021_01_02_425006	187	36	ATU	ATU	NNP
10_1101-2021_01_02_425006	187	37	clusters	cluster	NNS
10_1101-2021_01_02_425006	187	38	.	.	.
10_1101-2021_01_02_425006	188	1	The	the	DT
10_1101-2021_01_02_425006	188	2	fact	fact	NN
10_1101-2021_01_02_425006	188	3	294	294	CD
10_1101-2021_01_02_425006	188	4	there	there	EX
10_1101-2021_01_02_425006	188	5	were	be	VBD
10_1101-2021_01_02_425006	188	6	distinct	distinct	JJ
10_1101-2021_01_02_425006	188	7	ATUs	atu	NNS
10_1101-2021_01_02_425006	188	8	under	under	IN
10_1101-2021_01_02_425006	188	9	the	the	DT
10_1101-2021_01_02_425006	188	10	two	two	CD
10_1101-2021_01_02_425006	188	11	conditions	condition	NNS
10_1101-2021_01_02_425006	188	12	suggests	suggest	VBZ
10_1101-2021_01_02_425006	188	13	that	that	IN
10_1101-2021_01_02_425006	188	14	ATUs	atu	NNS
10_1101-2021_01_02_425006	188	15	are	be	VBP
10_1101-2021_01_02_425006	188	16	dynamically	dynamically	RB
10_1101-2021_01_02_425006	188	17	responsive	responsive	JJ
10_1101-2021_01_02_425006	188	18	to	to	IN
10_1101-2021_01_02_425006	188	19	295	295	CD
10_1101-2021_01_02_425006	188	20	.CC	.CC	,
10_1101-2021_01_02_425006	188	21	-	-	HYPH
10_1101-2021_01_02_425006	188	22	BY	by	IN
10_1101-2021_01_02_425006	188	23	-	-	HYPH
10_1101-2021_01_02_425006	188	24	NC	NC	NNP
10_1101-2021_01_02_425006	188	25	-	-	HYPH
10_1101-2021_01_02_425006	188	26	ND	ND	NNP
10_1101-2021_01_02_425006	188	27	4.0	4.0	CD
10_1101-2021_01_02_425006	188	28	International	International	NNP
10_1101-2021_01_02_425006	188	29	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	188	30	under	under	IN
10_1101-2021_01_02_425006	188	31	a	a	DT
10_1101-2021_01_02_425006	188	32	(	(	-LRB-
10_1101-2021_01_02_425006	188	33	which	which	WDT
10_1101-2021_01_02_425006	188	34	was	be	VBD
10_1101-2021_01_02_425006	188	35	not	not	RB
10_1101-2021_01_02_425006	188	36	certified	certify	VBN
10_1101-2021_01_02_425006	188	37	by	by	IN
10_1101-2021_01_02_425006	188	38	peer	peer	NN
10_1101-2021_01_02_425006	188	39	review	review	NN
10_1101-2021_01_02_425006	188	40	)	)	-RRB-
10_1101-2021_01_02_425006	188	41	is	be	VBZ
10_1101-2021_01_02_425006	188	42	the	the	DT
10_1101-2021_01_02_425006	188	43	author	author	NN
10_1101-2021_01_02_425006	188	44	/	/	SYM
10_1101-2021_01_02_425006	188	45	funder	funder	NN
10_1101-2021_01_02_425006	188	46	,	,	,
10_1101-2021_01_02_425006	188	47	who	who	WP
10_1101-2021_01_02_425006	188	48	has	have	VBZ
10_1101-2021_01_02_425006	188	49	granted	grant	VBN
10_1101-2021_01_02_425006	188	50	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	188	51	a	a	DT
10_1101-2021_01_02_425006	188	52	license	license	NN
10_1101-2021_01_02_425006	188	53	to	to	TO
10_1101-2021_01_02_425006	188	54	display	display	VB
10_1101-2021_01_02_425006	188	55	the	the	DT
10_1101-2021_01_02_425006	188	56	preprint	preprint	NN
10_1101-2021_01_02_425006	188	57	in	in	IN
10_1101-2021_01_02_425006	188	58	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	188	59	.	.	.
10_1101-2021_01_02_425006	189	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	189	2	is	be	VBZ
10_1101-2021_01_02_425006	189	3	made	make	VBN
10_1101-2021_01_02_425006	189	4	The	the	DT
10_1101-2021_01_02_425006	189	5	copyright	copyright	NN
10_1101-2021_01_02_425006	189	6	holder	holder	NN
10_1101-2021_01_02_425006	189	7	for	for	IN
10_1101-2021_01_02_425006	189	8	this	this	DT
10_1101-2021_01_02_425006	189	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	189	10	version	version	NN
10_1101-2021_01_02_425006	189	11	posted	post	VBD
10_1101-2021_01_02_425006	189	12	January	January	NNP
10_1101-2021_01_02_425006	189	13	6	6	CD
10_1101-2021_01_02_425006	189	14	,	,	,
10_1101-2021_01_02_425006	189	15	2021	2021	CD
10_1101-2021_01_02_425006	189	16	.	.	.
10_1101-2021_01_02_425006	189	17	;	;	:
10_1101-2021_01_02_425006	189	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	189	19	:	:	:
10_1101-2021_01_02_425006	189	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	189	21	preprint	preprint	NN
10_1101-2021_01_02_425006	189	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	189	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	189	24	18	18	CD
10_1101-2021_01_02_425006	189	25	different	different	JJ
10_1101-2021_01_02_425006	189	26	conditions	condition	NNS
10_1101-2021_01_02_425006	189	27	or	or	CC
10_1101-2021_01_02_425006	189	28	environmental	environmental	JJ
10_1101-2021_01_02_425006	189	29	stimuli	stimulus	NNS
10_1101-2021_01_02_425006	189	30	(	(	-LRB-
10_1101-2021_01_02_425006	189	31	for	for	IN
10_1101-2021_01_02_425006	189	32	more	more	JJR
10_1101-2021_01_02_425006	189	33	real	real	JJ
10_1101-2021_01_02_425006	189	34	examples	example	NNS
10_1101-2021_01_02_425006	189	35	about	about	IN
10_1101-2021_01_02_425006	189	36	the	the	DT
10_1101-2021_01_02_425006	189	37	ATUs	atu	NNS
10_1101-2021_01_02_425006	189	38	under	under	IN
10_1101-2021_01_02_425006	189	39	different	different	JJ
10_1101-2021_01_02_425006	189	40	296	296	CD
10_1101-2021_01_02_425006	189	41	conditions	condition	NNS
10_1101-2021_01_02_425006	189	42	,	,	,
10_1101-2021_01_02_425006	189	43	see	see	VB
10_1101-2021_01_02_425006	189	44	fig	fig	NN
10_1101-2021_01_02_425006	189	45	.	.	.
10_1101-2021_01_02_425006	190	1	S6	S6	NNP
10_1101-2021_01_02_425006	190	2	)	)	-RRB-
10_1101-2021_01_02_425006	190	3	.	.	.
10_1101-2021_01_02_425006	191	1	297	297	CD
10_1101-2021_01_02_425006	191	2	The	the	DT
10_1101-2021_01_02_425006	191	3	dynamic	dynamic	JJ
10_1101-2021_01_02_425006	191	4	composition	composition	NN
10_1101-2021_01_02_425006	191	5	of	of	IN
10_1101-2021_01_02_425006	191	6	predicted	predict	VBN
10_1101-2021_01_02_425006	191	7	ATUs	atu	NNS
10_1101-2021_01_02_425006	191	8	by	by	IN
10_1101-2021_01_02_425006	191	9	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	191	10	is	be	VBZ
10_1101-2021_01_02_425006	191	11	of	of	IN
10_1101-2021_01_02_425006	191	12	great	great	JJ
10_1101-2021_01_02_425006	191	13	significance	significance	NN
10_1101-2021_01_02_425006	191	14	to	to	TO
10_1101-2021_01_02_425006	191	15	understand	understand	VB
10_1101-2021_01_02_425006	191	16	the	the	DT
10_1101-2021_01_02_425006	191	17	298	298	CD
10_1101-2021_01_02_425006	191	18	interactions	interaction	NNS
10_1101-2021_01_02_425006	191	19	inside	inside	IN
10_1101-2021_01_02_425006	191	20	polymicrobial	polymicrobial	JJ
10_1101-2021_01_02_425006	191	21	communities	community	NNS
10_1101-2021_01_02_425006	191	22	.	.	.
10_1101-2021_01_02_425006	192	1	For	for	IN
10_1101-2021_01_02_425006	192	2	example	example	NN
10_1101-2021_01_02_425006	192	3	,	,	,
10_1101-2021_01_02_425006	192	4	chronic	chronic	JJ
10_1101-2021_01_02_425006	192	5	airway	airway	NN
10_1101-2021_01_02_425006	192	6	infection	infection	NN
10_1101-2021_01_02_425006	192	7	by	by	IN
10_1101-2021_01_02_425006	192	8	Pseudomonas	Pseudomonas	NNP
10_1101-2021_01_02_425006	192	9	299	299	CD
10_1101-2021_01_02_425006	192	10	aeruginosa	aeruginosa	NNP
10_1101-2021_01_02_425006	192	11	considerably	considerably	RB
10_1101-2021_01_02_425006	192	12	contributes	contribute	VBZ
10_1101-2021_01_02_425006	192	13	to	to	IN
10_1101-2021_01_02_425006	192	14	lung	lung	NN
10_1101-2021_01_02_425006	192	15	tissue	tissue	NN
10_1101-2021_01_02_425006	192	16	destruction	destruction	NN
10_1101-2021_01_02_425006	192	17	and	and	CC
10_1101-2021_01_02_425006	192	18	impairment	impairment	NN
10_1101-2021_01_02_425006	192	19	of	of	IN
10_1101-2021_01_02_425006	192	20	pulmonary	pulmonary	JJ
10_1101-2021_01_02_425006	192	21	function	function	NN
10_1101-2021_01_02_425006	192	22	in	in	IN
10_1101-2021_01_02_425006	192	23	300	300	CD
10_1101-2021_01_02_425006	192	24	cystic	cystic	JJ
10_1101-2021_01_02_425006	192	25	-	-	HYPH
10_1101-2021_01_02_425006	192	26	fibrosis	fibrosis	NN
10_1101-2021_01_02_425006	192	27	(	(	-LRB-
10_1101-2021_01_02_425006	192	28	CF	cf	NN
10_1101-2021_01_02_425006	192	29	)	)	-RRB-
10_1101-2021_01_02_425006	192	30	patients	patient	NNS
10_1101-2021_01_02_425006	192	31	(	(	-LRB-
10_1101-2021_01_02_425006	192	32	39	39	CD
10_1101-2021_01_02_425006	192	33	)	)	-RRB-
10_1101-2021_01_02_425006	192	34	.	.	.
10_1101-2021_01_02_425006	193	1	Marie	Marie	NNP
10_1101-2021_01_02_425006	193	2	et	et	NNP
10_1101-2021_01_02_425006	193	3	al	al	NNP
10_1101-2021_01_02_425006	193	4	.	.	.
10_1101-2021_01_02_425006	194	1	found	find	VBD
10_1101-2021_01_02_425006	194	2	that	that	IN
10_1101-2021_01_02_425006	194	3	the	the	DT
10_1101-2021_01_02_425006	194	4	presence	presence	NN
10_1101-2021_01_02_425006	194	5	of	of	IN
10_1101-2021_01_02_425006	194	6	E.	E.	NNP
10_1101-2021_01_02_425006	194	7	coli	coli	NNS
10_1101-2021_01_02_425006	194	8	complemented	complement	VBD
10_1101-2021_01_02_425006	194	9	the	the	DT
10_1101-2021_01_02_425006	194	10	301	301	CD
10_1101-2021_01_02_425006	194	11	growth	growth	NN
10_1101-2021_01_02_425006	194	12	defect	defect	NN
10_1101-2021_01_02_425006	194	13	of	of	IN
10_1101-2021_01_02_425006	194	14	a	a	DT
10_1101-2021_01_02_425006	194	15	P.	P.	NNP
10_1101-2021_01_02_425006	194	16	aeruginosa	aeruginosa	NNP
10_1101-2021_01_02_425006	194	17	bioA	bioa	RB
10_1101-2021_01_02_425006	194	18	-	-	HYPH
10_1101-2021_01_02_425006	194	19	disrupted	disrupt	VBN
10_1101-2021_01_02_425006	194	20	mutant	mutant	NN
10_1101-2021_01_02_425006	194	21	that	that	WDT
10_1101-2021_01_02_425006	194	22	is	be	VBZ
10_1101-2021_01_02_425006	194	23	unable	unable	JJ
10_1101-2021_01_02_425006	194	24	to	to	TO
10_1101-2021_01_02_425006	194	25	grow	grow	VB
10_1101-2021_01_02_425006	194	26	on	on	IN
10_1101-2021_01_02_425006	194	27	rich	rich	JJ
10_1101-2021_01_02_425006	194	28	medium	medium	NN
10_1101-2021_01_02_425006	194	29	,	,	,
10_1101-2021_01_02_425006	194	30	and	and	CC
10_1101-2021_01_02_425006	194	31	can	can	MD
10_1101-2021_01_02_425006	194	32	302	302	CD
10_1101-2021_01_02_425006	194	33	be	be	VB
10_1101-2021_01_02_425006	194	34	beneficial	beneficial	JJ
10_1101-2021_01_02_425006	194	35	to	to	IN
10_1101-2021_01_02_425006	194	36	P.	P.	NNP
10_1101-2021_01_02_425006	194	37	aeruginosa	aeruginosa	NNP
10_1101-2021_01_02_425006	194	38	when	when	WRB
10_1101-2021_01_02_425006	194	39	biotin	biotin	JJ
10_1101-2021_01_02_425006	194	40	supply	supply	NN
10_1101-2021_01_02_425006	194	41	is	be	VBZ
10_1101-2021_01_02_425006	194	42	limited	limit	VBN
10_1101-2021_01_02_425006	194	43	(	(	-LRB-
10_1101-2021_01_02_425006	194	44	39	39	CD
10_1101-2021_01_02_425006	194	45	)	)	-RRB-
10_1101-2021_01_02_425006	194	46	.	.	.
10_1101-2021_01_02_425006	195	1	An	an	DT
10_1101-2021_01_02_425006	195	2	ATU	ATU	NNP
10_1101-2021_01_02_425006	195	3	with	with	IN
10_1101-2021_01_02_425006	195	4	a	a	DT
10_1101-2021_01_02_425006	195	5	high	high	JJ
10_1101-2021_01_02_425006	195	6	expression	expression	NN
10_1101-2021_01_02_425006	195	7	level	level	NN
10_1101-2021_01_02_425006	195	8	303	303	CD
10_1101-2021_01_02_425006	195	9	coded	code	VBN
10_1101-2021_01_02_425006	195	10	by	by	IN
10_1101-2021_01_02_425006	195	11	the	the	DT
10_1101-2021_01_02_425006	195	12	uvrB	uvrb	CD
10_1101-2021_01_02_425006	195	13	gene	gene	NN
10_1101-2021_01_02_425006	195	14	is	be	VBZ
10_1101-2021_01_02_425006	195	15	identified	identify	VBN
10_1101-2021_01_02_425006	195	16	by	by	IN
10_1101-2021_01_02_425006	195	17	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	195	18	in	in	IN
10_1101-2021_01_02_425006	195	19	Rich	Rich	NNP
10_1101-2021_01_02_425006	195	20	medium	medium	NN
10_1101-2021_01_02_425006	195	21	,	,	,
10_1101-2021_01_02_425006	195	22	while	while	IN
10_1101-2021_01_02_425006	195	23	it	-PRON-	PRP
10_1101-2021_01_02_425006	195	24	does	do	VBZ
10_1101-2021_01_02_425006	195	25	not	not	RB
10_1101-2021_01_02_425006	195	26	exist	exist	VB
10_1101-2021_01_02_425006	195	27	in	in	IN
10_1101-2021_01_02_425006	195	28	M9	M9	NNP
10_1101-2021_01_02_425006	195	29	minimal	minimal	JJ
10_1101-2021_01_02_425006	195	30	304	304	CD
10_1101-2021_01_02_425006	195	31	medium	medium	NN
10_1101-2021_01_02_425006	195	32	(	(	-LRB-
10_1101-2021_01_02_425006	195	33	Fig	fig	NN
10_1101-2021_01_02_425006	195	34	.	.	.
10_1101-2021_01_02_425006	196	1	6	6	LS
10_1101-2021_01_02_425006	196	2	)	)	-RRB-
10_1101-2021_01_02_425006	196	3	.	.	.
10_1101-2021_01_02_425006	197	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	197	2	predicted	predict	VBD
10_1101-2021_01_02_425006	197	3	the	the	DT
10_1101-2021_01_02_425006	197	4	uvrB	uvrb	JJ
10_1101-2021_01_02_425006	197	5	gene	gene	NN
10_1101-2021_01_02_425006	197	6	to	to	TO
10_1101-2021_01_02_425006	197	7	be	be	VB
10_1101-2021_01_02_425006	197	8	involved	involve	VBN
10_1101-2021_01_02_425006	197	9	in	in	IN
10_1101-2021_01_02_425006	197	10	the	the	DT
10_1101-2021_01_02_425006	197	11	biotin	biotin	JJ
10_1101-2021_01_02_425006	197	12	metabolism	metabolism	NN
10_1101-2021_01_02_425006	197	13	pathway	pathway	NN
10_1101-2021_01_02_425006	197	14	,	,	,
10_1101-2021_01_02_425006	197	15	as	as	IN
10_1101-2021_01_02_425006	197	16	the	the	DT
10_1101-2021_01_02_425006	197	17	305	305	CD
10_1101-2021_01_02_425006	197	18	bioB	bioB	NNS
10_1101-2021_01_02_425006	197	19	,	,	,
10_1101-2021_01_02_425006	197	20	bioF	biof	NN
10_1101-2021_01_02_425006	197	21	,	,	,
10_1101-2021_01_02_425006	197	22	bioC	bioc	ADD
10_1101-2021_01_02_425006	197	23	,	,	,
10_1101-2021_01_02_425006	197	24	and	and	CC
10_1101-2021_01_02_425006	197	25	bioD	biod	NN
10_1101-2021_01_02_425006	197	26	genes	gene	NNS
10_1101-2021_01_02_425006	197	27	contained	contain	VBN
10_1101-2021_01_02_425006	197	28	in	in	IN
10_1101-2021_01_02_425006	197	29	a	a	DT
10_1101-2021_01_02_425006	197	30	same	same	JJ
10_1101-2021_01_02_425006	197	31	ATU	ATU	NNP
10_1101-2021_01_02_425006	197	32	with	with	IN
10_1101-2021_01_02_425006	197	33	it	-PRON-	PRP
10_1101-2021_01_02_425006	197	34	have	have	VBP
10_1101-2021_01_02_425006	197	35	been	be	VBN
10_1101-2021_01_02_425006	197	36	known	know	VBN
10_1101-2021_01_02_425006	197	37	in	in	IN
10_1101-2021_01_02_425006	197	38	the	the	DT
10_1101-2021_01_02_425006	197	39	biotin	biotin	JJ
10_1101-2021_01_02_425006	197	40	306	306	CD
10_1101-2021_01_02_425006	197	41	metabolism	metabolism	NN
10_1101-2021_01_02_425006	197	42	KEGG	KEGG	NNP
10_1101-2021_01_02_425006	197	43	pathway	pathway	NN
10_1101-2021_01_02_425006	197	44	.	.	.
10_1101-2021_01_02_425006	198	1	Therefore	therefore	RB
10_1101-2021_01_02_425006	198	2	,	,	,
10_1101-2021_01_02_425006	198	3	the	the	DT
10_1101-2021_01_02_425006	198	4	observation	observation	NN
10_1101-2021_01_02_425006	198	5	by	by	IN
10_1101-2021_01_02_425006	198	6	Marie	Marie	NNP
10_1101-2021_01_02_425006	198	7	et	et	NNP
10_1101-2021_01_02_425006	198	8	al	al	NNP
10_1101-2021_01_02_425006	198	9	.	.	.
10_1101-2021_01_02_425006	199	1	can	can	MD
10_1101-2021_01_02_425006	199	2	be	be	VB
10_1101-2021_01_02_425006	199	3	explained	explain	VBN
10_1101-2021_01_02_425006	199	4	that	that	IN
10_1101-2021_01_02_425006	199	5	the	the	DT
10_1101-2021_01_02_425006	199	6	ATUs	atu	NNS
10_1101-2021_01_02_425006	199	7	307	307	CD
10_1101-2021_01_02_425006	199	8	coded	code	VBN
10_1101-2021_01_02_425006	199	9	by	by	IN
10_1101-2021_01_02_425006	199	10	the	the	DT
10_1101-2021_01_02_425006	199	11	uvrB	uvrb	JJ
10_1101-2021_01_02_425006	199	12	gene	gene	NN
10_1101-2021_01_02_425006	199	13	of	of	IN
10_1101-2021_01_02_425006	199	14	E.	E.	NNP
10_1101-2021_01_02_425006	199	15	coli	coli	NNS
10_1101-2021_01_02_425006	199	16	can	can	MD
10_1101-2021_01_02_425006	199	17	provide	provide	VB
10_1101-2021_01_02_425006	199	18	the	the	DT
10_1101-2021_01_02_425006	199	19	biotin	biotin	JJ
10_1101-2021_01_02_425006	199	20	supply	supply	NN
10_1101-2021_01_02_425006	199	21	for	for	IN
10_1101-2021_01_02_425006	199	22	P.	P.	NNP
10_1101-2021_01_02_425006	199	23	aeruginosa	aeruginosa	NNP
10_1101-2021_01_02_425006	199	24	under	under	IN
10_1101-2021_01_02_425006	199	25	rich	rich	JJ
10_1101-2021_01_02_425006	199	26	medium	medium	NN
10_1101-2021_01_02_425006	199	27	.	.	.
10_1101-2021_01_02_425006	200	1	308	308	LS
10_1101-2021_01_02_425006	200	2	This	this	DT
10_1101-2021_01_02_425006	200	3	result	result	NN
10_1101-2021_01_02_425006	200	4	showed	show	VBD
10_1101-2021_01_02_425006	200	5	that	that	IN
10_1101-2021_01_02_425006	200	6	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	200	7	could	could	MD
10_1101-2021_01_02_425006	200	8	increase	increase	VB
10_1101-2021_01_02_425006	200	9	our	-PRON-	PRP$
10_1101-2021_01_02_425006	200	10	understanding	understanding	NN
10_1101-2021_01_02_425006	200	11	of	of	IN
10_1101-2021_01_02_425006	200	12	interspecies	interspecie	NNS
10_1101-2021_01_02_425006	200	13	competition	competition	NN
10_1101-2021_01_02_425006	200	14	and	and	CC
10_1101-2021_01_02_425006	200	15	309	309	CD
10_1101-2021_01_02_425006	200	16	cooperation	cooperation	NN
10_1101-2021_01_02_425006	200	17	,	,	,
10_1101-2021_01_02_425006	200	18	which	which	WDT
10_1101-2021_01_02_425006	200	19	play	play	VBP
10_1101-2021_01_02_425006	200	20	an	an	DT
10_1101-2021_01_02_425006	200	21	important	important	JJ
10_1101-2021_01_02_425006	200	22	role	role	NN
10_1101-2021_01_02_425006	200	23	in	in	IN
10_1101-2021_01_02_425006	200	24	shaping	shape	VBG
10_1101-2021_01_02_425006	200	25	the	the	DT
10_1101-2021_01_02_425006	200	26	composition	composition	NN
10_1101-2021_01_02_425006	200	27	and	and	CC
10_1101-2021_01_02_425006	200	28	structure	structure	NN
10_1101-2021_01_02_425006	200	29	of	of	IN
10_1101-2021_01_02_425006	200	30	polymicrobial	polymicrobial	JJ
10_1101-2021_01_02_425006	200	31	310	310	CD
10_1101-2021_01_02_425006	200	32	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	200	33	populations	population	NNS
10_1101-2021_01_02_425006	200	34	.	.	.
10_1101-2021_01_02_425006	201	1	311	311	CD
10_1101-2021_01_02_425006	201	2	Please	please	UH
10_1101-2021_01_02_425006	201	3	place	place	NN
10_1101-2021_01_02_425006	201	4	Fig	fig	NN
10_1101-2021_01_02_425006	201	5	.	.	.
10_1101-2021_01_02_425006	202	1	5	5	CD
10_1101-2021_01_02_425006	202	2	here	here	RB
10_1101-2021_01_02_425006	202	3	.	.	.
10_1101-2021_01_02_425006	203	1	312	312	CD
10_1101-2021_01_02_425006	203	2	Please	please	UH
10_1101-2021_01_02_425006	203	3	place	place	VB
10_1101-2021_01_02_425006	203	4	Fig	Fig	NNP
10_1101-2021_01_02_425006	203	5	.	.	.
10_1101-2021_01_02_425006	204	1	6	6	CD
10_1101-2021_01_02_425006	204	2	here	here	RB
10_1101-2021_01_02_425006	204	3	.	.	.
10_1101-2021_01_02_425006	205	1	313	313	CD
10_1101-2021_01_02_425006	205	2	.CC	.CC	:
10_1101-2021_01_02_425006	205	3	-	-	HYPH
10_1101-2021_01_02_425006	205	4	BY	by	IN
10_1101-2021_01_02_425006	205	5	-	-	HYPH
10_1101-2021_01_02_425006	205	6	NC	NC	NNP
10_1101-2021_01_02_425006	205	7	-	-	HYPH
10_1101-2021_01_02_425006	205	8	ND	ND	NNP
10_1101-2021_01_02_425006	205	9	4.0	4.0	CD
10_1101-2021_01_02_425006	205	10	International	International	NNP
10_1101-2021_01_02_425006	205	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	205	12	under	under	IN
10_1101-2021_01_02_425006	205	13	a	a	DT
10_1101-2021_01_02_425006	205	14	(	(	-LRB-
10_1101-2021_01_02_425006	205	15	which	which	WDT
10_1101-2021_01_02_425006	205	16	was	be	VBD
10_1101-2021_01_02_425006	205	17	not	not	RB
10_1101-2021_01_02_425006	205	18	certified	certify	VBN
10_1101-2021_01_02_425006	205	19	by	by	IN
10_1101-2021_01_02_425006	205	20	peer	peer	NN
10_1101-2021_01_02_425006	205	21	review	review	NN
10_1101-2021_01_02_425006	205	22	)	)	-RRB-
10_1101-2021_01_02_425006	205	23	is	be	VBZ
10_1101-2021_01_02_425006	205	24	the	the	DT
10_1101-2021_01_02_425006	205	25	author	author	NN
10_1101-2021_01_02_425006	205	26	/	/	SYM
10_1101-2021_01_02_425006	205	27	funder	funder	NN
10_1101-2021_01_02_425006	205	28	,	,	,
10_1101-2021_01_02_425006	205	29	who	who	WP
10_1101-2021_01_02_425006	205	30	has	have	VBZ
10_1101-2021_01_02_425006	205	31	granted	grant	VBN
10_1101-2021_01_02_425006	205	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	205	33	a	a	DT
10_1101-2021_01_02_425006	205	34	license	license	NN
10_1101-2021_01_02_425006	205	35	to	to	TO
10_1101-2021_01_02_425006	205	36	display	display	VB
10_1101-2021_01_02_425006	205	37	the	the	DT
10_1101-2021_01_02_425006	205	38	preprint	preprint	NN
10_1101-2021_01_02_425006	205	39	in	in	IN
10_1101-2021_01_02_425006	205	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	205	41	.	.	.
10_1101-2021_01_02_425006	206	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	206	2	is	be	VBZ
10_1101-2021_01_02_425006	206	3	made	make	VBN
10_1101-2021_01_02_425006	206	4	The	the	DT
10_1101-2021_01_02_425006	206	5	copyright	copyright	NN
10_1101-2021_01_02_425006	206	6	holder	holder	NN
10_1101-2021_01_02_425006	206	7	for	for	IN
10_1101-2021_01_02_425006	206	8	this	this	DT
10_1101-2021_01_02_425006	206	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	206	10	version	version	NN
10_1101-2021_01_02_425006	206	11	posted	post	VBD
10_1101-2021_01_02_425006	206	12	January	January	NNP
10_1101-2021_01_02_425006	206	13	6	6	CD
10_1101-2021_01_02_425006	206	14	,	,	,
10_1101-2021_01_02_425006	206	15	2021	2021	CD
10_1101-2021_01_02_425006	206	16	.	.	.
10_1101-2021_01_02_425006	206	17	;	;	:
10_1101-2021_01_02_425006	206	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	206	19	:	:	:
10_1101-2021_01_02_425006	206	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	206	21	preprint	preprint	NN
10_1101-2021_01_02_425006	206	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	206	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	206	24	19	19	CD
10_1101-2021_01_02_425006	206	25	Predicted	predict	VBN
10_1101-2021_01_02_425006	206	26	ATUs	atu	NNS
10_1101-2021_01_02_425006	206	27	by	by	IN
10_1101-2021_01_02_425006	206	28	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	206	29	are	be	VBP
10_1101-2021_01_02_425006	206	30	verified	verify	VBN
10_1101-2021_01_02_425006	206	31	by	by	IN
10_1101-2021_01_02_425006	206	32	experimental	experimental	JJ
10_1101-2021_01_02_425006	206	33	TSSs	tss	NNS
10_1101-2021_01_02_425006	206	34	and	and	CC
10_1101-2021_01_02_425006	206	35	TTSs	tts	NNS
10_1101-2021_01_02_425006	206	36	314	314	CD
10_1101-2021_01_02_425006	206	37	An	an	DT
10_1101-2021_01_02_425006	206	38	experimental	experimental	JJ
10_1101-2021_01_02_425006	206	39	TSS	TSS	NNP
10_1101-2021_01_02_425006	206	40	dataset	dataset	NN
10_1101-2021_01_02_425006	206	41	of	of	IN
10_1101-2021_01_02_425006	206	42	E.	E.	NNP
10_1101-2021_01_02_425006	206	43	coli	coli	NNS
10_1101-2021_01_02_425006	206	44	from	from	IN
10_1101-2021_01_02_425006	206	45	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	206	46	-	-	HYPH
10_1101-2021_01_02_425006	206	47	seq	seq	NNP
10_1101-2021_01_02_425006	206	48	(	(	-LRB-
10_1101-2021_01_02_425006	206	49	7	7	CD
10_1101-2021_01_02_425006	206	50	)	)	-RRB-
10_1101-2021_01_02_425006	206	51	and	and	CC
10_1101-2021_01_02_425006	206	52	a	a	DT
10_1101-2021_01_02_425006	206	53	TF	TF	NNP
10_1101-2021_01_02_425006	206	54	binding	bind	VBG
10_1101-2021_01_02_425006	206	55	site	site	NN
10_1101-2021_01_02_425006	206	56	dataset	dataset	NN
10_1101-2021_01_02_425006	206	57	of	of	IN
10_1101-2021_01_02_425006	206	58	E.	E.	NNP
10_1101-2021_01_02_425006	206	59	coli	coli	NNS
10_1101-2021_01_02_425006	206	60	from	from	IN
10_1101-2021_01_02_425006	206	61	315	315	CD
10_1101-2021_01_02_425006	206	62	the	the	DT
10_1101-2021_01_02_425006	206	63	experimental	experimental	JJ
10_1101-2021_01_02_425006	206	64	dataset	dataset	NN
10_1101-2021_01_02_425006	206	65	of	of	IN
10_1101-2021_01_02_425006	206	66	RegulonDB	RegulonDB	NNP
10_1101-2021_01_02_425006	206	67	(	(	-LRB-
10_1101-2021_01_02_425006	206	68	19	19	CD
10_1101-2021_01_02_425006	206	69	)	)	-RRB-
10_1101-2021_01_02_425006	206	70	were	be	VBD
10_1101-2021_01_02_425006	206	71	used	use	VBN
10_1101-2021_01_02_425006	206	72	to	to	TO
10_1101-2021_01_02_425006	206	73	further	further	RB
10_1101-2021_01_02_425006	206	74	verify	verify	VB
10_1101-2021_01_02_425006	206	75	the	the	DT
10_1101-2021_01_02_425006	206	76	reliability	reliability	NN
10_1101-2021_01_02_425006	206	77	of	of	IN
10_1101-2021_01_02_425006	206	78	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	206	79	and	and	CC
10_1101-2021_01_02_425006	206	80	316	316	CD
10_1101-2021_01_02_425006	206	81	were	be	VBD
10_1101-2021_01_02_425006	206	82	named	name	VBN
10_1101-2021_01_02_425006	206	83	dataset	dataset	NNP
10_1101-2021_01_02_425006	206	84	1	1	CD
10_1101-2021_01_02_425006	206	85	and	and	CC
10_1101-2021_01_02_425006	206	86	dataset	dataset	VBD
10_1101-2021_01_02_425006	206	87	2	2	CD
10_1101-2021_01_02_425006	206	88	,	,	,
10_1101-2021_01_02_425006	206	89	respectively	respectively	RB
10_1101-2021_01_02_425006	206	90	.	.	.
10_1101-2021_01_02_425006	207	1	There	there	EX
10_1101-2021_01_02_425006	207	2	were	be	VBD
10_1101-2021_01_02_425006	207	3	5,512	5,512	CD
10_1101-2021_01_02_425006	207	4	experimental	experimental	JJ
10_1101-2021_01_02_425006	207	5	TSSs	tss	NNS
10_1101-2021_01_02_425006	207	6	in	in	IN
10_1101-2021_01_02_425006	207	7	dataset	dataset	NNP
10_1101-2021_01_02_425006	207	8	1	1	CD
10_1101-2021_01_02_425006	207	9	and	and	CC
10_1101-2021_01_02_425006	207	10	317	317	CD
10_1101-2021_01_02_425006	207	11	3,220	3,220	CD
10_1101-2021_01_02_425006	207	12	experimental	experimental	JJ
10_1101-2021_01_02_425006	207	13	TF	TF	NNP
10_1101-2021_01_02_425006	207	14	binding	bind	VBG
10_1101-2021_01_02_425006	207	15	sites	site	NNS
10_1101-2021_01_02_425006	207	16	in	in	IN
10_1101-2021_01_02_425006	207	17	dataset	dataset	NNP
10_1101-2021_01_02_425006	207	18	2	2	CD
10_1101-2021_01_02_425006	207	19	.	.	.
10_1101-2021_01_02_425006	208	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	208	2	considered	consider	VBD
10_1101-2021_01_02_425006	208	3	the	the	DT
10_1101-2021_01_02_425006	208	4	5’-end	5’-end	CD
10_1101-2021_01_02_425006	208	5	genes	gene	NNS
10_1101-2021_01_02_425006	208	6	and	and	CC
10_1101-2021_01_02_425006	208	7	no	no	DT
10_1101-2021_01_02_425006	208	8	5’-end	5’-end	CD
10_1101-2021_01_02_425006	208	9	genes	gene	NNS
10_1101-2021_01_02_425006	208	10	of	of	IN
10_1101-2021_01_02_425006	208	11	318	318	CD
10_1101-2021_01_02_425006	208	12	the	the	DT
10_1101-2021_01_02_425006	208	13	predicted	predict	VBN
10_1101-2021_01_02_425006	208	14	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	208	15	by	by	IN
10_1101-2021_01_02_425006	208	16	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	208	17	.	.	.
10_1101-2021_01_02_425006	209	1	A	a	DT
10_1101-2021_01_02_425006	209	2	gene	gene	NN
10_1101-2021_01_02_425006	209	3	that	that	WDT
10_1101-2021_01_02_425006	209	4	is	be	VBZ
10_1101-2021_01_02_425006	209	5	not	not	RB
10_1101-2021_01_02_425006	209	6	the	the	DT
10_1101-2021_01_02_425006	209	7	5’-end	5’-end	CD
10_1101-2021_01_02_425006	209	8	gene	gene	NN
10_1101-2021_01_02_425006	209	9	of	of	IN
10_1101-2021_01_02_425006	209	10	any	any	DT
10_1101-2021_01_02_425006	209	11	predicted	predict	VBN
10_1101-2021_01_02_425006	209	12	ATU	ATU	NNP
10_1101-2021_01_02_425006	209	13	is	be	VBZ
10_1101-2021_01_02_425006	209	14	named	name	VBN
10_1101-2021_01_02_425006	209	15	a	a	DT
10_1101-2021_01_02_425006	209	16	no	no	DT
10_1101-2021_01_02_425006	209	17	319	319	CD
10_1101-2021_01_02_425006	209	18	5’-end	5’-end	CD
10_1101-2021_01_02_425006	209	19	gene	gene	NN
10_1101-2021_01_02_425006	209	20	.	.	.
10_1101-2021_01_02_425006	210	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	210	2	identified	identify	VBD
10_1101-2021_01_02_425006	210	3	2,177/2,005	2,177/2,005	CD
10_1101-2021_01_02_425006	210	4	5’-end	5’-end	CD
10_1101-2021_01_02_425006	210	5	genes	gene	NNS
10_1101-2021_01_02_425006	210	6	and	and	CC
10_1101-2021_01_02_425006	210	7	1,266/1,160	1,266/1,160	CD
10_1101-2021_01_02_425006	210	8	no	no	DT
10_1101-2021_01_02_425006	210	9	5’-end	5’-end	CD
10_1101-2021_01_02_425006	210	10	genes	gene	NNS
10_1101-2021_01_02_425006	210	11	of	of	IN
10_1101-2021_01_02_425006	210	12	the	the	DT
10_1101-2021_01_02_425006	210	13	predicted	predict	VBN
10_1101-2021_01_02_425006	210	14	320	320	CD
10_1101-2021_01_02_425006	210	15	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	210	16	for	for	IN
10_1101-2021_01_02_425006	210	17	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	210	18	/	/	SYM
10_1101-2021_01_02_425006	210	19	RiEnich	RiEnich	NNP
10_1101-2021_01_02_425006	210	20	.	.	.
10_1101-2021_01_02_425006	211	1	A	a	DT
10_1101-2021_01_02_425006	211	2	gene	gene	NN
10_1101-2021_01_02_425006	211	3	validated	validate	VBN
10_1101-2021_01_02_425006	211	4	by	by	IN
10_1101-2021_01_02_425006	211	5	experimental	experimental	JJ
10_1101-2021_01_02_425006	211	6	TSSs	tss	NNS
10_1101-2021_01_02_425006	211	7	or	or	CC
10_1101-2021_01_02_425006	211	8	TF	TF	NNP
10_1101-2021_01_02_425006	211	9	binding	bind	VBG
10_1101-2021_01_02_425006	211	10	sites	site	NNS
10_1101-2021_01_02_425006	211	11	means	mean	VBZ
10_1101-2021_01_02_425006	211	12	321	321	CD
10_1101-2021_01_02_425006	211	13	that	that	IN
10_1101-2021_01_02_425006	211	14	it	-PRON-	PRP
10_1101-2021_01_02_425006	211	15	is	be	VBZ
10_1101-2021_01_02_425006	211	16	the	the	DT
10_1101-2021_01_02_425006	211	17	immediate	immediate	JJ
10_1101-2021_01_02_425006	211	18	downstream	downstream	JJ
10_1101-2021_01_02_425006	211	19	gene	gene	NN
10_1101-2021_01_02_425006	211	20	of	of	IN
10_1101-2021_01_02_425006	211	21	an	an	DT
10_1101-2021_01_02_425006	211	22	experimental	experimental	JJ
10_1101-2021_01_02_425006	211	23	TSS	TSS	NNP
10_1101-2021_01_02_425006	211	24	or	or	CC
10_1101-2021_01_02_425006	211	25	TF	TF	NNP
10_1101-2021_01_02_425006	211	26	binding	binding	NN
10_1101-2021_01_02_425006	211	27	site	site	NN
10_1101-2021_01_02_425006	211	28	.	.	.
10_1101-2021_01_02_425006	212	1	As	as	IN
10_1101-2021_01_02_425006	212	2	a	a	DT
10_1101-2021_01_02_425006	212	3	result	result	NN
10_1101-2021_01_02_425006	212	4	,	,	,
10_1101-2021_01_02_425006	212	5	the	the	DT
10_1101-2021_01_02_425006	212	6	322	322	CD
10_1101-2021_01_02_425006	212	7	proportion	proportion	NN
10_1101-2021_01_02_425006	212	8	of	of	IN
10_1101-2021_01_02_425006	212	9	5’-end	5’-end	CD
10_1101-2021_01_02_425006	212	10	genes	gene	NNS
10_1101-2021_01_02_425006	212	11	of	of	IN
10_1101-2021_01_02_425006	212	12	the	the	DT
10_1101-2021_01_02_425006	212	13	predicted	predict	VBN
10_1101-2021_01_02_425006	212	14	ATUs	atu	NNS
10_1101-2021_01_02_425006	212	15	that	that	WDT
10_1101-2021_01_02_425006	212	16	were	be	VBD
10_1101-2021_01_02_425006	212	17	validated	validate	VBN
10_1101-2021_01_02_425006	212	18	by	by	IN
10_1101-2021_01_02_425006	212	19	experimental	experimental	JJ
10_1101-2021_01_02_425006	212	20	TSSs	tss	NNS
10_1101-2021_01_02_425006	212	21	or	or	CC
10_1101-2021_01_02_425006	212	22	TF	TF	NNP
10_1101-2021_01_02_425006	212	23	323	323	CD
10_1101-2021_01_02_425006	212	24	binding	bind	VBG
10_1101-2021_01_02_425006	212	25	sites	site	NNS
10_1101-2021_01_02_425006	212	26	was	be	VBD
10_1101-2021_01_02_425006	212	27	over	over	IN
10_1101-2021_01_02_425006	212	28	1.7	1.7	CD
10_1101-2021_01_02_425006	212	29	times	time	NNS
10_1101-2021_01_02_425006	212	30	greater	great	JJR
10_1101-2021_01_02_425006	212	31	than	than	IN
10_1101-2021_01_02_425006	212	32	that	that	DT
10_1101-2021_01_02_425006	212	33	of	of	IN
10_1101-2021_01_02_425006	212	34	the	the	DT
10_1101-2021_01_02_425006	212	35	no	no	NN
10_1101-2021_01_02_425006	212	36	5’-end	5’-end	CD
10_1101-2021_01_02_425006	212	37	genes	gene	NNS
10_1101-2021_01_02_425006	212	38	(	(	-LRB-
10_1101-2021_01_02_425006	212	39	Table	table	NN
10_1101-2021_01_02_425006	212	40	1	1	CD
10_1101-2021_01_02_425006	212	41	)	)	-RRB-
10_1101-2021_01_02_425006	212	42	.	.	.
10_1101-2021_01_02_425006	213	1	Specifically	specifically	RB
10_1101-2021_01_02_425006	213	2	,	,	,
10_1101-2021_01_02_425006	213	3	the	the	DT
10_1101-2021_01_02_425006	213	4	324	324	CD
10_1101-2021_01_02_425006	213	5	proportion	proportion	NN
10_1101-2021_01_02_425006	213	6	of	of	IN
10_1101-2021_01_02_425006	213	7	5’-end	5’-end	CD
10_1101-2021_01_02_425006	213	8	genes	gene	NNS
10_1101-2021_01_02_425006	213	9	(	(	-LRB-
10_1101-2021_01_02_425006	213	10	29%/30	29%/30	CD
10_1101-2021_01_02_425006	213	11	%	%	NN
10_1101-2021_01_02_425006	213	12	for	for	IN
10_1101-2021_01_02_425006	213	13	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	213	14	/	/	SYM
10_1101-2021_01_02_425006	213	15	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	213	16	)	)	-RRB-
10_1101-2021_01_02_425006	213	17	validated	validate	VBN
10_1101-2021_01_02_425006	213	18	by	by	IN
10_1101-2021_01_02_425006	213	19	experimental	experimental	JJ
10_1101-2021_01_02_425006	213	20	TF	TF	NNP
10_1101-2021_01_02_425006	213	21	325	325	CD
10_1101-2021_01_02_425006	213	22	binding	bind	VBG
10_1101-2021_01_02_425006	213	23	sites	site	NNS
10_1101-2021_01_02_425006	213	24	was	be	VBD
10_1101-2021_01_02_425006	213	25	over	over	IN
10_1101-2021_01_02_425006	213	26	three	three	CD
10_1101-2021_01_02_425006	213	27	times	time	NNS
10_1101-2021_01_02_425006	213	28	greater	great	JJR
10_1101-2021_01_02_425006	213	29	than	than	IN
10_1101-2021_01_02_425006	213	30	the	the	DT
10_1101-2021_01_02_425006	213	31	no	no	NN
10_1101-2021_01_02_425006	213	32	5’-end	5’-end	CD
10_1101-2021_01_02_425006	213	33	genes	gene	NNS
10_1101-2021_01_02_425006	213	34	(	(	-LRB-
10_1101-2021_01_02_425006	213	35	9.2%/9.0	9.2%/9.0	CD
10_1101-2021_01_02_425006	213	36	%	%	NN
10_1101-2021_01_02_425006	213	37	for	for	IN
10_1101-2021_01_02_425006	213	38	326	326	CD
10_1101-2021_01_02_425006	213	39	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	213	40	/	/	SYM
10_1101-2021_01_02_425006	213	41	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	213	42	)	)	-RRB-
10_1101-2021_01_02_425006	213	43	.	.	.
10_1101-2021_01_02_425006	214	1	These	these	DT
10_1101-2021_01_02_425006	214	2	results	result	NNS
10_1101-2021_01_02_425006	214	3	further	further	RB
10_1101-2021_01_02_425006	214	4	verified	verify	VBD
10_1101-2021_01_02_425006	214	5	the	the	DT
10_1101-2021_01_02_425006	214	6	reliability	reliability	NN
10_1101-2021_01_02_425006	214	7	of	of	IN
10_1101-2021_01_02_425006	214	8	the	the	DT
10_1101-2021_01_02_425006	214	9	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	214	10	predicted	predict	VBN
10_1101-2021_01_02_425006	214	11	by	by	IN
10_1101-2021_01_02_425006	214	12	327	327	CD
10_1101-2021_01_02_425006	214	13	SeqATU	seqatu	NN
10_1101-2021_01_02_425006	214	14	in	in	IN
10_1101-2021_01_02_425006	214	15	terms	term	NNS
10_1101-2021_01_02_425006	214	16	of	of	IN
10_1101-2021_01_02_425006	214	17	the	the	DT
10_1101-2021_01_02_425006	214	18	TSS	TSS	NNP
10_1101-2021_01_02_425006	214	19	level	level	NN
10_1101-2021_01_02_425006	214	20	.	.	.
10_1101-2021_01_02_425006	215	1	In	in	IN
10_1101-2021_01_02_425006	215	2	addition	addition	NN
10_1101-2021_01_02_425006	215	3	,	,	,
10_1101-2021_01_02_425006	215	4	four	four	CD
10_1101-2021_01_02_425006	215	5	other	other	JJ
10_1101-2021_01_02_425006	215	6	experimental	experimental	JJ
10_1101-2021_01_02_425006	215	7	TSS	tss	NN
10_1101-2021_01_02_425006	215	8	or	or	CC
10_1101-2021_01_02_425006	215	9	promoter	promoter	NN
10_1101-2021_01_02_425006	215	10	datasets	dataset	NNS
10_1101-2021_01_02_425006	215	11	from	from	IN
10_1101-2021_01_02_425006	215	12	328	328	CD
10_1101-2021_01_02_425006	215	13	RegulonDB	regulondb	NN
10_1101-2021_01_02_425006	215	14	(	(	-LRB-
10_1101-2021_01_02_425006	215	15	19	19	CD
10_1101-2021_01_02_425006	215	16	)	)	-RRB-
10_1101-2021_01_02_425006	215	17	,	,	,
10_1101-2021_01_02_425006	215	18	dRNA	drna	NN
10_1101-2021_01_02_425006	215	19	-	-	HYPH
10_1101-2021_01_02_425006	215	20	seq	seq	NN
10_1101-2021_01_02_425006	215	21	(	(	-LRB-
10_1101-2021_01_02_425006	215	22	14	14	CD
10_1101-2021_01_02_425006	215	23	)	)	-RRB-
10_1101-2021_01_02_425006	215	24	,	,	,
10_1101-2021_01_02_425006	215	25	and	and	CC
10_1101-2021_01_02_425006	215	26	Cappable	cappable	JJ
10_1101-2021_01_02_425006	215	27	-	-	HYPH
10_1101-2021_01_02_425006	215	28	seq	seq	NN
10_1101-2021_01_02_425006	215	29	(	(	-LRB-
10_1101-2021_01_02_425006	215	30	13	13	CD
10_1101-2021_01_02_425006	215	31	)	)	-RRB-
10_1101-2021_01_02_425006	215	32	were	be	VBD
10_1101-2021_01_02_425006	215	33	also	also	RB
10_1101-2021_01_02_425006	215	34	examined	examine	VBN
10_1101-2021_01_02_425006	215	35	.	.	.
10_1101-2021_01_02_425006	216	1	The	the	DT
10_1101-2021_01_02_425006	216	2	results	result	NNS
10_1101-2021_01_02_425006	216	3	are	be	VBP
10_1101-2021_01_02_425006	216	4	shown	show	VBN
10_1101-2021_01_02_425006	216	5	in	in	IN
10_1101-2021_01_02_425006	216	6	329	329	CD
10_1101-2021_01_02_425006	216	7	table	table	NN
10_1101-2021_01_02_425006	216	8	S3	S3	NNP
10_1101-2021_01_02_425006	216	9	,	,	,
10_1101-2021_01_02_425006	216	10	and	and	CC
10_1101-2021_01_02_425006	216	11	we	-PRON-	PRP
10_1101-2021_01_02_425006	216	12	also	also	RB
10_1101-2021_01_02_425006	216	13	found	find	VBD
10_1101-2021_01_02_425006	216	14	a	a	DT
10_1101-2021_01_02_425006	216	15	higher	high	JJR
10_1101-2021_01_02_425006	216	16	proportion	proportion	NN
10_1101-2021_01_02_425006	216	17	of	of	IN
10_1101-2021_01_02_425006	216	18	5’-end	5’-end	CD
10_1101-2021_01_02_425006	216	19	genes	gene	NNS
10_1101-2021_01_02_425006	216	20	of	of	IN
10_1101-2021_01_02_425006	216	21	the	the	DT
10_1101-2021_01_02_425006	216	22	predicted	predict	VBN
10_1101-2021_01_02_425006	216	23	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	216	24	validated	validate	VBN
10_1101-2021_01_02_425006	216	25	by	by	IN
10_1101-2021_01_02_425006	216	26	330	330	CD
10_1101-2021_01_02_425006	216	27	experimental	experimental	JJ
10_1101-2021_01_02_425006	216	28	TSSs	tss	NNS
10_1101-2021_01_02_425006	216	29	or	or	CC
10_1101-2021_01_02_425006	216	30	promoters	promoter	NNS
10_1101-2021_01_02_425006	216	31	than	than	IN
10_1101-2021_01_02_425006	216	32	that	that	DT
10_1101-2021_01_02_425006	216	33	of	of	IN
10_1101-2021_01_02_425006	216	34	no	no	DT
10_1101-2021_01_02_425006	216	35	5’-end	5’-end	CD
10_1101-2021_01_02_425006	216	36	genes	gene	NNS
10_1101-2021_01_02_425006	216	37	.	.	.
10_1101-2021_01_02_425006	217	1	331	331	CD
10_1101-2021_01_02_425006	217	2	We	-PRON-	PRP
10_1101-2021_01_02_425006	217	3	also	also	RB
10_1101-2021_01_02_425006	217	4	used	use	VBD
10_1101-2021_01_02_425006	217	5	two	two	CD
10_1101-2021_01_02_425006	217	6	experimental	experimental	JJ
10_1101-2021_01_02_425006	217	7	TTS	TTS	NNP
10_1101-2021_01_02_425006	217	8	datasets	dataset	NNS
10_1101-2021_01_02_425006	217	9	of	of	IN
10_1101-2021_01_02_425006	217	10	E.	E.	NNP
10_1101-2021_01_02_425006	217	11	coli	coli	NNS
10_1101-2021_01_02_425006	217	12	from	from	IN
10_1101-2021_01_02_425006	217	13	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	217	14	-	-	HYPH
10_1101-2021_01_02_425006	217	15	seq	seq	NNP
10_1101-2021_01_02_425006	217	16	(	(	-LRB-
10_1101-2021_01_02_425006	217	17	7	7	CD
10_1101-2021_01_02_425006	217	18	)	)	-RRB-
10_1101-2021_01_02_425006	217	19	and	and	CC
10_1101-2021_01_02_425006	217	20	RegulonDB	regulondb	NN
10_1101-2021_01_02_425006	217	21	(	(	-LRB-
10_1101-2021_01_02_425006	217	22	19	19	CD
10_1101-2021_01_02_425006	217	23	)	)	-RRB-
10_1101-2021_01_02_425006	217	24	to	to	IN
10_1101-2021_01_02_425006	217	25	332	332	CD
10_1101-2021_01_02_425006	217	26	.CC	.CC	:
10_1101-2021_01_02_425006	217	27	-	-	HYPH
10_1101-2021_01_02_425006	217	28	BY	by	IN
10_1101-2021_01_02_425006	217	29	-	-	HYPH
10_1101-2021_01_02_425006	217	30	NC	NC	NNP
10_1101-2021_01_02_425006	217	31	-	-	HYPH
10_1101-2021_01_02_425006	217	32	ND	ND	NNP
10_1101-2021_01_02_425006	217	33	4.0	4.0	CD
10_1101-2021_01_02_425006	217	34	International	International	NNP
10_1101-2021_01_02_425006	217	35	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	217	36	under	under	IN
10_1101-2021_01_02_425006	217	37	a	a	DT
10_1101-2021_01_02_425006	217	38	(	(	-LRB-
10_1101-2021_01_02_425006	217	39	which	which	WDT
10_1101-2021_01_02_425006	217	40	was	be	VBD
10_1101-2021_01_02_425006	217	41	not	not	RB
10_1101-2021_01_02_425006	217	42	certified	certify	VBN
10_1101-2021_01_02_425006	217	43	by	by	IN
10_1101-2021_01_02_425006	217	44	peer	peer	NN
10_1101-2021_01_02_425006	217	45	review	review	NN
10_1101-2021_01_02_425006	217	46	)	)	-RRB-
10_1101-2021_01_02_425006	217	47	is	be	VBZ
10_1101-2021_01_02_425006	217	48	the	the	DT
10_1101-2021_01_02_425006	217	49	author	author	NN
10_1101-2021_01_02_425006	217	50	/	/	SYM
10_1101-2021_01_02_425006	217	51	funder	funder	NN
10_1101-2021_01_02_425006	217	52	,	,	,
10_1101-2021_01_02_425006	217	53	who	who	WP
10_1101-2021_01_02_425006	217	54	has	have	VBZ
10_1101-2021_01_02_425006	217	55	granted	grant	VBN
10_1101-2021_01_02_425006	217	56	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	217	57	a	a	DT
10_1101-2021_01_02_425006	217	58	license	license	NN
10_1101-2021_01_02_425006	217	59	to	to	TO
10_1101-2021_01_02_425006	217	60	display	display	VB
10_1101-2021_01_02_425006	217	61	the	the	DT
10_1101-2021_01_02_425006	217	62	preprint	preprint	NN
10_1101-2021_01_02_425006	217	63	in	in	IN
10_1101-2021_01_02_425006	217	64	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	217	65	.	.	.
10_1101-2021_01_02_425006	218	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	218	2	is	be	VBZ
10_1101-2021_01_02_425006	218	3	made	make	VBN
10_1101-2021_01_02_425006	218	4	The	the	DT
10_1101-2021_01_02_425006	218	5	copyright	copyright	NN
10_1101-2021_01_02_425006	218	6	holder	holder	NN
10_1101-2021_01_02_425006	218	7	for	for	IN
10_1101-2021_01_02_425006	218	8	this	this	DT
10_1101-2021_01_02_425006	218	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	218	10	version	version	NN
10_1101-2021_01_02_425006	218	11	posted	post	VBD
10_1101-2021_01_02_425006	218	12	January	January	NNP
10_1101-2021_01_02_425006	218	13	6	6	CD
10_1101-2021_01_02_425006	218	14	,	,	,
10_1101-2021_01_02_425006	218	15	2021	2021	CD
10_1101-2021_01_02_425006	218	16	.	.	.
10_1101-2021_01_02_425006	218	17	;	;	:
10_1101-2021_01_02_425006	218	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	218	19	:	:	:
10_1101-2021_01_02_425006	218	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	218	21	preprint	preprint	NN
10_1101-2021_01_02_425006	218	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	218	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	218	24	20	20	CD
10_1101-2021_01_02_425006	218	25	verify	verify	VBP
10_1101-2021_01_02_425006	218	26	the	the	DT
10_1101-2021_01_02_425006	218	27	reliability	reliability	NN
10_1101-2021_01_02_425006	218	28	of	of	IN
10_1101-2021_01_02_425006	218	29	predicted	predict	VBN
10_1101-2021_01_02_425006	218	30	ATUs	atu	NNS
10_1101-2021_01_02_425006	218	31	by	by	IN
10_1101-2021_01_02_425006	218	32	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	218	33	in	in	IN
10_1101-2021_01_02_425006	218	34	terms	term	NNS
10_1101-2021_01_02_425006	218	35	of	of	IN
10_1101-2021_01_02_425006	218	36	TTS	TTS	NNP
10_1101-2021_01_02_425006	218	37	level	level	NN
10_1101-2021_01_02_425006	218	38	.	.	.
10_1101-2021_01_02_425006	219	1	These	these	DT
10_1101-2021_01_02_425006	219	2	two	two	CD
10_1101-2021_01_02_425006	219	3	experimental	experimental	JJ
10_1101-2021_01_02_425006	219	4	TTS	TTS	NNP
10_1101-2021_01_02_425006	219	5	333	333	CD
10_1101-2021_01_02_425006	219	6	datasets	dataset	NNS
10_1101-2021_01_02_425006	219	7	were	be	VBD
10_1101-2021_01_02_425006	219	8	named	name	VBN
10_1101-2021_01_02_425006	219	9	dataset	dataset	NNP
10_1101-2021_01_02_425006	219	10	3	3	CD
10_1101-2021_01_02_425006	219	11	and	and	CC
10_1101-2021_01_02_425006	219	12	dataset	dataset	VBD
10_1101-2021_01_02_425006	219	13	4	4	CD
10_1101-2021_01_02_425006	219	14	,	,	,
10_1101-2021_01_02_425006	219	15	respectively	respectively	RB
10_1101-2021_01_02_425006	219	16	.	.	.
10_1101-2021_01_02_425006	220	1	There	there	EX
10_1101-2021_01_02_425006	220	2	were	be	VBD
10_1101-2021_01_02_425006	220	3	1,540	1,540	CD
10_1101-2021_01_02_425006	220	4	experimental	experimental	JJ
10_1101-2021_01_02_425006	220	5	TTSs	TTSs	NNPS
10_1101-2021_01_02_425006	220	6	in	in	IN
10_1101-2021_01_02_425006	220	7	334	334	CD
10_1101-2021_01_02_425006	220	8	dataset	dataset	NN
10_1101-2021_01_02_425006	220	9	3	3	CD
10_1101-2021_01_02_425006	220	10	and	and	CC
10_1101-2021_01_02_425006	220	11	367	367	CD
10_1101-2021_01_02_425006	220	12	experimental	experimental	JJ
10_1101-2021_01_02_425006	220	13	TTSs	TTSs	NNPS
10_1101-2021_01_02_425006	220	14	in	in	IN
10_1101-2021_01_02_425006	220	15	dataset	dataset	NN
10_1101-2021_01_02_425006	220	16	4	4	CD
10_1101-2021_01_02_425006	220	17	.	.	.
10_1101-2021_01_02_425006	221	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	221	2	considered	consider	VBD
10_1101-2021_01_02_425006	221	3	the	the	DT
10_1101-2021_01_02_425006	221	4	3’-end	3’-end	CD
10_1101-2021_01_02_425006	221	5	genes	gene	NNS
10_1101-2021_01_02_425006	221	6	and	and	CC
10_1101-2021_01_02_425006	221	7	no	no	DT
10_1101-2021_01_02_425006	221	8	3’-end	3’-end	CD
10_1101-2021_01_02_425006	221	9	genes	gene	NNS
10_1101-2021_01_02_425006	221	10	335	335	CD
10_1101-2021_01_02_425006	221	11	of	of	IN
10_1101-2021_01_02_425006	221	12	the	the	DT
10_1101-2021_01_02_425006	221	13	predicted	predict	VBN
10_1101-2021_01_02_425006	221	14	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	221	15	by	by	IN
10_1101-2021_01_02_425006	221	16	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	221	17	.	.	.
10_1101-2021_01_02_425006	222	1	A	a	DT
10_1101-2021_01_02_425006	222	2	gene	gene	NN
10_1101-2021_01_02_425006	222	3	that	that	WDT
10_1101-2021_01_02_425006	222	4	is	be	VBZ
10_1101-2021_01_02_425006	222	5	not	not	RB
10_1101-2021_01_02_425006	222	6	the	the	DT
10_1101-2021_01_02_425006	222	7	3’-end	3’-end	CD
10_1101-2021_01_02_425006	222	8	gene	gene	NN
10_1101-2021_01_02_425006	222	9	of	of	IN
10_1101-2021_01_02_425006	222	10	any	any	DT
10_1101-2021_01_02_425006	222	11	predicted	predict	VBN
10_1101-2021_01_02_425006	222	12	ATU	ATU	NNP
10_1101-2021_01_02_425006	222	13	is	be	VBZ
10_1101-2021_01_02_425006	222	14	named	name	VBN
10_1101-2021_01_02_425006	222	15	a	a	DT
10_1101-2021_01_02_425006	222	16	336	336	CD
10_1101-2021_01_02_425006	222	17	no	no	DT
10_1101-2021_01_02_425006	222	18	3’-end	3’-end	CD
10_1101-2021_01_02_425006	222	19	gene	gene	NN
10_1101-2021_01_02_425006	222	20	.	.	.
10_1101-2021_01_02_425006	223	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	223	2	identified	identify	VBD
10_1101-2021_01_02_425006	223	3	2,290/2,187	2,290/2,187	,
10_1101-2021_01_02_425006	223	4	3’-end	3’-end	CD
10_1101-2021_01_02_425006	223	5	genes	gene	NNS
10_1101-2021_01_02_425006	223	6	and	and	CC
10_1101-2021_01_02_425006	223	7	1,153/978	1,153/978	CD
10_1101-2021_01_02_425006	223	8	no	no	DT
10_1101-2021_01_02_425006	223	9	3’-end	3’-end	CD
10_1101-2021_01_02_425006	223	10	genes	gene	NNS
10_1101-2021_01_02_425006	223	11	of	of	IN
10_1101-2021_01_02_425006	223	12	the	the	DT
10_1101-2021_01_02_425006	223	13	predicted	predict	VBN
10_1101-2021_01_02_425006	223	14	337	337	CD
10_1101-2021_01_02_425006	223	15	ATUs	atu	NNS
10_1101-2021_01_02_425006	223	16	for	for	IN
10_1101-2021_01_02_425006	223	17	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	223	18	/	/	SYM
10_1101-2021_01_02_425006	223	19	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	223	20	.	.	.
10_1101-2021_01_02_425006	224	1	A	a	DT
10_1101-2021_01_02_425006	224	2	gene	gene	NN
10_1101-2021_01_02_425006	224	3	validated	validate	VBN
10_1101-2021_01_02_425006	224	4	by	by	IN
10_1101-2021_01_02_425006	224	5	experimental	experimental	JJ
10_1101-2021_01_02_425006	224	6	TTSs	TTSs	NNPS
10_1101-2021_01_02_425006	224	7	means	mean	VBZ
10_1101-2021_01_02_425006	224	8	that	that	IN
10_1101-2021_01_02_425006	224	9	it	-PRON-	PRP
10_1101-2021_01_02_425006	224	10	is	be	VBZ
10_1101-2021_01_02_425006	224	11	the	the	DT
10_1101-2021_01_02_425006	224	12	338	338	CD
10_1101-2021_01_02_425006	224	13	immediate	immediate	JJ
10_1101-2021_01_02_425006	224	14	upstream	upstream	JJ
10_1101-2021_01_02_425006	224	15	gene	gene	NN
10_1101-2021_01_02_425006	224	16	of	of	IN
10_1101-2021_01_02_425006	224	17	an	an	DT
10_1101-2021_01_02_425006	224	18	experimental	experimental	JJ
10_1101-2021_01_02_425006	224	19	TTS	TTS	NNP
10_1101-2021_01_02_425006	224	20	.	.	.
10_1101-2021_01_02_425006	225	1	As	as	IN
10_1101-2021_01_02_425006	225	2	a	a	DT
10_1101-2021_01_02_425006	225	3	result	result	NN
10_1101-2021_01_02_425006	225	4	,	,	,
10_1101-2021_01_02_425006	225	5	the	the	DT
10_1101-2021_01_02_425006	225	6	proportion	proportion	NN
10_1101-2021_01_02_425006	225	7	of	of	IN
10_1101-2021_01_02_425006	225	8	3’-end	3’-end	CD
10_1101-2021_01_02_425006	225	9	genes	gene	NNS
10_1101-2021_01_02_425006	225	10	of	of	IN
10_1101-2021_01_02_425006	225	11	the	the	DT
10_1101-2021_01_02_425006	225	12	339	339	CD
10_1101-2021_01_02_425006	225	13	predicted	predict	VBD
10_1101-2021_01_02_425006	225	14	ATUs	atu	NNS
10_1101-2021_01_02_425006	225	15	that	that	WDT
10_1101-2021_01_02_425006	225	16	were	be	VBD
10_1101-2021_01_02_425006	225	17	validated	validate	VBN
10_1101-2021_01_02_425006	225	18	by	by	IN
10_1101-2021_01_02_425006	225	19	experimental	experimental	JJ
10_1101-2021_01_02_425006	225	20	TTSs	TTSs	NNPS
10_1101-2021_01_02_425006	225	21	was	be	VBD
10_1101-2021_01_02_425006	225	22	over	over	IN
10_1101-2021_01_02_425006	225	23	two	two	CD
10_1101-2021_01_02_425006	225	24	times	time	NNS
10_1101-2021_01_02_425006	225	25	greater	great	JJR
10_1101-2021_01_02_425006	225	26	than	than	IN
10_1101-2021_01_02_425006	225	27	that	that	DT
10_1101-2021_01_02_425006	225	28	of	of	IN
10_1101-2021_01_02_425006	225	29	no	no	DT
10_1101-2021_01_02_425006	225	30	3’-340	3’-340	CD
10_1101-2021_01_02_425006	225	31	end	end	NN
10_1101-2021_01_02_425006	225	32	genes	gene	NNS
10_1101-2021_01_02_425006	225	33	(	(	-LRB-
10_1101-2021_01_02_425006	225	34	Table	table	NN
10_1101-2021_01_02_425006	225	35	2	2	CD
10_1101-2021_01_02_425006	225	36	)	)	-RRB-
10_1101-2021_01_02_425006	225	37	.	.	.
10_1101-2021_01_02_425006	226	1	Specifically	specifically	RB
10_1101-2021_01_02_425006	226	2	,	,	,
10_1101-2021_01_02_425006	226	3	the	the	DT
10_1101-2021_01_02_425006	226	4	proportion	proportion	NN
10_1101-2021_01_02_425006	226	5	of	of	IN
10_1101-2021_01_02_425006	226	6	3’-end	3’-end	CD
10_1101-2021_01_02_425006	226	7	genes	gene	NNS
10_1101-2021_01_02_425006	226	8	(	(	-LRB-
10_1101-2021_01_02_425006	226	9	51%/53	51%/53	CD
10_1101-2021_01_02_425006	226	10	%	%	NN
10_1101-2021_01_02_425006	226	11	for	for	IN
10_1101-2021_01_02_425006	226	12	341	341	CD
10_1101-2021_01_02_425006	226	13	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	226	14	/	/	SYM
10_1101-2021_01_02_425006	226	15	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	226	16	)	)	-RRB-
10_1101-2021_01_02_425006	226	17	validated	validate	VBN
10_1101-2021_01_02_425006	226	18	by	by	IN
10_1101-2021_01_02_425006	226	19	experimental	experimental	JJ
10_1101-2021_01_02_425006	226	20	TTSs	TTSs	NNPS
10_1101-2021_01_02_425006	226	21	from	from	IN
10_1101-2021_01_02_425006	226	22	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	226	23	-	-	HYPH
10_1101-2021_01_02_425006	226	24	seq	seq	NNP
10_1101-2021_01_02_425006	226	25	was	be	VBD
10_1101-2021_01_02_425006	226	26	over	over	IN
10_1101-2021_01_02_425006	226	27	three	three	CD
10_1101-2021_01_02_425006	226	28	times	time	NNS
10_1101-2021_01_02_425006	226	29	342	342	CD
10_1101-2021_01_02_425006	226	30	greater	great	JJR
10_1101-2021_01_02_425006	226	31	than	than	IN
10_1101-2021_01_02_425006	226	32	that	that	DT
10_1101-2021_01_02_425006	226	33	of	of	IN
10_1101-2021_01_02_425006	226	34	no	no	DT
10_1101-2021_01_02_425006	226	35	3’-end	3’-end	CD
10_1101-2021_01_02_425006	226	36	genes	gene	NNS
10_1101-2021_01_02_425006	226	37	(	(	-LRB-
10_1101-2021_01_02_425006	226	38	15%/14	15%/14	CD
10_1101-2021_01_02_425006	226	39	%	%	NN
10_1101-2021_01_02_425006	226	40	for	for	IN
10_1101-2021_01_02_425006	226	41	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	226	42	/	/	SYM
10_1101-2021_01_02_425006	226	43	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	226	44	)	)	-RRB-
10_1101-2021_01_02_425006	226	45	.	.	.
10_1101-2021_01_02_425006	227	1	These	these	DT
10_1101-2021_01_02_425006	227	2	results	result	NNS
10_1101-2021_01_02_425006	227	3	further	far	RBR
10_1101-2021_01_02_425006	227	4	343	343	CD
10_1101-2021_01_02_425006	227	5	verified	verify	VBD
10_1101-2021_01_02_425006	227	6	the	the	DT
10_1101-2021_01_02_425006	227	7	reliability	reliability	NN
10_1101-2021_01_02_425006	227	8	of	of	IN
10_1101-2021_01_02_425006	227	9	the	the	DT
10_1101-2021_01_02_425006	227	10	ATUs	atu	NNS
10_1101-2021_01_02_425006	227	11	predicted	predict	VBN
10_1101-2021_01_02_425006	227	12	by	by	IN
10_1101-2021_01_02_425006	227	13	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	227	14	in	in	IN
10_1101-2021_01_02_425006	227	15	terms	term	NNS
10_1101-2021_01_02_425006	227	16	of	of	IN
10_1101-2021_01_02_425006	227	17	the	the	DT
10_1101-2021_01_02_425006	227	18	TTS	TTS	NNP
10_1101-2021_01_02_425006	227	19	level	level	NN
10_1101-2021_01_02_425006	227	20	.	.	.
10_1101-2021_01_02_425006	228	1	In	in	IN
10_1101-2021_01_02_425006	228	2	addition	addition	NN
10_1101-2021_01_02_425006	228	3	,	,	,
10_1101-2021_01_02_425006	228	4	two	two	CD
10_1101-2021_01_02_425006	228	5	344	344	CD
10_1101-2021_01_02_425006	228	6	other	other	JJ
10_1101-2021_01_02_425006	228	7	computationally	computationally	RB
10_1101-2021_01_02_425006	228	8	predicted	predict	VBD
10_1101-2021_01_02_425006	228	9	TTS	TTS	NNP
10_1101-2021_01_02_425006	228	10	datasets	dataset	NNS
10_1101-2021_01_02_425006	228	11	from	from	IN
10_1101-2021_01_02_425006	228	12	the	the	DT
10_1101-2021_01_02_425006	228	13	works	work	NNS
10_1101-2021_01_02_425006	228	14	by	by	IN
10_1101-2021_01_02_425006	228	15	Nadiras	Nadiras	NNP
10_1101-2021_01_02_425006	228	16	et	et	FW
10_1101-2021_01_02_425006	228	17	al	al	NNP
10_1101-2021_01_02_425006	228	18	.	.	.
10_1101-2021_01_02_425006	229	1	(	(	-LRB-
10_1101-2021_01_02_425006	229	2	40	40	CD
10_1101-2021_01_02_425006	229	3	)	)	-RRB-
10_1101-2021_01_02_425006	229	4	and	and	CC
10_1101-2021_01_02_425006	229	5	Kingsford	Kingsford	NNP
10_1101-2021_01_02_425006	229	6	et	et	NNP
10_1101-2021_01_02_425006	229	7	al	al	NNP
10_1101-2021_01_02_425006	229	8	.	.	.
10_1101-2021_01_02_425006	230	1	345	345	CD
10_1101-2021_01_02_425006	230	2	(	(	-LRB-
10_1101-2021_01_02_425006	230	3	41	41	CD
10_1101-2021_01_02_425006	230	4	)	)	-RRB-
10_1101-2021_01_02_425006	230	5	were	be	VBD
10_1101-2021_01_02_425006	230	6	also	also	RB
10_1101-2021_01_02_425006	230	7	examined	examine	VBN
10_1101-2021_01_02_425006	230	8	.	.	.
10_1101-2021_01_02_425006	231	1	The	the	DT
10_1101-2021_01_02_425006	231	2	results	result	NNS
10_1101-2021_01_02_425006	231	3	are	be	VBP
10_1101-2021_01_02_425006	231	4	shown	show	VBN
10_1101-2021_01_02_425006	231	5	in	in	IN
10_1101-2021_01_02_425006	231	6	table	table	NN
10_1101-2021_01_02_425006	231	7	S4	s4	NN
10_1101-2021_01_02_425006	231	8	,	,	,
10_1101-2021_01_02_425006	231	9	and	and	CC
10_1101-2021_01_02_425006	231	10	we	-PRON-	PRP
10_1101-2021_01_02_425006	231	11	also	also	RB
10_1101-2021_01_02_425006	231	12	found	find	VBD
10_1101-2021_01_02_425006	231	13	the	the	DT
10_1101-2021_01_02_425006	231	14	proportion	proportion	NN
10_1101-2021_01_02_425006	231	15	of	of	IN
10_1101-2021_01_02_425006	231	16	3’-end	3’-end	CD
10_1101-2021_01_02_425006	231	17	346	346	CD
10_1101-2021_01_02_425006	231	18	genes	gene	NNS
10_1101-2021_01_02_425006	231	19	(	(	-LRB-
10_1101-2021_01_02_425006	231	20	63%/62	63%/62	NNP
10_1101-2021_01_02_425006	231	21	%	%	NN
10_1101-2021_01_02_425006	231	22	for	for	IN
10_1101-2021_01_02_425006	231	23	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	231	24	/	/	SYM
10_1101-2021_01_02_425006	231	25	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	231	26	)	)	-RRB-
10_1101-2021_01_02_425006	231	27	validated	validate	VBN
10_1101-2021_01_02_425006	231	28	by	by	IN
10_1101-2021_01_02_425006	231	29	computationally	computationally	RB
10_1101-2021_01_02_425006	231	30	predicted	predict	VBD
10_1101-2021_01_02_425006	231	31	Rho-347	rho-347	CD
10_1101-2021_01_02_425006	231	32	independent	independent	JJ
10_1101-2021_01_02_425006	231	33	TTSs	TTSs	NNPS
10_1101-2021_01_02_425006	231	34	was	be	VBD
10_1101-2021_01_02_425006	231	35	over	over	IN
10_1101-2021_01_02_425006	231	36	two	two	CD
10_1101-2021_01_02_425006	231	37	times	time	NNS
10_1101-2021_01_02_425006	231	38	greater	great	JJR
10_1101-2021_01_02_425006	231	39	than	than	IN
10_1101-2021_01_02_425006	231	40	that	that	DT
10_1101-2021_01_02_425006	231	41	of	of	IN
10_1101-2021_01_02_425006	231	42	no	no	DT
10_1101-2021_01_02_425006	231	43	3’-end	3’-end	CD
10_1101-2021_01_02_425006	231	44	genes	gene	NNS
10_1101-2021_01_02_425006	231	45	(	(	-LRB-
10_1101-2021_01_02_425006	231	46	29%/29	29%/29	CD
10_1101-2021_01_02_425006	231	47	%	%	NN
10_1101-2021_01_02_425006	231	48	for	for	IN
10_1101-2021_01_02_425006	231	49	348	348	CD
10_1101-2021_01_02_425006	231	50	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	231	51	/	/	SYM
10_1101-2021_01_02_425006	231	52	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	231	53	)	)	-RRB-
10_1101-2021_01_02_425006	231	54	.	.	.
10_1101-2021_01_02_425006	232	1	349	349	CD
10_1101-2021_01_02_425006	232	2	Please	please	UH
10_1101-2021_01_02_425006	232	3	place	place	VB
10_1101-2021_01_02_425006	232	4	Table	table	NN
10_1101-2021_01_02_425006	232	5	1	1	CD
10_1101-2021_01_02_425006	232	6	here	here	RB
10_1101-2021_01_02_425006	232	7	.	.	.
10_1101-2021_01_02_425006	233	1	350	350	CD
10_1101-2021_01_02_425006	233	2	Please	please	UH
10_1101-2021_01_02_425006	233	3	place	place	VB
10_1101-2021_01_02_425006	233	4	Table	table	NN
10_1101-2021_01_02_425006	233	5	2	2	CD
10_1101-2021_01_02_425006	233	6	here	here	RB
10_1101-2021_01_02_425006	233	7	.	.	.
10_1101-2021_01_02_425006	234	1	351	351	CD
10_1101-2021_01_02_425006	234	2	.CC	.CC	:
10_1101-2021_01_02_425006	234	3	-	-	HYPH
10_1101-2021_01_02_425006	234	4	BY	by	IN
10_1101-2021_01_02_425006	234	5	-	-	HYPH
10_1101-2021_01_02_425006	234	6	NC	NC	NNP
10_1101-2021_01_02_425006	234	7	-	-	HYPH
10_1101-2021_01_02_425006	234	8	ND	ND	NNP
10_1101-2021_01_02_425006	234	9	4.0	4.0	CD
10_1101-2021_01_02_425006	234	10	International	International	NNP
10_1101-2021_01_02_425006	234	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	234	12	under	under	IN
10_1101-2021_01_02_425006	234	13	a	a	DT
10_1101-2021_01_02_425006	234	14	(	(	-LRB-
10_1101-2021_01_02_425006	234	15	which	which	WDT
10_1101-2021_01_02_425006	234	16	was	be	VBD
10_1101-2021_01_02_425006	234	17	not	not	RB
10_1101-2021_01_02_425006	234	18	certified	certify	VBN
10_1101-2021_01_02_425006	234	19	by	by	IN
10_1101-2021_01_02_425006	234	20	peer	peer	NN
10_1101-2021_01_02_425006	234	21	review	review	NN
10_1101-2021_01_02_425006	234	22	)	)	-RRB-
10_1101-2021_01_02_425006	234	23	is	be	VBZ
10_1101-2021_01_02_425006	234	24	the	the	DT
10_1101-2021_01_02_425006	234	25	author	author	NN
10_1101-2021_01_02_425006	234	26	/	/	SYM
10_1101-2021_01_02_425006	234	27	funder	funder	NN
10_1101-2021_01_02_425006	234	28	,	,	,
10_1101-2021_01_02_425006	234	29	who	who	WP
10_1101-2021_01_02_425006	234	30	has	have	VBZ
10_1101-2021_01_02_425006	234	31	granted	grant	VBN
10_1101-2021_01_02_425006	234	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	234	33	a	a	DT
10_1101-2021_01_02_425006	234	34	license	license	NN
10_1101-2021_01_02_425006	234	35	to	to	TO
10_1101-2021_01_02_425006	234	36	display	display	VB
10_1101-2021_01_02_425006	234	37	the	the	DT
10_1101-2021_01_02_425006	234	38	preprint	preprint	NN
10_1101-2021_01_02_425006	234	39	in	in	IN
10_1101-2021_01_02_425006	234	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	234	41	.	.	.
10_1101-2021_01_02_425006	235	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	235	2	is	be	VBZ
10_1101-2021_01_02_425006	235	3	made	make	VBN
10_1101-2021_01_02_425006	235	4	The	the	DT
10_1101-2021_01_02_425006	235	5	copyright	copyright	NN
10_1101-2021_01_02_425006	235	6	holder	holder	NN
10_1101-2021_01_02_425006	235	7	for	for	IN
10_1101-2021_01_02_425006	235	8	this	this	DT
10_1101-2021_01_02_425006	235	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	235	10	version	version	NN
10_1101-2021_01_02_425006	235	11	posted	post	VBD
10_1101-2021_01_02_425006	235	12	January	January	NNP
10_1101-2021_01_02_425006	235	13	6	6	CD
10_1101-2021_01_02_425006	235	14	,	,	,
10_1101-2021_01_02_425006	235	15	2021	2021	CD
10_1101-2021_01_02_425006	235	16	.	.	.
10_1101-2021_01_02_425006	235	17	;	;	:
10_1101-2021_01_02_425006	235	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	235	19	:	:	:
10_1101-2021_01_02_425006	235	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	235	21	preprint	preprint	NN
10_1101-2021_01_02_425006	235	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	235	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	235	24	21	21	CD
10_1101-2021_01_02_425006	235	25	The	the	DT
10_1101-2021_01_02_425006	235	26	gene	gene	NN
10_1101-2021_01_02_425006	235	27	pairs	pair	NNS
10_1101-2021_01_02_425006	235	28	frequently	frequently	RB
10_1101-2021_01_02_425006	235	29	encoded	encode	VBN
10_1101-2021_01_02_425006	235	30	in	in	IN
10_1101-2021_01_02_425006	235	31	the	the	DT
10_1101-2021_01_02_425006	235	32	same	same	JJ
10_1101-2021_01_02_425006	235	33	ATUs	atu	NNS
10_1101-2021_01_02_425006	235	34	are	be	VBP
10_1101-2021_01_02_425006	235	35	more	more	RBR
10_1101-2021_01_02_425006	235	36	functionally	functionally	RB
10_1101-2021_01_02_425006	235	37	related	related	JJ
10_1101-2021_01_02_425006	235	38	than	than	IN
10_1101-2021_01_02_425006	235	39	those	those	DT
10_1101-2021_01_02_425006	235	40	that	that	IN
10_1101-2021_01_02_425006	235	41	352	352	CD
10_1101-2021_01_02_425006	235	42	can	can	MD
10_1101-2021_01_02_425006	235	43	belong	belong	VB
10_1101-2021_01_02_425006	235	44	to	to	IN
10_1101-2021_01_02_425006	235	45	two	two	CD
10_1101-2021_01_02_425006	235	46	distinct	distinct	JJ
10_1101-2021_01_02_425006	235	47	ATUs	atu	NNS
10_1101-2021_01_02_425006	235	48	353	353	CD
10_1101-2021_01_02_425006	235	49	Functional	functional	JJ
10_1101-2021_01_02_425006	235	50	analysis	analysis	NN
10_1101-2021_01_02_425006	235	51	was	be	VBD
10_1101-2021_01_02_425006	235	52	conducted	conduct	VBN
10_1101-2021_01_02_425006	235	53	by	by	IN
10_1101-2021_01_02_425006	235	54	integrating	integrate	VBG
10_1101-2021_01_02_425006	235	55	GO	GO	NNP
10_1101-2021_01_02_425006	235	56	terms	term	NNS
10_1101-2021_01_02_425006	235	57	from	from	IN
10_1101-2021_01_02_425006	235	58	the	the	DT
10_1101-2021_01_02_425006	235	59	Gene	Gene	NNP
10_1101-2021_01_02_425006	235	60	Ontology	Ontology	NNP
10_1101-2021_01_02_425006	235	61	(	(	-LRB-
10_1101-2021_01_02_425006	235	62	GO	GO	NNP
10_1101-2021_01_02_425006	235	63	)	)	-RRB-
10_1101-2021_01_02_425006	235	64	database	database	NN
10_1101-2021_01_02_425006	235	65	354	354	CD
10_1101-2021_01_02_425006	235	66	(	(	-LRB-
10_1101-2021_01_02_425006	235	67	42	42	CD
10_1101-2021_01_02_425006	235	68	)	)	-RRB-
10_1101-2021_01_02_425006	235	69	.	.	.
10_1101-2021_01_02_425006	236	1	In	in	IN
10_1101-2021_01_02_425006	236	2	detail	detail	NN
10_1101-2021_01_02_425006	236	3	,	,	,
10_1101-2021_01_02_425006	236	4	we	-PRON-	PRP
10_1101-2021_01_02_425006	236	5	measured	measure	VBD
10_1101-2021_01_02_425006	236	6	the	the	DT
10_1101-2021_01_02_425006	236	7	level	level	NN
10_1101-2021_01_02_425006	236	8	of	of	IN
10_1101-2021_01_02_425006	236	9	functional	functional	JJ
10_1101-2021_01_02_425006	236	10	relatedness	relatedness	NN
10_1101-2021_01_02_425006	236	11	for	for	IN
10_1101-2021_01_02_425006	236	12	two	two	CD
10_1101-2021_01_02_425006	236	13	types	type	NNS
10_1101-2021_01_02_425006	236	14	of	of	IN
10_1101-2021_01_02_425006	236	15	consecutive	consecutive	JJ
10_1101-2021_01_02_425006	236	16	gene	gene	NN
10_1101-2021_01_02_425006	236	17	pairs	pair	NNS
10_1101-2021_01_02_425006	236	18	,	,	,
10_1101-2021_01_02_425006	236	19	355	355	CD
10_1101-2021_01_02_425006	236	20	which	which	WDT
10_1101-2021_01_02_425006	236	21	is	be	VBZ
10_1101-2021_01_02_425006	236	22	similar	similar	JJ
10_1101-2021_01_02_425006	236	23	to	to	IN
10_1101-2021_01_02_425006	236	24	the	the	DT
10_1101-2021_01_02_425006	236	25	definition	definition	NN
10_1101-2021_01_02_425006	236	26	in	in	IN
10_1101-2021_01_02_425006	236	27	the	the	DT
10_1101-2021_01_02_425006	236	28	work	work	NN
10_1101-2021_01_02_425006	236	29	by	by	IN
10_1101-2021_01_02_425006	236	30	Mao	Mao	NNP
10_1101-2021_01_02_425006	236	31	et	et	NNP
10_1101-2021_01_02_425006	236	32	al	al	NNP
10_1101-2021_01_02_425006	236	33	.	.	.
10_1101-2021_01_02_425006	237	1	(	(	-LRB-
10_1101-2021_01_02_425006	237	2	38	38	CD
10_1101-2021_01_02_425006	237	3	)	)	-RRB-
10_1101-2021_01_02_425006	237	4	.	.	.
10_1101-2021_01_02_425006	238	1	Two	two	CD
10_1101-2021_01_02_425006	238	2	types	type	NNS
10_1101-2021_01_02_425006	238	3	of	of	IN
10_1101-2021_01_02_425006	238	4	consecutive	consecutive	JJ
10_1101-2021_01_02_425006	238	5	gene	gene	NN
10_1101-2021_01_02_425006	238	6	pairs	pairs	NNP
10_1101-2021_01_02_425006	238	7	356	356	CD
10_1101-2021_01_02_425006	238	8	were	be	VBD
10_1101-2021_01_02_425006	238	9	(	(	-LRB-
10_1101-2021_01_02_425006	238	10	i	i	NN
10_1101-2021_01_02_425006	238	11	)	)	-RRB-
10_1101-2021_01_02_425006	238	12	gene	gene	VBP
10_1101-2021_01_02_425006	238	13	pairs	pair	NNS
10_1101-2021_01_02_425006	238	14	each	each	DT
10_1101-2021_01_02_425006	238	15	consisting	consisting	NN
10_1101-2021_01_02_425006	238	16	of	of	IN
10_1101-2021_01_02_425006	238	17	a	a	DT
10_1101-2021_01_02_425006	238	18	5’-end	5’-end	CD
10_1101-2021_01_02_425006	238	19	gene	gene	NN
10_1101-2021_01_02_425006	238	20	of	of	IN
10_1101-2021_01_02_425006	238	21	an	an	DT
10_1101-2021_01_02_425006	238	22	ATU	ATU	NNP
10_1101-2021_01_02_425006	238	23	and	and	CC
10_1101-2021_01_02_425006	238	24	the	the	DT
10_1101-2021_01_02_425006	238	25	gene	gene	NN
10_1101-2021_01_02_425006	238	26	in	in	IN
10_1101-2021_01_02_425006	238	27	its	-PRON-	PRP$
10_1101-2021_01_02_425006	238	28	immediate	immediate	JJ
10_1101-2021_01_02_425006	238	29	upstream	upstream	NN
10_1101-2021_01_02_425006	238	30	357	357	CD
10_1101-2021_01_02_425006	238	31	on	on	IN
10_1101-2021_01_02_425006	238	32	the	the	DT
10_1101-2021_01_02_425006	238	33	same	same	JJ
10_1101-2021_01_02_425006	238	34	strand	strand	NN
10_1101-2021_01_02_425006	238	35	and	and	CC
10_1101-2021_01_02_425006	238	36	(	(	-LRB-
10_1101-2021_01_02_425006	238	37	ii	ii	LS
10_1101-2021_01_02_425006	238	38	)	)	-RRB-
10_1101-2021_01_02_425006	238	39	all	all	PDT
10_1101-2021_01_02_425006	238	40	the	the	DT
10_1101-2021_01_02_425006	238	41	other	other	JJ
10_1101-2021_01_02_425006	238	42	gene	gene	NN
10_1101-2021_01_02_425006	238	43	pairs	pair	NNS
10_1101-2021_01_02_425006	238	44	inside	inside	IN
10_1101-2021_01_02_425006	238	45	an	an	DT
10_1101-2021_01_02_425006	238	46	ATU	ATU	NNP
10_1101-2021_01_02_425006	238	47	(	(	-LRB-
10_1101-2021_01_02_425006	238	48	Fig	fig	NN
10_1101-2021_01_02_425006	238	49	.	.	.
10_1101-2021_01_02_425006	239	1	7A	7a	NN
10_1101-2021_01_02_425006	239	2	)	)	-RRB-
10_1101-2021_01_02_425006	239	3	.	.	.
10_1101-2021_01_02_425006	240	1	In	in	IN
10_1101-2021_01_02_425006	240	2	addition	addition	NN
10_1101-2021_01_02_425006	240	3	,	,	,
10_1101-2021_01_02_425006	240	4	we	-PRON-	PRP
10_1101-2021_01_02_425006	240	5	used	use	VBD
10_1101-2021_01_02_425006	240	6	a	a	DT
10_1101-2021_01_02_425006	240	7	358	358	CD
10_1101-2021_01_02_425006	240	8	scoring	score	VBG
10_1101-2021_01_02_425006	240	9	scheme	scheme	NN
10_1101-2021_01_02_425006	240	10	to	to	TO
10_1101-2021_01_02_425006	240	11	measure	measure	VB
10_1101-2021_01_02_425006	240	12	the	the	DT
10_1101-2021_01_02_425006	240	13	GO	GO	NNP
10_1101-2021_01_02_425006	240	14	-	-	HYPH
10_1101-2021_01_02_425006	240	15	based	base	VBN
10_1101-2021_01_02_425006	240	16	functional	functional	JJ
10_1101-2021_01_02_425006	240	17	similarity	similarity	NN
10_1101-2021_01_02_425006	240	18	between	between	IN
10_1101-2021_01_02_425006	240	19	a	a	DT
10_1101-2021_01_02_425006	240	20	pair	pair	NN
10_1101-2021_01_02_425006	240	21	of	of	IN
10_1101-2021_01_02_425006	240	22	genes	gene	NNS
10_1101-2021_01_02_425006	240	23	by	by	IN
10_1101-2021_01_02_425006	240	24	Wu	Wu	NNP
10_1101-2021_01_02_425006	240	25	et	et	NNP
10_1101-2021_01_02_425006	240	26	al	al	NNP
10_1101-2021_01_02_425006	240	27	.	.	.
10_1101-2021_01_02_425006	241	1	(	(	-LRB-
10_1101-2021_01_02_425006	241	2	43	43	CD
10_1101-2021_01_02_425006	241	3	)	)	-RRB-
10_1101-2021_01_02_425006	241	4	.	.	.
10_1101-2021_01_02_425006	242	1	359	359	CD
10_1101-2021_01_02_425006	242	2	This	this	DT
10_1101-2021_01_02_425006	242	3	study	study	NN
10_1101-2021_01_02_425006	242	4	developed	develop	VBD
10_1101-2021_01_02_425006	242	5	a	a	DT
10_1101-2021_01_02_425006	242	6	GO	GO	NNP
10_1101-2021_01_02_425006	242	7	similarity	similarity	NN
10_1101-2021_01_02_425006	242	8	score	score	NN
10_1101-2021_01_02_425006	242	9	and	and	CC
10_1101-2021_01_02_425006	242	10	showed	show	VBD
10_1101-2021_01_02_425006	242	11	that	that	IN
10_1101-2021_01_02_425006	242	12	the	the	DT
10_1101-2021_01_02_425006	242	13	larger	large	JJR
10_1101-2021_01_02_425006	242	14	the	the	DT
10_1101-2021_01_02_425006	242	15	score	score	NN
10_1101-2021_01_02_425006	242	16	,	,	,
10_1101-2021_01_02_425006	242	17	the	the	DT
10_1101-2021_01_02_425006	242	18	more	more	RBR
10_1101-2021_01_02_425006	242	19	likely	likely	JJ
10_1101-2021_01_02_425006	242	20	that	that	IN
10_1101-2021_01_02_425006	242	21	360	360	CD
10_1101-2021_01_02_425006	242	22	two	two	CD
10_1101-2021_01_02_425006	242	23	genes	gene	NNS
10_1101-2021_01_02_425006	242	24	are	be	VBP
10_1101-2021_01_02_425006	242	25	functionally	functionally	RB
10_1101-2021_01_02_425006	242	26	related	relate	VBN
10_1101-2021_01_02_425006	242	27	.	.	.
10_1101-2021_01_02_425006	243	1	In	in	IN
10_1101-2021_01_02_425006	243	2	brief	brief	NN
10_1101-2021_01_02_425006	243	3	,	,	,
10_1101-2021_01_02_425006	243	4	the	the	DT
10_1101-2021_01_02_425006	243	5	GO	GO	NNP
10_1101-2021_01_02_425006	243	6	similarity	similarity	NN
10_1101-2021_01_02_425006	243	7	score	score	NN
10_1101-2021_01_02_425006	243	8	of	of	IN
10_1101-2021_01_02_425006	243	9	a	a	DT
10_1101-2021_01_02_425006	243	10	gene	gene	NN
10_1101-2021_01_02_425006	243	11	pair	pair	NN
10_1101-2021_01_02_425006	243	12	�	�	NNP
10_1101-2021_01_02_425006	243	13	�	�	NNP
10_1101-2021_01_02_425006	243	14	and	and	CC
10_1101-2021_01_02_425006	243	15	�	�	NNP
10_1101-2021_01_02_425006	243	16	�	�	NNP
10_1101-2021_01_02_425006	243	17	is	be	VBZ
10_1101-2021_01_02_425006	243	18	361	361	CD
10_1101-2021_01_02_425006	243	19	denoted	denote	VBN
10_1101-2021_01_02_425006	243	20	as	as	IN
10_1101-2021_01_02_425006	243	21	�	�	NNP
10_1101-2021_01_02_425006	243	22	�	�	NNS
10_1101-2021_01_02_425006	243	23	�	�	,
10_1101-2021_01_02_425006	243	24	(	(	-LRB-
10_1101-2021_01_02_425006	243	25	�	�	NNP
10_1101-2021_01_02_425006	243	26	�	�	NNP
10_1101-2021_01_02_425006	243	27	,	,	,
10_1101-2021_01_02_425006	243	28	�	�	NNP
10_1101-2021_01_02_425006	243	29	�	�	NNP
10_1101-2021_01_02_425006	243	30	):	):	NN
10_1101-2021_01_02_425006	243	31	362	362	CD
10_1101-2021_01_02_425006	243	32	�	�	NNS
10_1101-2021_01_02_425006	243	33	�	�	JJ
10_1101-2021_01_02_425006	243	34	�	�	NNS
10_1101-2021_01_02_425006	243	35	�	�	JJ
10_1101-2021_01_02_425006	243	36	�	�	NNP
10_1101-2021_01_02_425006	243	37	�	�	NNP
10_1101-2021_01_02_425006	243	38	,	,	,
10_1101-2021_01_02_425006	243	39	�	�	NNP
10_1101-2021_01_02_425006	243	40	�	�	ADD
10_1101-2021_01_02_425006	243	41	�	�	NNP
10_1101-2021_01_02_425006	243	42	=	=	VBZ
10_1101-2021_01_02_425006	243	43	�	�	ADD
10_1101-2021_01_02_425006	243	44	�	�	VBZ
10_1101-2021_01_02_425006	243	45	�	�	NN
10_1101-2021_01_02_425006	243	46	�	�	NNS
10_1101-2021_01_02_425006	243	47	�	�	VBZ
10_1101-2021_01_02_425006	243	48	∈	∈	JJ
10_1101-2021_01_02_425006	243	49	�	�	NN
10_1101-2021_01_02_425006	243	50	(	(	-LRB-
10_1101-2021_01_02_425006	243	51	�	�	NNP
10_1101-2021_01_02_425006	243	52	�	�	NNP
10_1101-2021_01_02_425006	243	53	)	)	-RRB-
10_1101-2021_01_02_425006	243	54	,	,	,
10_1101-2021_01_02_425006	243	55	�	�	NNP
10_1101-2021_01_02_425006	243	56	�	�	NNP
10_1101-2021_01_02_425006	243	57	∈	∈	IN
10_1101-2021_01_02_425006	243	58	�	�	NNP
10_1101-2021_01_02_425006	243	59	(	(	-LRB-
10_1101-2021_01_02_425006	243	60	�	�	NNP
10_1101-2021_01_02_425006	243	61	�	�	NNP
10_1101-2021_01_02_425006	243	62	)	)	-RRB-
10_1101-2021_01_02_425006	243	63	�	�	NNP
10_1101-2021_01_02_425006	243	64	(	(	-LRB-
10_1101-2021_01_02_425006	243	65	�	�	NNP
10_1101-2021_01_02_425006	243	66	�	�	NNP
10_1101-2021_01_02_425006	243	67	,	,	,
10_1101-2021_01_02_425006	243	68	�	�	NNP
10_1101-2021_01_02_425006	243	69	�	�	NNP
10_1101-2021_01_02_425006	243	70	)	)	-RRB-
10_1101-2021_01_02_425006	243	71	363	363	CD
10_1101-2021_01_02_425006	243	72	where	where	WRB
10_1101-2021_01_02_425006	243	73	�	�	JJ
10_1101-2021_01_02_425006	243	74	�	�	NNP
10_1101-2021_01_02_425006	243	75	and	and	CC
10_1101-2021_01_02_425006	243	76	�	�	NNP
10_1101-2021_01_02_425006	243	77	�	�	NNP
10_1101-2021_01_02_425006	243	78	are	be	VBP
10_1101-2021_01_02_425006	243	79	the	the	DT
10_1101-2021_01_02_425006	243	80	GO	GO	NNP
10_1101-2021_01_02_425006	243	81	terms	term	NNS
10_1101-2021_01_02_425006	243	82	assigned	assign	VBN
10_1101-2021_01_02_425006	243	83	to	to	IN
10_1101-2021_01_02_425006	243	84	�	�	NNP
10_1101-2021_01_02_425006	243	85	�	�	NNP
10_1101-2021_01_02_425006	243	86	and	and	CC
10_1101-2021_01_02_425006	243	87	�	�	NNP
10_1101-2021_01_02_425006	243	88	�	�	NNP
10_1101-2021_01_02_425006	243	89	,	,	,
10_1101-2021_01_02_425006	243	90	respectively	respectively	RB
10_1101-2021_01_02_425006	243	91	;	;	:
10_1101-2021_01_02_425006	243	92	�	�	NNP
10_1101-2021_01_02_425006	243	93	(	(	-LRB-
10_1101-2021_01_02_425006	243	94	�	�	NNP
10_1101-2021_01_02_425006	243	95	�	�	NNP
10_1101-2021_01_02_425006	243	96	,	,	,
10_1101-2021_01_02_425006	243	97	�	�	NNP
10_1101-2021_01_02_425006	243	98	�	�	NNP
10_1101-2021_01_02_425006	243	99	)	)	-RRB-
10_1101-2021_01_02_425006	243	100	is	be	VBZ
10_1101-2021_01_02_425006	243	101	the	the	DT
10_1101-2021_01_02_425006	243	102	maximal	maximal	JJ
10_1101-2021_01_02_425006	243	103	364	364	CD
10_1101-2021_01_02_425006	243	104	number	number	NN
10_1101-2021_01_02_425006	243	105	of	of	IN
10_1101-2021_01_02_425006	243	106	common	common	JJ
10_1101-2021_01_02_425006	243	107	terms	term	NNS
10_1101-2021_01_02_425006	243	108	between	between	IN
10_1101-2021_01_02_425006	243	109	paths	path	NNS
10_1101-2021_01_02_425006	243	110	in	in	IN
10_1101-2021_01_02_425006	243	111	the	the	DT
10_1101-2021_01_02_425006	243	112	two	two	CD
10_1101-2021_01_02_425006	243	113	GO	GO	NNP
10_1101-2021_01_02_425006	243	114	graphs	graphs	NN
10_1101-2021_01_02_425006	243	115	induced	induce	VBN
10_1101-2021_01_02_425006	243	116	by	by	IN
10_1101-2021_01_02_425006	243	117	the	the	DT
10_1101-2021_01_02_425006	243	118	GO	GO	NNP
10_1101-2021_01_02_425006	243	119	terms	term	NNS
10_1101-2021_01_02_425006	243	120	�	�	NNS
10_1101-2021_01_02_425006	243	121	�	�	NNP
10_1101-2021_01_02_425006	243	122	and	and	CC
10_1101-2021_01_02_425006	243	123	�	�	NNP
10_1101-2021_01_02_425006	243	124	�	�	NNP
10_1101-2021_01_02_425006	243	125	.	.	.
10_1101-2021_01_02_425006	244	1	365	365	CD
10_1101-2021_01_02_425006	244	2	As	as	IN
10_1101-2021_01_02_425006	244	3	a	a	DT
10_1101-2021_01_02_425006	244	4	result	result	NN
10_1101-2021_01_02_425006	244	5	,	,	,
10_1101-2021_01_02_425006	244	6	the	the	DT
10_1101-2021_01_02_425006	244	7	mean	mean	JJ
10_1101-2021_01_02_425006	244	8	GO	GO	NNP
10_1101-2021_01_02_425006	244	9	similarity	similarity	NN
10_1101-2021_01_02_425006	244	10	score	score	NN
10_1101-2021_01_02_425006	244	11	was	be	VBD
10_1101-2021_01_02_425006	244	12	higher	high	JJR
10_1101-2021_01_02_425006	244	13	for	for	IN
10_1101-2021_01_02_425006	244	14	type	type	NN
10_1101-2021_01_02_425006	244	15	-	-	HYPH
10_1101-2021_01_02_425006	244	16	ii	ii	NN
10_1101-2021_01_02_425006	244	17	gene	gene	NN
10_1101-2021_01_02_425006	244	18	pairs	pair	NNS
10_1101-2021_01_02_425006	244	19	(	(	-LRB-
10_1101-2021_01_02_425006	244	20	5.97	5.97	CD
10_1101-2021_01_02_425006	244	21	versus	versus	IN
10_1101-2021_01_02_425006	244	22	4.04	4.04	CD
10_1101-2021_01_02_425006	244	23	for	for	IN
10_1101-2021_01_02_425006	244	24	366	366	CD
10_1101-2021_01_02_425006	244	25	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	244	26	and	and	CC
10_1101-2021_01_02_425006	244	27	5.86	5.86	CD
10_1101-2021_01_02_425006	244	28	versus	versus	IN
10_1101-2021_01_02_425006	244	29	3.91	3.91	CD
10_1101-2021_01_02_425006	244	30	for	for	IN
10_1101-2021_01_02_425006	244	31	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	244	32	)	)	-RRB-
10_1101-2021_01_02_425006	244	33	than	than	IN
10_1101-2021_01_02_425006	244	34	for	for	IN
10_1101-2021_01_02_425006	244	35	type	type	NN
10_1101-2021_01_02_425006	244	36	-	-	:
10_1101-2021_01_02_425006	244	37	i	i	PRP
10_1101-2021_01_02_425006	244	38	gene	gene	NN
10_1101-2021_01_02_425006	244	39	pairs	pair	NNS
10_1101-2021_01_02_425006	244	40	.	.	.
10_1101-2021_01_02_425006	245	1	A	a	DT
10_1101-2021_01_02_425006	245	2	total	total	NN
10_1101-2021_01_02_425006	245	3	of	of	IN
10_1101-2021_01_02_425006	245	4	574/524	574/524	NNP
10_1101-2021_01_02_425006	245	5	367	367	CD
10_1101-2021_01_02_425006	245	6	type	type	NN
10_1101-2021_01_02_425006	245	7	-	-	HYPH
10_1101-2021_01_02_425006	245	8	ii	ii	NN
10_1101-2021_01_02_425006	245	9	gene	gene	NN
10_1101-2021_01_02_425006	245	10	pairs	pair	NNS
10_1101-2021_01_02_425006	245	11	had	have	VBD
10_1101-2021_01_02_425006	245	12	GO	GO	NNP
10_1101-2021_01_02_425006	245	13	similarity	similarity	NN
10_1101-2021_01_02_425006	245	14	scores	score	NNS
10_1101-2021_01_02_425006	245	15	greater	great	JJR
10_1101-2021_01_02_425006	245	16	than	than	IN
10_1101-2021_01_02_425006	245	17	four	four	CD
10_1101-2021_01_02_425006	245	18	(	(	-LRB-
10_1101-2021_01_02_425006	245	19	64%/63	64%/63	CD
10_1101-2021_01_02_425006	245	20	%	%	NN
10_1101-2021_01_02_425006	245	21	of	of	IN
10_1101-2021_01_02_425006	245	22	a	a	DT
10_1101-2021_01_02_425006	245	23	total	total	NN
10_1101-2021_01_02_425006	245	24	of	of	IN
10_1101-2021_01_02_425006	245	25	899/834	899/834	NNS
10_1101-2021_01_02_425006	245	26	)	)	-RRB-
10_1101-2021_01_02_425006	245	27	,	,	,
10_1101-2021_01_02_425006	245	28	while	while	IN
10_1101-2021_01_02_425006	245	29	368	368	CD
10_1101-2021_01_02_425006	245	30	only	only	RB
10_1101-2021_01_02_425006	245	31	461/404	461/404	CD
10_1101-2021_01_02_425006	245	32	type	type	NN
10_1101-2021_01_02_425006	245	33	-	-	:
10_1101-2021_01_02_425006	245	34	i	i	PRP
10_1101-2021_01_02_425006	245	35	gene	gene	NN
10_1101-2021_01_02_425006	245	36	pairs	pair	NNS
10_1101-2021_01_02_425006	245	37	had	have	VBD
10_1101-2021_01_02_425006	245	38	GO	GO	NNP
10_1101-2021_01_02_425006	245	39	similarity	similarity	NN
10_1101-2021_01_02_425006	245	40	scores	score	NNS
10_1101-2021_01_02_425006	245	41	greater	great	JJR
10_1101-2021_01_02_425006	245	42	than	than	IN
10_1101-2021_01_02_425006	245	43	four	four	CD
10_1101-2021_01_02_425006	245	44	(	(	-LRB-
10_1101-2021_01_02_425006	245	45	36%/34	36%/34	CD
10_1101-2021_01_02_425006	245	46	%	%	NN
10_1101-2021_01_02_425006	245	47	of	of	IN
10_1101-2021_01_02_425006	245	48	a	a	DT
10_1101-2021_01_02_425006	245	49	total	total	NN
10_1101-2021_01_02_425006	245	50	of	of	IN
10_1101-2021_01_02_425006	245	51	369	369	CD
10_1101-2021_01_02_425006	245	52	1,274/1,179	1,274/1,179	NNS
10_1101-2021_01_02_425006	245	53	)	)	-RRB-
10_1101-2021_01_02_425006	245	54	for	for	IN
10_1101-2021_01_02_425006	245	55	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	245	56	/	/	SYM
10_1101-2021_01_02_425006	245	57	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	245	58	.	.	.
10_1101-2021_01_02_425006	246	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	246	2	also	also	RB
10_1101-2021_01_02_425006	246	3	applied	apply	VBD
10_1101-2021_01_02_425006	246	4	a	a	DT
10_1101-2021_01_02_425006	246	5	c	c	NN
10_1101-2021_01_02_425006	246	6	�	�	NN
10_1101-2021_01_02_425006	246	7	-test	-test	,
10_1101-2021_01_02_425006	246	8	(	(	-LRB-
10_1101-2021_01_02_425006	246	9	44	44	CD
10_1101-2021_01_02_425006	246	10	)	)	-RRB-
10_1101-2021_01_02_425006	246	11	to	to	TO
10_1101-2021_01_02_425006	246	12	determine	determine	VB
10_1101-2021_01_02_425006	246	13	whether	whether	IN
10_1101-2021_01_02_425006	246	14	the	the	DT
10_1101-2021_01_02_425006	246	15	370	370	CD
10_1101-2021_01_02_425006	246	16	.CC	.CC	,
10_1101-2021_01_02_425006	246	17	-	-	HYPH
10_1101-2021_01_02_425006	246	18	BY	by	IN
10_1101-2021_01_02_425006	246	19	-	-	HYPH
10_1101-2021_01_02_425006	246	20	NC	NC	NNP
10_1101-2021_01_02_425006	246	21	-	-	HYPH
10_1101-2021_01_02_425006	246	22	ND	ND	NNP
10_1101-2021_01_02_425006	246	23	4.0	4.0	CD
10_1101-2021_01_02_425006	246	24	International	International	NNP
10_1101-2021_01_02_425006	246	25	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	246	26	under	under	IN
10_1101-2021_01_02_425006	246	27	a	a	DT
10_1101-2021_01_02_425006	246	28	(	(	-LRB-
10_1101-2021_01_02_425006	246	29	which	which	WDT
10_1101-2021_01_02_425006	246	30	was	be	VBD
10_1101-2021_01_02_425006	246	31	not	not	RB
10_1101-2021_01_02_425006	246	32	certified	certify	VBN
10_1101-2021_01_02_425006	246	33	by	by	IN
10_1101-2021_01_02_425006	246	34	peer	peer	NN
10_1101-2021_01_02_425006	246	35	review	review	NN
10_1101-2021_01_02_425006	246	36	)	)	-RRB-
10_1101-2021_01_02_425006	246	37	is	be	VBZ
10_1101-2021_01_02_425006	246	38	the	the	DT
10_1101-2021_01_02_425006	246	39	author	author	NN
10_1101-2021_01_02_425006	246	40	/	/	SYM
10_1101-2021_01_02_425006	246	41	funder	funder	NN
10_1101-2021_01_02_425006	246	42	,	,	,
10_1101-2021_01_02_425006	246	43	who	who	WP
10_1101-2021_01_02_425006	246	44	has	have	VBZ
10_1101-2021_01_02_425006	246	45	granted	grant	VBN
10_1101-2021_01_02_425006	246	46	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	246	47	a	a	DT
10_1101-2021_01_02_425006	246	48	license	license	NN
10_1101-2021_01_02_425006	246	49	to	to	TO
10_1101-2021_01_02_425006	246	50	display	display	VB
10_1101-2021_01_02_425006	246	51	the	the	DT
10_1101-2021_01_02_425006	246	52	preprint	preprint	NN
10_1101-2021_01_02_425006	246	53	in	in	IN
10_1101-2021_01_02_425006	246	54	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	246	55	.	.	.
10_1101-2021_01_02_425006	247	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	247	2	is	be	VBZ
10_1101-2021_01_02_425006	247	3	made	make	VBN
10_1101-2021_01_02_425006	247	4	The	the	DT
10_1101-2021_01_02_425006	247	5	copyright	copyright	NN
10_1101-2021_01_02_425006	247	6	holder	holder	NN
10_1101-2021_01_02_425006	247	7	for	for	IN
10_1101-2021_01_02_425006	247	8	this	this	DT
10_1101-2021_01_02_425006	247	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	247	10	version	version	NN
10_1101-2021_01_02_425006	247	11	posted	post	VBD
10_1101-2021_01_02_425006	247	12	January	January	NNP
10_1101-2021_01_02_425006	247	13	6	6	CD
10_1101-2021_01_02_425006	247	14	,	,	,
10_1101-2021_01_02_425006	247	15	2021	2021	CD
10_1101-2021_01_02_425006	247	16	.	.	.
10_1101-2021_01_02_425006	247	17	;	;	:
10_1101-2021_01_02_425006	247	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	247	19	:	:	:
10_1101-2021_01_02_425006	247	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	247	21	preprint	preprint	NN
10_1101-2021_01_02_425006	247	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	247	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	247	24	22	22	CD
10_1101-2021_01_02_425006	247	25	distribution	distribution	NN
10_1101-2021_01_02_425006	247	26	of	of	IN
10_1101-2021_01_02_425006	247	27	�	�	NNP
10_1101-2021_01_02_425006	247	28	�	�	JJ
10_1101-2021_01_02_425006	247	29	�	�	NNS
10_1101-2021_01_02_425006	247	30	�	�	JJ
10_1101-2021_01_02_425006	247	31	�	�	NNP
10_1101-2021_01_02_425006	247	32	�	�	NNP
10_1101-2021_01_02_425006	247	33	,	,	,
10_1101-2021_01_02_425006	247	34	�	�	NNP
10_1101-2021_01_02_425006	247	35	�	�	NNP
10_1101-2021_01_02_425006	247	36	�	�	NNP
10_1101-2021_01_02_425006	247	37	was	be	VBD
10_1101-2021_01_02_425006	247	38	different	different	JJ
10_1101-2021_01_02_425006	247	39	for	for	IN
10_1101-2021_01_02_425006	247	40	the	the	DT
10_1101-2021_01_02_425006	247	41	type	type	NN
10_1101-2021_01_02_425006	247	42	-	-	:
10_1101-2021_01_02_425006	247	43	i	i	PRP
10_1101-2021_01_02_425006	247	44	gene	gene	VBP
10_1101-2021_01_02_425006	247	45	pairs	pair	NNS
10_1101-2021_01_02_425006	247	46	and	and	CC
10_1101-2021_01_02_425006	247	47	type	type	NNP
10_1101-2021_01_02_425006	247	48	-	-	HYPH
10_1101-2021_01_02_425006	247	49	ii	ii	NN
10_1101-2021_01_02_425006	247	50	gene	gene	NN
10_1101-2021_01_02_425006	247	51	pairs	pair	NNS
10_1101-2021_01_02_425006	247	52	.	.	.
10_1101-2021_01_02_425006	248	1	The	the	DT
10_1101-2021_01_02_425006	248	2	c	c	NNP
10_1101-2021_01_02_425006	248	3	�	�	,
10_1101-2021_01_02_425006	248	4	-371	-371	NN
10_1101-2021_01_02_425006	248	5	statistics	statistic	NNS
10_1101-2021_01_02_425006	248	6	corresponded	correspond	VBD
10_1101-2021_01_02_425006	248	7	to	to	IN
10_1101-2021_01_02_425006	248	8	a	a	DT
10_1101-2021_01_02_425006	248	9	P	p	NN
10_1101-2021_01_02_425006	248	10	-	-	HYPH
10_1101-2021_01_02_425006	248	11	value	value	NN
10_1101-2021_01_02_425006	248	12	less	less	JJR
10_1101-2021_01_02_425006	248	13	than	than	IN
10_1101-2021_01_02_425006	248	14	10	10	CD
10_1101-2021_01_02_425006	248	15	�	�	NNP
10_1101-2021_01_02_425006	248	16	�	�	NNP
10_1101-2021_01_02_425006	248	17	,	,	,
10_1101-2021_01_02_425006	248	18	which	which	WDT
10_1101-2021_01_02_425006	248	19	revealed	reveal	VBD
10_1101-2021_01_02_425006	248	20	that	that	IN
10_1101-2021_01_02_425006	248	21	the	the	DT
10_1101-2021_01_02_425006	248	22	distribution	distribution	NN
10_1101-2021_01_02_425006	248	23	of	of	IN
10_1101-2021_01_02_425006	248	24	�	�	NNP
10_1101-2021_01_02_425006	248	25	�	�	JJ
10_1101-2021_01_02_425006	248	26	�	�	NNS
10_1101-2021_01_02_425006	248	27	�	�	JJ
10_1101-2021_01_02_425006	248	28	�	�	NNP
10_1101-2021_01_02_425006	248	29	�	�	NNP
10_1101-2021_01_02_425006	248	30	,	,	,
10_1101-2021_01_02_425006	248	31	�	�	NNP
10_1101-2021_01_02_425006	248	32	�	�	NNP
10_1101-2021_01_02_425006	248	33	�	�	NNP
10_1101-2021_01_02_425006	248	34	372	372	CD
10_1101-2021_01_02_425006	248	35	for	for	IN
10_1101-2021_01_02_425006	248	36	the	the	DT
10_1101-2021_01_02_425006	248	37	type	type	NN
10_1101-2021_01_02_425006	248	38	-	-	HYPH
10_1101-2021_01_02_425006	248	39	ii	ii	NN
10_1101-2021_01_02_425006	248	40	gene	gene	NN
10_1101-2021_01_02_425006	248	41	pairs	pairs	NNP
10_1101-2021_01_02_425006	248	42	was	be	VBD
10_1101-2021_01_02_425006	248	43	significantly	significantly	RB
10_1101-2021_01_02_425006	248	44	different	different	JJ
10_1101-2021_01_02_425006	248	45	from	from	IN
10_1101-2021_01_02_425006	248	46	the	the	DT
10_1101-2021_01_02_425006	248	47	type	type	NN
10_1101-2021_01_02_425006	248	48	-	-	:
10_1101-2021_01_02_425006	248	49	i	i	PRP
10_1101-2021_01_02_425006	248	50	gene	gene	NN
10_1101-2021_01_02_425006	248	51	pairs	pair	NNS
10_1101-2021_01_02_425006	248	52	.	.	.
10_1101-2021_01_02_425006	249	1	Fig	fig	NN
10_1101-2021_01_02_425006	249	2	.	.	.
10_1101-2021_01_02_425006	250	1	7B	7B	NNP
10_1101-2021_01_02_425006	250	2	shows	show	VBZ
10_1101-2021_01_02_425006	250	3	the	the	DT
10_1101-2021_01_02_425006	250	4	373	373	CD
10_1101-2021_01_02_425006	250	5	distribution	distribution	NN
10_1101-2021_01_02_425006	250	6	of	of	IN
10_1101-2021_01_02_425006	250	7	�	�	NNP
10_1101-2021_01_02_425006	250	8	�	�	JJ
10_1101-2021_01_02_425006	250	9	�	�	NNS
10_1101-2021_01_02_425006	250	10	�	�	JJ
10_1101-2021_01_02_425006	250	11	�	�	NNP
10_1101-2021_01_02_425006	250	12	�	�	NNP
10_1101-2021_01_02_425006	250	13	,	,	,
10_1101-2021_01_02_425006	250	14	�	�	NNP
10_1101-2021_01_02_425006	250	15	�	�	ADD
10_1101-2021_01_02_425006	250	16	�	�	NNP
10_1101-2021_01_02_425006	250	17	for	for	IN
10_1101-2021_01_02_425006	250	18	the	the	DT
10_1101-2021_01_02_425006	250	19	type	type	NN
10_1101-2021_01_02_425006	250	20	-	-	:
10_1101-2021_01_02_425006	250	21	i	i	PRP
10_1101-2021_01_02_425006	250	22	gene	gene	VBP
10_1101-2021_01_02_425006	250	23	pairs	pair	NNS
10_1101-2021_01_02_425006	250	24	and	and	CC
10_1101-2021_01_02_425006	250	25	the	the	DT
10_1101-2021_01_02_425006	250	26	type	type	NN
10_1101-2021_01_02_425006	250	27	-	-	HYPH
10_1101-2021_01_02_425006	250	28	ii	ii	NN
10_1101-2021_01_02_425006	250	29	gene	gene	NN
10_1101-2021_01_02_425006	250	30	pairs	pair	NNS
10_1101-2021_01_02_425006	250	31	.	.	.
10_1101-2021_01_02_425006	251	1	These	these	DT
10_1101-2021_01_02_425006	251	2	results	result	NNS
10_1101-2021_01_02_425006	251	3	strongly	strongly	RB
10_1101-2021_01_02_425006	251	4	374	374	CD
10_1101-2021_01_02_425006	251	5	indicated	indicate	VBD
10_1101-2021_01_02_425006	251	6	that	that	IN
10_1101-2021_01_02_425006	251	7	the	the	DT
10_1101-2021_01_02_425006	251	8	type	type	NN
10_1101-2021_01_02_425006	251	9	-	-	HYPH
10_1101-2021_01_02_425006	251	10	ii	ii	NN
10_1101-2021_01_02_425006	251	11	gene	gene	NN
10_1101-2021_01_02_425006	251	12	pairs	pair	NNS
10_1101-2021_01_02_425006	251	13	had	have	VBD
10_1101-2021_01_02_425006	251	14	a	a	DT
10_1101-2021_01_02_425006	251	15	higher	high	JJR
10_1101-2021_01_02_425006	251	16	degree	degree	NN
10_1101-2021_01_02_425006	251	17	of	of	IN
10_1101-2021_01_02_425006	251	18	GO	GO	NNP
10_1101-2021_01_02_425006	251	19	similarity	similarity	NN
10_1101-2021_01_02_425006	251	20	than	than	IN
10_1101-2021_01_02_425006	251	21	the	the	DT
10_1101-2021_01_02_425006	251	22	type	type	NN
10_1101-2021_01_02_425006	251	23	-	-	:
10_1101-2021_01_02_425006	251	24	i	i	PRP
10_1101-2021_01_02_425006	251	25	gene	gene	NN
10_1101-2021_01_02_425006	251	26	pairs	pair	NNS
10_1101-2021_01_02_425006	251	27	,	,	,
10_1101-2021_01_02_425006	251	28	375	375	CD
10_1101-2021_01_02_425006	251	29	suggesting	suggest	VBG
10_1101-2021_01_02_425006	251	30	that	that	IN
10_1101-2021_01_02_425006	251	31	the	the	DT
10_1101-2021_01_02_425006	251	32	gene	gene	NN
10_1101-2021_01_02_425006	251	33	pairs	pair	NNS
10_1101-2021_01_02_425006	251	34	frequently	frequently	RB
10_1101-2021_01_02_425006	251	35	encoded	encode	VBN
10_1101-2021_01_02_425006	251	36	in	in	IN
10_1101-2021_01_02_425006	251	37	the	the	DT
10_1101-2021_01_02_425006	251	38	same	same	JJ
10_1101-2021_01_02_425006	251	39	ATUs	atu	NNS
10_1101-2021_01_02_425006	251	40	(	(	-LRB-
10_1101-2021_01_02_425006	251	41	type	type	NN
10_1101-2021_01_02_425006	251	42	-	-	HYPH
10_1101-2021_01_02_425006	251	43	ii	ii	NN
10_1101-2021_01_02_425006	251	44	gene	gene	NN
10_1101-2021_01_02_425006	251	45	pairs	pairs	NNP
10_1101-2021_01_02_425006	251	46	)	)	-RRB-
10_1101-2021_01_02_425006	251	47	are	be	VBP
10_1101-2021_01_02_425006	251	48	more	more	RBR
10_1101-2021_01_02_425006	251	49	376	376	CD
10_1101-2021_01_02_425006	251	50	functionally	functionally	RB
10_1101-2021_01_02_425006	251	51	related	relate	VBN
10_1101-2021_01_02_425006	251	52	than	than	IN
10_1101-2021_01_02_425006	251	53	those	those	DT
10_1101-2021_01_02_425006	251	54	that	that	WDT
10_1101-2021_01_02_425006	251	55	can	can	MD
10_1101-2021_01_02_425006	251	56	belong	belong	VB
10_1101-2021_01_02_425006	251	57	to	to	IN
10_1101-2021_01_02_425006	251	58	two	two	CD
10_1101-2021_01_02_425006	251	59	distinct	distinct	JJ
10_1101-2021_01_02_425006	251	60	ATUs	atu	NNS
10_1101-2021_01_02_425006	251	61	(	(	-LRB-
10_1101-2021_01_02_425006	251	62	type	type	NN
10_1101-2021_01_02_425006	251	63	-	-	:
10_1101-2021_01_02_425006	251	64	i	i	PRP
10_1101-2021_01_02_425006	251	65	gene	gene	VBP
10_1101-2021_01_02_425006	251	66	pairs	pair	NNS
10_1101-2021_01_02_425006	251	67	)	)	-RRB-
10_1101-2021_01_02_425006	251	68	.	.	.
10_1101-2021_01_02_425006	252	1	377	377	CD
10_1101-2021_01_02_425006	252	2	We	-PRON-	PRP
10_1101-2021_01_02_425006	252	3	also	also	RB
10_1101-2021_01_02_425006	252	4	carried	carry	VBD
10_1101-2021_01_02_425006	252	5	out	out	RP
10_1101-2021_01_02_425006	252	6	a	a	DT
10_1101-2021_01_02_425006	252	7	similar	similar	JJ
10_1101-2021_01_02_425006	252	8	analysis	analysis	NN
10_1101-2021_01_02_425006	252	9	of	of	IN
10_1101-2021_01_02_425006	252	10	the	the	DT
10_1101-2021_01_02_425006	252	11	two	two	CD
10_1101-2021_01_02_425006	252	12	different	different	JJ
10_1101-2021_01_02_425006	252	13	gene	gene	NN
10_1101-2021_01_02_425006	252	14	pairs	pair	NNS
10_1101-2021_01_02_425006	252	15	based	base	VBN
10_1101-2021_01_02_425006	252	16	on	on	IN
10_1101-2021_01_02_425006	252	17	KEGG	KEGG	NNP
10_1101-2021_01_02_425006	252	18	enrichment	enrichment	NN
10_1101-2021_01_02_425006	252	19	378	378	CD
10_1101-2021_01_02_425006	252	20	analysis	analysis	NN
10_1101-2021_01_02_425006	252	21	(	(	-LRB-
10_1101-2021_01_02_425006	252	22	see	see	VB
10_1101-2021_01_02_425006	252	23	more	more	JJR
10_1101-2021_01_02_425006	252	24	details	detail	NNS
10_1101-2021_01_02_425006	252	25	in	in	IN
10_1101-2021_01_02_425006	252	26	method	method	NN
10_1101-2021_01_02_425006	252	27	S9	s9	NN
10_1101-2021_01_02_425006	252	28	)	)	-RRB-
10_1101-2021_01_02_425006	252	29	and	and	CC
10_1101-2021_01_02_425006	252	30	found	find	VBD
10_1101-2021_01_02_425006	252	31	that	that	IN
10_1101-2021_01_02_425006	252	32	the	the	DT
10_1101-2021_01_02_425006	252	33	proportion	proportion	NN
10_1101-2021_01_02_425006	252	34	of	of	IN
10_1101-2021_01_02_425006	252	35	type	type	NN
10_1101-2021_01_02_425006	252	36	-	-	HYPH
10_1101-2021_01_02_425006	252	37	ii	ii	NN
10_1101-2021_01_02_425006	252	38	gene	gene	NN
10_1101-2021_01_02_425006	252	39	pairs	pair	NNS
10_1101-2021_01_02_425006	252	40	(	(	-LRB-
10_1101-2021_01_02_425006	252	41	59%/57	59%/57	CD
10_1101-2021_01_02_425006	252	42	%	%	NN
10_1101-2021_01_02_425006	252	43	379	379	CD
10_1101-2021_01_02_425006	252	44	for	for	IN
10_1101-2021_01_02_425006	252	45	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	252	46	/	/	SYM
10_1101-2021_01_02_425006	252	47	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	252	48	)	)	-RRB-
10_1101-2021_01_02_425006	252	49	,	,	,
10_1101-2021_01_02_425006	252	50	whose	whose	WP$
10_1101-2021_01_02_425006	252	51	two	two	CD
10_1101-2021_01_02_425006	252	52	genes	gene	NNS
10_1101-2021_01_02_425006	252	53	were	be	VBD
10_1101-2021_01_02_425006	252	54	contained	contain	VBN
10_1101-2021_01_02_425006	252	55	in	in	IN
10_1101-2021_01_02_425006	252	56	the	the	DT
10_1101-2021_01_02_425006	252	57	same	same	JJ
10_1101-2021_01_02_425006	252	58	KEGG	KEGG	NNP
10_1101-2021_01_02_425006	252	59	pathway	pathway	NN
10_1101-2021_01_02_425006	252	60	,	,	,
10_1101-2021_01_02_425006	252	61	was	be	VBD
10_1101-2021_01_02_425006	252	62	380	380	CD
10_1101-2021_01_02_425006	252	63	higher	high	JJR
10_1101-2021_01_02_425006	252	64	than	than	IN
10_1101-2021_01_02_425006	252	65	the	the	DT
10_1101-2021_01_02_425006	252	66	proportion	proportion	NN
10_1101-2021_01_02_425006	252	67	of	of	IN
10_1101-2021_01_02_425006	252	68	type	type	NN
10_1101-2021_01_02_425006	252	69	-	-	:
10_1101-2021_01_02_425006	252	70	i	i	PRP
10_1101-2021_01_02_425006	252	71	gene	gene	NN
10_1101-2021_01_02_425006	252	72	pairs	pair	NNS
10_1101-2021_01_02_425006	252	73	(	(	-LRB-
10_1101-2021_01_02_425006	252	74	32%/28	32%/28	CD
10_1101-2021_01_02_425006	252	75	%	%	NN
10_1101-2021_01_02_425006	252	76	for	for	IN
10_1101-2021_01_02_425006	252	77	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	252	78	/	/	SYM
10_1101-2021_01_02_425006	252	79	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	252	80	)	)	-RRB-
10_1101-2021_01_02_425006	252	81	(	(	-LRB-
10_1101-2021_01_02_425006	252	82	Fig	fig	NN
10_1101-2021_01_02_425006	252	83	.	.	.
10_1101-2021_01_02_425006	253	1	7C	7C	NNP
10_1101-2021_01_02_425006	253	2	)	)	-RRB-
10_1101-2021_01_02_425006	253	3	.	.	.
10_1101-2021_01_02_425006	254	1	381	381	CD
10_1101-2021_01_02_425006	254	2	The	the	DT
10_1101-2021_01_02_425006	254	3	distribution	distribution	NN
10_1101-2021_01_02_425006	254	4	of	of	IN
10_1101-2021_01_02_425006	254	5	the	the	DT
10_1101-2021_01_02_425006	254	6	KEGG	KEGG	NNP
10_1101-2021_01_02_425006	254	7	similarity	similarity	NN
10_1101-2021_01_02_425006	254	8	scores	score	NNS
10_1101-2021_01_02_425006	254	9	of	of	IN
10_1101-2021_01_02_425006	254	10	the	the	DT
10_1101-2021_01_02_425006	254	11	two	two	CD
10_1101-2021_01_02_425006	254	12	different	different	JJ
10_1101-2021_01_02_425006	254	13	types	type	NNS
10_1101-2021_01_02_425006	254	14	of	of	IN
10_1101-2021_01_02_425006	254	15	gene	gene	NN
10_1101-2021_01_02_425006	254	16	pairs	pair	NNS
10_1101-2021_01_02_425006	254	17	is	be	VBZ
10_1101-2021_01_02_425006	254	18	shown	show	VBN
10_1101-2021_01_02_425006	254	19	in	in	IN
10_1101-2021_01_02_425006	254	20	Fig	Fig	NNP
10_1101-2021_01_02_425006	254	21	.	.	.
10_1101-2021_01_02_425006	255	1	382	382	CD
10_1101-2021_01_02_425006	255	2	7D	7D	NNS
10_1101-2021_01_02_425006	255	3	,	,	,
10_1101-2021_01_02_425006	255	4	suggesting	suggest	VBG
10_1101-2021_01_02_425006	255	5	that	that	IN
10_1101-2021_01_02_425006	255	6	genes	gene	NNS
10_1101-2021_01_02_425006	255	7	of	of	IN
10_1101-2021_01_02_425006	255	8	type	type	NN
10_1101-2021_01_02_425006	255	9	-	-	HYPH
10_1101-2021_01_02_425006	255	10	ii	ii	NN
10_1101-2021_01_02_425006	255	11	gene	gene	NN
10_1101-2021_01_02_425006	255	12	pairs	pair	NNS
10_1101-2021_01_02_425006	255	13	have	have	VBP
10_1101-2021_01_02_425006	255	14	a	a	DT
10_1101-2021_01_02_425006	255	15	higher	high	JJR
10_1101-2021_01_02_425006	255	16	probability	probability	NN
10_1101-2021_01_02_425006	255	17	of	of	IN
10_1101-2021_01_02_425006	255	18	participating	participate	VBG
10_1101-2021_01_02_425006	255	19	in	in	IN
10_1101-2021_01_02_425006	255	20	the	the	DT
10_1101-2021_01_02_425006	255	21	same	same	JJ
10_1101-2021_01_02_425006	255	22	383	383	CD
10_1101-2021_01_02_425006	255	23	KEGG	KEGG	NNP
10_1101-2021_01_02_425006	255	24	pathway	pathway	NN
10_1101-2021_01_02_425006	255	25	than	than	IN
10_1101-2021_01_02_425006	255	26	those	those	DT
10_1101-2021_01_02_425006	255	27	of	of	IN
10_1101-2021_01_02_425006	255	28	type	type	NN
10_1101-2021_01_02_425006	255	29	-	-	:
10_1101-2021_01_02_425006	255	30	i	i	PRP
10_1101-2021_01_02_425006	255	31	gene	gene	NN
10_1101-2021_01_02_425006	255	32	pairs	pair	NNS
10_1101-2021_01_02_425006	255	33	.	.	.
10_1101-2021_01_02_425006	256	1	384	384	CD
10_1101-2021_01_02_425006	256	2	Please	please	UH
10_1101-2021_01_02_425006	256	3	place	place	VB
10_1101-2021_01_02_425006	256	4	Fig	Fig	NNP
10_1101-2021_01_02_425006	256	5	.	.	.
10_1101-2021_01_02_425006	257	1	7	7	CD
10_1101-2021_01_02_425006	257	2	here	here	RB
10_1101-2021_01_02_425006	257	3	.	.	.
10_1101-2021_01_02_425006	258	1	385	385	CD
10_1101-2021_01_02_425006	258	2	DISCUSSION	discussion	NN
10_1101-2021_01_02_425006	258	3	386	386	CD
10_1101-2021_01_02_425006	258	4	We	-PRON-	PRP
10_1101-2021_01_02_425006	258	5	developed	develop	VBD
10_1101-2021_01_02_425006	258	6	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	258	7	,	,	,
10_1101-2021_01_02_425006	258	8	the	the	DT
10_1101-2021_01_02_425006	258	9	first	first	JJ
10_1101-2021_01_02_425006	258	10	computational	computational	JJ
10_1101-2021_01_02_425006	258	11	method	method	NN
10_1101-2021_01_02_425006	258	12	for	for	IN
10_1101-2021_01_02_425006	258	13	genome	genome	NN
10_1101-2021_01_02_425006	258	14	-	-	HYPH
10_1101-2021_01_02_425006	258	15	scale	scale	NN
10_1101-2021_01_02_425006	258	16	ATU	ATU	NNP
10_1101-2021_01_02_425006	258	17	prediction	prediction	NN
10_1101-2021_01_02_425006	258	18	by	by	IN
10_1101-2021_01_02_425006	258	19	analyzing	analyze	VBG
10_1101-2021_01_02_425006	258	20	387	387	CD
10_1101-2021_01_02_425006	258	21	next-	next-	JJ
10_1101-2021_01_02_425006	258	22	and	and	CC
10_1101-2021_01_02_425006	258	23	third	third	JJ
10_1101-2021_01_02_425006	258	24	-	-	HYPH
10_1101-2021_01_02_425006	258	25	generation	generation	NN
10_1101-2021_01_02_425006	258	26	RNA	RNA	NNP
10_1101-2021_01_02_425006	258	27	-	-	HYPH
10_1101-2021_01_02_425006	258	28	Seq	Seq	NNP
10_1101-2021_01_02_425006	258	29	data	datum	NNS
10_1101-2021_01_02_425006	258	30	,	,	,
10_1101-2021_01_02_425006	258	31	using	use	VBG
10_1101-2021_01_02_425006	258	32	a	a	DT
10_1101-2021_01_02_425006	258	33	CQP	CQP	NNP
10_1101-2021_01_02_425006	258	34	model	model	NN
10_1101-2021_01_02_425006	258	35	.	.	.
10_1101-2021_01_02_425006	259	1	Linear	linear	JJ
10_1101-2021_01_02_425006	259	2	constraints	constraint	NNS
10_1101-2021_01_02_425006	259	3	provided	provide	VBN
10_1101-2021_01_02_425006	259	4	by	by	IN
10_1101-2021_01_02_425006	259	5	the	the	DT
10_1101-2021_01_02_425006	259	6	bias	bias	NN
10_1101-2021_01_02_425006	259	7	388	388	CD
10_1101-2021_01_02_425006	259	8	.CC	.CC	:
10_1101-2021_01_02_425006	259	9	-	-	HYPH
10_1101-2021_01_02_425006	259	10	BY	by	IN
10_1101-2021_01_02_425006	259	11	-	-	HYPH
10_1101-2021_01_02_425006	259	12	NC	NC	NNP
10_1101-2021_01_02_425006	259	13	-	-	HYPH
10_1101-2021_01_02_425006	259	14	ND	ND	NNP
10_1101-2021_01_02_425006	259	15	4.0	4.0	CD
10_1101-2021_01_02_425006	259	16	International	International	NNP
10_1101-2021_01_02_425006	259	17	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	259	18	under	under	IN
10_1101-2021_01_02_425006	259	19	a	a	DT
10_1101-2021_01_02_425006	259	20	(	(	-LRB-
10_1101-2021_01_02_425006	259	21	which	which	WDT
10_1101-2021_01_02_425006	259	22	was	be	VBD
10_1101-2021_01_02_425006	259	23	not	not	RB
10_1101-2021_01_02_425006	259	24	certified	certify	VBN
10_1101-2021_01_02_425006	259	25	by	by	IN
10_1101-2021_01_02_425006	259	26	peer	peer	NN
10_1101-2021_01_02_425006	259	27	review	review	NN
10_1101-2021_01_02_425006	259	28	)	)	-RRB-
10_1101-2021_01_02_425006	259	29	is	be	VBZ
10_1101-2021_01_02_425006	259	30	the	the	DT
10_1101-2021_01_02_425006	259	31	author	author	NN
10_1101-2021_01_02_425006	259	32	/	/	SYM
10_1101-2021_01_02_425006	259	33	funder	funder	NN
10_1101-2021_01_02_425006	259	34	,	,	,
10_1101-2021_01_02_425006	259	35	who	who	WP
10_1101-2021_01_02_425006	259	36	has	have	VBZ
10_1101-2021_01_02_425006	259	37	granted	grant	VBN
10_1101-2021_01_02_425006	259	38	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	259	39	a	a	DT
10_1101-2021_01_02_425006	259	40	license	license	NN
10_1101-2021_01_02_425006	259	41	to	to	TO
10_1101-2021_01_02_425006	259	42	display	display	VB
10_1101-2021_01_02_425006	259	43	the	the	DT
10_1101-2021_01_02_425006	259	44	preprint	preprint	NN
10_1101-2021_01_02_425006	259	45	in	in	IN
10_1101-2021_01_02_425006	259	46	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	259	47	.	.	.
10_1101-2021_01_02_425006	260	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	260	2	is	be	VBZ
10_1101-2021_01_02_425006	260	3	made	make	VBN
10_1101-2021_01_02_425006	260	4	The	the	DT
10_1101-2021_01_02_425006	260	5	copyright	copyright	NN
10_1101-2021_01_02_425006	260	6	holder	holder	NN
10_1101-2021_01_02_425006	260	7	for	for	IN
10_1101-2021_01_02_425006	260	8	this	this	DT
10_1101-2021_01_02_425006	260	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	260	10	version	version	NN
10_1101-2021_01_02_425006	260	11	posted	post	VBD
10_1101-2021_01_02_425006	260	12	January	January	NNP
10_1101-2021_01_02_425006	260	13	6	6	CD
10_1101-2021_01_02_425006	260	14	,	,	,
10_1101-2021_01_02_425006	260	15	2021	2021	CD
10_1101-2021_01_02_425006	260	16	.	.	.
10_1101-2021_01_02_425006	260	17	;	;	:
10_1101-2021_01_02_425006	260	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	260	19	:	:	:
10_1101-2021_01_02_425006	260	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	260	21	preprint	preprint	NN
10_1101-2021_01_02_425006	260	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	260	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	260	24	23	23	CD
10_1101-2021_01_02_425006	260	25	rate	rate	NN
10_1101-2021_01_02_425006	260	26	of	of	IN
10_1101-2021_01_02_425006	260	27	read	read	VBN
10_1101-2021_01_02_425006	260	28	distribution	distribution	NN
10_1101-2021_01_02_425006	260	29	were	be	VBD
10_1101-2021_01_02_425006	260	30	,	,	,
10_1101-2021_01_02_425006	260	31	for	for	IN
10_1101-2021_01_02_425006	260	32	the	the	DT
10_1101-2021_01_02_425006	260	33	first	first	JJ
10_1101-2021_01_02_425006	260	34	time	time	NN
10_1101-2021_01_02_425006	260	35	,	,	,
10_1101-2021_01_02_425006	260	36	integrated	integrate	VBN
10_1101-2021_01_02_425006	260	37	into	into	IN
10_1101-2021_01_02_425006	260	38	the	the	DT
10_1101-2021_01_02_425006	260	39	CQP	CQP	NNP
10_1101-2021_01_02_425006	260	40	model	model	NN
10_1101-2021_01_02_425006	260	41	.	.	.
10_1101-2021_01_02_425006	261	1	Positional	positional	JJ
10_1101-2021_01_02_425006	261	2	bias	bias	NN
10_1101-2021_01_02_425006	261	3	refers	refer	VBZ
10_1101-2021_01_02_425006	261	4	to	to	IN
10_1101-2021_01_02_425006	261	5	389	389	CD
10_1101-2021_01_02_425006	261	6	the	the	DT
10_1101-2021_01_02_425006	261	7	non	non	JJ
10_1101-2021_01_02_425006	261	8	-	-	JJ
10_1101-2021_01_02_425006	261	9	uniform	uniform	JJ
10_1101-2021_01_02_425006	261	10	distribution	distribution	NN
10_1101-2021_01_02_425006	261	11	of	of	IN
10_1101-2021_01_02_425006	261	12	reads	read	NNS
10_1101-2021_01_02_425006	261	13	over	over	IN
10_1101-2021_01_02_425006	261	14	different	different	JJ
10_1101-2021_01_02_425006	261	15	positions	position	NNS
10_1101-2021_01_02_425006	261	16	of	of	IN
10_1101-2021_01_02_425006	261	17	a	a	DT
10_1101-2021_01_02_425006	261	18	transcript	transcript	NN
10_1101-2021_01_02_425006	261	19	(	(	-LRB-
10_1101-2021_01_02_425006	261	20	33	33	CD
10_1101-2021_01_02_425006	261	21	,	,	,
10_1101-2021_01_02_425006	261	22	35	35	CD
10_1101-2021_01_02_425006	261	23	)	)	-RRB-
10_1101-2021_01_02_425006	261	24	,	,	,
10_1101-2021_01_02_425006	261	25	which	which	WDT
10_1101-2021_01_02_425006	261	26	is	be	VBZ
10_1101-2021_01_02_425006	261	27	handled	handle	VBN
10_1101-2021_01_02_425006	261	28	390	390	CD
10_1101-2021_01_02_425006	261	29	by	by	IN
10_1101-2021_01_02_425006	261	30	learning	learn	VBG
10_1101-2021_01_02_425006	261	31	non	non	JJ
10_1101-2021_01_02_425006	261	32	-	-	JJ
10_1101-2021_01_02_425006	261	33	uniform	uniform	JJ
10_1101-2021_01_02_425006	261	34	read	read	VB
10_1101-2021_01_02_425006	261	35	distributions	distribution	NNS
10_1101-2021_01_02_425006	261	36	from	from	IN
10_1101-2021_01_02_425006	261	37	given	give	VBN
10_1101-2021_01_02_425006	261	38	RNA	RNA	NNP
10_1101-2021_01_02_425006	261	39	-	-	HYPH
10_1101-2021_01_02_425006	261	40	Seq	Seq	NNP
10_1101-2021_01_02_425006	261	41	reads	read	VBZ
10_1101-2021_01_02_425006	261	42	(	(	-LRB-
10_1101-2021_01_02_425006	261	43	32	32	CD
10_1101-2021_01_02_425006	261	44	)	)	-RRB-
10_1101-2021_01_02_425006	261	45	or	or	CC
10_1101-2021_01_02_425006	261	46	modeling	model	VBG
10_1101-2021_01_02_425006	261	47	the	the	DT
10_1101-2021_01_02_425006	261	48	RNA	RNA	NNP
10_1101-2021_01_02_425006	261	49	391	391	CD
10_1101-2021_01_02_425006	261	50	degradation	degradation	NN
10_1101-2021_01_02_425006	261	51	(	(	-LRB-
10_1101-2021_01_02_425006	261	52	45	45	CD
10_1101-2021_01_02_425006	261	53	)	)	-RRB-
10_1101-2021_01_02_425006	261	54	.	.	.
10_1101-2021_01_02_425006	262	1	The	the	DT
10_1101-2021_01_02_425006	262	2	bias	bias	NN
10_1101-2021_01_02_425006	262	3	rate	rate	NN
10_1101-2021_01_02_425006	262	4	function	function	NN
10_1101-2021_01_02_425006	262	5	we	-PRON-	PRP
10_1101-2021_01_02_425006	262	6	proposed	propose	VBD
10_1101-2021_01_02_425006	262	7	can	can	MD
10_1101-2021_01_02_425006	262	8	address	address	VB
10_1101-2021_01_02_425006	262	9	the	the	DT
10_1101-2021_01_02_425006	262	10	non	non	JJ
10_1101-2021_01_02_425006	262	11	-	-	JJ
10_1101-2021_01_02_425006	262	12	uniform	uniform	JJ
10_1101-2021_01_02_425006	262	13	read	read	VBD
10_1101-2021_01_02_425006	262	14	distribution	distribution	NN
10_1101-2021_01_02_425006	262	15	392	392	CD
10_1101-2021_01_02_425006	262	16	along	along	IN
10_1101-2021_01_02_425006	262	17	mRNA	mRNA	NNS
10_1101-2021_01_02_425006	262	18	transcripts	transcript	NNS
10_1101-2021_01_02_425006	262	19	and	and	CC
10_1101-2021_01_02_425006	262	20	also	also	RB
10_1101-2021_01_02_425006	262	21	be	be	VB
10_1101-2021_01_02_425006	262	22	desirable	desirable	JJ
10_1101-2021_01_02_425006	262	23	for	for	IN
10_1101-2021_01_02_425006	262	24	standard	standard	JJ
10_1101-2021_01_02_425006	262	25	next	next	JJ
10_1101-2021_01_02_425006	262	26	-	-	HYPH
10_1101-2021_01_02_425006	262	27	generation	generation	NN
10_1101-2021_01_02_425006	262	28	RNA	RNA	NNP
10_1101-2021_01_02_425006	262	29	-	-	HYPH
10_1101-2021_01_02_425006	262	30	Seq	Seq	NNP
10_1101-2021_01_02_425006	262	31	data	datum	NNS
10_1101-2021_01_02_425006	262	32	that	that	WDT
10_1101-2021_01_02_425006	262	33	involves	involve	VBZ
10_1101-2021_01_02_425006	262	34	393	393	CD
10_1101-2021_01_02_425006	262	35	more	more	RBR
10_1101-2021_01_02_425006	262	36	degraded	degraded	JJ
10_1101-2021_01_02_425006	262	37	mRNAs	mrnas	ADD
10_1101-2021_01_02_425006	262	38	,	,	,
10_1101-2021_01_02_425006	262	39	as	as	IN
10_1101-2021_01_02_425006	262	40	the	the	DT
10_1101-2021_01_02_425006	262	41	exponential	exponential	JJ
10_1101-2021_01_02_425006	262	42	function	function	NN
10_1101-2021_01_02_425006	262	43	has	have	VBZ
10_1101-2021_01_02_425006	262	44	been	be	VBN
10_1101-2021_01_02_425006	262	45	used	use	VBN
10_1101-2021_01_02_425006	262	46	to	to	TO
10_1101-2021_01_02_425006	262	47	model	model	VB
10_1101-2021_01_02_425006	262	48	the	the	DT
10_1101-2021_01_02_425006	262	49	degradation	degradation	NN
10_1101-2021_01_02_425006	262	50	of	of	IN
10_1101-2021_01_02_425006	262	51	mRNA	mRNA	NNP
10_1101-2021_01_02_425006	262	52	394	394	CD
10_1101-2021_01_02_425006	262	53	transcripts	transcript	NNS
10_1101-2021_01_02_425006	262	54	(	(	-LRB-
10_1101-2021_01_02_425006	262	55	45	45	CD
10_1101-2021_01_02_425006	262	56	)	)	-RRB-
10_1101-2021_01_02_425006	262	57	.	.	.
10_1101-2021_01_02_425006	263	1	As	as	IN
10_1101-2021_01_02_425006	263	2	a	a	DT
10_1101-2021_01_02_425006	263	3	result	result	NN
10_1101-2021_01_02_425006	263	4	,	,	,
10_1101-2021_01_02_425006	263	5	a	a	DT
10_1101-2021_01_02_425006	263	6	total	total	NN
10_1101-2021_01_02_425006	263	7	of	of	IN
10_1101-2021_01_02_425006	263	8	2,973	2,973	CD
10_1101-2021_01_02_425006	263	9	distinct	distinct	JJ
10_1101-2021_01_02_425006	263	10	ATUs	atu	NNS
10_1101-2021_01_02_425006	263	11	for	for	IN
10_1101-2021_01_02_425006	263	12	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	263	13	and	and	CC
10_1101-2021_01_02_425006	263	14	2,767	2,767	CD
10_1101-2021_01_02_425006	263	15	distinct	distinct	JJ
10_1101-2021_01_02_425006	263	16	ATUs	atu	NNS
10_1101-2021_01_02_425006	263	17	395	395	CD
10_1101-2021_01_02_425006	263	18	for	for	IN
10_1101-2021_01_02_425006	263	19	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	263	20	were	be	VBD
10_1101-2021_01_02_425006	263	21	identified	identify	VBN
10_1101-2021_01_02_425006	263	22	by	by	IN
10_1101-2021_01_02_425006	263	23	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	263	24	.	.	.
10_1101-2021_01_02_425006	264	1	The	the	DT
10_1101-2021_01_02_425006	264	2	precision	precision	NN
10_1101-2021_01_02_425006	264	3	and	and	CC
10_1101-2021_01_02_425006	264	4	recall	recall	NN
10_1101-2021_01_02_425006	264	5	reached	reach	VBD
10_1101-2021_01_02_425006	264	6	0.67/0.64	0.67/0.64	NNP
10_1101-2021_01_02_425006	264	7	and	and	CC
10_1101-2021_01_02_425006	264	8	0.67/0.68	0.67/0.68	NN
10_1101-2021_01_02_425006	264	9	,	,	,
10_1101-2021_01_02_425006	264	10	396	396	CD
10_1101-2021_01_02_425006	264	11	respectively	respectively	RB
10_1101-2021_01_02_425006	264	12	,	,	,
10_1101-2021_01_02_425006	264	13	based	base	VBN
10_1101-2021_01_02_425006	264	14	on	on	IN
10_1101-2021_01_02_425006	264	15	perfect	perfect	JJ
10_1101-2021_01_02_425006	264	16	matching	matching	NN
10_1101-2021_01_02_425006	264	17	and	and	CC
10_1101-2021_01_02_425006	264	18	0.77/0.74	0.77/0.74	NN
10_1101-2021_01_02_425006	264	19	and	and	CC
10_1101-2021_01_02_425006	264	20	0.75/0.76	0.75/0.76	NN
10_1101-2021_01_02_425006	264	21	,	,	,
10_1101-2021_01_02_425006	264	22	respectively	respectively	RB
10_1101-2021_01_02_425006	264	23	,	,	,
10_1101-2021_01_02_425006	264	24	based	base	VBN
10_1101-2021_01_02_425006	264	25	on	on	IN
10_1101-2021_01_02_425006	264	26	relaxed	relaxed	JJ
10_1101-2021_01_02_425006	264	27	397	397	CD
10_1101-2021_01_02_425006	264	28	matching	match	VBG
10_1101-2021_01_02_425006	264	29	for	for	IN
10_1101-2021_01_02_425006	264	30	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	264	31	/	/	SYM
10_1101-2021_01_02_425006	264	32	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	264	33	.	.	.
10_1101-2021_01_02_425006	265	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	265	2	further	further	RB
10_1101-2021_01_02_425006	265	3	validated	validate	VBD
10_1101-2021_01_02_425006	265	4	predicted	predict	VBD
10_1101-2021_01_02_425006	265	5	ATUs	atu	NNS
10_1101-2021_01_02_425006	265	6	using	use	VBG
10_1101-2021_01_02_425006	265	7	experimental	experimental	JJ
10_1101-2021_01_02_425006	265	8	398	398	CD
10_1101-2021_01_02_425006	265	9	transcription	transcription	NN
10_1101-2021_01_02_425006	265	10	factor	factor	NN
10_1101-2021_01_02_425006	265	11	binding	bind	VBG
10_1101-2021_01_02_425006	265	12	sites	site	NNS
10_1101-2021_01_02_425006	265	13	or	or	CC
10_1101-2021_01_02_425006	265	14	transcription	transcription	NN
10_1101-2021_01_02_425006	265	15	termination	termination	NN
10_1101-2021_01_02_425006	265	16	sites	site	NNS
10_1101-2021_01_02_425006	265	17	from	from	IN
10_1101-2021_01_02_425006	265	18	RegulonDB	regulondb	NN
10_1101-2021_01_02_425006	265	19	and	and	CC
10_1101-2021_01_02_425006	265	20	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	265	21	-	-	HYPH
10_1101-2021_01_02_425006	265	22	Seq	Seq	NNP
10_1101-2021_01_02_425006	265	23	.	.	.
10_1101-2021_01_02_425006	266	1	In	in	IN
10_1101-2021_01_02_425006	266	2	399	399	CD
10_1101-2021_01_02_425006	266	3	addition	addition	NN
10_1101-2021_01_02_425006	266	4	,	,	,
10_1101-2021_01_02_425006	266	5	the	the	DT
10_1101-2021_01_02_425006	266	6	proportion	proportion	NN
10_1101-2021_01_02_425006	266	7	of	of	IN
10_1101-2021_01_02_425006	266	8	the	the	DT
10_1101-2021_01_02_425006	266	9	5’-	5’-	CD
10_1101-2021_01_02_425006	266	10	or	or	CC
10_1101-2021_01_02_425006	266	11	3’-end	3’-end	CD
10_1101-2021_01_02_425006	266	12	genes	gene	NNS
10_1101-2021_01_02_425006	266	13	of	of	IN
10_1101-2021_01_02_425006	266	14	predicted	predict	VBN
10_1101-2021_01_02_425006	266	15	ATUs	atu	NNS
10_1101-2021_01_02_425006	266	16	that	that	WDT
10_1101-2021_01_02_425006	266	17	were	be	VBD
10_1101-2021_01_02_425006	266	18	validated	validate	VBN
10_1101-2021_01_02_425006	266	19	by	by	IN
10_1101-2021_01_02_425006	266	20	400	400	CD
10_1101-2021_01_02_425006	266	21	experimental	experimental	JJ
10_1101-2021_01_02_425006	266	22	transcription	transcription	NN
10_1101-2021_01_02_425006	266	23	factor	factor	NN
10_1101-2021_01_02_425006	266	24	binding	bind	VBG
10_1101-2021_01_02_425006	266	25	sites	site	NNS
10_1101-2021_01_02_425006	266	26	and	and	CC
10_1101-2021_01_02_425006	266	27	transcription	transcription	NN
10_1101-2021_01_02_425006	266	28	termination	termination	NN
10_1101-2021_01_02_425006	266	29	sites	site	NNS
10_1101-2021_01_02_425006	266	30	was	be	VBD
10_1101-2021_01_02_425006	266	31	over	over	IN
10_1101-2021_01_02_425006	266	32	three	three	CD
10_1101-2021_01_02_425006	266	33	times	time	NNS
10_1101-2021_01_02_425006	266	34	401	401	CD
10_1101-2021_01_02_425006	266	35	greater	great	JJR
10_1101-2021_01_02_425006	266	36	than	than	IN
10_1101-2021_01_02_425006	266	37	that	that	DT
10_1101-2021_01_02_425006	266	38	of	of	IN
10_1101-2021_01_02_425006	266	39	no	no	DT
10_1101-2021_01_02_425006	266	40	5’-	5’-	NN
10_1101-2021_01_02_425006	266	41	or	or	CC
10_1101-2021_01_02_425006	266	42	3’-end	3’-end	CD
10_1101-2021_01_02_425006	266	43	genes	gene	NNS
10_1101-2021_01_02_425006	266	44	,	,	,
10_1101-2021_01_02_425006	266	45	demonstrating	demonstrate	VBG
10_1101-2021_01_02_425006	266	46	the	the	DT
10_1101-2021_01_02_425006	266	47	high	high	JJ
10_1101-2021_01_02_425006	266	48	reliability	reliability	NN
10_1101-2021_01_02_425006	266	49	of	of	IN
10_1101-2021_01_02_425006	266	50	predicted	predict	VBN
10_1101-2021_01_02_425006	266	51	ATUs	atu	NNS
10_1101-2021_01_02_425006	266	52	.	.	.
10_1101-2021_01_02_425006	267	1	Gene	gene	NN
10_1101-2021_01_02_425006	267	2	402	402	CD
10_1101-2021_01_02_425006	267	3	pairs	pair	NNS
10_1101-2021_01_02_425006	267	4	frequently	frequently	RB
10_1101-2021_01_02_425006	267	5	encoded	encode	VBN
10_1101-2021_01_02_425006	267	6	in	in	IN
10_1101-2021_01_02_425006	267	7	the	the	DT
10_1101-2021_01_02_425006	267	8	same	same	JJ
10_1101-2021_01_02_425006	267	9	ATUs	atu	NNS
10_1101-2021_01_02_425006	267	10	were	be	VBD
10_1101-2021_01_02_425006	267	11	more	more	RBR
10_1101-2021_01_02_425006	267	12	functionally	functionally	RB
10_1101-2021_01_02_425006	267	13	related	related	JJ
10_1101-2021_01_02_425006	267	14	than	than	IN
10_1101-2021_01_02_425006	267	15	those	those	DT
10_1101-2021_01_02_425006	267	16	that	that	WDT
10_1101-2021_01_02_425006	267	17	can	can	MD
10_1101-2021_01_02_425006	267	18	belong	belong	VB
10_1101-2021_01_02_425006	267	19	to	to	IN
10_1101-2021_01_02_425006	267	20	403	403	CD
10_1101-2021_01_02_425006	267	21	two	two	CD
10_1101-2021_01_02_425006	267	22	distinct	distinct	JJ
10_1101-2021_01_02_425006	267	23	ATUs	atu	NNS
10_1101-2021_01_02_425006	267	24	according	accord	VBG
10_1101-2021_01_02_425006	267	25	to	to	IN
10_1101-2021_01_02_425006	267	26	GO	GO	NNP
10_1101-2021_01_02_425006	267	27	and	and	CC
10_1101-2021_01_02_425006	267	28	KEGG	KEGG	NNP
10_1101-2021_01_02_425006	267	29	enrichment	enrichment	NN
10_1101-2021_01_02_425006	267	30	analyses	analysis	NNS
10_1101-2021_01_02_425006	267	31	.	.	.
10_1101-2021_01_02_425006	268	1	These	these	DT
10_1101-2021_01_02_425006	268	2	results	result	NNS
10_1101-2021_01_02_425006	268	3	demonstrated	demonstrate	VBD
10_1101-2021_01_02_425006	268	4	the	the	DT
10_1101-2021_01_02_425006	268	5	404	404	CD
10_1101-2021_01_02_425006	268	6	reliability	reliability	NN
10_1101-2021_01_02_425006	268	7	and	and	CC
10_1101-2021_01_02_425006	268	8	accuracy	accuracy	NN
10_1101-2021_01_02_425006	268	9	of	of	IN
10_1101-2021_01_02_425006	268	10	our	-PRON-	PRP$
10_1101-2021_01_02_425006	268	11	predicted	predict	VBN
10_1101-2021_01_02_425006	268	12	ATUs	atu	NNS
10_1101-2021_01_02_425006	268	13	,	,	,
10_1101-2021_01_02_425006	268	14	implying	imply	VBG
10_1101-2021_01_02_425006	268	15	the	the	DT
10_1101-2021_01_02_425006	268	16	ability	ability	NN
10_1101-2021_01_02_425006	268	17	of	of	IN
10_1101-2021_01_02_425006	268	18	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	268	19	to	to	TO
10_1101-2021_01_02_425006	268	20	reveal	reveal	VB
10_1101-2021_01_02_425006	268	21	the	the	DT
10_1101-2021_01_02_425006	268	22	405	405	CD
10_1101-2021_01_02_425006	268	23	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	268	24	architecture	architecture	NN
10_1101-2021_01_02_425006	268	25	of	of	IN
10_1101-2021_01_02_425006	268	26	the	the	DT
10_1101-2021_01_02_425006	268	27	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	268	28	genome	genome	NN
10_1101-2021_01_02_425006	268	29	.	.	.
10_1101-2021_01_02_425006	269	1	406	406	CD
10_1101-2021_01_02_425006	269	2	In	in	IN
10_1101-2021_01_02_425006	269	3	fact	fact	NN
10_1101-2021_01_02_425006	269	4	,	,	,
10_1101-2021_01_02_425006	269	5	the	the	DT
10_1101-2021_01_02_425006	269	6	ATU	ATU	NNP
10_1101-2021_01_02_425006	269	7	architecture	architecture	NN
10_1101-2021_01_02_425006	269	8	of	of	IN
10_1101-2021_01_02_425006	269	9	bacteria	bacteria	NNS
10_1101-2021_01_02_425006	269	10	is	be	VBZ
10_1101-2021_01_02_425006	269	11	much	much	RB
10_1101-2021_01_02_425006	269	12	more	more	RBR
10_1101-2021_01_02_425006	269	13	complex	complex	JJ
10_1101-2021_01_02_425006	269	14	than	than	IN
10_1101-2021_01_02_425006	269	15	that	that	DT
10_1101-2021_01_02_425006	269	16	determined	determine	VBN
10_1101-2021_01_02_425006	269	17	with	with	IN
10_1101-2021_01_02_425006	269	18	currently	currently	RB
10_1101-2021_01_02_425006	269	19	407	407	CD
10_1101-2021_01_02_425006	269	20	.CC	.CC	,
10_1101-2021_01_02_425006	269	21	-	-	HYPH
10_1101-2021_01_02_425006	269	22	BY	by	IN
10_1101-2021_01_02_425006	269	23	-	-	HYPH
10_1101-2021_01_02_425006	269	24	NC	NC	NNP
10_1101-2021_01_02_425006	269	25	-	-	HYPH
10_1101-2021_01_02_425006	269	26	ND	ND	NNP
10_1101-2021_01_02_425006	269	27	4.0	4.0	CD
10_1101-2021_01_02_425006	269	28	International	International	NNP
10_1101-2021_01_02_425006	269	29	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	269	30	under	under	IN
10_1101-2021_01_02_425006	269	31	a	a	DT
10_1101-2021_01_02_425006	269	32	(	(	-LRB-
10_1101-2021_01_02_425006	269	33	which	which	WDT
10_1101-2021_01_02_425006	269	34	was	be	VBD
10_1101-2021_01_02_425006	269	35	not	not	RB
10_1101-2021_01_02_425006	269	36	certified	certify	VBN
10_1101-2021_01_02_425006	269	37	by	by	IN
10_1101-2021_01_02_425006	269	38	peer	peer	NN
10_1101-2021_01_02_425006	269	39	review	review	NN
10_1101-2021_01_02_425006	269	40	)	)	-RRB-
10_1101-2021_01_02_425006	269	41	is	be	VBZ
10_1101-2021_01_02_425006	269	42	the	the	DT
10_1101-2021_01_02_425006	269	43	author	author	NN
10_1101-2021_01_02_425006	269	44	/	/	SYM
10_1101-2021_01_02_425006	269	45	funder	funder	NN
10_1101-2021_01_02_425006	269	46	,	,	,
10_1101-2021_01_02_425006	269	47	who	who	WP
10_1101-2021_01_02_425006	269	48	has	have	VBZ
10_1101-2021_01_02_425006	269	49	granted	grant	VBN
10_1101-2021_01_02_425006	269	50	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	269	51	a	a	DT
10_1101-2021_01_02_425006	269	52	license	license	NN
10_1101-2021_01_02_425006	269	53	to	to	TO
10_1101-2021_01_02_425006	269	54	display	display	VB
10_1101-2021_01_02_425006	269	55	the	the	DT
10_1101-2021_01_02_425006	269	56	preprint	preprint	NN
10_1101-2021_01_02_425006	269	57	in	in	IN
10_1101-2021_01_02_425006	269	58	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	269	59	.	.	.
10_1101-2021_01_02_425006	270	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	270	2	is	be	VBZ
10_1101-2021_01_02_425006	270	3	made	make	VBN
10_1101-2021_01_02_425006	270	4	The	the	DT
10_1101-2021_01_02_425006	270	5	copyright	copyright	NN
10_1101-2021_01_02_425006	270	6	holder	holder	NN
10_1101-2021_01_02_425006	270	7	for	for	IN
10_1101-2021_01_02_425006	270	8	this	this	DT
10_1101-2021_01_02_425006	270	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	270	10	version	version	NN
10_1101-2021_01_02_425006	270	11	posted	post	VBD
10_1101-2021_01_02_425006	270	12	January	January	NNP
10_1101-2021_01_02_425006	270	13	6	6	CD
10_1101-2021_01_02_425006	270	14	,	,	,
10_1101-2021_01_02_425006	270	15	2021	2021	CD
10_1101-2021_01_02_425006	270	16	.	.	.
10_1101-2021_01_02_425006	270	17	;	;	:
10_1101-2021_01_02_425006	270	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	270	19	:	:	:
10_1101-2021_01_02_425006	270	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	270	21	preprint	preprint	NN
10_1101-2021_01_02_425006	270	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	270	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	270	24	24	24	CD
10_1101-2021_01_02_425006	270	25	used	use	VBD
10_1101-2021_01_02_425006	270	26	experimental	experimental	JJ
10_1101-2021_01_02_425006	270	27	techniques	technique	NNS
10_1101-2021_01_02_425006	270	28	.	.	.
10_1101-2021_01_02_425006	271	1	We	-PRON-	PRP
10_1101-2021_01_02_425006	271	2	investigated	investigate	VBD
10_1101-2021_01_02_425006	271	3	the	the	DT
10_1101-2021_01_02_425006	271	4	5’-end	5’-end	CD
10_1101-2021_01_02_425006	271	5	genes	gene	NNS
10_1101-2021_01_02_425006	271	6	and	and	CC
10_1101-2021_01_02_425006	271	7	no	no	DT
10_1101-2021_01_02_425006	271	8	5’-end	5’-end	CD
10_1101-2021_01_02_425006	271	9	genes	gene	NNS
10_1101-2021_01_02_425006	271	10	of	of	IN
10_1101-2021_01_02_425006	271	11	the	the	DT
10_1101-2021_01_02_425006	271	12	experimental	experimental	JJ
10_1101-2021_01_02_425006	271	13	408	408	CD
10_1101-2021_01_02_425006	271	14	ATUs	atu	NNS
10_1101-2021_01_02_425006	271	15	identified	identify	VBN
10_1101-2021_01_02_425006	271	16	by	by	IN
10_1101-2021_01_02_425006	271	17	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	271	18	-	-	HYPH
10_1101-2021_01_02_425006	271	19	Cappable	cappable	JJ
10_1101-2021_01_02_425006	271	20	-	-	HYPH
10_1101-2021_01_02_425006	271	21	seq	seq	NN
10_1101-2021_01_02_425006	271	22	(	(	-LRB-
10_1101-2021_01_02_425006	271	23	6	6	CD
10_1101-2021_01_02_425006	271	24	)	)	-RRB-
10_1101-2021_01_02_425006	271	25	using	use	VBG
10_1101-2021_01_02_425006	271	26	a	a	DT
10_1101-2021_01_02_425006	271	27	combination	combination	NN
10_1101-2021_01_02_425006	271	28	of	of	IN
10_1101-2021_01_02_425006	271	29	experimental	experimental	JJ
10_1101-2021_01_02_425006	271	30	TSSs	tss	NNS
10_1101-2021_01_02_425006	271	31	from	from	IN
10_1101-2021_01_02_425006	271	32	409	409	CD
10_1101-2021_01_02_425006	271	33	RegulonDB	regulondb	NN
10_1101-2021_01_02_425006	271	34	(	(	-LRB-
10_1101-2021_01_02_425006	271	35	19	19	CD
10_1101-2021_01_02_425006	271	36	)	)	-RRB-
10_1101-2021_01_02_425006	271	37	,	,	,
10_1101-2021_01_02_425006	271	38	dRNA	drna	NN
10_1101-2021_01_02_425006	271	39	-	-	HYPH
10_1101-2021_01_02_425006	271	40	seq	seq	NN
10_1101-2021_01_02_425006	271	41	(	(	-LRB-
10_1101-2021_01_02_425006	271	42	14	14	CD
10_1101-2021_01_02_425006	271	43	)	)	-RRB-
10_1101-2021_01_02_425006	271	44	,	,	,
10_1101-2021_01_02_425006	271	45	Cappable	cappable	JJ
10_1101-2021_01_02_425006	271	46	-	-	HYPH
10_1101-2021_01_02_425006	271	47	seq	seq	NN
10_1101-2021_01_02_425006	271	48	(	(	-LRB-
10_1101-2021_01_02_425006	271	49	13	13	CD
10_1101-2021_01_02_425006	271	50	)	)	-RRB-
10_1101-2021_01_02_425006	271	51	,	,	,
10_1101-2021_01_02_425006	271	52	and	and	CC
10_1101-2021_01_02_425006	271	53	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	271	54	-	-	HYPH
10_1101-2021_01_02_425006	271	55	seq	seq	NNP
10_1101-2021_01_02_425006	271	56	(	(	-LRB-
10_1101-2021_01_02_425006	271	57	7	7	CD
10_1101-2021_01_02_425006	271	58	)	)	-RRB-
10_1101-2021_01_02_425006	271	59	.	.	.
10_1101-2021_01_02_425006	272	1	As	as	IN
10_1101-2021_01_02_425006	272	2	a	a	DT
10_1101-2021_01_02_425006	272	3	result	result	NN
10_1101-2021_01_02_425006	272	4	,	,	,
10_1101-2021_01_02_425006	272	5	we	-PRON-	PRP
10_1101-2021_01_02_425006	272	6	found	find	VBD
10_1101-2021_01_02_425006	272	7	that	that	IN
10_1101-2021_01_02_425006	272	8	the	the	DT
10_1101-2021_01_02_425006	272	9	410	410	CD
10_1101-2021_01_02_425006	272	10	proportion	proportion	NN
10_1101-2021_01_02_425006	272	11	of	of	IN
10_1101-2021_01_02_425006	272	12	5’-end	5’-end	CD
10_1101-2021_01_02_425006	272	13	genes	gene	NNS
10_1101-2021_01_02_425006	272	14	(	(	-LRB-
10_1101-2021_01_02_425006	272	15	99	99	CD
10_1101-2021_01_02_425006	272	16	%	%	NN
10_1101-2021_01_02_425006	272	17	)	)	-RRB-
10_1101-2021_01_02_425006	272	18	validated	validate	VBN
10_1101-2021_01_02_425006	272	19	by	by	IN
10_1101-2021_01_02_425006	272	20	experimental	experimental	JJ
10_1101-2021_01_02_425006	272	21	TSSs	tss	NNS
10_1101-2021_01_02_425006	272	22	was	be	VBD
10_1101-2021_01_02_425006	272	23	not	not	RB
10_1101-2021_01_02_425006	272	24	significantly	significantly	RB
10_1101-2021_01_02_425006	272	25	different	different	JJ
10_1101-2021_01_02_425006	272	26	from	from	IN
10_1101-2021_01_02_425006	272	27	411	411	CD
10_1101-2021_01_02_425006	272	28	that	that	DT
10_1101-2021_01_02_425006	272	29	of	of	IN
10_1101-2021_01_02_425006	272	30	no	no	DT
10_1101-2021_01_02_425006	272	31	5’-end	5’-end	CD
10_1101-2021_01_02_425006	272	32	genes	gene	NNS
10_1101-2021_01_02_425006	272	33	(	(	-LRB-
10_1101-2021_01_02_425006	272	34	92	92	CD
10_1101-2021_01_02_425006	272	35	%	%	NN
10_1101-2021_01_02_425006	272	36	)	)	-RRB-
10_1101-2021_01_02_425006	272	37	.	.	.
10_1101-2021_01_02_425006	273	1	The	the	DT
10_1101-2021_01_02_425006	273	2	high	high	JJ
10_1101-2021_01_02_425006	273	3	percentage	percentage	NN
10_1101-2021_01_02_425006	273	4	of	of	IN
10_1101-2021_01_02_425006	273	5	no	no	DT
10_1101-2021_01_02_425006	273	6	5’-end	5’-end	CD
10_1101-2021_01_02_425006	273	7	genes	gene	NNS
10_1101-2021_01_02_425006	273	8	validated	validate	VBN
10_1101-2021_01_02_425006	273	9	by	by	IN
10_1101-2021_01_02_425006	273	10	experimental	experimental	JJ
10_1101-2021_01_02_425006	273	11	TSSs	tss	NNS
10_1101-2021_01_02_425006	273	12	412	412	CD
10_1101-2021_01_02_425006	273	13	implied	imply	VBD
10_1101-2021_01_02_425006	273	14	that	that	IN
10_1101-2021_01_02_425006	273	15	the	the	DT
10_1101-2021_01_02_425006	273	16	ATUs	atu	NNS
10_1101-2021_01_02_425006	273	17	identified	identify	VBN
10_1101-2021_01_02_425006	273	18	by	by	IN
10_1101-2021_01_02_425006	273	19	experimental	experimental	JJ
10_1101-2021_01_02_425006	273	20	techniques	technique	NNS
10_1101-2021_01_02_425006	273	21	are	be	VBP
10_1101-2021_01_02_425006	273	22	only	only	RB
10_1101-2021_01_02_425006	273	23	a	a	DT
10_1101-2021_01_02_425006	273	24	small	small	JJ
10_1101-2021_01_02_425006	273	25	proportion	proportion	NN
10_1101-2021_01_02_425006	273	26	of	of	IN
10_1101-2021_01_02_425006	273	27	the	the	DT
10_1101-2021_01_02_425006	273	28	413	413	CD
10_1101-2021_01_02_425006	273	29	comprehensive	comprehensive	JJ
10_1101-2021_01_02_425006	273	30	ATUs	atu	NNS
10_1101-2021_01_02_425006	273	31	in	in	IN
10_1101-2021_01_02_425006	273	32	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	273	33	organisms	organism	NNS
10_1101-2021_01_02_425006	273	34	due	due	JJ
10_1101-2021_01_02_425006	273	35	to	to	IN
10_1101-2021_01_02_425006	273	36	the	the	DT
10_1101-2021_01_02_425006	273	37	dynamic	dynamic	JJ
10_1101-2021_01_02_425006	273	38	mechanisms	mechanism	NNS
10_1101-2021_01_02_425006	273	39	of	of	IN
10_1101-2021_01_02_425006	273	40	ATUs	atu	NNS
10_1101-2021_01_02_425006	273	41	.	.	.
10_1101-2021_01_02_425006	274	1	These	these	DT
10_1101-2021_01_02_425006	274	2	results	result	NNS
10_1101-2021_01_02_425006	274	3	414	414	CD
10_1101-2021_01_02_425006	274	4	further	further	RB
10_1101-2021_01_02_425006	274	5	verified	verify	VBD
10_1101-2021_01_02_425006	274	6	the	the	DT
10_1101-2021_01_02_425006	274	7	necessity	necessity	NN
10_1101-2021_01_02_425006	274	8	of	of	IN
10_1101-2021_01_02_425006	274	9	developing	develop	VBG
10_1101-2021_01_02_425006	274	10	robust	robust	JJ
10_1101-2021_01_02_425006	274	11	computational	computational	JJ
10_1101-2021_01_02_425006	274	12	methods	method	NNS
10_1101-2021_01_02_425006	274	13	for	for	IN
10_1101-2021_01_02_425006	274	14	ATU	ATU	NNP
10_1101-2021_01_02_425006	274	15	identification	identification	NN
10_1101-2021_01_02_425006	274	16	.	.	.
10_1101-2021_01_02_425006	275	1	415	415	CD
10_1101-2021_01_02_425006	275	2	SeqATU	seqatu	IN
10_1101-2021_01_02_425006	275	3	not	not	RB
10_1101-2021_01_02_425006	275	4	only	only	RB
10_1101-2021_01_02_425006	275	5	provides	provide	VBZ
10_1101-2021_01_02_425006	275	6	a	a	DT
10_1101-2021_01_02_425006	275	7	powerful	powerful	JJ
10_1101-2021_01_02_425006	275	8	tool	tool	NN
10_1101-2021_01_02_425006	275	9	to	to	TO
10_1101-2021_01_02_425006	275	10	understand	understand	VB
10_1101-2021_01_02_425006	275	11	the	the	DT
10_1101-2021_01_02_425006	275	12	transcription	transcription	NN
10_1101-2021_01_02_425006	275	13	mechanism	mechanism	NN
10_1101-2021_01_02_425006	275	14	of	of	IN
10_1101-2021_01_02_425006	275	15	bacteria	bacteria	NNS
10_1101-2021_01_02_425006	275	16	but	but	CC
10_1101-2021_01_02_425006	275	17	416	416	CD
10_1101-2021_01_02_425006	275	18	also	also	RB
10_1101-2021_01_02_425006	275	19	provides	provide	VBZ
10_1101-2021_01_02_425006	275	20	a	a	DT
10_1101-2021_01_02_425006	275	21	fundamental	fundamental	JJ
10_1101-2021_01_02_425006	275	22	tool	tool	NN
10_1101-2021_01_02_425006	275	23	to	to	TO
10_1101-2021_01_02_425006	275	24	guide	guide	VB
10_1101-2021_01_02_425006	275	25	the	the	DT
10_1101-2021_01_02_425006	275	26	reconstruction	reconstruction	NN
10_1101-2021_01_02_425006	275	27	of	of	IN
10_1101-2021_01_02_425006	275	28	a	a	DT
10_1101-2021_01_02_425006	275	29	genome	genome	JJ
10_1101-2021_01_02_425006	275	30	-	-	HYPH
10_1101-2021_01_02_425006	275	31	scale	scale	NN
10_1101-2021_01_02_425006	275	32	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	275	33	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	275	34	417	417	CD
10_1101-2021_01_02_425006	275	35	network	network	NN
10_1101-2021_01_02_425006	275	36	.	.	.
10_1101-2021_01_02_425006	276	1	First	first	RB
10_1101-2021_01_02_425006	276	2	,	,	,
10_1101-2021_01_02_425006	276	3	the	the	DT
10_1101-2021_01_02_425006	276	4	ATU	ATU	NNP
10_1101-2021_01_02_425006	276	5	structure	structure	NN
10_1101-2021_01_02_425006	276	6	can	can	MD
10_1101-2021_01_02_425006	276	7	help	help	VB
10_1101-2021_01_02_425006	276	8	us	-PRON-	PRP
10_1101-2021_01_02_425006	276	9	to	to	TO
10_1101-2021_01_02_425006	276	10	make	make	VB
10_1101-2021_01_02_425006	276	11	new	new	JJ
10_1101-2021_01_02_425006	276	12	functional	functional	JJ
10_1101-2021_01_02_425006	276	13	predictions	prediction	NNS
10_1101-2021_01_02_425006	276	14	,	,	,
10_1101-2021_01_02_425006	276	15	as	as	IN
10_1101-2021_01_02_425006	276	16	genes	gene	NNS
10_1101-2021_01_02_425006	276	17	in	in	IN
10_1101-2021_01_02_425006	276	18	an	an	DT
10_1101-2021_01_02_425006	276	19	ATU	ATU	NNP
10_1101-2021_01_02_425006	276	20	418	418	CD
10_1101-2021_01_02_425006	276	21	tend	tend	VBP
10_1101-2021_01_02_425006	276	22	to	to	TO
10_1101-2021_01_02_425006	276	23	have	have	VB
10_1101-2021_01_02_425006	276	24	related	relate	VBN
10_1101-2021_01_02_425006	276	25	functions	function	NNS
10_1101-2021_01_02_425006	276	26	.	.	.
10_1101-2021_01_02_425006	277	1	Second	second	JJ
10_1101-2021_01_02_425006	277	2	,	,	,
10_1101-2021_01_02_425006	277	3	ATUs	atu	NNS
10_1101-2021_01_02_425006	277	4	can	can	MD
10_1101-2021_01_02_425006	277	5	elucidate	elucidate	VB
10_1101-2021_01_02_425006	277	6	condition	condition	NN
10_1101-2021_01_02_425006	277	7	-	-	HYPH
10_1101-2021_01_02_425006	277	8	specific	specific	JJ
10_1101-2021_01_02_425006	277	9	uses	use	NNS
10_1101-2021_01_02_425006	277	10	of	of	IN
10_1101-2021_01_02_425006	277	11	alternative	alternative	JJ
10_1101-2021_01_02_425006	277	12	sigma	sigma	NNP
10_1101-2021_01_02_425006	277	13	419	419	CD
10_1101-2021_01_02_425006	277	14	factors	factor	NNS
10_1101-2021_01_02_425006	277	15	(	(	-LRB-
10_1101-2021_01_02_425006	277	16	8	8	CD
10_1101-2021_01_02_425006	277	17	,	,	,
10_1101-2021_01_02_425006	277	18	46	46	CD
10_1101-2021_01_02_425006	277	19	)	)	-RRB-
10_1101-2021_01_02_425006	277	20	.	.	.
10_1101-2021_01_02_425006	278	1	For	for	IN
10_1101-2021_01_02_425006	278	2	example	example	NN
10_1101-2021_01_02_425006	278	3	,	,	,
10_1101-2021_01_02_425006	278	4	the	the	DT
10_1101-2021_01_02_425006	278	5	thrLABC	thrLABC	NNP
10_1101-2021_01_02_425006	278	6	operon	operon	NN
10_1101-2021_01_02_425006	278	7	is	be	VBZ
10_1101-2021_01_02_425006	278	8	regulated	regulate	VBN
10_1101-2021_01_02_425006	278	9	by	by	IN
10_1101-2021_01_02_425006	278	10	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	278	11	attenuation	attenuation	NN
10_1101-2021_01_02_425006	278	12	.	.	.
10_1101-2021_01_02_425006	279	1	Totsuka	Totsuka	NNP
10_1101-2021_01_02_425006	279	2	et	et	NNP
10_1101-2021_01_02_425006	279	3	420	420	CD
10_1101-2021_01_02_425006	279	4	al	al	NNP
10_1101-2021_01_02_425006	279	5	.	.	.
10_1101-2021_01_02_425006	280	1	found	find	VBD
10_1101-2021_01_02_425006	280	2	that	that	IN
10_1101-2021_01_02_425006	280	3	under	under	IN
10_1101-2021_01_02_425006	280	4	the	the	DT
10_1101-2021_01_02_425006	280	5	log	log	NN
10_1101-2021_01_02_425006	280	6	phase	phase	NN
10_1101-2021_01_02_425006	280	7	growth	growth	NN
10_1101-2021_01_02_425006	280	8	condition	condition	NN
10_1101-2021_01_02_425006	280	9	,	,	,
10_1101-2021_01_02_425006	280	10	the	the	DT
10_1101-2021_01_02_425006	280	11	thrLABC	thrLABC	NNP
10_1101-2021_01_02_425006	280	12	operon	operon	NN
10_1101-2021_01_02_425006	280	13	is	be	VBZ
10_1101-2021_01_02_425006	280	14	the	the	DT
10_1101-2021_01_02_425006	280	15	only	only	JJ
10_1101-2021_01_02_425006	280	16	transcript	transcript	NN
10_1101-2021_01_02_425006	280	17	,	,	,
10_1101-2021_01_02_425006	280	18	while	while	IN
10_1101-2021_01_02_425006	280	19	421	421	CD
10_1101-2021_01_02_425006	280	20	two	two	CD
10_1101-2021_01_02_425006	280	21	transcripts	transcript	NNS
10_1101-2021_01_02_425006	280	22	are	be	VBP
10_1101-2021_01_02_425006	280	23	found	find	VBN
10_1101-2021_01_02_425006	280	24	under	under	IN
10_1101-2021_01_02_425006	280	25	stationary	stationary	JJ
10_1101-2021_01_02_425006	280	26	phase	phase	NN
10_1101-2021_01_02_425006	280	27	growth	growth	NN
10_1101-2021_01_02_425006	280	28	condition	condition	NN
10_1101-2021_01_02_425006	280	29	,	,	,
10_1101-2021_01_02_425006	280	30	the	the	DT
10_1101-2021_01_02_425006	280	31	thrLABC	thrLABC	NNP
10_1101-2021_01_02_425006	280	32	and	and	CC
10_1101-2021_01_02_425006	280	33	thrBC	thrbc	ADD
10_1101-2021_01_02_425006	280	34	.	.	.
10_1101-2021_01_02_425006	281	1	As	as	IN
10_1101-2021_01_02_425006	281	2	validated	validate	VBN
10_1101-2021_01_02_425006	281	3	422	422	CD
10_1101-2021_01_02_425006	281	4	experimentally	experimentally	RB
10_1101-2021_01_02_425006	281	5	,	,	,
10_1101-2021_01_02_425006	281	6	�	�	ADD
10_1101-2021_01_02_425006	281	7	�	�	NNP
10_1101-2021_01_02_425006	281	8	can	can	MD
10_1101-2021_01_02_425006	281	9	regulate	regulate	VB
10_1101-2021_01_02_425006	281	10	the	the	DT
10_1101-2021_01_02_425006	281	11	additional	additional	JJ
10_1101-2021_01_02_425006	281	12	promoter	promoter	NN
10_1101-2021_01_02_425006	281	13	located	locate	VBN
10_1101-2021_01_02_425006	281	14	in	in	IN
10_1101-2021_01_02_425006	281	15	front	front	NN
10_1101-2021_01_02_425006	281	16	of	of	IN
10_1101-2021_01_02_425006	281	17	thrB	thrb	CD
10_1101-2021_01_02_425006	281	18	under	under	IN
10_1101-2021_01_02_425006	281	19	the	the	DT
10_1101-2021_01_02_425006	281	20	stationary	stationary	JJ
10_1101-2021_01_02_425006	281	21	423	423	CD
10_1101-2021_01_02_425006	281	22	phase	phase	NN
10_1101-2021_01_02_425006	281	23	growth	growth	NN
10_1101-2021_01_02_425006	281	24	condition	condition	NN
10_1101-2021_01_02_425006	281	25	and	and	CC
10_1101-2021_01_02_425006	281	26	then	then	RB
10_1101-2021_01_02_425006	281	27	separately	separately	RB
10_1101-2021_01_02_425006	281	28	regulate	regulate	VB
10_1101-2021_01_02_425006	281	29	thrBC	thrbc	ADD
10_1101-2021_01_02_425006	281	30	,	,	,
10_1101-2021_01_02_425006	281	31	which	which	WDT
10_1101-2021_01_02_425006	281	32	elucidates	elucidate	VBZ
10_1101-2021_01_02_425006	281	33	the	the	DT
10_1101-2021_01_02_425006	281	34	condition	condition	NN
10_1101-2021_01_02_425006	281	35	-	-	HYPH
10_1101-2021_01_02_425006	281	36	specific	specific	JJ
10_1101-2021_01_02_425006	281	37	uses	use	VBZ
10_1101-2021_01_02_425006	281	38	424	424	CD
10_1101-2021_01_02_425006	281	39	of	of	IN
10_1101-2021_01_02_425006	281	40	�	�	NNP
10_1101-2021_01_02_425006	281	41	�	�	NNP
10_1101-2021_01_02_425006	281	42	(	(	-LRB-
10_1101-2021_01_02_425006	281	43	8)	8)	CD
10_1101-2021_01_02_425006	281	44	.	.	.
10_1101-2021_01_02_425006	282	1	Third	third	JJ
10_1101-2021_01_02_425006	282	2	,	,	,
10_1101-2021_01_02_425006	282	3	understanding	understand	VBG
10_1101-2021_01_02_425006	282	4	the	the	DT
10_1101-2021_01_02_425006	282	5	ATU	ATU	NNP
10_1101-2021_01_02_425006	282	6	structure	structure	NN
10_1101-2021_01_02_425006	282	7	is	be	VBZ
10_1101-2021_01_02_425006	282	8	of	of	IN
10_1101-2021_01_02_425006	282	9	great	great	JJ
10_1101-2021_01_02_425006	282	10	help	help	NN
10_1101-2021_01_02_425006	282	11	to	to	TO
10_1101-2021_01_02_425006	282	12	construct	construct	VB
10_1101-2021_01_02_425006	282	13	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	282	14	and	and	CC
10_1101-2021_01_02_425006	282	15	425	425	CD
10_1101-2021_01_02_425006	282	16	translation	translation	NN
10_1101-2021_01_02_425006	282	17	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	282	18	networks	network	NNS
10_1101-2021_01_02_425006	282	19	,	,	,
10_1101-2021_01_02_425006	282	20	such	such	JJ
10_1101-2021_01_02_425006	282	21	as	as	IN
10_1101-2021_01_02_425006	282	22	for	for	IN
10_1101-2021_01_02_425006	282	23	the	the	DT
10_1101-2021_01_02_425006	282	24	construction	construction	NN
10_1101-2021_01_02_425006	282	25	of	of	IN
10_1101-2021_01_02_425006	282	26	the	the	DT
10_1101-2021_01_02_425006	282	27	σ	σ	NNP
10_1101-2021_01_02_425006	282	28	-	-	HYPH
10_1101-2021_01_02_425006	282	29	TUG	TUG	NNP
10_1101-2021_01_02_425006	282	30	(	(	-LRB-
10_1101-2021_01_02_425006	282	31	σ	σ	NN
10_1101-2021_01_02_425006	282	32	-	-	HYPH
10_1101-2021_01_02_425006	282	33	factor	factor	NN
10_1101-2021_01_02_425006	282	34	-	-	HYPH
10_1101-2021_01_02_425006	282	35	transcription	transcription	NN
10_1101-2021_01_02_425006	282	36	unit	unit	NN
10_1101-2021_01_02_425006	282	37	426	426	CD
10_1101-2021_01_02_425006	282	38	.CC	.CC	:
10_1101-2021_01_02_425006	282	39	-	-	HYPH
10_1101-2021_01_02_425006	282	40	BY	by	IN
10_1101-2021_01_02_425006	282	41	-	-	HYPH
10_1101-2021_01_02_425006	282	42	NC	NC	NNP
10_1101-2021_01_02_425006	282	43	-	-	HYPH
10_1101-2021_01_02_425006	282	44	ND	ND	NNP
10_1101-2021_01_02_425006	282	45	4.0	4.0	CD
10_1101-2021_01_02_425006	282	46	International	International	NNP
10_1101-2021_01_02_425006	282	47	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	282	48	under	under	IN
10_1101-2021_01_02_425006	282	49	a	a	DT
10_1101-2021_01_02_425006	282	50	(	(	-LRB-
10_1101-2021_01_02_425006	282	51	which	which	WDT
10_1101-2021_01_02_425006	282	52	was	be	VBD
10_1101-2021_01_02_425006	282	53	not	not	RB
10_1101-2021_01_02_425006	282	54	certified	certify	VBN
10_1101-2021_01_02_425006	282	55	by	by	IN
10_1101-2021_01_02_425006	282	56	peer	peer	NN
10_1101-2021_01_02_425006	282	57	review	review	NN
10_1101-2021_01_02_425006	282	58	)	)	-RRB-
10_1101-2021_01_02_425006	282	59	is	be	VBZ
10_1101-2021_01_02_425006	282	60	the	the	DT
10_1101-2021_01_02_425006	282	61	author	author	NN
10_1101-2021_01_02_425006	282	62	/	/	SYM
10_1101-2021_01_02_425006	282	63	funder	funder	NN
10_1101-2021_01_02_425006	282	64	,	,	,
10_1101-2021_01_02_425006	282	65	who	who	WP
10_1101-2021_01_02_425006	282	66	has	have	VBZ
10_1101-2021_01_02_425006	282	67	granted	grant	VBN
10_1101-2021_01_02_425006	282	68	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	282	69	a	a	DT
10_1101-2021_01_02_425006	282	70	license	license	NN
10_1101-2021_01_02_425006	282	71	to	to	TO
10_1101-2021_01_02_425006	282	72	display	display	VB
10_1101-2021_01_02_425006	282	73	the	the	DT
10_1101-2021_01_02_425006	282	74	preprint	preprint	NN
10_1101-2021_01_02_425006	282	75	in	in	IN
10_1101-2021_01_02_425006	282	76	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	282	77	.	.	.
10_1101-2021_01_02_425006	283	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	283	2	is	be	VBZ
10_1101-2021_01_02_425006	283	3	made	make	VBN
10_1101-2021_01_02_425006	283	4	The	the	DT
10_1101-2021_01_02_425006	283	5	copyright	copyright	NN
10_1101-2021_01_02_425006	283	6	holder	holder	NN
10_1101-2021_01_02_425006	283	7	for	for	IN
10_1101-2021_01_02_425006	283	8	this	this	DT
10_1101-2021_01_02_425006	283	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	283	10	version	version	NN
10_1101-2021_01_02_425006	283	11	posted	post	VBD
10_1101-2021_01_02_425006	283	12	January	January	NNP
10_1101-2021_01_02_425006	283	13	6	6	CD
10_1101-2021_01_02_425006	283	14	,	,	,
10_1101-2021_01_02_425006	283	15	2021	2021	CD
10_1101-2021_01_02_425006	283	16	.	.	.
10_1101-2021_01_02_425006	283	17	;	;	:
10_1101-2021_01_02_425006	283	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	283	19	:	:	:
10_1101-2021_01_02_425006	283	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	283	21	preprint	preprint	NN
10_1101-2021_01_02_425006	283	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	283	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	283	24	25	25	CD
10_1101-2021_01_02_425006	283	25	gene	gene	NN
10_1101-2021_01_02_425006	283	26	)	)	-RRB-
10_1101-2021_01_02_425006	283	27	network	network	NN
10_1101-2021_01_02_425006	283	28	(	(	-LRB-
10_1101-2021_01_02_425006	283	29	47	47	CD
10_1101-2021_01_02_425006	283	30	)	)	-RRB-
10_1101-2021_01_02_425006	283	31	.	.	.
10_1101-2021_01_02_425006	284	1	The	the	DT
10_1101-2021_01_02_425006	284	2	transcription	transcription	NN
10_1101-2021_01_02_425006	284	3	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	284	4	network	network	NN
10_1101-2021_01_02_425006	284	5	consists	consist	VBZ
10_1101-2021_01_02_425006	284	6	of	of	IN
10_1101-2021_01_02_425006	284	7	nodes	node	NNS
10_1101-2021_01_02_425006	284	8	(	(	-LRB-
10_1101-2021_01_02_425006	284	9	ATU	ATU	NNP
10_1101-2021_01_02_425006	284	10	and	and	CC
10_1101-2021_01_02_425006	284	11	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	284	12	427	427	CD
10_1101-2021_01_02_425006	284	13	proteins	protein	NNS
10_1101-2021_01_02_425006	284	14	)	)	-RRB-
10_1101-2021_01_02_425006	284	15	and	and	CC
10_1101-2021_01_02_425006	284	16	links	link	NNS
10_1101-2021_01_02_425006	284	17	(	(	-LRB-
10_1101-2021_01_02_425006	284	18	interactions	interaction	NNS
10_1101-2021_01_02_425006	284	19	)	)	-RRB-
10_1101-2021_01_02_425006	284	20	(	(	-LRB-
10_1101-2021_01_02_425006	284	21	48	48	CD
10_1101-2021_01_02_425006	284	22	)	)	-RRB-
10_1101-2021_01_02_425006	284	23	,	,	,
10_1101-2021_01_02_425006	284	24	and	and	CC
10_1101-2021_01_02_425006	284	25	the	the	DT
10_1101-2021_01_02_425006	284	26	comprehensive	comprehensive	JJ
10_1101-2021_01_02_425006	284	27	ATU	ATU	NNP
10_1101-2021_01_02_425006	284	28	structure	structure	NN
10_1101-2021_01_02_425006	284	29	can	can	MD
10_1101-2021_01_02_425006	284	30	provide	provide	VB
10_1101-2021_01_02_425006	284	31	a	a	DT
10_1101-2021_01_02_425006	284	32	nearly	nearly	RB
10_1101-2021_01_02_425006	284	33	428	428	CD
10_1101-2021_01_02_425006	284	34	complete	complete	JJ
10_1101-2021_01_02_425006	284	35	set	set	NN
10_1101-2021_01_02_425006	284	36	of	of	IN
10_1101-2021_01_02_425006	284	37	nodes	node	NNS
10_1101-2021_01_02_425006	284	38	,	,	,
10_1101-2021_01_02_425006	284	39	which	which	WDT
10_1101-2021_01_02_425006	284	40	can	can	MD
10_1101-2021_01_02_425006	284	41	improve	improve	VB
10_1101-2021_01_02_425006	284	42	the	the	DT
10_1101-2021_01_02_425006	284	43	accuracy	accuracy	NN
10_1101-2021_01_02_425006	284	44	of	of	IN
10_1101-2021_01_02_425006	284	45	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	284	46	prediction	prediction	NN
10_1101-2021_01_02_425006	284	47	.	.	.
10_1101-2021_01_02_425006	285	1	429	429	CD
10_1101-2021_01_02_425006	285	2	Although	although	IN
10_1101-2021_01_02_425006	285	3	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	285	4	has	have	VBZ
10_1101-2021_01_02_425006	285	5	obtained	obtain	VBN
10_1101-2021_01_02_425006	285	6	satisfactory	satisfactory	JJ
10_1101-2021_01_02_425006	285	7	predicted	predict	VBN
10_1101-2021_01_02_425006	285	8	results	result	NNS
10_1101-2021_01_02_425006	285	9	,	,	,
10_1101-2021_01_02_425006	285	10	there	there	EX
10_1101-2021_01_02_425006	285	11	are	be	VBP
10_1101-2021_01_02_425006	285	12	still	still	RB
10_1101-2021_01_02_425006	285	13	several	several	JJ
10_1101-2021_01_02_425006	285	14	challenges	challenge	NNS
10_1101-2021_01_02_425006	285	15	430	430	CD
10_1101-2021_01_02_425006	285	16	regarding	regard	VBG
10_1101-2021_01_02_425006	285	17	the	the	DT
10_1101-2021_01_02_425006	285	18	computational	computational	JJ
10_1101-2021_01_02_425006	285	19	prediction	prediction	NN
10_1101-2021_01_02_425006	285	20	of	of	IN
10_1101-2021_01_02_425006	285	21	ATUs	atu	NNS
10_1101-2021_01_02_425006	285	22	.	.	.
10_1101-2021_01_02_425006	286	1	On	on	IN
10_1101-2021_01_02_425006	286	2	the	the	DT
10_1101-2021_01_02_425006	286	3	one	one	CD
10_1101-2021_01_02_425006	286	4	hand	hand	NN
10_1101-2021_01_02_425006	286	5	,	,	,
10_1101-2021_01_02_425006	286	6	due	due	IN
10_1101-2021_01_02_425006	286	7	to	to	IN
10_1101-2021_01_02_425006	286	8	the	the	DT
10_1101-2021_01_02_425006	286	9	influence	influence	NN
10_1101-2021_01_02_425006	286	10	of	of	IN
10_1101-2021_01_02_425006	286	11	the	the	DT
10_1101-2021_01_02_425006	286	12	3	3	CD
10_1101-2021_01_02_425006	286	13	’	'	''
10_1101-2021_01_02_425006	286	14	431	431	CD
10_1101-2021_01_02_425006	286	15	untranslated	untranslated	JJ
10_1101-2021_01_02_425006	286	16	region	region	NN
10_1101-2021_01_02_425006	286	17	(	(	-LRB-
10_1101-2021_01_02_425006	286	18	UTR	UTR	NNP
10_1101-2021_01_02_425006	286	19	)	)	-RRB-
10_1101-2021_01_02_425006	286	20	and	and	CC
10_1101-2021_01_02_425006	286	21	5	5	CD
10_1101-2021_01_02_425006	286	22	’	'	''
10_1101-2021_01_02_425006	286	23	untranslated	untranslated	JJ
10_1101-2021_01_02_425006	286	24	region	region	NN
10_1101-2021_01_02_425006	286	25	(	(	-LRB-
10_1101-2021_01_02_425006	286	26	UTR	UTR	NNP
10_1101-2021_01_02_425006	286	27	)	)	-RRB-
10_1101-2021_01_02_425006	286	28	in	in	IN
10_1101-2021_01_02_425006	286	29	the	the	DT
10_1101-2021_01_02_425006	286	30	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	286	31	regions	region	NNS
10_1101-2021_01_02_425006	286	32	,	,	,
10_1101-2021_01_02_425006	286	33	the	the	DT
10_1101-2021_01_02_425006	286	34	expression	expression	NN
10_1101-2021_01_02_425006	286	35	432	432	CD
10_1101-2021_01_02_425006	286	36	value	value	NN
10_1101-2021_01_02_425006	286	37	of	of	IN
10_1101-2021_01_02_425006	286	38	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	286	39	regions	region	NNS
10_1101-2021_01_02_425006	286	40	can	can	MD
10_1101-2021_01_02_425006	286	41	not	not	RB
10_1101-2021_01_02_425006	286	42	be	be	VB
10_1101-2021_01_02_425006	286	43	reproduced	reproduce	VBN
10_1101-2021_01_02_425006	286	44	perfectly	perfectly	RB
10_1101-2021_01_02_425006	286	45	by	by	IN
10_1101-2021_01_02_425006	286	46	the	the	DT
10_1101-2021_01_02_425006	286	47	same	same	JJ
10_1101-2021_01_02_425006	286	48	calculation	calculation	NN
10_1101-2021_01_02_425006	286	49	used	use	VBN
10_1101-2021_01_02_425006	286	50	for	for	IN
10_1101-2021_01_02_425006	286	51	the	the	DT
10_1101-2021_01_02_425006	286	52	433	433	CD
10_1101-2021_01_02_425006	286	53	expression	expression	NN
10_1101-2021_01_02_425006	286	54	value	value	NN
10_1101-2021_01_02_425006	286	55	of	of	IN
10_1101-2021_01_02_425006	286	56	genetic	genetic	JJ
10_1101-2021_01_02_425006	286	57	regions	region	NNS
10_1101-2021_01_02_425006	286	58	.	.	.
10_1101-2021_01_02_425006	287	1	Without	without	IN
10_1101-2021_01_02_425006	287	2	accurate	accurate	JJ
10_1101-2021_01_02_425006	287	3	reproduction	reproduction	NN
10_1101-2021_01_02_425006	287	4	,	,	,
10_1101-2021_01_02_425006	287	5	it	-PRON-	PRP
10_1101-2021_01_02_425006	287	6	is	be	VBZ
10_1101-2021_01_02_425006	287	7	difficult	difficult	JJ
10_1101-2021_01_02_425006	287	8	to	to	TO
10_1101-2021_01_02_425006	287	9	obtain	obtain	VB
10_1101-2021_01_02_425006	287	10	the	the	DT
10_1101-2021_01_02_425006	287	11	best	good	JJS
10_1101-2021_01_02_425006	287	12	434	434	CD
10_1101-2021_01_02_425006	287	13	expression	expression	NN
10_1101-2021_01_02_425006	287	14	combination	combination	NN
10_1101-2021_01_02_425006	287	15	of	of	IN
10_1101-2021_01_02_425006	287	16	ATUs	atu	NNS
10_1101-2021_01_02_425006	287	17	by	by	IN
10_1101-2021_01_02_425006	287	18	the	the	DT
10_1101-2021_01_02_425006	287	19	programming	programming	NN
10_1101-2021_01_02_425006	287	20	model	model	NN
10_1101-2021_01_02_425006	287	21	based	base	VBN
10_1101-2021_01_02_425006	287	22	on	on	IN
10_1101-2021_01_02_425006	287	23	the	the	DT
10_1101-2021_01_02_425006	287	24	expression	expression	NN
10_1101-2021_01_02_425006	287	25	value	value	NN
10_1101-2021_01_02_425006	287	26	of	of	IN
10_1101-2021_01_02_425006	287	27	genetic	genetic	JJ
10_1101-2021_01_02_425006	287	28	435	435	CD
10_1101-2021_01_02_425006	287	29	and	and	CC
10_1101-2021_01_02_425006	287	30	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	287	31	regions	region	NNS
10_1101-2021_01_02_425006	287	32	.	.	.
10_1101-2021_01_02_425006	288	1	On	on	IN
10_1101-2021_01_02_425006	288	2	the	the	DT
10_1101-2021_01_02_425006	288	3	other	other	JJ
10_1101-2021_01_02_425006	288	4	hand	hand	NN
10_1101-2021_01_02_425006	288	5	,	,	,
10_1101-2021_01_02_425006	288	6	due	due	IN
10_1101-2021_01_02_425006	288	7	to	to	IN
10_1101-2021_01_02_425006	288	8	the	the	DT
10_1101-2021_01_02_425006	288	9	lack	lack	NN
10_1101-2021_01_02_425006	288	10	of	of	IN
10_1101-2021_01_02_425006	288	11	strand	strand	NN
10_1101-2021_01_02_425006	288	12	-	-	HYPH
10_1101-2021_01_02_425006	288	13	specific	specific	JJ
10_1101-2021_01_02_425006	288	14	RNA	RNA	NNP
10_1101-2021_01_02_425006	288	15	-	-	HYPH
10_1101-2021_01_02_425006	288	16	Seq	seq	NN
10_1101-2021_01_02_425006	288	17	data	datum	NNS
10_1101-2021_01_02_425006	288	18	,	,	,
10_1101-2021_01_02_425006	288	19	it	-PRON-	PRP
10_1101-2021_01_02_425006	288	20	is	be	VBZ
10_1101-2021_01_02_425006	288	21	difficult	difficult	JJ
10_1101-2021_01_02_425006	288	22	436	436	CD
10_1101-2021_01_02_425006	288	23	to	to	TO
10_1101-2021_01_02_425006	288	24	distinguish	distinguish	VB
10_1101-2021_01_02_425006	288	25	the	the	DT
10_1101-2021_01_02_425006	288	26	expression	expression	NN
10_1101-2021_01_02_425006	288	27	level	level	NN
10_1101-2021_01_02_425006	288	28	of	of	IN
10_1101-2021_01_02_425006	288	29	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	288	30	regions	region	NNS
10_1101-2021_01_02_425006	288	31	between	between	IN
10_1101-2021_01_02_425006	288	32	two	two	CD
10_1101-2021_01_02_425006	288	33	consecutive	consecutive	JJ
10_1101-2021_01_02_425006	288	34	genes	gene	NNS
10_1101-2021_01_02_425006	288	35	on	on	IN
10_1101-2021_01_02_425006	288	36	the	the	DT
10_1101-2021_01_02_425006	288	37	same	same	JJ
10_1101-2021_01_02_425006	288	38	437	437	CD
10_1101-2021_01_02_425006	288	39	strand	strand	NN
10_1101-2021_01_02_425006	288	40	derived	derive	VBN
10_1101-2021_01_02_425006	288	41	from	from	IN
10_1101-2021_01_02_425006	288	42	ATUs	atu	NNS
10_1101-2021_01_02_425006	288	43	containing	contain	VBG
10_1101-2021_01_02_425006	288	44	these	these	DT
10_1101-2021_01_02_425006	288	45	two	two	CD
10_1101-2021_01_02_425006	288	46	genes	gene	NNS
10_1101-2021_01_02_425006	288	47	or	or	CC
10_1101-2021_01_02_425006	288	48	antisense	antisense	NN
10_1101-2021_01_02_425006	288	49	RNAs	rna	NNS
10_1101-2021_01_02_425006	288	50	(	(	-LRB-
10_1101-2021_01_02_425006	288	51	asRNAs	asrnas	NN
10_1101-2021_01_02_425006	288	52	)	)	-RRB-
10_1101-2021_01_02_425006	288	53	(	(	-LRB-
10_1101-2021_01_02_425006	288	54	6	6	CD
10_1101-2021_01_02_425006	288	55	,	,	,
10_1101-2021_01_02_425006	288	56	49	49	CD
10_1101-2021_01_02_425006	288	57	)	)	-RRB-
10_1101-2021_01_02_425006	288	58	.	.	.
10_1101-2021_01_02_425006	289	1	All	all	DT
10_1101-2021_01_02_425006	289	2	of	of	IN
10_1101-2021_01_02_425006	289	3	these	these	DT
10_1101-2021_01_02_425006	289	4	438	438	CD
10_1101-2021_01_02_425006	289	5	challenges	challenge	NNS
10_1101-2021_01_02_425006	289	6	and	and	CC
10_1101-2021_01_02_425006	289	7	the	the	DT
10_1101-2021_01_02_425006	289	8	great	great	JJ
10_1101-2021_01_02_425006	289	9	significance	significance	NN
10_1101-2021_01_02_425006	289	10	of	of	IN
10_1101-2021_01_02_425006	289	11	ATU	ATU	NNP
10_1101-2021_01_02_425006	289	12	prediction	prediction	NN
10_1101-2021_01_02_425006	289	13	inspire	inspire	VBP
10_1101-2021_01_02_425006	289	14	and	and	CC
10_1101-2021_01_02_425006	289	15	encourage	encourage	VBP
10_1101-2021_01_02_425006	289	16	us	-PRON-	PRP
10_1101-2021_01_02_425006	289	17	to	to	TO
10_1101-2021_01_02_425006	289	18	discover	discover	VB
10_1101-2021_01_02_425006	289	19	more	more	JJR
10_1101-2021_01_02_425006	289	20	439	439	CD
10_1101-2021_01_02_425006	289	21	information	information	NN
10_1101-2021_01_02_425006	289	22	to	to	TO
10_1101-2021_01_02_425006	289	23	determine	determine	VB
10_1101-2021_01_02_425006	289	24	the	the	DT
10_1101-2021_01_02_425006	289	25	ATU	ATU	NNP
10_1101-2021_01_02_425006	289	26	structure	structure	NN
10_1101-2021_01_02_425006	289	27	in	in	IN
10_1101-2021_01_02_425006	289	28	bacteria	bacteria	NNS
10_1101-2021_01_02_425006	289	29	.	.	.
10_1101-2021_01_02_425006	290	1	For	for	IN
10_1101-2021_01_02_425006	290	2	example	example	NN
10_1101-2021_01_02_425006	290	3	,	,	,
10_1101-2021_01_02_425006	290	4	we	-PRON-	PRP
10_1101-2021_01_02_425006	290	5	plan	plan	VBP
10_1101-2021_01_02_425006	290	6	to	to	TO
10_1101-2021_01_02_425006	290	7	add	add	VB
10_1101-2021_01_02_425006	290	8	high	high	JJ
10_1101-2021_01_02_425006	290	9	confidence	confidence	NN
10_1101-2021_01_02_425006	290	10	440	440	CD
10_1101-2021_01_02_425006	290	11	TSSs	tss	NNS
10_1101-2021_01_02_425006	290	12	and	and	CC
10_1101-2021_01_02_425006	290	13	TTSs	tts	NNS
10_1101-2021_01_02_425006	290	14	information	information	NN
10_1101-2021_01_02_425006	290	15	to	to	IN
10_1101-2021_01_02_425006	290	16	our	-PRON-	PRP$
10_1101-2021_01_02_425006	290	17	programming	programming	NN
10_1101-2021_01_02_425006	290	18	model	model	NN
10_1101-2021_01_02_425006	290	19	in	in	IN
10_1101-2021_01_02_425006	290	20	the	the	DT
10_1101-2021_01_02_425006	290	21	future	future	NN
10_1101-2021_01_02_425006	290	22	.	.	.
10_1101-2021_01_02_425006	291	1	Additionally	additionally	RB
10_1101-2021_01_02_425006	291	2	,	,	,
10_1101-2021_01_02_425006	291	3	since	since	IN
10_1101-2021_01_02_425006	291	4	the	the	DT
10_1101-2021_01_02_425006	291	5	microbiome	microbiome	NN
10_1101-2021_01_02_425006	291	6	441	441	CD
10_1101-2021_01_02_425006	291	7	is	be	VBZ
10_1101-2021_01_02_425006	291	8	increasingly	increasingly	RB
10_1101-2021_01_02_425006	291	9	recognized	recognize	VBN
10_1101-2021_01_02_425006	291	10	as	as	IN
10_1101-2021_01_02_425006	291	11	a	a	DT
10_1101-2021_01_02_425006	291	12	critical	critical	JJ
10_1101-2021_01_02_425006	291	13	component	component	NN
10_1101-2021_01_02_425006	291	14	in	in	IN
10_1101-2021_01_02_425006	291	15	human	human	JJ
10_1101-2021_01_02_425006	291	16	diseases	disease	NNS
10_1101-2021_01_02_425006	291	17	,	,	,
10_1101-2021_01_02_425006	291	18	such	such	JJ
10_1101-2021_01_02_425006	291	19	as	as	IN
10_1101-2021_01_02_425006	291	20	inflammatory	inflammatory	JJ
10_1101-2021_01_02_425006	291	21	bowel	bowel	NN
10_1101-2021_01_02_425006	291	22	442	442	CD
10_1101-2021_01_02_425006	291	23	disease	disease	NN
10_1101-2021_01_02_425006	291	24	(	(	-LRB-
10_1101-2021_01_02_425006	291	25	50	50	CD
10_1101-2021_01_02_425006	291	26	)	)	-RRB-
10_1101-2021_01_02_425006	291	27	,	,	,
10_1101-2021_01_02_425006	291	28	antibiotic	antibiotic	NNP
10_1101-2021_01_02_425006	291	29	-	-	HYPH
10_1101-2021_01_02_425006	291	30	associated	associate	VBN
10_1101-2021_01_02_425006	291	31	diarrhoea	diarrhoea	NNP
10_1101-2021_01_02_425006	291	32	(	(	-LRB-
10_1101-2021_01_02_425006	291	33	51	51	CD
10_1101-2021_01_02_425006	291	34	)	)	-RRB-
10_1101-2021_01_02_425006	291	35	,	,	,
10_1101-2021_01_02_425006	291	36	neurological	neurological	JJ
10_1101-2021_01_02_425006	291	37	disorders	disorder	NNS
10_1101-2021_01_02_425006	291	38	(	(	-LRB-
10_1101-2021_01_02_425006	291	39	52	52	CD
10_1101-2021_01_02_425006	291	40	)	)	-RRB-
10_1101-2021_01_02_425006	291	41	,	,	,
10_1101-2021_01_02_425006	291	42	and	and	CC
10_1101-2021_01_02_425006	291	43	cancer	cancer	NN
10_1101-2021_01_02_425006	291	44	(	(	-LRB-
10_1101-2021_01_02_425006	291	45	53	53	CD
10_1101-2021_01_02_425006	291	46	)	)	-RRB-
10_1101-2021_01_02_425006	291	47	(	(	-LRB-
10_1101-2021_01_02_425006	291	48	54	54	CD
10_1101-2021_01_02_425006	291	49	)	)	-RRB-
10_1101-2021_01_02_425006	291	50	,	,	,
10_1101-2021_01_02_425006	291	51	443	443	CD
10_1101-2021_01_02_425006	291	52	predicting	predict	VBG
10_1101-2021_01_02_425006	291	53	new	new	JJ
10_1101-2021_01_02_425006	291	54	ATUs	atu	NNS
10_1101-2021_01_02_425006	291	55	of	of	IN
10_1101-2021_01_02_425006	291	56	uncultured	uncultured	JJ
10_1101-2021_01_02_425006	291	57	species	specie	NNS
10_1101-2021_01_02_425006	291	58	from	from	IN
10_1101-2021_01_02_425006	291	59	metagenomic	metagenomic	JJ
10_1101-2021_01_02_425006	291	60	and	and	CC
10_1101-2021_01_02_425006	291	61	metatranscriptomic	metatranscriptomic	JJ
10_1101-2021_01_02_425006	291	62	data	datum	NNS
10_1101-2021_01_02_425006	291	63	is	be	VBZ
10_1101-2021_01_02_425006	291	64	of	of	IN
10_1101-2021_01_02_425006	291	65	great	great	JJ
10_1101-2021_01_02_425006	291	66	444	444	CD
10_1101-2021_01_02_425006	291	67	significance	significance	NN
10_1101-2021_01_02_425006	291	68	in	in	IN
10_1101-2021_01_02_425006	291	69	uncovering	uncover	VBG
10_1101-2021_01_02_425006	291	70	new	new	JJ
10_1101-2021_01_02_425006	291	71	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	291	72	pathway	pathway	NN
10_1101-2021_01_02_425006	291	73	and	and	CC
10_1101-2021_01_02_425006	291	74	metabolic	metabolic	JJ
10_1101-2021_01_02_425006	291	75	products	product	NNS
10_1101-2021_01_02_425006	291	76	during	during	IN
10_1101-2021_01_02_425006	291	77	the	the	DT
10_1101-2021_01_02_425006	291	78	development	development	NN
10_1101-2021_01_02_425006	291	79	of	of	IN
10_1101-2021_01_02_425006	291	80	445	445	CD
10_1101-2021_01_02_425006	291	81	.CC	.CC	:
10_1101-2021_01_02_425006	291	82	-	-	:
10_1101-2021_01_02_425006	291	83	BY	by	IN
10_1101-2021_01_02_425006	291	84	-	-	HYPH
10_1101-2021_01_02_425006	291	85	NC	NC	NNP
10_1101-2021_01_02_425006	291	86	-	-	HYPH
10_1101-2021_01_02_425006	291	87	ND	ND	NNP
10_1101-2021_01_02_425006	291	88	4.0	4.0	CD
10_1101-2021_01_02_425006	291	89	International	International	NNP
10_1101-2021_01_02_425006	291	90	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	291	91	under	under	IN
10_1101-2021_01_02_425006	291	92	a	a	DT
10_1101-2021_01_02_425006	291	93	(	(	-LRB-
10_1101-2021_01_02_425006	291	94	which	which	WDT
10_1101-2021_01_02_425006	291	95	was	be	VBD
10_1101-2021_01_02_425006	291	96	not	not	RB
10_1101-2021_01_02_425006	291	97	certified	certify	VBN
10_1101-2021_01_02_425006	291	98	by	by	IN
10_1101-2021_01_02_425006	291	99	peer	peer	NN
10_1101-2021_01_02_425006	291	100	review	review	NN
10_1101-2021_01_02_425006	291	101	)	)	-RRB-
10_1101-2021_01_02_425006	291	102	is	be	VBZ
10_1101-2021_01_02_425006	291	103	the	the	DT
10_1101-2021_01_02_425006	291	104	author	author	NN
10_1101-2021_01_02_425006	291	105	/	/	SYM
10_1101-2021_01_02_425006	291	106	funder	funder	NN
10_1101-2021_01_02_425006	291	107	,	,	,
10_1101-2021_01_02_425006	291	108	who	who	WP
10_1101-2021_01_02_425006	291	109	has	have	VBZ
10_1101-2021_01_02_425006	291	110	granted	grant	VBN
10_1101-2021_01_02_425006	291	111	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	291	112	a	a	DT
10_1101-2021_01_02_425006	291	113	license	license	NN
10_1101-2021_01_02_425006	291	114	to	to	TO
10_1101-2021_01_02_425006	291	115	display	display	VB
10_1101-2021_01_02_425006	291	116	the	the	DT
10_1101-2021_01_02_425006	291	117	preprint	preprint	NN
10_1101-2021_01_02_425006	291	118	in	in	IN
10_1101-2021_01_02_425006	291	119	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	291	120	.	.	.
10_1101-2021_01_02_425006	292	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	292	2	is	be	VBZ
10_1101-2021_01_02_425006	292	3	made	make	VBN
10_1101-2021_01_02_425006	292	4	The	the	DT
10_1101-2021_01_02_425006	292	5	copyright	copyright	NN
10_1101-2021_01_02_425006	292	6	holder	holder	NN
10_1101-2021_01_02_425006	292	7	for	for	IN
10_1101-2021_01_02_425006	292	8	this	this	DT
10_1101-2021_01_02_425006	292	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	292	10	version	version	NN
10_1101-2021_01_02_425006	292	11	posted	post	VBD
10_1101-2021_01_02_425006	292	12	January	January	NNP
10_1101-2021_01_02_425006	292	13	6	6	CD
10_1101-2021_01_02_425006	292	14	,	,	,
10_1101-2021_01_02_425006	292	15	2021	2021	CD
10_1101-2021_01_02_425006	292	16	.	.	.
10_1101-2021_01_02_425006	292	17	;	;	:
10_1101-2021_01_02_425006	292	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	292	19	:	:	:
10_1101-2021_01_02_425006	292	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	292	21	preprint	preprint	NN
10_1101-2021_01_02_425006	292	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	292	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	292	24	26	26	CD
10_1101-2021_01_02_425006	292	25	diseases	disease	NNS
10_1101-2021_01_02_425006	292	26	(	(	-LRB-
10_1101-2021_01_02_425006	292	27	55	55	CD
10_1101-2021_01_02_425006	292	28	)	)	-RRB-
10_1101-2021_01_02_425006	292	29	.	.	.
10_1101-2021_01_02_425006	293	1	However	however	RB
10_1101-2021_01_02_425006	293	2	,	,	,
10_1101-2021_01_02_425006	293	3	due	due	IN
10_1101-2021_01_02_425006	293	4	to	to	IN
10_1101-2021_01_02_425006	293	5	a	a	DT
10_1101-2021_01_02_425006	293	6	majority	majority	NN
10_1101-2021_01_02_425006	293	7	of	of	IN
10_1101-2021_01_02_425006	293	8	species	specie	NNS
10_1101-2021_01_02_425006	293	9	with	with	IN
10_1101-2021_01_02_425006	293	10	unknown	unknown	JJ
10_1101-2021_01_02_425006	293	11	genomes	genome	NNS
10_1101-2021_01_02_425006	293	12	or	or	CC
10_1101-2021_01_02_425006	293	13	genome	genome	JJ
10_1101-2021_01_02_425006	293	14	annotations	annotation	NNS
10_1101-2021_01_02_425006	293	15	446	446	CD
10_1101-2021_01_02_425006	293	16	within	within	IN
10_1101-2021_01_02_425006	293	17	a	a	DT
10_1101-2021_01_02_425006	293	18	microbial	microbial	JJ
10_1101-2021_01_02_425006	293	19	community	community	NN
10_1101-2021_01_02_425006	293	20	,	,	,
10_1101-2021_01_02_425006	293	21	ATU	ATU	NNP
10_1101-2021_01_02_425006	293	22	prediction	prediction	NN
10_1101-2021_01_02_425006	293	23	on	on	IN
10_1101-2021_01_02_425006	293	24	metagenomics	metagenomics	NNP
10_1101-2021_01_02_425006	293	25	and	and	CC
10_1101-2021_01_02_425006	293	26	metatranscriptomics	metatranscriptomics	NNP
10_1101-2021_01_02_425006	293	27	is	be	VBZ
10_1101-2021_01_02_425006	293	28	still	still	RB
10_1101-2021_01_02_425006	293	29	a	a	DT
10_1101-2021_01_02_425006	293	30	447	447	CD
10_1101-2021_01_02_425006	293	31	challenging	challenging	NN
10_1101-2021_01_02_425006	293	32	task	task	NN
10_1101-2021_01_02_425006	293	33	,	,	,
10_1101-2021_01_02_425006	293	34	which	which	WDT
10_1101-2021_01_02_425006	293	35	encourage	encourage	VBP
10_1101-2021_01_02_425006	293	36	us	-PRON-	PRP
10_1101-2021_01_02_425006	293	37	to	to	TO
10_1101-2021_01_02_425006	293	38	pay	pay	VB
10_1101-2021_01_02_425006	293	39	more	more	JJR
10_1101-2021_01_02_425006	293	40	attention	attention	NN
10_1101-2021_01_02_425006	293	41	on	on	IN
10_1101-2021_01_02_425006	293	42	it	-PRON-	PRP
10_1101-2021_01_02_425006	293	43	.	.	.
10_1101-2021_01_02_425006	294	1	448	448	CD
10_1101-2021_01_02_425006	294	2	REFERENCES	reference	NNS
10_1101-2021_01_02_425006	294	3	449	449	CD
10_1101-2021_01_02_425006	294	4	1	1	CD
10_1101-2021_01_02_425006	294	5	.	.	.
10_1101-2021_01_02_425006	295	1	F.	F.	NNP
10_1101-2021_01_02_425006	295	2	Jacob	Jacob	NNP
10_1101-2021_01_02_425006	295	3	,	,	,
10_1101-2021_01_02_425006	295	4	D.	D.	NNP
10_1101-2021_01_02_425006	295	5	Perrin	Perrin	NNP
10_1101-2021_01_02_425006	295	6	,	,	,
10_1101-2021_01_02_425006	295	7	C.	C.	NNP
10_1101-2021_01_02_425006	295	8	Sanchez	Sanchez	NNP
10_1101-2021_01_02_425006	295	9	,	,	,
10_1101-2021_01_02_425006	295	10	J.	J.	NNP
10_1101-2021_01_02_425006	295	11	Monod	Monod	NNP
10_1101-2021_01_02_425006	295	12	,	,	,
10_1101-2021_01_02_425006	295	13	Operon	Operon	NNP
10_1101-2021_01_02_425006	295	14	:	:	:
10_1101-2021_01_02_425006	295	15	a	a	DT
10_1101-2021_01_02_425006	295	16	group	group	NN
10_1101-2021_01_02_425006	295	17	of	of	IN
10_1101-2021_01_02_425006	295	18	genes	gene	NNS
10_1101-2021_01_02_425006	295	19	with	with	IN
10_1101-2021_01_02_425006	295	20	the	the	DT
10_1101-2021_01_02_425006	295	21	expression	expression	NN
10_1101-2021_01_02_425006	295	22	450	450	CD
10_1101-2021_01_02_425006	295	23	coordinated	coordinate	VBN
10_1101-2021_01_02_425006	295	24	by	by	IN
10_1101-2021_01_02_425006	295	25	an	an	DT
10_1101-2021_01_02_425006	295	26	operator	operator	NN
10_1101-2021_01_02_425006	295	27	.	.	.
10_1101-2021_01_02_425006	296	1	C	C	NNP
10_1101-2021_01_02_425006	296	2	R	R	NNP
10_1101-2021_01_02_425006	296	3	Hebd	Hebd	NNP
10_1101-2021_01_02_425006	296	4	.	.	.
10_1101-2021_01_02_425006	297	1	Seances	seance	NNS
10_1101-2021_01_02_425006	297	2	.	.	.
10_1101-2021_01_02_425006	298	1	Acad	Acad	NNS
10_1101-2021_01_02_425006	298	2	.	.	.
10_1101-2021_01_02_425006	299	1	Sci	Sci	NNP
10_1101-2021_01_02_425006	299	2	250	250	CD
10_1101-2021_01_02_425006	299	3	,	,	,
10_1101-2021_01_02_425006	299	4	1727	1727	CD
10_1101-2021_01_02_425006	299	5	-	-	SYM
10_1101-2021_01_02_425006	299	6	1729	1729	CD
10_1101-2021_01_02_425006	299	7	(	(	-LRB-
10_1101-2021_01_02_425006	299	8	1960	1960	CD
10_1101-2021_01_02_425006	299	9	)	)	-RRB-
10_1101-2021_01_02_425006	299	10	.	.	.
10_1101-2021_01_02_425006	300	1	451	451	CD
10_1101-2021_01_02_425006	300	2	2	2	CD
10_1101-2021_01_02_425006	300	3	.	.	.
10_1101-2021_01_02_425006	301	1	F.	F.	NNP
10_1101-2021_01_02_425006	301	2	Jacob	Jacob	NNP
10_1101-2021_01_02_425006	301	3	,	,	,
10_1101-2021_01_02_425006	301	4	J.	J.	NNP
10_1101-2021_01_02_425006	301	5	Monod	Monod	NNP
10_1101-2021_01_02_425006	301	6	,	,	,
10_1101-2021_01_02_425006	301	7	Genetic	genetic	JJ
10_1101-2021_01_02_425006	301	8	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	301	9	mechanisms	mechanism	NNS
10_1101-2021_01_02_425006	301	10	in	in	IN
10_1101-2021_01_02_425006	301	11	the	the	DT
10_1101-2021_01_02_425006	301	12	synthesis	synthesis	NN
10_1101-2021_01_02_425006	301	13	of	of	IN
10_1101-2021_01_02_425006	301	14	proteins	protein	NNS
10_1101-2021_01_02_425006	301	15	.	.	.
10_1101-2021_01_02_425006	302	1	J.	J.	NNP
10_1101-2021_01_02_425006	302	2	Mol	Mol	NNP
10_1101-2021_01_02_425006	302	3	.	.	.
10_1101-2021_01_02_425006	303	1	Biol	Biol	NNP
10_1101-2021_01_02_425006	303	2	.	.	.
10_1101-2021_01_02_425006	304	1	3	3	CD
10_1101-2021_01_02_425006	304	2	,	,	,
10_1101-2021_01_02_425006	304	3	452	452	CD
10_1101-2021_01_02_425006	304	4	318	318	CD
10_1101-2021_01_02_425006	304	5	-	-	SYM
10_1101-2021_01_02_425006	304	6	356	356	CD
10_1101-2021_01_02_425006	304	7	(	(	-LRB-
10_1101-2021_01_02_425006	304	8	1961	1961	CD
10_1101-2021_01_02_425006	304	9	)	)	-RRB-
10_1101-2021_01_02_425006	304	10	.	.	.
10_1101-2021_01_02_425006	305	1	453	453	CD
10_1101-2021_01_02_425006	305	2	3	3	CD
10_1101-2021_01_02_425006	305	3	.	.	.
10_1101-2021_01_02_425006	306	1	Z.	Z.	NNP
10_1101-2021_01_02_425006	306	2	Liu	Liu	NNP
10_1101-2021_01_02_425006	306	3	,	,	,
10_1101-2021_01_02_425006	306	4	J.	J.	NNP
10_1101-2021_01_02_425006	306	5	Feng	Feng	NNP
10_1101-2021_01_02_425006	306	6	,	,	,
10_1101-2021_01_02_425006	306	7	B.	B.	NNP
10_1101-2021_01_02_425006	306	8	Yu	Yu	NNP
10_1101-2021_01_02_425006	306	9	,	,	,
10_1101-2021_01_02_425006	306	10	Q.	Q.	NNP
10_1101-2021_01_02_425006	306	11	Ma	Ma	NNP
10_1101-2021_01_02_425006	306	12	,	,	,
10_1101-2021_01_02_425006	306	13	B.	B.	NNP
10_1101-2021_01_02_425006	306	14	Liu	Liu	NNP
10_1101-2021_01_02_425006	306	15	,	,	,
10_1101-2021_01_02_425006	306	16	The	the	DT
10_1101-2021_01_02_425006	306	17	functional	functional	JJ
10_1101-2021_01_02_425006	306	18	determinants	determinant	NNS
10_1101-2021_01_02_425006	306	19	in	in	IN
10_1101-2021_01_02_425006	306	20	the	the	DT
10_1101-2021_01_02_425006	306	21	organization	organization	NN
10_1101-2021_01_02_425006	306	22	of	of	IN
10_1101-2021_01_02_425006	306	23	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	306	24	454	454	CD
10_1101-2021_01_02_425006	306	25	genomes	genome	NNS
10_1101-2021_01_02_425006	306	26	.	.	.
10_1101-2021_01_02_425006	307	1	Brief	brief	JJ
10_1101-2021_01_02_425006	307	2	.	.	.
10_1101-2021_01_02_425006	308	1	Bioinform	Bioinform	NNP
10_1101-2021_01_02_425006	308	2	.	.	NNP
10_1101-2021_01_02_425006	308	3	,	,	,
10_1101-2021_01_02_425006	308	4	doi.org/10.1093/bib/bbaa1172	doi.org/10.1093/bib/bbaa1172	NN
10_1101-2021_01_02_425006	308	5	(	(	-LRB-
10_1101-2021_01_02_425006	308	6	2020	2020	CD
10_1101-2021_01_02_425006	308	7	)	)	-RRB-
10_1101-2021_01_02_425006	308	8	.	.	.
10_1101-2021_01_02_425006	309	1	455	455	CD
10_1101-2021_01_02_425006	309	2	4	4	CD
10_1101-2021_01_02_425006	309	3	.	.	.
10_1101-2021_01_02_425006	310	1	W.-C.	W.-C.	NNP
10_1101-2021_01_02_425006	310	2	Chou	Chou	NNP
10_1101-2021_01_02_425006	310	3	,	,	,
10_1101-2021_01_02_425006	310	4	Q.	Q.	NNP
10_1101-2021_01_02_425006	310	5	Ma	Ma	NNP
10_1101-2021_01_02_425006	310	6	,	,	,
10_1101-2021_01_02_425006	310	7	S.	S.	NNP
10_1101-2021_01_02_425006	310	8	Yang	Yang	NNP
10_1101-2021_01_02_425006	310	9	,	,	,
10_1101-2021_01_02_425006	310	10	S.	S.	NNP
10_1101-2021_01_02_425006	310	11	Cao	Cao	NNP
10_1101-2021_01_02_425006	310	12	,	,	,
10_1101-2021_01_02_425006	310	13	D.	D.	NNP
10_1101-2021_01_02_425006	310	14	M.	M.	NNP
10_1101-2021_01_02_425006	310	15	Klingeman	Klingeman	NNP
10_1101-2021_01_02_425006	310	16	,	,	,
10_1101-2021_01_02_425006	310	17	S.	S.	NNP
10_1101-2021_01_02_425006	310	18	D.	D.	NNP
10_1101-2021_01_02_425006	310	19	Brown	Brown	NNP
10_1101-2021_01_02_425006	310	20	,	,	,
10_1101-2021_01_02_425006	310	21	Y.	Y.	NNP
10_1101-2021_01_02_425006	310	22	Xu	Xu	NNP
10_1101-2021_01_02_425006	310	23	,	,	,
10_1101-2021_01_02_425006	310	24	Analysis	Analysis	NNP
10_1101-2021_01_02_425006	310	25	of	of	IN
10_1101-2021_01_02_425006	310	26	strand-456	strand-456	NNP
10_1101-2021_01_02_425006	310	27	specific	specific	JJ
10_1101-2021_01_02_425006	310	28	RNA	RNA	NNP
10_1101-2021_01_02_425006	310	29	-	-	HYPH
10_1101-2021_01_02_425006	310	30	seq	seq	NN
10_1101-2021_01_02_425006	310	31	data	datum	NNS
10_1101-2021_01_02_425006	310	32	using	use	VBG
10_1101-2021_01_02_425006	310	33	machine	machine	NN
10_1101-2021_01_02_425006	310	34	learning	learning	NN
10_1101-2021_01_02_425006	310	35	reveals	reveal	VBZ
10_1101-2021_01_02_425006	310	36	the	the	DT
10_1101-2021_01_02_425006	310	37	structures	structure	NNS
10_1101-2021_01_02_425006	310	38	of	of	IN
10_1101-2021_01_02_425006	310	39	transcription	transcription	NN
10_1101-2021_01_02_425006	310	40	units	unit	NNS
10_1101-2021_01_02_425006	310	41	in	in	IN
10_1101-2021_01_02_425006	310	42	457	457	CD
10_1101-2021_01_02_425006	310	43	Clostridium	Clostridium	NNP
10_1101-2021_01_02_425006	310	44	thermocellum	thermocellum	NN
10_1101-2021_01_02_425006	310	45	.	.	.
10_1101-2021_01_02_425006	311	1	Nucleic	Nucleic	NNP
10_1101-2021_01_02_425006	311	2	Acids	Acids	NNPS
10_1101-2021_01_02_425006	311	3	Res	Res	NNP
10_1101-2021_01_02_425006	311	4	.	.	.
10_1101-2021_01_02_425006	312	1	43	43	CD
10_1101-2021_01_02_425006	312	2	,	,	,
10_1101-2021_01_02_425006	312	3	e67-e67	e67-e67	NNP
10_1101-2021_01_02_425006	312	4	(	(	-LRB-
10_1101-2021_01_02_425006	312	5	2015	2015	CD
10_1101-2021_01_02_425006	312	6	)	)	-RRB-
10_1101-2021_01_02_425006	312	7	.	.	.
10_1101-2021_01_02_425006	313	1	458	458	CD
10_1101-2021_01_02_425006	313	2	5	5	CD
10_1101-2021_01_02_425006	313	3	.	.	.
10_1101-2021_01_02_425006	314	1	S.-Y.	s.-y.	XX
10_1101-2021_01_02_425006	315	1	Niu	niu	UH
10_1101-2021_01_02_425006	315	2	,	,	,
10_1101-2021_01_02_425006	315	3	B.	B.	NNP
10_1101-2021_01_02_425006	315	4	Liu	Liu	NNP
10_1101-2021_01_02_425006	315	5	,	,	,
10_1101-2021_01_02_425006	315	6	Q.	Q.	NNP
10_1101-2021_01_02_425006	315	7	Ma	Ma	NNP
10_1101-2021_01_02_425006	315	8	,	,	,
10_1101-2021_01_02_425006	315	9	W.-C.	W.-C.	NNP
10_1101-2021_01_02_425006	315	10	Chou	Chou	NNP
10_1101-2021_01_02_425006	315	11	,	,	,
10_1101-2021_01_02_425006	315	12	rSeqTU	rseqtu	CD
10_1101-2021_01_02_425006	315	13	—	—	:
10_1101-2021_01_02_425006	315	14	a	a	DT
10_1101-2021_01_02_425006	315	15	machine	machine	NN
10_1101-2021_01_02_425006	315	16	-	-	HYPH
10_1101-2021_01_02_425006	315	17	learning	learn	VBG
10_1101-2021_01_02_425006	315	18	based	base	VBN
10_1101-2021_01_02_425006	315	19	R	r	NN
10_1101-2021_01_02_425006	315	20	package	package	NN
10_1101-2021_01_02_425006	315	21	for	for	IN
10_1101-2021_01_02_425006	315	22	459	459	CD
10_1101-2021_01_02_425006	315	23	prediction	prediction	NN
10_1101-2021_01_02_425006	315	24	of	of	IN
10_1101-2021_01_02_425006	315	25	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	315	26	transcription	transcription	NN
10_1101-2021_01_02_425006	315	27	units	unit	NNS
10_1101-2021_01_02_425006	315	28	.	.	.
10_1101-2021_01_02_425006	316	1	Frontiers	frontier	NNS
10_1101-2021_01_02_425006	316	2	in	in	IN
10_1101-2021_01_02_425006	316	3	genetics	genetic	NNS
10_1101-2021_01_02_425006	316	4	10	10	CD
10_1101-2021_01_02_425006	316	5	,	,	,
10_1101-2021_01_02_425006	316	6	374	374	CD
10_1101-2021_01_02_425006	316	7	(	(	-LRB-
10_1101-2021_01_02_425006	316	8	2019	2019	CD
10_1101-2021_01_02_425006	316	9	)	)	-RRB-
10_1101-2021_01_02_425006	316	10	.	.	.
10_1101-2021_01_02_425006	317	1	460	460	CD
10_1101-2021_01_02_425006	317	2	6	6	CD
10_1101-2021_01_02_425006	317	3	.	.	.
10_1101-2021_01_02_425006	318	1	B.	B.	NNP
10_1101-2021_01_02_425006	318	2	Yan	Yan	NNP
10_1101-2021_01_02_425006	318	3	,	,	,
10_1101-2021_01_02_425006	318	4	M.	M.	NNP
10_1101-2021_01_02_425006	318	5	Boitano	Boitano	NNP
10_1101-2021_01_02_425006	318	6	,	,	,
10_1101-2021_01_02_425006	318	7	T.	T.	NNP
10_1101-2021_01_02_425006	318	8	A.	a.	NN
10_1101-2021_01_02_425006	318	9	Clark	Clark	NNP
10_1101-2021_01_02_425006	318	10	,	,	,
10_1101-2021_01_02_425006	318	11	L.	L.	NNP
10_1101-2021_01_02_425006	318	12	Ettwiller	Ettwiller	NNP
10_1101-2021_01_02_425006	318	13	,	,	,
10_1101-2021_01_02_425006	318	14	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	318	15	-	-	HYPH
10_1101-2021_01_02_425006	318	16	Cappable	cappable	JJ
10_1101-2021_01_02_425006	318	17	-	-	HYPH
10_1101-2021_01_02_425006	318	18	seq	seq	NN
10_1101-2021_01_02_425006	318	19	reveals	reveal	VBZ
10_1101-2021_01_02_425006	318	20	complex	complex	JJ
10_1101-2021_01_02_425006	318	21	operon	operon	NNP
10_1101-2021_01_02_425006	318	22	461	461	CD
10_1101-2021_01_02_425006	318	23	variants	variant	NNS
10_1101-2021_01_02_425006	318	24	in	in	IN
10_1101-2021_01_02_425006	318	25	bacteria	bacteria	NNS
10_1101-2021_01_02_425006	318	26	.	.	.
10_1101-2021_01_02_425006	319	1	Nat	Nat	NNP
10_1101-2021_01_02_425006	319	2	.	.	.
10_1101-2021_01_02_425006	320	1	Commun	Commun	VBN
10_1101-2021_01_02_425006	320	2	.	.	.
10_1101-2021_01_02_425006	321	1	9	9	CD
10_1101-2021_01_02_425006	321	2	,	,	,
10_1101-2021_01_02_425006	321	3	3676	3676	CD
10_1101-2021_01_02_425006	321	4	(	(	-LRB-
10_1101-2021_01_02_425006	321	5	2018	2018	CD
10_1101-2021_01_02_425006	321	6	)	)	-RRB-
10_1101-2021_01_02_425006	321	7	.	.	.
10_1101-2021_01_02_425006	322	1	462	462	CD
10_1101-2021_01_02_425006	322	2	.CC	.CC	:
10_1101-2021_01_02_425006	322	3	-	-	HYPH
10_1101-2021_01_02_425006	322	4	BY	by	IN
10_1101-2021_01_02_425006	322	5	-	-	HYPH
10_1101-2021_01_02_425006	322	6	NC	NC	NNP
10_1101-2021_01_02_425006	322	7	-	-	HYPH
10_1101-2021_01_02_425006	322	8	ND	ND	NNP
10_1101-2021_01_02_425006	322	9	4.0	4.0	CD
10_1101-2021_01_02_425006	322	10	International	International	NNP
10_1101-2021_01_02_425006	322	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	322	12	under	under	IN
10_1101-2021_01_02_425006	322	13	a	a	DT
10_1101-2021_01_02_425006	322	14	(	(	-LRB-
10_1101-2021_01_02_425006	322	15	which	which	WDT
10_1101-2021_01_02_425006	322	16	was	be	VBD
10_1101-2021_01_02_425006	322	17	not	not	RB
10_1101-2021_01_02_425006	322	18	certified	certify	VBN
10_1101-2021_01_02_425006	322	19	by	by	IN
10_1101-2021_01_02_425006	322	20	peer	peer	NN
10_1101-2021_01_02_425006	322	21	review	review	NN
10_1101-2021_01_02_425006	322	22	)	)	-RRB-
10_1101-2021_01_02_425006	322	23	is	be	VBZ
10_1101-2021_01_02_425006	322	24	the	the	DT
10_1101-2021_01_02_425006	322	25	author	author	NN
10_1101-2021_01_02_425006	322	26	/	/	SYM
10_1101-2021_01_02_425006	322	27	funder	funder	NN
10_1101-2021_01_02_425006	322	28	,	,	,
10_1101-2021_01_02_425006	322	29	who	who	WP
10_1101-2021_01_02_425006	322	30	has	have	VBZ
10_1101-2021_01_02_425006	322	31	granted	grant	VBN
10_1101-2021_01_02_425006	322	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	322	33	a	a	DT
10_1101-2021_01_02_425006	322	34	license	license	NN
10_1101-2021_01_02_425006	322	35	to	to	TO
10_1101-2021_01_02_425006	322	36	display	display	VB
10_1101-2021_01_02_425006	322	37	the	the	DT
10_1101-2021_01_02_425006	322	38	preprint	preprint	NN
10_1101-2021_01_02_425006	322	39	in	in	IN
10_1101-2021_01_02_425006	322	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	322	41	.	.	.
10_1101-2021_01_02_425006	323	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	323	2	is	be	VBZ
10_1101-2021_01_02_425006	323	3	made	make	VBN
10_1101-2021_01_02_425006	323	4	The	the	DT
10_1101-2021_01_02_425006	323	5	copyright	copyright	NN
10_1101-2021_01_02_425006	323	6	holder	holder	NN
10_1101-2021_01_02_425006	323	7	for	for	IN
10_1101-2021_01_02_425006	323	8	this	this	DT
10_1101-2021_01_02_425006	323	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	323	10	version	version	NN
10_1101-2021_01_02_425006	323	11	posted	post	VBD
10_1101-2021_01_02_425006	323	12	January	January	NNP
10_1101-2021_01_02_425006	323	13	6	6	CD
10_1101-2021_01_02_425006	323	14	,	,	,
10_1101-2021_01_02_425006	323	15	2021	2021	CD
10_1101-2021_01_02_425006	323	16	.	.	.
10_1101-2021_01_02_425006	323	17	;	;	:
10_1101-2021_01_02_425006	323	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	323	19	:	:	:
10_1101-2021_01_02_425006	323	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	323	21	preprint	preprint	NN
10_1101-2021_01_02_425006	323	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	323	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	323	24	27	27	CD
10_1101-2021_01_02_425006	323	25	7	7	CD
10_1101-2021_01_02_425006	323	26	.	.	.
10_1101-2021_01_02_425006	324	1	X.	X.	NNP
10_1101-2021_01_02_425006	324	2	Ju	Ju	NNP
10_1101-2021_01_02_425006	324	3	,	,	,
10_1101-2021_01_02_425006	324	4	D.	D.	NNP
10_1101-2021_01_02_425006	324	5	Li	Li	NNP
10_1101-2021_01_02_425006	324	6	,	,	,
10_1101-2021_01_02_425006	324	7	S.	S.	NNP
10_1101-2021_01_02_425006	324	8	Liu	Liu	NNP
10_1101-2021_01_02_425006	324	9	,	,	,
10_1101-2021_01_02_425006	324	10	Full	Full	NNP
10_1101-2021_01_02_425006	324	11	-	-	HYPH
10_1101-2021_01_02_425006	324	12	length	length	NN
10_1101-2021_01_02_425006	324	13	RNA	RNA	NNP
10_1101-2021_01_02_425006	324	14	profiling	profiling	NN
10_1101-2021_01_02_425006	324	15	reveals	reveal	VBZ
10_1101-2021_01_02_425006	324	16	pervasive	pervasive	JJ
10_1101-2021_01_02_425006	324	17	bidirectional	bidirectional	JJ
10_1101-2021_01_02_425006	324	18	transcription	transcription	NN
10_1101-2021_01_02_425006	324	19	463	463	CD
10_1101-2021_01_02_425006	324	20	terminators	terminator	NNS
10_1101-2021_01_02_425006	324	21	in	in	IN
10_1101-2021_01_02_425006	324	22	bacteria	bacteria	NNS
10_1101-2021_01_02_425006	324	23	.	.	.
10_1101-2021_01_02_425006	325	1	Nature	nature	NN
10_1101-2021_01_02_425006	325	2	microbiology	microbiology	NN
10_1101-2021_01_02_425006	325	3	4	4	CD
10_1101-2021_01_02_425006	325	4	,	,	,
10_1101-2021_01_02_425006	325	5	1907	1907	CD
10_1101-2021_01_02_425006	325	6	-	-	SYM
10_1101-2021_01_02_425006	325	7	1918	1918	CD
10_1101-2021_01_02_425006	325	8	(	(	-LRB-
10_1101-2021_01_02_425006	325	9	2019	2019	CD
10_1101-2021_01_02_425006	325	10	)	)	-RRB-
10_1101-2021_01_02_425006	325	11	.	.	.
10_1101-2021_01_02_425006	326	1	464	464	CD
10_1101-2021_01_02_425006	326	2	8	8	CD
10_1101-2021_01_02_425006	326	3	.	.	.
10_1101-2021_01_02_425006	327	1	K.	K.	NNP
10_1101-2021_01_02_425006	327	2	Totsuka	Totsuka	NNP
10_1101-2021_01_02_425006	327	3	,	,	,
10_1101-2021_01_02_425006	327	4	K.	K.	NNP
10_1101-2021_01_02_425006	327	5	Totsuka	Totsuka	NNP
10_1101-2021_01_02_425006	327	6	,	,	,
10_1101-2021_01_02_425006	327	7	The	the	DT
10_1101-2021_01_02_425006	327	8	Transcription	Transcription	NNP
10_1101-2021_01_02_425006	327	9	Unit	Unit	NNP
10_1101-2021_01_02_425006	327	10	Architecture	Architecture	NNP
10_1101-2021_01_02_425006	327	11	of	of	IN
10_1101-2021_01_02_425006	327	12	the	the	DT
10_1101-2021_01_02_425006	327	13	Escherichia	Escherichia	NNP
10_1101-2021_01_02_425006	327	14	Coli	Coli	NNPS
10_1101-2021_01_02_425006	327	15	Genome	Genome	NNP
10_1101-2021_01_02_425006	327	16	.	.	.
10_1101-2021_01_02_425006	328	1	Nat	Nat	NNP
10_1101-2021_01_02_425006	328	2	.	.	.
10_1101-2021_01_02_425006	329	1	465	465	CD
10_1101-2021_01_02_425006	329	2	Biotechnol	Biotechnol	NNPS
10_1101-2021_01_02_425006	329	3	.	.	.
10_1101-2021_01_02_425006	330	1	27	27	CD
10_1101-2021_01_02_425006	330	2	,	,	,
10_1101-2021_01_02_425006	330	3	1043	1043	CD
10_1101-2021_01_02_425006	330	4	-	-	SYM
10_1101-2021_01_02_425006	330	5	1049	1049	CD
10_1101-2021_01_02_425006	330	6	(	(	-LRB-
10_1101-2021_01_02_425006	330	7	2009	2009	CD
10_1101-2021_01_02_425006	330	8	)	)	-RRB-
10_1101-2021_01_02_425006	330	9	.	.	.
10_1101-2021_01_02_425006	331	1	466	466	CD
10_1101-2021_01_02_425006	331	2	9	9	CD
10_1101-2021_01_02_425006	331	3	.	.	.
10_1101-2021_01_02_425006	332	1	A.	A.	NNP
10_1101-2021_01_02_425006	332	2	H.	H.	NNP
10_1101-2021_01_02_425006	332	3	Bhat	Bhat	NNP
10_1101-2021_01_02_425006	332	4	,	,	,
10_1101-2021_01_02_425006	332	5	D.	D.	NNP
10_1101-2021_01_02_425006	332	6	Pathak	Pathak	NNP
10_1101-2021_01_02_425006	332	7	,	,	,
10_1101-2021_01_02_425006	332	8	A.	a.	NN
10_1101-2021_01_02_425006	332	9	Rao	Rao	NNP
10_1101-2021_01_02_425006	332	10	,	,	,
10_1101-2021_01_02_425006	332	11	The	the	DT
10_1101-2021_01_02_425006	332	12	alr	alr	NN
10_1101-2021_01_02_425006	332	13	-	-	HYPH
10_1101-2021_01_02_425006	332	14	groEL1	groel1	NN
10_1101-2021_01_02_425006	332	15	operon	operon	NN
10_1101-2021_01_02_425006	332	16	in	in	IN
10_1101-2021_01_02_425006	332	17	Mycobacterium	Mycobacterium	NNP
10_1101-2021_01_02_425006	332	18	tuberculosis	tuberculosis	NN
10_1101-2021_01_02_425006	332	19	:	:	:
10_1101-2021_01_02_425006	332	20	an	an	DT
10_1101-2021_01_02_425006	332	21	interplay	interplay	NN
10_1101-2021_01_02_425006	332	22	467	467	CD
10_1101-2021_01_02_425006	332	23	of	of	IN
10_1101-2021_01_02_425006	332	24	multiple	multiple	JJ
10_1101-2021_01_02_425006	332	25	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	332	26	elements	element	NNS
10_1101-2021_01_02_425006	332	27	.	.	.
10_1101-2021_01_02_425006	333	1	Scientific	Scientific	NNP
10_1101-2021_01_02_425006	333	2	Reports	report	NNS
10_1101-2021_01_02_425006	333	3	7	7	CD
10_1101-2021_01_02_425006	333	4	,	,	,
10_1101-2021_01_02_425006	333	5	43772	43772	CD
10_1101-2021_01_02_425006	333	6	(	(	-LRB-
10_1101-2021_01_02_425006	333	7	2017	2017	CD
10_1101-2021_01_02_425006	333	8	)	)	-RRB-
10_1101-2021_01_02_425006	333	9	.	.	.
10_1101-2021_01_02_425006	334	1	468	468	CD
10_1101-2021_01_02_425006	334	2	10	10	CD
10_1101-2021_01_02_425006	334	3	.	.	.
10_1101-2021_01_02_425006	335	1	C.	C.	NNP
10_1101-2021_01_02_425006	335	2	M.	M.	NNP
10_1101-2021_01_02_425006	335	3	Sharma	Sharma	NNP
10_1101-2021_01_02_425006	335	4	,	,	,
10_1101-2021_01_02_425006	335	5	S.	S.	NNP
10_1101-2021_01_02_425006	335	6	Hoffmann	Hoffmann	NNP
10_1101-2021_01_02_425006	335	7	,	,	,
10_1101-2021_01_02_425006	335	8	F.	F.	NNP
10_1101-2021_01_02_425006	335	9	Darfeuille	Darfeuille	NNP
10_1101-2021_01_02_425006	335	10	,	,	,
10_1101-2021_01_02_425006	335	11	J.	J.	NNP
10_1101-2021_01_02_425006	335	12	Reignier	Reignier	NNP
10_1101-2021_01_02_425006	335	13	,	,	,
10_1101-2021_01_02_425006	335	14	S.	S.	NNP
10_1101-2021_01_02_425006	335	15	Findeiß	Findeiß	NNP
10_1101-2021_01_02_425006	335	16	,	,	,
10_1101-2021_01_02_425006	335	17	A.	A.	NNP
10_1101-2021_01_02_425006	335	18	Sittka	Sittka	NNP
10_1101-2021_01_02_425006	335	19	,	,	,
10_1101-2021_01_02_425006	335	20	S.	S.	NNP
10_1101-2021_01_02_425006	335	21	Chabas	Chabas	NNP
10_1101-2021_01_02_425006	335	22	,	,	,
10_1101-2021_01_02_425006	335	23	K.	K.	NNP
10_1101-2021_01_02_425006	335	24	Reiche	Reiche	NNP
10_1101-2021_01_02_425006	335	25	,	,	,
10_1101-2021_01_02_425006	335	26	469	469	CD
10_1101-2021_01_02_425006	335	27	J.	J.	NNP
10_1101-2021_01_02_425006	335	28	Hackermüller	Hackermüller	NNP
10_1101-2021_01_02_425006	335	29	,	,	,
10_1101-2021_01_02_425006	335	30	R.	R.	NNP
10_1101-2021_01_02_425006	335	31	Reinhardt	Reinhardt	NNP
10_1101-2021_01_02_425006	335	32	,	,	,
10_1101-2021_01_02_425006	335	33	The	the	DT
10_1101-2021_01_02_425006	335	34	primary	primary	JJ
10_1101-2021_01_02_425006	335	35	transcriptome	transcriptome	NN
10_1101-2021_01_02_425006	335	36	of	of	IN
10_1101-2021_01_02_425006	335	37	the	the	DT
10_1101-2021_01_02_425006	335	38	major	major	JJ
10_1101-2021_01_02_425006	335	39	human	human	JJ
10_1101-2021_01_02_425006	335	40	pathogen	pathogen	NN
10_1101-2021_01_02_425006	335	41	470	470	CD
10_1101-2021_01_02_425006	335	42	Helicobacter	Helicobacter	NNP
10_1101-2021_01_02_425006	335	43	pylori	pylori	NN
10_1101-2021_01_02_425006	335	44	.	.	.
10_1101-2021_01_02_425006	336	1	Nature	nature	NN
10_1101-2021_01_02_425006	336	2	464	464	CD
10_1101-2021_01_02_425006	336	3	,	,	,
10_1101-2021_01_02_425006	336	4	250	250	CD
10_1101-2021_01_02_425006	336	5	-	-	HYPH
10_1101-2021_01_02_425006	336	6	255	255	CD
10_1101-2021_01_02_425006	336	7	(	(	-LRB-
10_1101-2021_01_02_425006	336	8	2010	2010	CD
10_1101-2021_01_02_425006	336	9	)	)	-RRB-
10_1101-2021_01_02_425006	336	10	.	.	.
10_1101-2021_01_02_425006	337	1	471	471	CD
10_1101-2021_01_02_425006	337	2	11	11	CD
10_1101-2021_01_02_425006	337	3	.	.	.
10_1101-2021_01_02_425006	338	1	J.	J.	NNP
10_1101-2021_01_02_425006	338	2	M.	M.	NNP
10_1101-2021_01_02_425006	338	3	Durand	Durand	NNP
10_1101-2021_01_02_425006	338	4	,	,	,
10_1101-2021_01_02_425006	338	5	G.	G.	NNP
10_1101-2021_01_02_425006	338	6	R.	R.	NNP
10_1101-2021_01_02_425006	338	7	Bjork	Bjork	NNP
10_1101-2021_01_02_425006	338	8	,	,	,
10_1101-2021_01_02_425006	338	9	Putrescine	Putrescine	NNP
10_1101-2021_01_02_425006	338	10	or	or	CC
10_1101-2021_01_02_425006	338	11	a	a	DT
10_1101-2021_01_02_425006	338	12	combination	combination	NN
10_1101-2021_01_02_425006	338	13	of	of	IN
10_1101-2021_01_02_425006	338	14	methionine	methionine	NN
10_1101-2021_01_02_425006	338	15	and	and	CC
10_1101-2021_01_02_425006	338	16	arginine	arginine	NNP
10_1101-2021_01_02_425006	338	17	restores	restore	VBZ
10_1101-2021_01_02_425006	338	18	472	472	CD
10_1101-2021_01_02_425006	338	19	virulence	virulence	NN
10_1101-2021_01_02_425006	338	20	gene	gene	NN
10_1101-2021_01_02_425006	338	21	expression	expression	NN
10_1101-2021_01_02_425006	338	22	in	in	IN
10_1101-2021_01_02_425006	338	23	a	a	DT
10_1101-2021_01_02_425006	338	24	tRNA	trna	NN
10_1101-2021_01_02_425006	338	25	modification	modification	NN
10_1101-2021_01_02_425006	338	26	-	-	HYPH
10_1101-2021_01_02_425006	338	27	deficient	deficient	JJ
10_1101-2021_01_02_425006	338	28	mutant	mutant	NN
10_1101-2021_01_02_425006	338	29	of	of	IN
10_1101-2021_01_02_425006	338	30	Shigella	Shigella	NNP
10_1101-2021_01_02_425006	338	31	flexneri	flexneri	NN
10_1101-2021_01_02_425006	338	32	:	:	:
10_1101-2021_01_02_425006	338	33	a	a	DT
10_1101-2021_01_02_425006	338	34	possible	possible	JJ
10_1101-2021_01_02_425006	338	35	473	473	CD
10_1101-2021_01_02_425006	338	36	role	role	NN
10_1101-2021_01_02_425006	338	37	in	in	IN
10_1101-2021_01_02_425006	338	38	adaptation	adaptation	NN
10_1101-2021_01_02_425006	338	39	of	of	IN
10_1101-2021_01_02_425006	338	40	virulence	virulence	NN
10_1101-2021_01_02_425006	338	41	.	.	.
10_1101-2021_01_02_425006	339	1	Mol	Mol	NNP
10_1101-2021_01_02_425006	339	2	.	.	.
10_1101-2021_01_02_425006	340	1	Microbiol	Microbiol	NNP
10_1101-2021_01_02_425006	340	2	.	.	.
10_1101-2021_01_02_425006	341	1	47	47	CD
10_1101-2021_01_02_425006	341	2	,	,	,
10_1101-2021_01_02_425006	341	3	519	519	CD
10_1101-2021_01_02_425006	341	4	-	-	SYM
10_1101-2021_01_02_425006	341	5	527	527	CD
10_1101-2021_01_02_425006	341	6	(	(	-LRB-
10_1101-2021_01_02_425006	341	7	2010	2010	CD
10_1101-2021_01_02_425006	341	8	)	)	-RRB-
10_1101-2021_01_02_425006	341	9	.	.	.
10_1101-2021_01_02_425006	342	1	474	474	CD
10_1101-2021_01_02_425006	342	2	12	12	CD
10_1101-2021_01_02_425006	342	3	.	.	.
10_1101-2021_01_02_425006	343	1	L.	L.	NNP
10_1101-2021_01_02_425006	343	2	E.	E.	NNP
10_1101-2021_01_02_425006	343	3	Wroblewski	Wroblewski	NNP
10_1101-2021_01_02_425006	343	4	,	,	,
10_1101-2021_01_02_425006	343	5	R.	R.	NNP
10_1101-2021_01_02_425006	343	6	M.	M.	NNP
10_1101-2021_01_02_425006	343	7	Peek	Peek	NNP
10_1101-2021_01_02_425006	343	8	,	,	,
10_1101-2021_01_02_425006	343	9	K.	K.	NNP
10_1101-2021_01_02_425006	343	10	T.	T.	NNP
10_1101-2021_01_02_425006	343	11	Wilson	Wilson	NNP
10_1101-2021_01_02_425006	343	12	,	,	,
10_1101-2021_01_02_425006	343	13	Helicobacter	Helicobacter	NNP
10_1101-2021_01_02_425006	343	14	pylori	pylori	NN
10_1101-2021_01_02_425006	343	15	and	and	CC
10_1101-2021_01_02_425006	343	16	gastric	gastric	JJ
10_1101-2021_01_02_425006	343	17	cancer	cancer	NN
10_1101-2021_01_02_425006	343	18	:	:	:
10_1101-2021_01_02_425006	343	19	factors	factor	NNS
10_1101-2021_01_02_425006	343	20	that	that	IN
10_1101-2021_01_02_425006	343	21	475	475	CD
10_1101-2021_01_02_425006	343	22	modulate	modulate	NN
10_1101-2021_01_02_425006	343	23	disease	disease	NN
10_1101-2021_01_02_425006	343	24	risk	risk	NN
10_1101-2021_01_02_425006	343	25	.	.	.
10_1101-2021_01_02_425006	344	1	Clin	Clin	NNP
10_1101-2021_01_02_425006	344	2	.	.	.
10_1101-2021_01_02_425006	345	1	Microbiol	Microbiol	NNP
10_1101-2021_01_02_425006	345	2	.	.	.
10_1101-2021_01_02_425006	346	1	Rev.	Rev.	NNP
10_1101-2021_01_02_425006	347	1	23	23	CD
10_1101-2021_01_02_425006	347	2	,	,	,
10_1101-2021_01_02_425006	347	3	713	713	CD
10_1101-2021_01_02_425006	347	4	-	-	SYM
10_1101-2021_01_02_425006	347	5	739	739	CD
10_1101-2021_01_02_425006	347	6	(	(	-LRB-
10_1101-2021_01_02_425006	347	7	2010	2010	CD
10_1101-2021_01_02_425006	347	8	)	)	-RRB-
10_1101-2021_01_02_425006	347	9	.	.	.
10_1101-2021_01_02_425006	348	1	476	476	CD
10_1101-2021_01_02_425006	348	2	13	13	CD
10_1101-2021_01_02_425006	348	3	.	.	.
10_1101-2021_01_02_425006	349	1	L.	L.	NNP
10_1101-2021_01_02_425006	349	2	Ettwiller	Ettwiller	NNP
10_1101-2021_01_02_425006	349	3	,	,	,
10_1101-2021_01_02_425006	349	4	J.	J.	NNP
10_1101-2021_01_02_425006	349	5	Buswell	Buswell	NNP
10_1101-2021_01_02_425006	349	6	,	,	,
10_1101-2021_01_02_425006	349	7	E.	E.	NNP
10_1101-2021_01_02_425006	349	8	Yigit	Yigit	NNP
10_1101-2021_01_02_425006	349	9	,	,	,
10_1101-2021_01_02_425006	349	10	I.	I.	NNP
10_1101-2021_01_02_425006	349	11	Schildkraut	Schildkraut	NNP
10_1101-2021_01_02_425006	349	12	,	,	,
10_1101-2021_01_02_425006	349	13	A	a	DT
10_1101-2021_01_02_425006	349	14	novel	novel	JJ
10_1101-2021_01_02_425006	349	15	enrichment	enrichment	NN
10_1101-2021_01_02_425006	349	16	strategy	strategy	NN
10_1101-2021_01_02_425006	349	17	reveals	reveal	VBZ
10_1101-2021_01_02_425006	349	18	unprecedented	unprecedented	JJ
10_1101-2021_01_02_425006	349	19	477	477	CD
10_1101-2021_01_02_425006	349	20	number	number	NN
10_1101-2021_01_02_425006	349	21	of	of	IN
10_1101-2021_01_02_425006	349	22	novel	novel	JJ
10_1101-2021_01_02_425006	349	23	transcription	transcription	NN
10_1101-2021_01_02_425006	349	24	start	start	NN
10_1101-2021_01_02_425006	349	25	sites	site	NNS
10_1101-2021_01_02_425006	349	26	at	at	IN
10_1101-2021_01_02_425006	349	27	single	single	JJ
10_1101-2021_01_02_425006	349	28	base	base	NN
10_1101-2021_01_02_425006	349	29	resolution	resolution	NN
10_1101-2021_01_02_425006	349	30	in	in	IN
10_1101-2021_01_02_425006	349	31	a	a	DT
10_1101-2021_01_02_425006	349	32	model	model	NN
10_1101-2021_01_02_425006	349	33	prokaryote	prokaryote	NN
10_1101-2021_01_02_425006	349	34	and	and	CC
10_1101-2021_01_02_425006	349	35	the	the	DT
10_1101-2021_01_02_425006	349	36	478	478	CD
10_1101-2021_01_02_425006	349	37	gut	gut	NN
10_1101-2021_01_02_425006	349	38	microbiome	microbiome	NN
10_1101-2021_01_02_425006	349	39	.	.	.
10_1101-2021_01_02_425006	350	1	BMC	BMC	NNP
10_1101-2021_01_02_425006	350	2	Genomics	Genomics	NNP
10_1101-2021_01_02_425006	350	3	17	17	CD
10_1101-2021_01_02_425006	350	4	,	,	,
10_1101-2021_01_02_425006	350	5	199	199	CD
10_1101-2021_01_02_425006	350	6	-	-	SYM
10_1101-2021_01_02_425006	350	7	199	199	CD
10_1101-2021_01_02_425006	350	8	(	(	-LRB-
10_1101-2021_01_02_425006	350	9	2016	2016	CD
10_1101-2021_01_02_425006	350	10	)	)	-RRB-
10_1101-2021_01_02_425006	350	11	.	.	.
10_1101-2021_01_02_425006	351	1	479	479	CD
10_1101-2021_01_02_425006	351	2	.CC	.CC	:
10_1101-2021_01_02_425006	351	3	-	-	HYPH
10_1101-2021_01_02_425006	351	4	BY	by	IN
10_1101-2021_01_02_425006	351	5	-	-	HYPH
10_1101-2021_01_02_425006	351	6	NC	NC	NNP
10_1101-2021_01_02_425006	351	7	-	-	HYPH
10_1101-2021_01_02_425006	351	8	ND	ND	NNP
10_1101-2021_01_02_425006	351	9	4.0	4.0	CD
10_1101-2021_01_02_425006	351	10	International	International	NNP
10_1101-2021_01_02_425006	351	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	351	12	under	under	IN
10_1101-2021_01_02_425006	351	13	a	a	DT
10_1101-2021_01_02_425006	351	14	(	(	-LRB-
10_1101-2021_01_02_425006	351	15	which	which	WDT
10_1101-2021_01_02_425006	351	16	was	be	VBD
10_1101-2021_01_02_425006	351	17	not	not	RB
10_1101-2021_01_02_425006	351	18	certified	certify	VBN
10_1101-2021_01_02_425006	351	19	by	by	IN
10_1101-2021_01_02_425006	351	20	peer	peer	NN
10_1101-2021_01_02_425006	351	21	review	review	NN
10_1101-2021_01_02_425006	351	22	)	)	-RRB-
10_1101-2021_01_02_425006	351	23	is	be	VBZ
10_1101-2021_01_02_425006	351	24	the	the	DT
10_1101-2021_01_02_425006	351	25	author	author	NN
10_1101-2021_01_02_425006	351	26	/	/	SYM
10_1101-2021_01_02_425006	351	27	funder	funder	NN
10_1101-2021_01_02_425006	351	28	,	,	,
10_1101-2021_01_02_425006	351	29	who	who	WP
10_1101-2021_01_02_425006	351	30	has	have	VBZ
10_1101-2021_01_02_425006	351	31	granted	grant	VBN
10_1101-2021_01_02_425006	351	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	351	33	a	a	DT
10_1101-2021_01_02_425006	351	34	license	license	NN
10_1101-2021_01_02_425006	351	35	to	to	TO
10_1101-2021_01_02_425006	351	36	display	display	VB
10_1101-2021_01_02_425006	351	37	the	the	DT
10_1101-2021_01_02_425006	351	38	preprint	preprint	NN
10_1101-2021_01_02_425006	351	39	in	in	IN
10_1101-2021_01_02_425006	351	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	351	41	.	.	.
10_1101-2021_01_02_425006	352	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	352	2	is	be	VBZ
10_1101-2021_01_02_425006	352	3	made	make	VBN
10_1101-2021_01_02_425006	352	4	The	the	DT
10_1101-2021_01_02_425006	352	5	copyright	copyright	NN
10_1101-2021_01_02_425006	352	6	holder	holder	NN
10_1101-2021_01_02_425006	352	7	for	for	IN
10_1101-2021_01_02_425006	352	8	this	this	DT
10_1101-2021_01_02_425006	352	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	352	10	version	version	NN
10_1101-2021_01_02_425006	352	11	posted	post	VBD
10_1101-2021_01_02_425006	352	12	January	January	NNP
10_1101-2021_01_02_425006	352	13	6	6	CD
10_1101-2021_01_02_425006	352	14	,	,	,
10_1101-2021_01_02_425006	352	15	2021	2021	CD
10_1101-2021_01_02_425006	352	16	.	.	.
10_1101-2021_01_02_425006	352	17	;	;	:
10_1101-2021_01_02_425006	352	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	352	19	:	:	:
10_1101-2021_01_02_425006	352	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	352	21	preprint	preprint	NN
10_1101-2021_01_02_425006	352	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	352	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	352	24	28	28	CD
10_1101-2021_01_02_425006	352	25	14	14	CD
10_1101-2021_01_02_425006	352	26	.	.	.
10_1101-2021_01_02_425006	353	1	M.	M.	NNP
10_1101-2021_01_02_425006	353	2	K.	K.	NNP
10_1101-2021_01_02_425006	353	3	Thomason	Thomason	NNP
10_1101-2021_01_02_425006	353	4	,	,	,
10_1101-2021_01_02_425006	353	5	T.	T.	NNP
10_1101-2021_01_02_425006	353	6	Bischler	Bischler	NNP
10_1101-2021_01_02_425006	353	7	,	,	,
10_1101-2021_01_02_425006	353	8	S.	S.	NNP
10_1101-2021_01_02_425006	353	9	K.	K.	NNP
10_1101-2021_01_02_425006	353	10	Eisenbart	Eisenbart	NNP
10_1101-2021_01_02_425006	353	11	,	,	,
10_1101-2021_01_02_425006	353	12	K.	K.	NNP
10_1101-2021_01_02_425006	353	13	U.	U.	NNP
10_1101-2021_01_02_425006	353	14	Forstner	Forstner	NNP
10_1101-2021_01_02_425006	353	15	,	,	,
10_1101-2021_01_02_425006	353	16	A.	A.	NNP
10_1101-2021_01_02_425006	353	17	Zhang	Zhang	NNP
10_1101-2021_01_02_425006	353	18	,	,	,
10_1101-2021_01_02_425006	353	19	A.	A.	NNP
10_1101-2021_01_02_425006	353	20	Herbig	Herbig	NNP
10_1101-2021_01_02_425006	353	21	,	,	,
10_1101-2021_01_02_425006	353	22	K.	K.	NNP
10_1101-2021_01_02_425006	353	23	Nieselt	Nieselt	NNP
10_1101-2021_01_02_425006	353	24	,	,	,
10_1101-2021_01_02_425006	353	25	C.	C.	NNP
10_1101-2021_01_02_425006	353	26	480	480	CD
10_1101-2021_01_02_425006	353	27	M.	M.	NNP
10_1101-2021_01_02_425006	353	28	Sharma	Sharma	NNP
10_1101-2021_01_02_425006	353	29	,	,	,
10_1101-2021_01_02_425006	353	30	G.	G.	NNP
10_1101-2021_01_02_425006	353	31	Storz	Storz	NNP
10_1101-2021_01_02_425006	353	32	,	,	,
10_1101-2021_01_02_425006	353	33	Global	global	JJ
10_1101-2021_01_02_425006	353	34	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	353	35	start	start	NN
10_1101-2021_01_02_425006	353	36	site	site	NN
10_1101-2021_01_02_425006	353	37	mapping	mapping	NN
10_1101-2021_01_02_425006	353	38	using	use	VBG
10_1101-2021_01_02_425006	353	39	differential	differential	NN
10_1101-2021_01_02_425006	353	40	RNA	RNA	NNP
10_1101-2021_01_02_425006	353	41	sequencing	sequence	VBG
10_1101-2021_01_02_425006	353	42	481	481	CD
10_1101-2021_01_02_425006	353	43	reveals	reveal	NNS
10_1101-2021_01_02_425006	353	44	novel	novel	JJ
10_1101-2021_01_02_425006	353	45	antisense	antisense	NN
10_1101-2021_01_02_425006	353	46	RNAs	rna	NNS
10_1101-2021_01_02_425006	353	47	in	in	IN
10_1101-2021_01_02_425006	353	48	Escherichia	Escherichia	NNP
10_1101-2021_01_02_425006	353	49	coli	coli	NNS
10_1101-2021_01_02_425006	353	50	.	.	.
10_1101-2021_01_02_425006	354	1	J.	J.	NNP
10_1101-2021_01_02_425006	354	2	Bacteriol	Bacteriol	NNP
10_1101-2021_01_02_425006	354	3	.	.	.
10_1101-2021_01_02_425006	355	1	197	197	CD
10_1101-2021_01_02_425006	355	2	,	,	,
10_1101-2021_01_02_425006	355	3	18	18	CD
10_1101-2021_01_02_425006	355	4	-	-	SYM
10_1101-2021_01_02_425006	355	5	28	28	CD
10_1101-2021_01_02_425006	355	6	(	(	-LRB-
10_1101-2021_01_02_425006	355	7	2015	2015	CD
10_1101-2021_01_02_425006	355	8	)	)	-RRB-
10_1101-2021_01_02_425006	355	9	.	.	.
10_1101-2021_01_02_425006	356	1	482	482	CD
10_1101-2021_01_02_425006	356	2	15	15	CD
10_1101-2021_01_02_425006	356	3	.	.	.
10_1101-2021_01_02_425006	357	1	T.	T.	NNP
10_1101-2021_01_02_425006	357	2	Bischler	Bischler	NNP
10_1101-2021_01_02_425006	357	3	,	,	,
10_1101-2021_01_02_425006	357	4	H.	H.	NNP
10_1101-2021_01_02_425006	357	5	S.	S.	NNP
10_1101-2021_01_02_425006	357	6	Tan	Tan	NNP
10_1101-2021_01_02_425006	357	7	,	,	,
10_1101-2021_01_02_425006	357	8	K.	K.	NNP
10_1101-2021_01_02_425006	357	9	Nieselt	Nieselt	NNP
10_1101-2021_01_02_425006	357	10	,	,	,
10_1101-2021_01_02_425006	357	11	C.	C.	NNP
10_1101-2021_01_02_425006	357	12	M.	M.	NNP
10_1101-2021_01_02_425006	357	13	Sharma	Sharma	NNP
10_1101-2021_01_02_425006	357	14	,	,	,
10_1101-2021_01_02_425006	357	15	Differential	Differential	NNP
10_1101-2021_01_02_425006	357	16	RNA	RNA	NNP
10_1101-2021_01_02_425006	357	17	-	-	HYPH
10_1101-2021_01_02_425006	357	18	seq	seq	NNP
10_1101-2021_01_02_425006	357	19	(	(	-LRB-
10_1101-2021_01_02_425006	357	20	dRNA	drna	NN
10_1101-2021_01_02_425006	357	21	-	-	HYPH
10_1101-2021_01_02_425006	357	22	seq	seq	NN
10_1101-2021_01_02_425006	357	23	)	)	-RRB-
10_1101-2021_01_02_425006	357	24	for	for	IN
10_1101-2021_01_02_425006	357	25	annotation	annotation	NN
10_1101-2021_01_02_425006	357	26	483	483	CD
10_1101-2021_01_02_425006	357	27	of	of	IN
10_1101-2021_01_02_425006	357	28	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	357	29	start	start	NN
10_1101-2021_01_02_425006	357	30	sites	site	NNS
10_1101-2021_01_02_425006	357	31	and	and	CC
10_1101-2021_01_02_425006	357	32	small	small	JJ
10_1101-2021_01_02_425006	357	33	RNAs	rna	NNS
10_1101-2021_01_02_425006	357	34	in	in	IN
10_1101-2021_01_02_425006	357	35	Helicobacter	Helicobacter	NNP
10_1101-2021_01_02_425006	357	36	pylori	pylori	NN
10_1101-2021_01_02_425006	357	37	.	.	.
10_1101-2021_01_02_425006	358	1	Methods	method	NNS
10_1101-2021_01_02_425006	358	2	86	86	CD
10_1101-2021_01_02_425006	358	3	,	,	,
10_1101-2021_01_02_425006	358	4	89	89	CD
10_1101-2021_01_02_425006	358	5	-	-	SYM
10_1101-2021_01_02_425006	358	6	101	101	CD
10_1101-2021_01_02_425006	358	7	(	(	-LRB-
10_1101-2021_01_02_425006	358	8	2015	2015	CD
10_1101-2021_01_02_425006	358	9	)	)	-RRB-
10_1101-2021_01_02_425006	358	10	.	.	.
10_1101-2021_01_02_425006	359	1	484	484	CD
10_1101-2021_01_02_425006	359	2	16	16	CD
10_1101-2021_01_02_425006	359	3	.	.	.
10_1101-2021_01_02_425006	360	1	D.	D.	NNP
10_1101-2021_01_02_425006	360	2	Dar	Dar	NNP
10_1101-2021_01_02_425006	360	3	,	,	,
10_1101-2021_01_02_425006	360	4	M.	M.	NNP
10_1101-2021_01_02_425006	360	5	Shamir	Shamir	NNP
10_1101-2021_01_02_425006	360	6	,	,	,
10_1101-2021_01_02_425006	360	7	J.	J.	NNP
10_1101-2021_01_02_425006	360	8	Mellin	Mellin	NNP
10_1101-2021_01_02_425006	360	9	,	,	,
10_1101-2021_01_02_425006	360	10	M.	M.	NNP
10_1101-2021_01_02_425006	360	11	Koutero	Koutero	NNP
10_1101-2021_01_02_425006	360	12	,	,	,
10_1101-2021_01_02_425006	360	13	N.	N.	NNP
10_1101-2021_01_02_425006	360	14	Stern	Stern	NNP
10_1101-2021_01_02_425006	360	15	-	-	HYPH
10_1101-2021_01_02_425006	360	16	Ginossar	Ginossar	NNP
10_1101-2021_01_02_425006	360	17	,	,	,
10_1101-2021_01_02_425006	360	18	P.	P.	NNP
10_1101-2021_01_02_425006	360	19	Cossart	Cossart	NNP
10_1101-2021_01_02_425006	360	20	,	,	,
10_1101-2021_01_02_425006	360	21	R.	R.	NNP
10_1101-2021_01_02_425006	360	22	Sorek	Sorek	NNP
10_1101-2021_01_02_425006	360	23	,	,	,
10_1101-2021_01_02_425006	360	24	Term	Term	NNP
10_1101-2021_01_02_425006	360	25	-	-	HYPH
10_1101-2021_01_02_425006	360	26	seq	seq	NN
10_1101-2021_01_02_425006	360	27	485	485	CD
10_1101-2021_01_02_425006	360	28	reveals	reveal	VBZ
10_1101-2021_01_02_425006	360	29	abundant	abundant	JJ
10_1101-2021_01_02_425006	360	30	ribo	ribo	NN
10_1101-2021_01_02_425006	360	31	-	-	HYPH
10_1101-2021_01_02_425006	360	32	regulation	regulation	NN
10_1101-2021_01_02_425006	360	33	of	of	IN
10_1101-2021_01_02_425006	360	34	antibiotics	antibiotic	NNS
10_1101-2021_01_02_425006	360	35	resistance	resistance	NN
10_1101-2021_01_02_425006	360	36	in	in	IN
10_1101-2021_01_02_425006	360	37	bacteria	bacteria	NNS
10_1101-2021_01_02_425006	360	38	.	.	.
10_1101-2021_01_02_425006	361	1	Science	science	NN
10_1101-2021_01_02_425006	361	2	352	352	CD
10_1101-2021_01_02_425006	361	3	,	,	,
10_1101-2021_01_02_425006	361	4	6282	6282	CD
10_1101-2021_01_02_425006	361	5	(	(	-LRB-
10_1101-2021_01_02_425006	361	6	2016	2016	CD
10_1101-2021_01_02_425006	361	7	)	)	-RRB-
10_1101-2021_01_02_425006	361	8	.	.	.
10_1101-2021_01_02_425006	362	1	486	486	CD
10_1101-2021_01_02_425006	362	2	17	17	CD
10_1101-2021_01_02_425006	362	3	.	.	.
10_1101-2021_01_02_425006	363	1	J.	J.	NNP
10_1101-2021_01_02_425006	363	2	Clauwaert	Clauwaert	NNP
10_1101-2021_01_02_425006	363	3	,	,	,
10_1101-2021_01_02_425006	363	4	G.	G.	NNP
10_1101-2021_01_02_425006	363	5	Menschaert	Menschaert	NNP
10_1101-2021_01_02_425006	363	6	,	,	,
10_1101-2021_01_02_425006	363	7	W.	W.	NNP
10_1101-2021_01_02_425006	363	8	Waegeman	Waegeman	NNP
10_1101-2021_01_02_425006	363	9	,	,	,
10_1101-2021_01_02_425006	363	10	An	an	DT
10_1101-2021_01_02_425006	363	11	in	in	IN
10_1101-2021_01_02_425006	363	12	-	-	HYPH
10_1101-2021_01_02_425006	363	13	depth	depth	NN
10_1101-2021_01_02_425006	363	14	evaluation	evaluation	NN
10_1101-2021_01_02_425006	363	15	of	of	IN
10_1101-2021_01_02_425006	363	16	annotated	annotate	VBN
10_1101-2021_01_02_425006	363	17	transcription	transcription	NN
10_1101-2021_01_02_425006	363	18	487	487	CD
10_1101-2021_01_02_425006	363	19	start	start	NN
10_1101-2021_01_02_425006	363	20	sites	site	NNS
10_1101-2021_01_02_425006	363	21	in	in	IN
10_1101-2021_01_02_425006	363	22	E.	E.	NNP
10_1101-2021_01_02_425006	363	23	coli	coli	NNS
10_1101-2021_01_02_425006	363	24	using	use	VBG
10_1101-2021_01_02_425006	363	25	deep	deep	JJ
10_1101-2021_01_02_425006	363	26	learning	learning	NN
10_1101-2021_01_02_425006	363	27	.	.	.
10_1101-2021_01_02_425006	364	1	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	364	2	,	,	,
10_1101-2021_01_02_425006	364	3	doi	doi	XX
10_1101-2021_01_02_425006	364	4	:	:	:
10_1101-2021_01_02_425006	364	5	https://doi.org/10.1101/2020.03.16.993501	https://doi.org/10.1101/2020.03.16.993501	ADD
10_1101-2021_01_02_425006	364	6	,	,	,
10_1101-2021_01_02_425006	364	7	488	488	CD
10_1101-2021_01_02_425006	364	8	4	4	CD
10_1101-2021_01_02_425006	364	9	November	November	NNP
10_1101-2021_01_02_425006	364	10	2020	2020	CD
10_1101-2021_01_02_425006	364	11	,	,	,
10_1101-2021_01_02_425006	364	12	pre	pre	NN
10_1101-2021_01_02_425006	364	13	-	-	NN
10_1101-2021_01_02_425006	364	14	print	print	NN
10_1101-2021_01_02_425006	364	15	:	:	:
10_1101-2021_01_02_425006	364	16	not	not	RB
10_1101-2021_01_02_425006	364	17	peer	peer	NN
10_1101-2021_01_02_425006	364	18	-	-	HYPH
10_1101-2021_01_02_425006	364	19	reviewed	review	VBN
10_1101-2021_01_02_425006	364	20	.	.	.
10_1101-2021_01_02_425006	365	1	(	(	-LRB-
10_1101-2021_01_02_425006	365	2	2020	2020	CD
10_1101-2021_01_02_425006	365	3	)	)	-RRB-
10_1101-2021_01_02_425006	365	4	.	.	.
10_1101-2021_01_02_425006	366	1	489	489	CD
10_1101-2021_01_02_425006	366	2	18	18	CD
10_1101-2021_01_02_425006	366	3	.	.	.
10_1101-2021_01_02_425006	367	1	S.	S.	NNP
10_1101-2021_01_02_425006	367	2	Goodwin	Goodwin	NNP
10_1101-2021_01_02_425006	367	3	,	,	,
10_1101-2021_01_02_425006	367	4	J.	J.	NNP
10_1101-2021_01_02_425006	367	5	D.	D.	NNP
10_1101-2021_01_02_425006	367	6	Mcpherson	Mcpherson	NNP
10_1101-2021_01_02_425006	367	7	,	,	,
10_1101-2021_01_02_425006	367	8	W.	W.	NNP
10_1101-2021_01_02_425006	367	9	R.	R.	NNP
10_1101-2021_01_02_425006	367	10	Mccombie	Mccombie	NNP
10_1101-2021_01_02_425006	367	11	,	,	,
10_1101-2021_01_02_425006	367	12	Coming	come	VBG
10_1101-2021_01_02_425006	367	13	of	of	IN
10_1101-2021_01_02_425006	367	14	age	age	NN
10_1101-2021_01_02_425006	367	15	:	:	:
10_1101-2021_01_02_425006	367	16	ten	ten	CD
10_1101-2021_01_02_425006	367	17	years	year	NNS
10_1101-2021_01_02_425006	367	18	of	of	IN
10_1101-2021_01_02_425006	367	19	next	next	JJ
10_1101-2021_01_02_425006	367	20	-	-	HYPH
10_1101-2021_01_02_425006	367	21	generation	generation	NN
10_1101-2021_01_02_425006	367	22	490	490	CD
10_1101-2021_01_02_425006	367	23	sequencing	sequencing	NN
10_1101-2021_01_02_425006	367	24	technologies	technology	NNS
10_1101-2021_01_02_425006	367	25	.	.	.
10_1101-2021_01_02_425006	368	1	Nat	Nat	NNP
10_1101-2021_01_02_425006	368	2	.	.	.
10_1101-2021_01_02_425006	369	1	Rev.	Rev.	NNP
10_1101-2021_01_02_425006	370	1	Genet	Genet	NNP
10_1101-2021_01_02_425006	370	2	.	.	.
10_1101-2021_01_02_425006	371	1	17	17	CD
10_1101-2021_01_02_425006	371	2	,	,	,
10_1101-2021_01_02_425006	371	3	333	333	CD
10_1101-2021_01_02_425006	371	4	-	-	HYPH
10_1101-2021_01_02_425006	371	5	351	351	CD
10_1101-2021_01_02_425006	371	6	(	(	-LRB-
10_1101-2021_01_02_425006	371	7	2016	2016	CD
10_1101-2021_01_02_425006	371	8	)	)	-RRB-
10_1101-2021_01_02_425006	371	9	.	.	.
10_1101-2021_01_02_425006	372	1	491	491	CD
10_1101-2021_01_02_425006	372	2	19	19	CD
10_1101-2021_01_02_425006	372	3	.	.	.
10_1101-2021_01_02_425006	373	1	A.	A.	NNP
10_1101-2021_01_02_425006	373	2	Santos	Santos	NNP
10_1101-2021_01_02_425006	373	3	-	-	HYPH
10_1101-2021_01_02_425006	373	4	Zavaleta	Zavaleta	NNP
10_1101-2021_01_02_425006	373	5	,	,	,
10_1101-2021_01_02_425006	373	6	H.	H.	NNP
10_1101-2021_01_02_425006	373	7	Salgado	Salgado	NNP
10_1101-2021_01_02_425006	373	8	,	,	,
10_1101-2021_01_02_425006	373	9	S.	S.	NNP
10_1101-2021_01_02_425006	373	10	Gama	Gama	NNP
10_1101-2021_01_02_425006	373	11	-	-	HYPH
10_1101-2021_01_02_425006	373	12	Castro	Castro	NNP
10_1101-2021_01_02_425006	373	13	,	,	,
10_1101-2021_01_02_425006	373	14	M.	M.	NNP
10_1101-2021_01_02_425006	373	15	Sánchez	Sánchez	NNP
10_1101-2021_01_02_425006	373	16	-	-	HYPH
10_1101-2021_01_02_425006	373	17	Pérez	Pérez	NNP
10_1101-2021_01_02_425006	373	18	,	,	,
10_1101-2021_01_02_425006	373	19	L.	L.	NNP
10_1101-2021_01_02_425006	373	20	Gómez	Gómez	NNP
10_1101-2021_01_02_425006	373	21	-	-	HYPH
10_1101-2021_01_02_425006	373	22	Romero	Romero	NNP
10_1101-2021_01_02_425006	373	23	,	,	,
10_1101-2021_01_02_425006	373	24	D.	D.	NNP
10_1101-2021_01_02_425006	373	25	492	492	CD
10_1101-2021_01_02_425006	373	26	Ledezma	Ledezma	NNP
10_1101-2021_01_02_425006	373	27	-	-	HYPH
10_1101-2021_01_02_425006	373	28	Tejeida	Tejeida	NNP
10_1101-2021_01_02_425006	373	29	,	,	,
10_1101-2021_01_02_425006	373	30	J.	J.	NNP
10_1101-2021_01_02_425006	373	31	S.	S.	NNP
10_1101-2021_01_02_425006	373	32	García	García	NNP
10_1101-2021_01_02_425006	373	33	-	-	HYPH
10_1101-2021_01_02_425006	373	34	Sotelo	Sotelo	NNP
10_1101-2021_01_02_425006	373	35	,	,	,
10_1101-2021_01_02_425006	373	36	K.	K.	NNP
10_1101-2021_01_02_425006	373	37	Alquicira	Alquicira	NNP
10_1101-2021_01_02_425006	373	38	-	-	HYPH
10_1101-2021_01_02_425006	373	39	Hernández	Hernández	NNP
10_1101-2021_01_02_425006	373	40	,	,	,
10_1101-2021_01_02_425006	373	41	L.	L.	NNP
10_1101-2021_01_02_425006	373	42	J.	J.	NNP
10_1101-2021_01_02_425006	373	43	Muñiz	Muñiz	NNP
10_1101-2021_01_02_425006	373	44	-	-	HYPH
10_1101-2021_01_02_425006	373	45	Rascado	Rascado	NNP
10_1101-2021_01_02_425006	373	46	,	,	,
10_1101-2021_01_02_425006	373	47	P.	P.	NNP
10_1101-2021_01_02_425006	373	48	Peña-493	peña-493	NN
10_1101-2021_01_02_425006	373	49	Loredo	Loredo	NNP
10_1101-2021_01_02_425006	373	50	,	,	,
10_1101-2021_01_02_425006	373	51	RegulonDB	regulondb	IN
10_1101-2021_01_02_425006	373	52	v	v	NN
10_1101-2021_01_02_425006	373	53	10.5	10.5	CD
10_1101-2021_01_02_425006	373	54	:	:	:
10_1101-2021_01_02_425006	373	55	tackling	tackle	VBG
10_1101-2021_01_02_425006	373	56	challenges	challenge	NNS
10_1101-2021_01_02_425006	373	57	to	to	TO
10_1101-2021_01_02_425006	373	58	unify	unify	VB
10_1101-2021_01_02_425006	373	59	classic	classic	JJ
10_1101-2021_01_02_425006	373	60	and	and	CC
10_1101-2021_01_02_425006	373	61	high	high	JJ
10_1101-2021_01_02_425006	373	62	throughput	throughput	NN
10_1101-2021_01_02_425006	373	63	knowledge	knowledge	NN
10_1101-2021_01_02_425006	373	64	494	494	CD
10_1101-2021_01_02_425006	373	65	of	of	IN
10_1101-2021_01_02_425006	373	66	gene	gene	NN
10_1101-2021_01_02_425006	373	67	regulation	regulation	NN
10_1101-2021_01_02_425006	373	68	in	in	IN
10_1101-2021_01_02_425006	373	69	E.	E.	NNP
10_1101-2021_01_02_425006	373	70	coli	coli	NNS
10_1101-2021_01_02_425006	373	71	K-12	k-12	CD
10_1101-2021_01_02_425006	373	72	.	.	.
10_1101-2021_01_02_425006	374	1	Nucleic	Nucleic	NNP
10_1101-2021_01_02_425006	374	2	Acids	Acids	NNPS
10_1101-2021_01_02_425006	374	3	Res	Res	NNP
10_1101-2021_01_02_425006	374	4	.	.	.
10_1101-2021_01_02_425006	375	1	47	47	CD
10_1101-2021_01_02_425006	375	2	,	,	,
10_1101-2021_01_02_425006	375	3	D212-D220	D212-D220	NNP
10_1101-2021_01_02_425006	375	4	(	(	-LRB-
10_1101-2021_01_02_425006	375	5	2018	2018	CD
10_1101-2021_01_02_425006	375	6	)	)	-RRB-
10_1101-2021_01_02_425006	375	7	.	.	.
10_1101-2021_01_02_425006	376	1	495	495	CD
10_1101-2021_01_02_425006	376	2	20	20	CD
10_1101-2021_01_02_425006	376	3	.	.	.
10_1101-2021_01_02_425006	377	1	N.	N.	NNP
10_1101-2021_01_02_425006	377	2	Sierro	Sierro	NNP
10_1101-2021_01_02_425006	377	3	,	,	,
10_1101-2021_01_02_425006	377	4	Y.	Y.	NNP
10_1101-2021_01_02_425006	377	5	Makita	Makita	NNP
10_1101-2021_01_02_425006	377	6	,	,	,
10_1101-2021_01_02_425006	377	7	M.	M.	NNP
10_1101-2021_01_02_425006	377	8	J.	J.	NNP
10_1101-2021_01_02_425006	377	9	L.	L.	NNP
10_1101-2021_01_02_425006	377	10	De	De	NNP
10_1101-2021_01_02_425006	377	11	Hoon	Hoon	NNP
10_1101-2021_01_02_425006	377	12	,	,	,
10_1101-2021_01_02_425006	377	13	K.	K.	NNP
10_1101-2021_01_02_425006	377	14	Nakai	Nakai	NNP
10_1101-2021_01_02_425006	377	15	,	,	,
10_1101-2021_01_02_425006	377	16	DBTBS	DBTBS	NNP
10_1101-2021_01_02_425006	377	17	:	:	:
10_1101-2021_01_02_425006	377	18	a	a	DT
10_1101-2021_01_02_425006	377	19	database	database	NN
10_1101-2021_01_02_425006	377	20	of	of	IN
10_1101-2021_01_02_425006	377	21	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	377	22	regulation	regulation	NN
10_1101-2021_01_02_425006	377	23	496	496	CD
10_1101-2021_01_02_425006	377	24	in	in	IN
10_1101-2021_01_02_425006	377	25	Bacillus	bacillus	NN
10_1101-2021_01_02_425006	377	26	subtilis	subtili	NNS
10_1101-2021_01_02_425006	377	27	containing	contain	VBG
10_1101-2021_01_02_425006	377	28	upstream	upstream	JJ
10_1101-2021_01_02_425006	377	29	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	377	30	conservation	conservation	NN
10_1101-2021_01_02_425006	377	31	information	information	NN
10_1101-2021_01_02_425006	377	32	.	.	.
10_1101-2021_01_02_425006	378	1	Nucleic	Nucleic	NNP
10_1101-2021_01_02_425006	378	2	Acids	Acids	NNPS
10_1101-2021_01_02_425006	378	3	Res	Res	NNP
10_1101-2021_01_02_425006	378	4	.	.	.
10_1101-2021_01_02_425006	379	1	497	497	CD
10_1101-2021_01_02_425006	379	2	.CC	.CC	:
10_1101-2021_01_02_425006	379	3	-	-	HYPH
10_1101-2021_01_02_425006	379	4	BY	by	IN
10_1101-2021_01_02_425006	379	5	-	-	HYPH
10_1101-2021_01_02_425006	379	6	NC	NC	NNP
10_1101-2021_01_02_425006	379	7	-	-	HYPH
10_1101-2021_01_02_425006	379	8	ND	ND	NNP
10_1101-2021_01_02_425006	379	9	4.0	4.0	CD
10_1101-2021_01_02_425006	379	10	International	International	NNP
10_1101-2021_01_02_425006	379	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	379	12	under	under	IN
10_1101-2021_01_02_425006	379	13	a	a	DT
10_1101-2021_01_02_425006	379	14	(	(	-LRB-
10_1101-2021_01_02_425006	379	15	which	which	WDT
10_1101-2021_01_02_425006	379	16	was	be	VBD
10_1101-2021_01_02_425006	379	17	not	not	RB
10_1101-2021_01_02_425006	379	18	certified	certify	VBN
10_1101-2021_01_02_425006	379	19	by	by	IN
10_1101-2021_01_02_425006	379	20	peer	peer	NN
10_1101-2021_01_02_425006	379	21	review	review	NN
10_1101-2021_01_02_425006	379	22	)	)	-RRB-
10_1101-2021_01_02_425006	379	23	is	be	VBZ
10_1101-2021_01_02_425006	379	24	the	the	DT
10_1101-2021_01_02_425006	379	25	author	author	NN
10_1101-2021_01_02_425006	379	26	/	/	SYM
10_1101-2021_01_02_425006	379	27	funder	funder	NN
10_1101-2021_01_02_425006	379	28	,	,	,
10_1101-2021_01_02_425006	379	29	who	who	WP
10_1101-2021_01_02_425006	379	30	has	have	VBZ
10_1101-2021_01_02_425006	379	31	granted	grant	VBN
10_1101-2021_01_02_425006	379	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	379	33	a	a	DT
10_1101-2021_01_02_425006	379	34	license	license	NN
10_1101-2021_01_02_425006	379	35	to	to	TO
10_1101-2021_01_02_425006	379	36	display	display	VB
10_1101-2021_01_02_425006	379	37	the	the	DT
10_1101-2021_01_02_425006	379	38	preprint	preprint	NN
10_1101-2021_01_02_425006	379	39	in	in	IN
10_1101-2021_01_02_425006	379	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	379	41	.	.	.
10_1101-2021_01_02_425006	380	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	380	2	is	be	VBZ
10_1101-2021_01_02_425006	380	3	made	make	VBN
10_1101-2021_01_02_425006	380	4	The	the	DT
10_1101-2021_01_02_425006	380	5	copyright	copyright	NN
10_1101-2021_01_02_425006	380	6	holder	holder	NN
10_1101-2021_01_02_425006	380	7	for	for	IN
10_1101-2021_01_02_425006	380	8	this	this	DT
10_1101-2021_01_02_425006	380	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	380	10	version	version	NN
10_1101-2021_01_02_425006	380	11	posted	post	VBD
10_1101-2021_01_02_425006	380	12	January	January	NNP
10_1101-2021_01_02_425006	380	13	6	6	CD
10_1101-2021_01_02_425006	380	14	,	,	,
10_1101-2021_01_02_425006	380	15	2021	2021	CD
10_1101-2021_01_02_425006	380	16	.	.	.
10_1101-2021_01_02_425006	380	17	;	;	:
10_1101-2021_01_02_425006	380	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	380	19	:	:	:
10_1101-2021_01_02_425006	380	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	380	21	preprint	preprint	NN
10_1101-2021_01_02_425006	380	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	380	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	380	24	29	29	CD
10_1101-2021_01_02_425006	380	25	36	36	CD
10_1101-2021_01_02_425006	380	26	,	,	,
10_1101-2021_01_02_425006	380	27	93	93	CD
10_1101-2021_01_02_425006	380	28	-	-	SYM
10_1101-2021_01_02_425006	380	29	96	96	CD
10_1101-2021_01_02_425006	380	30	(	(	-LRB-
10_1101-2021_01_02_425006	380	31	2008	2008	CD
10_1101-2021_01_02_425006	380	32	)	)	-RRB-
10_1101-2021_01_02_425006	380	33	.	.	.
10_1101-2021_01_02_425006	381	1	498	498	CD
10_1101-2021_01_02_425006	381	2	21	21	CD
10_1101-2021_01_02_425006	381	3	.	.	.
10_1101-2021_01_02_425006	382	1	P.	P.	NNP
10_1101-2021_01_02_425006	382	2	S.	S.	NNP
10_1101-2021_01_02_425006	382	3	Dehal	Dehal	NNP
10_1101-2021_01_02_425006	382	4	,	,	,
10_1101-2021_01_02_425006	382	5	M.	M.	NNP
10_1101-2021_01_02_425006	382	6	P.	P.	NNP
10_1101-2021_01_02_425006	382	7	Joachimiak	Joachimiak	NNP
10_1101-2021_01_02_425006	382	8	,	,	,
10_1101-2021_01_02_425006	382	9	M.	M.	NNP
10_1101-2021_01_02_425006	382	10	N.	N.	NNP
10_1101-2021_01_02_425006	382	11	Price	Price	NNP
10_1101-2021_01_02_425006	382	12	,	,	,
10_1101-2021_01_02_425006	382	13	J.	J.	NNP
10_1101-2021_01_02_425006	382	14	T.	T.	NNP
10_1101-2021_01_02_425006	382	15	Bates	Bates	NNP
10_1101-2021_01_02_425006	382	16	,	,	,
10_1101-2021_01_02_425006	382	17	J.	J.	NNP
10_1101-2021_01_02_425006	382	18	K.	K.	NNP
10_1101-2021_01_02_425006	382	19	Baumohl	Baumohl	NNP
10_1101-2021_01_02_425006	382	20	,	,	,
10_1101-2021_01_02_425006	382	21	C.	C.	NNP
10_1101-2021_01_02_425006	382	22	Dylan	Dylan	NNP
10_1101-2021_01_02_425006	382	23	,	,	,
10_1101-2021_01_02_425006	382	24	G.	G.	NNP
10_1101-2021_01_02_425006	382	25	D.	D.	NNP
10_1101-2021_01_02_425006	382	26	Friedland	Friedland	NNP
10_1101-2021_01_02_425006	382	27	,	,	,
10_1101-2021_01_02_425006	382	28	499	499	CD
10_1101-2021_01_02_425006	382	29	K.	K.	NNP
10_1101-2021_01_02_425006	382	30	H.	H.	NNP
10_1101-2021_01_02_425006	382	31	Huang	Huang	NNP
10_1101-2021_01_02_425006	382	32	,	,	,
10_1101-2021_01_02_425006	382	33	K.	K.	NNP
10_1101-2021_01_02_425006	382	34	Keith	Keith	NNP
10_1101-2021_01_02_425006	382	35	,	,	,
10_1101-2021_01_02_425006	382	36	P.	P.	NNP
10_1101-2021_01_02_425006	382	37	S.	S.	NNP
10_1101-2021_01_02_425006	382	38	Novichkov	Novichkov	NNP
10_1101-2021_01_02_425006	382	39	,	,	,
10_1101-2021_01_02_425006	382	40	MicrobesOnline	MicrobesOnline	NNP
10_1101-2021_01_02_425006	382	41	:	:	:
10_1101-2021_01_02_425006	382	42	an	an	DT
10_1101-2021_01_02_425006	382	43	integrated	integrated	JJ
10_1101-2021_01_02_425006	382	44	portal	portal	NN
10_1101-2021_01_02_425006	382	45	for	for	IN
10_1101-2021_01_02_425006	382	46	comparative	comparative	JJ
10_1101-2021_01_02_425006	382	47	and	and	CC
10_1101-2021_01_02_425006	382	48	500	500	CD
10_1101-2021_01_02_425006	382	49	functional	functional	JJ
10_1101-2021_01_02_425006	382	50	genomics	genomic	NNS
10_1101-2021_01_02_425006	382	51	.	.	.
10_1101-2021_01_02_425006	383	1	Nucleic	Nucleic	NNP
10_1101-2021_01_02_425006	383	2	Acids	Acids	NNPS
10_1101-2021_01_02_425006	383	3	Res	Res	NNP
10_1101-2021_01_02_425006	383	4	.	.	.
10_1101-2021_01_02_425006	384	1	38	38	CD
10_1101-2021_01_02_425006	384	2	,	,	,
10_1101-2021_01_02_425006	384	3	D396-D400	D396-D400	NNP
10_1101-2021_01_02_425006	384	4	(	(	-LRB-
10_1101-2021_01_02_425006	384	5	2010	2010	CD
10_1101-2021_01_02_425006	384	6	)	)	-RRB-
10_1101-2021_01_02_425006	384	7	.	.	.
10_1101-2021_01_02_425006	385	1	501	501	CD
10_1101-2021_01_02_425006	385	2	22	22	CD
10_1101-2021_01_02_425006	385	3	.	.	.
10_1101-2021_01_02_425006	386	1	H.	H.	NNP
10_1101-2021_01_02_425006	386	2	Cao	Cao	NNP
10_1101-2021_01_02_425006	386	3	,	,	,
10_1101-2021_01_02_425006	386	4	Q.	Q.	NNP
10_1101-2021_01_02_425006	386	5	Ma	Ma	NNP
10_1101-2021_01_02_425006	386	6	,	,	,
10_1101-2021_01_02_425006	386	7	X.	X.	NNP
10_1101-2021_01_02_425006	386	8	Chen	Chen	NNP
10_1101-2021_01_02_425006	386	9	,	,	,
10_1101-2021_01_02_425006	386	10	Y.	Y.	NNP
10_1101-2021_01_02_425006	386	11	Xu	Xu	NNP
10_1101-2021_01_02_425006	386	12	,	,	,
10_1101-2021_01_02_425006	386	13	DOOR	DOOR	NNP
10_1101-2021_01_02_425006	386	14	:	:	:
10_1101-2021_01_02_425006	386	15	a	a	DT
10_1101-2021_01_02_425006	386	16	prokaryotic	prokaryotic	JJ
10_1101-2021_01_02_425006	386	17	operon	operon	NN
10_1101-2021_01_02_425006	386	18	database	database	NN
10_1101-2021_01_02_425006	386	19	for	for	IN
10_1101-2021_01_02_425006	386	20	genome	genome	JJ
10_1101-2021_01_02_425006	386	21	analyses	analysis	NNS
10_1101-2021_01_02_425006	386	22	and	and	CC
10_1101-2021_01_02_425006	386	23	502	502	CD
10_1101-2021_01_02_425006	386	24	functional	functional	JJ
10_1101-2021_01_02_425006	386	25	inference	inference	NN
10_1101-2021_01_02_425006	386	26	.	.	.
10_1101-2021_01_02_425006	387	1	Brief	brief	JJ
10_1101-2021_01_02_425006	387	2	.	.	.
10_1101-2021_01_02_425006	388	1	Bioinform	bioinform	NN
10_1101-2021_01_02_425006	388	2	.	.	.
10_1101-2021_01_02_425006	389	1	20	20	CD
10_1101-2021_01_02_425006	389	2	,	,	,
10_1101-2021_01_02_425006	389	3	1568	1568	CD
10_1101-2021_01_02_425006	389	4	-	-	SYM
10_1101-2021_01_02_425006	389	5	1577	1577	CD
10_1101-2021_01_02_425006	389	6	(	(	-LRB-
10_1101-2021_01_02_425006	389	7	2019	2019	CD
10_1101-2021_01_02_425006	389	8	)	)	-RRB-
10_1101-2021_01_02_425006	389	9	.	.	.
10_1101-2021_01_02_425006	390	1	503	503	CD
10_1101-2021_01_02_425006	390	2	23	23	CD
10_1101-2021_01_02_425006	390	3	.	.	.
10_1101-2021_01_02_425006	391	1	X.	X.	NNP
10_1101-2021_01_02_425006	391	2	Mao	Mao	NNP
10_1101-2021_01_02_425006	391	3	,	,	,
10_1101-2021_01_02_425006	391	4	Q.	Q.	NNP
10_1101-2021_01_02_425006	391	5	Ma	Ma	NNP
10_1101-2021_01_02_425006	391	6	,	,	,
10_1101-2021_01_02_425006	391	7	C.	C.	NNP
10_1101-2021_01_02_425006	391	8	Zhou	Zhou	NNP
10_1101-2021_01_02_425006	391	9	,	,	,
10_1101-2021_01_02_425006	391	10	X.	X.	NNP
10_1101-2021_01_02_425006	391	11	Chen	Chen	NNP
10_1101-2021_01_02_425006	391	12	,	,	,
10_1101-2021_01_02_425006	391	13	H.	H.	NNP
10_1101-2021_01_02_425006	391	14	Zhang	Zhang	NNP
10_1101-2021_01_02_425006	391	15	,	,	,
10_1101-2021_01_02_425006	391	16	J.	J.	NNP
10_1101-2021_01_02_425006	391	17	Yang	Yang	NNP
10_1101-2021_01_02_425006	391	18	,	,	,
10_1101-2021_01_02_425006	391	19	F.	F.	NNP
10_1101-2021_01_02_425006	391	20	Mao	Mao	NNP
10_1101-2021_01_02_425006	391	21	,	,	,
10_1101-2021_01_02_425006	391	22	W.	W.	NNP
10_1101-2021_01_02_425006	391	23	Lai	Lai	NNP
10_1101-2021_01_02_425006	391	24	,	,	,
10_1101-2021_01_02_425006	391	25	Y.	Y.	NNP
10_1101-2021_01_02_425006	391	26	Xu	Xu	NNP
10_1101-2021_01_02_425006	391	27	,	,	,
10_1101-2021_01_02_425006	391	28	DOOR	DOOR	NNP
10_1101-2021_01_02_425006	391	29	2.0	2.0	CD
10_1101-2021_01_02_425006	391	30	:	:	:
10_1101-2021_01_02_425006	391	31	presenting	present	VBG
10_1101-2021_01_02_425006	391	32	504	504	CD
10_1101-2021_01_02_425006	391	33	operons	operon	NNS
10_1101-2021_01_02_425006	391	34	and	and	CC
10_1101-2021_01_02_425006	391	35	their	-PRON-	PRP$
10_1101-2021_01_02_425006	391	36	functions	function	NNS
10_1101-2021_01_02_425006	391	37	through	through	IN
10_1101-2021_01_02_425006	391	38	dynamic	dynamic	JJ
10_1101-2021_01_02_425006	391	39	and	and	CC
10_1101-2021_01_02_425006	391	40	integrated	integrated	JJ
10_1101-2021_01_02_425006	391	41	views	view	NNS
10_1101-2021_01_02_425006	391	42	.	.	.
10_1101-2021_01_02_425006	392	1	Nucleic	Nucleic	NNP
10_1101-2021_01_02_425006	392	2	Acids	Acids	NNPS
10_1101-2021_01_02_425006	392	3	Res	Res	NNP
10_1101-2021_01_02_425006	392	4	.	.	.
10_1101-2021_01_02_425006	393	1	42	42	CD
10_1101-2021_01_02_425006	393	2	,	,	,
10_1101-2021_01_02_425006	393	3	D654	D654	NNP
10_1101-2021_01_02_425006	393	4	-	-	HYPH
10_1101-2021_01_02_425006	393	5	505	505	CD
10_1101-2021_01_02_425006	393	6	D659	d659	NN
10_1101-2021_01_02_425006	393	7	(	(	-LRB-
10_1101-2021_01_02_425006	393	8	2013	2013	CD
10_1101-2021_01_02_425006	393	9	)	)	-RRB-
10_1101-2021_01_02_425006	393	10	.	.	.
10_1101-2021_01_02_425006	394	1	506	506	CD
10_1101-2021_01_02_425006	394	2	24	24	CD
10_1101-2021_01_02_425006	394	3	.	.	.
10_1101-2021_01_02_425006	395	1	K.	K.	NNP
10_1101-2021_01_02_425006	395	2	Chetal	Chetal	NNP
10_1101-2021_01_02_425006	395	3	,	,	,
10_1101-2021_01_02_425006	395	4	S.	S.	NNP
10_1101-2021_01_02_425006	395	5	C.	C.	NNP
10_1101-2021_01_02_425006	395	6	Janga	Janga	NNP
10_1101-2021_01_02_425006	395	7	,	,	,
10_1101-2021_01_02_425006	395	8	OperomeDB	OperomeDB	NNP
10_1101-2021_01_02_425006	395	9	:	:	:
10_1101-2021_01_02_425006	395	10	A	a	DT
10_1101-2021_01_02_425006	395	11	Database	Database	NNP
10_1101-2021_01_02_425006	395	12	of	of	IN
10_1101-2021_01_02_425006	395	13	Condition	Condition	NNP
10_1101-2021_01_02_425006	395	14	-	-	HYPH
10_1101-2021_01_02_425006	395	15	Specific	Specific	NNP
10_1101-2021_01_02_425006	395	16	Transcription	Transcription	NNP
10_1101-2021_01_02_425006	395	17	Units	Units	NNPS
10_1101-2021_01_02_425006	395	18	in	in	IN
10_1101-2021_01_02_425006	395	19	507	507	CD
10_1101-2021_01_02_425006	395	20	Prokaryotic	Prokaryotic	NNP
10_1101-2021_01_02_425006	395	21	Genomes	Genomes	NNPS
10_1101-2021_01_02_425006	395	22	.	.	.
10_1101-2021_01_02_425006	396	1	Biomed	Biomed	NNP
10_1101-2021_01_02_425006	396	2	Research	Research	NNP
10_1101-2021_01_02_425006	396	3	International	International	NNP
10_1101-2021_01_02_425006	396	4	2015	2015	CD
10_1101-2021_01_02_425006	396	5	,	,	,
10_1101-2021_01_02_425006	396	6	1	1	CD
10_1101-2021_01_02_425006	396	7	-	-	SYM
10_1101-2021_01_02_425006	396	8	10	10	CD
10_1101-2021_01_02_425006	396	9	(	(	-LRB-
10_1101-2021_01_02_425006	396	10	2015	2015	CD
10_1101-2021_01_02_425006	396	11	)	)	-RRB-
10_1101-2021_01_02_425006	396	12	.	.	.
10_1101-2021_01_02_425006	397	1	508	508	CD
10_1101-2021_01_02_425006	397	2	25	25	CD
10_1101-2021_01_02_425006	397	3	.	.	.
10_1101-2021_01_02_425006	398	1	J.	J.	NNP
10_1101-2021_01_02_425006	398	2	Yang	Yang	NNP
10_1101-2021_01_02_425006	398	3	,	,	,
10_1101-2021_01_02_425006	398	4	X.	X.	NNP
10_1101-2021_01_02_425006	398	5	Chen	Chen	NNP
10_1101-2021_01_02_425006	398	6	,	,	,
10_1101-2021_01_02_425006	398	7	A.	A.	NNP
10_1101-2021_01_02_425006	398	8	Mcdermaid	Mcdermaid	NNP
10_1101-2021_01_02_425006	398	9	,	,	,
10_1101-2021_01_02_425006	398	10	Q.	Q.	NNP
10_1101-2021_01_02_425006	398	11	Ma	Ma	NNP
10_1101-2021_01_02_425006	398	12	,	,	,
10_1101-2021_01_02_425006	398	13	DMINDA	DMINDA	NNP
10_1101-2021_01_02_425006	398	14	2.0	2.0	CD
10_1101-2021_01_02_425006	398	15	:	:	:
10_1101-2021_01_02_425006	398	16	integrated	integrate	VBN
10_1101-2021_01_02_425006	398	17	and	and	CC
10_1101-2021_01_02_425006	398	18	systematic	systematic	JJ
10_1101-2021_01_02_425006	398	19	views	view	NNS
10_1101-2021_01_02_425006	398	20	of	of	IN
10_1101-2021_01_02_425006	398	21	509	509	CD
10_1101-2021_01_02_425006	398	22	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	398	23	DNA	dna	NN
10_1101-2021_01_02_425006	398	24	motif	motif	NN
10_1101-2021_01_02_425006	398	25	identification	identification	NN
10_1101-2021_01_02_425006	398	26	and	and	CC
10_1101-2021_01_02_425006	398	27	analyses	analysis	NNS
10_1101-2021_01_02_425006	398	28	.	.	.
10_1101-2021_01_02_425006	399	1	Bioinformatics	Bioinformatics	NNP
10_1101-2021_01_02_425006	399	2	33	33	CD
10_1101-2021_01_02_425006	399	3	,	,	,
10_1101-2021_01_02_425006	399	4	2586	2586	CD
10_1101-2021_01_02_425006	399	5	-	-	SYM
10_1101-2021_01_02_425006	399	6	2588	2588	CD
10_1101-2021_01_02_425006	399	7	(	(	-LRB-
10_1101-2021_01_02_425006	399	8	2017	2017	CD
10_1101-2021_01_02_425006	399	9	)	)	-RRB-
10_1101-2021_01_02_425006	399	10	.	.	.
10_1101-2021_01_02_425006	400	1	510	510	CD
10_1101-2021_01_02_425006	400	2	26	26	CD
10_1101-2021_01_02_425006	400	3	.	.	.
10_1101-2021_01_02_425006	401	1	T.	T.	NNP
10_1101-2021_01_02_425006	401	2	Blanca	Blanca	NNP
10_1101-2021_01_02_425006	401	3	,	,	,
10_1101-2021_01_02_425006	401	4	C.	C.	NNP
10_1101-2021_01_02_425006	401	5	Ricardo	Ricardo	NNP
10_1101-2021_01_02_425006	401	6	,	,	,
10_1101-2021_01_02_425006	401	7	C.	C.	NNP
10_1101-2021_01_02_425006	401	8	E.	E.	NNP
10_1101-2021_01_02_425006	401	9	Martinez	Martinez	NNP
10_1101-2021_01_02_425006	401	10	-	-	HYPH
10_1101-2021_01_02_425006	401	11	Guerrero	Guerrero	NNP
10_1101-2021_01_02_425006	401	12	,	,	,
10_1101-2021_01_02_425006	401	13	M.	M.	NNP
10_1101-2021_01_02_425006	401	14	Enrique	Enrique	NNP
10_1101-2021_01_02_425006	401	15	,	,	,
10_1101-2021_01_02_425006	401	16	ProOpDB	ProOpDB	NNP
10_1101-2021_01_02_425006	401	17	:	:	:
10_1101-2021_01_02_425006	401	18	Prokaryotic	Prokaryotic	NNP
10_1101-2021_01_02_425006	401	19	Operon	Operon	NNP
10_1101-2021_01_02_425006	401	20	511	511	CD
10_1101-2021_01_02_425006	401	21	DataBase	DataBase	NNP
10_1101-2021_01_02_425006	401	22	.	.	.
10_1101-2021_01_02_425006	402	1	Nucleic	Nucleic	NNP
10_1101-2021_01_02_425006	402	2	Acids	Acids	NNPS
10_1101-2021_01_02_425006	402	3	Res	Res	NNP
10_1101-2021_01_02_425006	402	4	.	.	.
10_1101-2021_01_02_425006	403	1	40	40	CD
10_1101-2021_01_02_425006	403	2	,	,	,
10_1101-2021_01_02_425006	403	3	D627-D631	D627-D631	NNP
10_1101-2021_01_02_425006	403	4	(	(	-LRB-
10_1101-2021_01_02_425006	403	5	2012	2012	CD
10_1101-2021_01_02_425006	403	6	)	)	-RRB-
10_1101-2021_01_02_425006	403	7	.	.	.
10_1101-2021_01_02_425006	404	1	512	512	CD
10_1101-2021_01_02_425006	404	2	27	27	CD
10_1101-2021_01_02_425006	404	3	.	.	.
10_1101-2021_01_02_425006	405	1	R.	R.	NNP
10_1101-2021_01_02_425006	405	2	McClure	McClure	NNP
10_1101-2021_01_02_425006	405	3	,	,	,
10_1101-2021_01_02_425006	405	4	D.	D.	NNP
10_1101-2021_01_02_425006	405	5	Balasubramanian	Balasubramanian	NNP
10_1101-2021_01_02_425006	405	6	,	,	,
10_1101-2021_01_02_425006	405	7	Y.	Y.	NNP
10_1101-2021_01_02_425006	406	1	Sun	Sun	NNP
10_1101-2021_01_02_425006	406	2	,	,	,
10_1101-2021_01_02_425006	406	3	M.	M.	NNP
10_1101-2021_01_02_425006	406	4	Bobrovskyy	Bobrovskyy	NNP
10_1101-2021_01_02_425006	406	5	,	,	,
10_1101-2021_01_02_425006	406	6	P.	P.	NNP
10_1101-2021_01_02_425006	406	7	Sumby	Sumby	NNP
10_1101-2021_01_02_425006	406	8	,	,	,
10_1101-2021_01_02_425006	406	9	C.	C.	NNP
10_1101-2021_01_02_425006	406	10	A.	A.	NNP
10_1101-2021_01_02_425006	406	11	Genco	Genco	NNP
10_1101-2021_01_02_425006	406	12	,	,	,
10_1101-2021_01_02_425006	406	13	C.	C.	NNP
10_1101-2021_01_02_425006	406	14	K.	K.	NNP
10_1101-2021_01_02_425006	406	15	513	513	CD
10_1101-2021_01_02_425006	406	16	Vanderpool	Vanderpool	NNP
10_1101-2021_01_02_425006	406	17	,	,	,
10_1101-2021_01_02_425006	406	18	B.	B.	NNP
10_1101-2021_01_02_425006	406	19	Tjaden	Tjaden	NNP
10_1101-2021_01_02_425006	406	20	,	,	,
10_1101-2021_01_02_425006	406	21	Computational	computational	JJ
10_1101-2021_01_02_425006	406	22	analysis	analysis	NN
10_1101-2021_01_02_425006	406	23	of	of	IN
10_1101-2021_01_02_425006	406	24	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	406	25	RNA	RNA	NNP
10_1101-2021_01_02_425006	406	26	-	-	HYPH
10_1101-2021_01_02_425006	406	27	Seq	Seq	NNP
10_1101-2021_01_02_425006	406	28	data	datum	NNS
10_1101-2021_01_02_425006	406	29	.	.	.
10_1101-2021_01_02_425006	407	1	Nucleic	Nucleic	NNP
10_1101-2021_01_02_425006	407	2	Acids	Acids	NNPS
10_1101-2021_01_02_425006	407	3	Res	Res	NNP
10_1101-2021_01_02_425006	407	4	.	.	.
10_1101-2021_01_02_425006	408	1	41	41	CD
10_1101-2021_01_02_425006	408	2	,	,	,
10_1101-2021_01_02_425006	408	3	514	514	CD
10_1101-2021_01_02_425006	408	4	.CC	.cc	SYM
10_1101-2021_01_02_425006	408	5	-	-	HYPH
10_1101-2021_01_02_425006	408	6	BY	by	IN
10_1101-2021_01_02_425006	408	7	-	-	HYPH
10_1101-2021_01_02_425006	408	8	NC	NC	NNP
10_1101-2021_01_02_425006	408	9	-	-	HYPH
10_1101-2021_01_02_425006	408	10	ND	ND	NNP
10_1101-2021_01_02_425006	408	11	4.0	4.0	CD
10_1101-2021_01_02_425006	408	12	International	International	NNP
10_1101-2021_01_02_425006	408	13	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	408	14	under	under	IN
10_1101-2021_01_02_425006	408	15	a	a	DT
10_1101-2021_01_02_425006	408	16	(	(	-LRB-
10_1101-2021_01_02_425006	408	17	which	which	WDT
10_1101-2021_01_02_425006	408	18	was	be	VBD
10_1101-2021_01_02_425006	408	19	not	not	RB
10_1101-2021_01_02_425006	408	20	certified	certify	VBN
10_1101-2021_01_02_425006	408	21	by	by	IN
10_1101-2021_01_02_425006	408	22	peer	peer	NN
10_1101-2021_01_02_425006	408	23	review	review	NN
10_1101-2021_01_02_425006	408	24	)	)	-RRB-
10_1101-2021_01_02_425006	408	25	is	be	VBZ
10_1101-2021_01_02_425006	408	26	the	the	DT
10_1101-2021_01_02_425006	408	27	author	author	NN
10_1101-2021_01_02_425006	408	28	/	/	SYM
10_1101-2021_01_02_425006	408	29	funder	funder	NN
10_1101-2021_01_02_425006	408	30	,	,	,
10_1101-2021_01_02_425006	408	31	who	who	WP
10_1101-2021_01_02_425006	408	32	has	have	VBZ
10_1101-2021_01_02_425006	408	33	granted	grant	VBN
10_1101-2021_01_02_425006	408	34	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	408	35	a	a	DT
10_1101-2021_01_02_425006	408	36	license	license	NN
10_1101-2021_01_02_425006	408	37	to	to	TO
10_1101-2021_01_02_425006	408	38	display	display	VB
10_1101-2021_01_02_425006	408	39	the	the	DT
10_1101-2021_01_02_425006	408	40	preprint	preprint	NN
10_1101-2021_01_02_425006	408	41	in	in	IN
10_1101-2021_01_02_425006	408	42	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	408	43	.	.	.
10_1101-2021_01_02_425006	409	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	409	2	is	be	VBZ
10_1101-2021_01_02_425006	409	3	made	make	VBN
10_1101-2021_01_02_425006	409	4	The	the	DT
10_1101-2021_01_02_425006	409	5	copyright	copyright	NN
10_1101-2021_01_02_425006	409	6	holder	holder	NN
10_1101-2021_01_02_425006	409	7	for	for	IN
10_1101-2021_01_02_425006	409	8	this	this	DT
10_1101-2021_01_02_425006	409	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	409	10	version	version	NN
10_1101-2021_01_02_425006	409	11	posted	post	VBD
10_1101-2021_01_02_425006	409	12	January	January	NNP
10_1101-2021_01_02_425006	409	13	6	6	CD
10_1101-2021_01_02_425006	409	14	,	,	,
10_1101-2021_01_02_425006	409	15	2021	2021	CD
10_1101-2021_01_02_425006	409	16	.	.	.
10_1101-2021_01_02_425006	409	17	;	;	:
10_1101-2021_01_02_425006	409	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	409	19	:	:	:
10_1101-2021_01_02_425006	409	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	409	21	preprint	preprint	NN
10_1101-2021_01_02_425006	409	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	409	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN
10_1101-2021_01_02_425006	409	24	30	30	CD
10_1101-2021_01_02_425006	409	25	e140-e140	e140-e140	NNS
10_1101-2021_01_02_425006	409	26	(	(	-LRB-
10_1101-2021_01_02_425006	409	27	2013	2013	CD
10_1101-2021_01_02_425006	409	28	)	)	-RRB-
10_1101-2021_01_02_425006	409	29	.	.	.
10_1101-2021_01_02_425006	410	1	515	515	CD
10_1101-2021_01_02_425006	410	2	28	28	CD
10_1101-2021_01_02_425006	410	3	.	.	.
10_1101-2021_01_02_425006	411	1	X.	X.	NNP
10_1101-2021_01_02_425006	411	2	Chen	Chen	NNP
10_1101-2021_01_02_425006	411	3	,	,	,
10_1101-2021_01_02_425006	411	4	W.	W.	NNP
10_1101-2021_01_02_425006	411	5	Chou	Chou	NNP
10_1101-2021_01_02_425006	411	6	,	,	,
10_1101-2021_01_02_425006	411	7	Q.	Q.	NNP
10_1101-2021_01_02_425006	411	8	Ma	Ma	NNP
10_1101-2021_01_02_425006	411	9	,	,	,
10_1101-2021_01_02_425006	411	10	Y.	Y.	NNP
10_1101-2021_01_02_425006	411	11	Xu	Xu	NNP
10_1101-2021_01_02_425006	411	12	,	,	,
10_1101-2021_01_02_425006	411	13	SeqTU	SeqTU	NNP
10_1101-2021_01_02_425006	411	14	:	:	:
10_1101-2021_01_02_425006	411	15	A	a	DT
10_1101-2021_01_02_425006	411	16	Web	web	NN
10_1101-2021_01_02_425006	411	17	Server	server	NN
10_1101-2021_01_02_425006	411	18	for	for	IN
10_1101-2021_01_02_425006	411	19	Identification	Identification	NNP
10_1101-2021_01_02_425006	411	20	of	of	IN
10_1101-2021_01_02_425006	411	21	Bacterial	Bacterial	NNP
10_1101-2021_01_02_425006	411	22	516	516	CD
10_1101-2021_01_02_425006	411	23	Transcription	Transcription	NNP
10_1101-2021_01_02_425006	411	24	Units	Units	NNPS
10_1101-2021_01_02_425006	411	25	.	.	.
10_1101-2021_01_02_425006	412	1	Scientific	Scientific	NNP
10_1101-2021_01_02_425006	412	2	Reports	Reports	NNPS
10_1101-2021_01_02_425006	412	3	7	7	CD
10_1101-2021_01_02_425006	412	4	,	,	,
10_1101-2021_01_02_425006	412	5	43925	43925	CD
10_1101-2021_01_02_425006	412	6	(	(	-LRB-
10_1101-2021_01_02_425006	412	7	2017	2017	CD
10_1101-2021_01_02_425006	412	8	)	)	-RRB-
10_1101-2021_01_02_425006	412	9	.	.	.
10_1101-2021_01_02_425006	413	1	517	517	CD
10_1101-2021_01_02_425006	413	2	29	29	CD
10_1101-2021_01_02_425006	413	3	.	.	.
10_1101-2021_01_02_425006	414	1	I.	I.	NNP
10_1101-2021_01_02_425006	415	1	A.	A.	NNP
10_1101-2021_01_02_425006	415	2	Garanina	Garanina	NNP
10_1101-2021_01_02_425006	415	3	,	,	,
10_1101-2021_01_02_425006	415	4	G.	G.	NNP
10_1101-2021_01_02_425006	415	5	Y.	Y.	NNP
10_1101-2021_01_02_425006	415	6	Fisunov	Fisunov	NNP
10_1101-2021_01_02_425006	415	7	,	,	,
10_1101-2021_01_02_425006	415	8	V.	V.	NNP
10_1101-2021_01_02_425006	415	9	M.	M.	NNP
10_1101-2021_01_02_425006	415	10	Govorun	Govorun	NNP
10_1101-2021_01_02_425006	415	11	,	,	,
10_1101-2021_01_02_425006	415	12	BAC	BAC	NNP
10_1101-2021_01_02_425006	415	13	-	-	HYPH
10_1101-2021_01_02_425006	415	14	BROWSER	BROWSER	NNP
10_1101-2021_01_02_425006	415	15	:	:	:
10_1101-2021_01_02_425006	415	16	The	the	DT
10_1101-2021_01_02_425006	415	17	Tool	Tool	NNP
10_1101-2021_01_02_425006	415	18	for	for	IN
10_1101-2021_01_02_425006	415	19	Visualization	Visualization	NNP
10_1101-2021_01_02_425006	415	20	and	and	CC
10_1101-2021_01_02_425006	415	21	518	518	CD
10_1101-2021_01_02_425006	415	22	Analysis	Analysis	NNP
10_1101-2021_01_02_425006	415	23	of	of	IN
10_1101-2021_01_02_425006	415	24	Prokaryotic	Prokaryotic	NNP
10_1101-2021_01_02_425006	415	25	Genomes	Genomes	NNPS
10_1101-2021_01_02_425006	415	26	.	.	.
10_1101-2021_01_02_425006	416	1	Frontiers	frontier	NNS
10_1101-2021_01_02_425006	416	2	in	in	IN
10_1101-2021_01_02_425006	416	3	Microbiology	Microbiology	NNP
10_1101-2021_01_02_425006	416	4	9	9	CD
10_1101-2021_01_02_425006	416	5	,	,	,
10_1101-2021_01_02_425006	416	6	2827	2827	CD
10_1101-2021_01_02_425006	416	7	(	(	-LRB-
10_1101-2021_01_02_425006	416	8	2018	2018	CD
10_1101-2021_01_02_425006	416	9	)	)	-RRB-
10_1101-2021_01_02_425006	416	10	.	.	.
10_1101-2021_01_02_425006	417	1	519	519	CD
10_1101-2021_01_02_425006	417	2	30	30	CD
10_1101-2021_01_02_425006	417	3	.	.	.
10_1101-2021_01_02_425006	418	1	B.	B.	NNP
10_1101-2021_01_02_425006	418	2	Taboada	Taboada	NNP
10_1101-2021_01_02_425006	418	3	,	,	,
10_1101-2021_01_02_425006	418	4	K.	K.	NNP
10_1101-2021_01_02_425006	418	5	Estrada	Estrada	NNP
10_1101-2021_01_02_425006	418	6	,	,	,
10_1101-2021_01_02_425006	418	7	R.	R.	NNP
10_1101-2021_01_02_425006	418	8	Ciria	Ciria	NNP
10_1101-2021_01_02_425006	418	9	,	,	,
10_1101-2021_01_02_425006	418	10	E.	E.	NNP
10_1101-2021_01_02_425006	418	11	Merino	Merino	NNP
10_1101-2021_01_02_425006	418	12	,	,	,
10_1101-2021_01_02_425006	418	13	Operon	Operon	NNP
10_1101-2021_01_02_425006	418	14	-	-	HYPH
10_1101-2021_01_02_425006	418	15	mapper	mapper	NNP
10_1101-2021_01_02_425006	418	16	:	:	:
10_1101-2021_01_02_425006	418	17	a	a	DT
10_1101-2021_01_02_425006	418	18	web	web	NN
10_1101-2021_01_02_425006	418	19	server	server	NN
10_1101-2021_01_02_425006	418	20	for	for	IN
10_1101-2021_01_02_425006	418	21	precise	precise	JJ
10_1101-2021_01_02_425006	418	22	operon	operon	NNP
10_1101-2021_01_02_425006	418	23	520	520	CD
10_1101-2021_01_02_425006	418	24	identification	identification	NN
10_1101-2021_01_02_425006	418	25	in	in	IN
10_1101-2021_01_02_425006	418	26	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	418	27	and	and	CC
10_1101-2021_01_02_425006	418	28	archaeal	archaeal	JJ
10_1101-2021_01_02_425006	418	29	genomes	genome	NNS
10_1101-2021_01_02_425006	418	30	.	.	.
10_1101-2021_01_02_425006	419	1	Bioinformatics	Bioinformatics	NNP
10_1101-2021_01_02_425006	419	2	34	34	CD
10_1101-2021_01_02_425006	419	3	,	,	,
10_1101-2021_01_02_425006	419	4	4118	4118	CD
10_1101-2021_01_02_425006	419	5	-	-	SYM
10_1101-2021_01_02_425006	419	6	4120	4120	CD
10_1101-2021_01_02_425006	419	7	(	(	-LRB-
10_1101-2021_01_02_425006	419	8	2018	2018	CD
10_1101-2021_01_02_425006	419	9	)	)	-RRB-
10_1101-2021_01_02_425006	419	10	.	.	.
10_1101-2021_01_02_425006	420	1	521	521	CD
10_1101-2021_01_02_425006	420	2	31	31	CD
10_1101-2021_01_02_425006	420	3	.	.	.
10_1101-2021_01_02_425006	421	1	H.	H.	NNP
10_1101-2021_01_02_425006	421	2	Li	Li	NNP
10_1101-2021_01_02_425006	421	3	,	,	,
10_1101-2021_01_02_425006	421	4	R.	R.	NNP
10_1101-2021_01_02_425006	421	5	Durbin	Durbin	NNP
10_1101-2021_01_02_425006	421	6	,	,	,
10_1101-2021_01_02_425006	421	7	Fast	Fast	NNP
10_1101-2021_01_02_425006	421	8	and	and	CC
10_1101-2021_01_02_425006	421	9	accurate	accurate	JJ
10_1101-2021_01_02_425006	421	10	short	short	JJ
10_1101-2021_01_02_425006	421	11	read	read	NN
10_1101-2021_01_02_425006	421	12	alignment	alignment	NN
10_1101-2021_01_02_425006	421	13	with	with	IN
10_1101-2021_01_02_425006	421	14	Burrows	Burrows	NNP
10_1101-2021_01_02_425006	421	15	–	–	:
10_1101-2021_01_02_425006	421	16	Wheeler	Wheeler	NNP
10_1101-2021_01_02_425006	421	17	transform	transform	NN
10_1101-2021_01_02_425006	421	18	.	.	.
10_1101-2021_01_02_425006	422	1	522	522	CD
10_1101-2021_01_02_425006	422	2	Bioinformatics	bioinformatic	NNS
10_1101-2021_01_02_425006	422	3	25	25	CD
10_1101-2021_01_02_425006	422	4	,	,	,
10_1101-2021_01_02_425006	422	5	1754	1754	CD
10_1101-2021_01_02_425006	422	6	-	-	SYM
10_1101-2021_01_02_425006	422	7	1760	1760	CD
10_1101-2021_01_02_425006	422	8	(	(	-LRB-
10_1101-2021_01_02_425006	422	9	2009	2009	CD
10_1101-2021_01_02_425006	422	10	)	)	-RRB-
10_1101-2021_01_02_425006	422	11	.	.	.
10_1101-2021_01_02_425006	423	1	523	523	CD
10_1101-2021_01_02_425006	423	2	32	32	CD
10_1101-2021_01_02_425006	423	3	.	.	.
10_1101-2021_01_02_425006	424	1	Z.	Z.	NNP
10_1101-2021_01_02_425006	424	2	Wu	Wu	NNP
10_1101-2021_01_02_425006	424	3	,	,	,
10_1101-2021_01_02_425006	424	4	X.	X.	NNP
10_1101-2021_01_02_425006	424	5	Wang	Wang	NNP
10_1101-2021_01_02_425006	424	6	,	,	,
10_1101-2021_01_02_425006	424	7	X.	X.	NNP
10_1101-2021_01_02_425006	424	8	Zhang	Zhang	NNP
10_1101-2021_01_02_425006	424	9	,	,	,
10_1101-2021_01_02_425006	424	10	Using	use	VBG
10_1101-2021_01_02_425006	424	11	non	non	JJ
10_1101-2021_01_02_425006	424	12	-	-	JJ
10_1101-2021_01_02_425006	424	13	uniform	uniform	JJ
10_1101-2021_01_02_425006	424	14	read	read	VBD
10_1101-2021_01_02_425006	424	15	distribution	distribution	NN
10_1101-2021_01_02_425006	424	16	models	model	NNS
10_1101-2021_01_02_425006	424	17	to	to	TO
10_1101-2021_01_02_425006	424	18	improve	improve	VB
10_1101-2021_01_02_425006	424	19	isoform	isoform	NN
10_1101-2021_01_02_425006	424	20	524	524	CD
10_1101-2021_01_02_425006	424	21	expression	expression	NN
10_1101-2021_01_02_425006	424	22	inference	inference	NN
10_1101-2021_01_02_425006	424	23	in	in	IN
10_1101-2021_01_02_425006	424	24	RNA	RNA	NNP
10_1101-2021_01_02_425006	424	25	-	-	HYPH
10_1101-2021_01_02_425006	424	26	Seq	Seq	NNP
10_1101-2021_01_02_425006	424	27	.	.	.
10_1101-2021_01_02_425006	425	1	Bioinformatics	Bioinformatics	NNP
10_1101-2021_01_02_425006	425	2	27	27	CD
10_1101-2021_01_02_425006	425	3	,	,	,
10_1101-2021_01_02_425006	425	4	502	502	CD
10_1101-2021_01_02_425006	425	5	-	-	HYPH
10_1101-2021_01_02_425006	425	6	508	508	CD
10_1101-2021_01_02_425006	425	7	(	(	-LRB-
10_1101-2021_01_02_425006	425	8	2011	2011	CD
10_1101-2021_01_02_425006	425	9	)	)	-RRB-
10_1101-2021_01_02_425006	425	10	.	.	.
10_1101-2021_01_02_425006	426	1	525	525	CD
10_1101-2021_01_02_425006	426	2	33	33	CD
10_1101-2021_01_02_425006	426	3	.	.	.
10_1101-2021_01_02_425006	427	1	A.	A.	NNP
10_1101-2021_01_02_425006	427	2	Roberts	Roberts	NNP
10_1101-2021_01_02_425006	427	3	,	,	,
10_1101-2021_01_02_425006	427	4	C.	C.	NNP
10_1101-2021_01_02_425006	427	5	Trapnell	Trapnell	NNP
10_1101-2021_01_02_425006	427	6	,	,	,
10_1101-2021_01_02_425006	427	7	J.	J.	NNP
10_1101-2021_01_02_425006	427	8	Donaghey	Donaghey	NNP
10_1101-2021_01_02_425006	427	9	,	,	,
10_1101-2021_01_02_425006	427	10	J.	J.	NNP
10_1101-2021_01_02_425006	427	11	L.	L.	NNP
10_1101-2021_01_02_425006	427	12	Rinn	Rinn	NNP
10_1101-2021_01_02_425006	427	13	,	,	,
10_1101-2021_01_02_425006	427	14	L.	L.	NNP
10_1101-2021_01_02_425006	427	15	Pachter	Pachter	NNP
10_1101-2021_01_02_425006	427	16	,	,	,
10_1101-2021_01_02_425006	427	17	Improving	Improving	NNP
10_1101-2021_01_02_425006	427	18	RNA	RNA	NNP
10_1101-2021_01_02_425006	427	19	-	-	HYPH
10_1101-2021_01_02_425006	427	20	Seq	Seq	NNP
10_1101-2021_01_02_425006	427	21	expression	expression	NN
10_1101-2021_01_02_425006	427	22	526	526	CD
10_1101-2021_01_02_425006	427	23	estimates	estimate	NNS
10_1101-2021_01_02_425006	427	24	by	by	IN
10_1101-2021_01_02_425006	427	25	correcting	correct	VBG
10_1101-2021_01_02_425006	427	26	for	for	IN
10_1101-2021_01_02_425006	427	27	fragment	fragment	NN
10_1101-2021_01_02_425006	427	28	bias	bias	NN
10_1101-2021_01_02_425006	427	29	.	.	.
10_1101-2021_01_02_425006	428	1	Genome	Genome	NNP
10_1101-2021_01_02_425006	428	2	Biol	Biol	NNP
10_1101-2021_01_02_425006	428	3	.	.	.
10_1101-2021_01_02_425006	429	1	12	12	CD
10_1101-2021_01_02_425006	429	2	,	,	,
10_1101-2021_01_02_425006	429	3	1	1	CD
10_1101-2021_01_02_425006	429	4	-	-	SYM
10_1101-2021_01_02_425006	429	5	14	14	CD
10_1101-2021_01_02_425006	429	6	(	(	-LRB-
10_1101-2021_01_02_425006	429	7	2011	2011	CD
10_1101-2021_01_02_425006	429	8	)	)	-RRB-
10_1101-2021_01_02_425006	429	9	.	.	.
10_1101-2021_01_02_425006	430	1	527	527	CD
10_1101-2021_01_02_425006	430	2	34	34	CD
10_1101-2021_01_02_425006	430	3	.	.	.
10_1101-2021_01_02_425006	431	1	R.	R.	NNP
10_1101-2021_01_02_425006	431	2	Bohnert	Bohnert	NNP
10_1101-2021_01_02_425006	431	3	,	,	,
10_1101-2021_01_02_425006	431	4	G.	G.	NNP
10_1101-2021_01_02_425006	431	5	Rï	Rï	NNP
10_1101-2021_01_02_425006	431	6	¿	¿	NNP
10_1101-2021_01_02_425006	431	7	½tsch	½tsch	NNS
10_1101-2021_01_02_425006	431	8	,	,	,
10_1101-2021_01_02_425006	431	9	rQuant	rQuant	NNP
10_1101-2021_01_02_425006	431	10	.	.	.
10_1101-2021_01_02_425006	432	1	web	web	NN
10_1101-2021_01_02_425006	432	2	:	:	:
10_1101-2021_01_02_425006	432	3	a	a	DT
10_1101-2021_01_02_425006	432	4	tool	tool	NN
10_1101-2021_01_02_425006	432	5	for	for	IN
10_1101-2021_01_02_425006	432	6	RNA	RNA	NNP
10_1101-2021_01_02_425006	432	7	-	-	HYPH
10_1101-2021_01_02_425006	432	8	Seq	Seq	NNP
10_1101-2021_01_02_425006	432	9	-	-	HYPH
10_1101-2021_01_02_425006	432	10	based	base	VBN
10_1101-2021_01_02_425006	432	11	transcript	transcript	NN
10_1101-2021_01_02_425006	432	12	quantitation	quantitation	NN
10_1101-2021_01_02_425006	432	13	.	.	.
10_1101-2021_01_02_425006	433	1	Nucleic	Nucleic	NNP
10_1101-2021_01_02_425006	433	2	528	528	CD
10_1101-2021_01_02_425006	433	3	Acids	Acids	NNPS
10_1101-2021_01_02_425006	433	4	Res	Res	NNP
10_1101-2021_01_02_425006	433	5	.	.	.
10_1101-2021_01_02_425006	434	1	38	38	CD
10_1101-2021_01_02_425006	434	2	,	,	,
10_1101-2021_01_02_425006	434	3	W348-W351	W348-W351	NNP
10_1101-2021_01_02_425006	434	4	(	(	-LRB-
10_1101-2021_01_02_425006	434	5	2010	2010	CD
10_1101-2021_01_02_425006	434	6	)	)	-RRB-
10_1101-2021_01_02_425006	434	7	.	.	.
10_1101-2021_01_02_425006	435	1	529	529	CD
10_1101-2021_01_02_425006	435	2	35	35	CD
10_1101-2021_01_02_425006	435	3	.	.	.
10_1101-2021_01_02_425006	436	1	W.	W.	NNP
10_1101-2021_01_02_425006	436	2	Li	Li	NNP
10_1101-2021_01_02_425006	436	3	,	,	,
10_1101-2021_01_02_425006	436	4	T.	T.	NNP
10_1101-2021_01_02_425006	436	5	Jiang	Jiang	NNP
10_1101-2021_01_02_425006	436	6	,	,	,
10_1101-2021_01_02_425006	436	7	Transcriptome	Transcriptome	NNP
10_1101-2021_01_02_425006	436	8	assembly	assembly	NN
10_1101-2021_01_02_425006	436	9	and	and	CC
10_1101-2021_01_02_425006	436	10	isoform	isoform	NN
10_1101-2021_01_02_425006	436	11	expression	expression	NN
10_1101-2021_01_02_425006	436	12	level	level	NN
10_1101-2021_01_02_425006	436	13	estimation	estimation	NN
10_1101-2021_01_02_425006	436	14	from	from	IN
10_1101-2021_01_02_425006	436	15	biased	biased	JJ
10_1101-2021_01_02_425006	436	16	530	530	CD
10_1101-2021_01_02_425006	436	17	RNA	RNA	NNP
10_1101-2021_01_02_425006	436	18	-	-	HYPH
10_1101-2021_01_02_425006	436	19	Seq	Seq	NNP
10_1101-2021_01_02_425006	436	20	reads	read	VBZ
10_1101-2021_01_02_425006	436	21	.	.	.
10_1101-2021_01_02_425006	437	1	Bioinformatics	Bioinformatics	NNP
10_1101-2021_01_02_425006	437	2	28	28	CD
10_1101-2021_01_02_425006	437	3	,	,	,
10_1101-2021_01_02_425006	437	4	2914	2914	CD
10_1101-2021_01_02_425006	437	5	-	-	SYM
10_1101-2021_01_02_425006	437	6	2921	2921	CD
10_1101-2021_01_02_425006	437	7	(	(	-LRB-
10_1101-2021_01_02_425006	437	8	2012	2012	CD
10_1101-2021_01_02_425006	437	9	)	)	-RRB-
10_1101-2021_01_02_425006	437	10	.	.	.
10_1101-2021_01_02_425006	438	1	531	531	CD
10_1101-2021_01_02_425006	438	2	.CC	.CC	:
10_1101-2021_01_02_425006	438	3	-	-	HYPH
10_1101-2021_01_02_425006	438	4	BY	by	IN
10_1101-2021_01_02_425006	438	5	-	-	HYPH
10_1101-2021_01_02_425006	438	6	NC	NC	NNP
10_1101-2021_01_02_425006	438	7	-	-	HYPH
10_1101-2021_01_02_425006	438	8	ND	ND	NNP
10_1101-2021_01_02_425006	438	9	4.0	4.0	CD
10_1101-2021_01_02_425006	438	10	International	International	NNP
10_1101-2021_01_02_425006	438	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	438	12	under	under	IN
10_1101-2021_01_02_425006	438	13	a	a	DT
10_1101-2021_01_02_425006	438	14	(	(	-LRB-
10_1101-2021_01_02_425006	438	15	which	which	WDT
10_1101-2021_01_02_425006	438	16	was	be	VBD
10_1101-2021_01_02_425006	438	17	not	not	RB
10_1101-2021_01_02_425006	438	18	certified	certify	VBN
10_1101-2021_01_02_425006	438	19	by	by	IN
10_1101-2021_01_02_425006	438	20	peer	peer	NN
10_1101-2021_01_02_425006	438	21	review	review	NN
10_1101-2021_01_02_425006	438	22	)	)	-RRB-
10_1101-2021_01_02_425006	438	23	is	be	VBZ
10_1101-2021_01_02_425006	438	24	the	the	DT
10_1101-2021_01_02_425006	438	25	author	author	NN
10_1101-2021_01_02_425006	438	26	/	/	SYM
10_1101-2021_01_02_425006	438	27	funder	funder	NN
10_1101-2021_01_02_425006	438	28	,	,	,
10_1101-2021_01_02_425006	438	29	who	who	WP
10_1101-2021_01_02_425006	438	30	has	have	VBZ
10_1101-2021_01_02_425006	438	31	granted	grant	VBN
10_1101-2021_01_02_425006	438	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	438	33	a	a	DT
10_1101-2021_01_02_425006	438	34	license	license	NN
10_1101-2021_01_02_425006	438	35	to	to	TO
10_1101-2021_01_02_425006	438	36	display	display	VB
10_1101-2021_01_02_425006	438	37	the	the	DT
10_1101-2021_01_02_425006	438	38	preprint	preprint	NN
10_1101-2021_01_02_425006	438	39	in	in	IN
10_1101-2021_01_02_425006	438	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	438	41	.	.	.
10_1101-2021_01_02_425006	439	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	439	2	is	be	VBZ
10_1101-2021_01_02_425006	439	3	made	make	VBN
10_1101-2021_01_02_425006	439	4	The	the	DT
10_1101-2021_01_02_425006	439	5	copyright	copyright	NN
10_1101-2021_01_02_425006	439	6	holder	holder	NN
10_1101-2021_01_02_425006	439	7	for	for	IN
10_1101-2021_01_02_425006	439	8	this	this	DT
10_1101-2021_01_02_425006	439	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	439	10	version	version	NN
10_1101-2021_01_02_425006	439	11	posted	post	VBD
10_1101-2021_01_02_425006	439	12	January	January	NNP
10_1101-2021_01_02_425006	439	13	6	6	CD
10_1101-2021_01_02_425006	439	14	,	,	,
10_1101-2021_01_02_425006	439	15	2021	2021	CD
10_1101-2021_01_02_425006	439	16	.	.	.
10_1101-2021_01_02_425006	439	17	;	;	:
10_1101-2021_01_02_425006	439	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	439	19	:	:	:
10_1101-2021_01_02_425006	439	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	439	21	preprint	preprint	NN
10_1101-2021_01_02_425006	439	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	439	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	439	24	31	31	CD
10_1101-2021_01_02_425006	439	25	36	36	CD
10_1101-2021_01_02_425006	439	26	.	.	.
10_1101-2021_01_02_425006	440	1	B.	B.	NNP
10_1101-2021_01_02_425006	440	2	Xiong	Xiong	NNP
10_1101-2021_01_02_425006	440	3	,	,	,
10_1101-2021_01_02_425006	440	4	Y.	Y.	NNP
10_1101-2021_01_02_425006	440	5	Yang	Yang	NNP
10_1101-2021_01_02_425006	440	6	,	,	,
10_1101-2021_01_02_425006	440	7	F.	F.	NNP
10_1101-2021_01_02_425006	440	8	R.	R.	NNP
10_1101-2021_01_02_425006	440	9	Fineis	Fineis	NNP
10_1101-2021_01_02_425006	440	10	,	,	,
10_1101-2021_01_02_425006	440	11	J.-P.	J.-P.	NNP
10_1101-2021_01_02_425006	440	12	Wang	Wang	NNP
10_1101-2021_01_02_425006	440	13	,	,	,
10_1101-2021_01_02_425006	440	14	DegNorm	DegNorm	NNP
10_1101-2021_01_02_425006	440	15	:	:	:
10_1101-2021_01_02_425006	440	16	normalization	normalization	NN
10_1101-2021_01_02_425006	440	17	of	of	IN
10_1101-2021_01_02_425006	440	18	generalized	generalize	VBN
10_1101-2021_01_02_425006	440	19	transcript	transcript	NNP
10_1101-2021_01_02_425006	440	20	532	532	CD
10_1101-2021_01_02_425006	440	21	degradation	degradation	NN
10_1101-2021_01_02_425006	440	22	improves	improve	VBZ
10_1101-2021_01_02_425006	440	23	accuracy	accuracy	NN
10_1101-2021_01_02_425006	440	24	in	in	IN
10_1101-2021_01_02_425006	440	25	RNA	RNA	NNP
10_1101-2021_01_02_425006	440	26	-	-	HYPH
10_1101-2021_01_02_425006	440	27	seq	seq	NN
10_1101-2021_01_02_425006	440	28	analysis	analysis	NN
10_1101-2021_01_02_425006	440	29	.	.	.
10_1101-2021_01_02_425006	441	1	Genome	Genome	NNP
10_1101-2021_01_02_425006	441	2	Biol	Biol	NNP
10_1101-2021_01_02_425006	441	3	.	.	.
10_1101-2021_01_02_425006	442	1	20	20	CD
10_1101-2021_01_02_425006	442	2	,	,	,
10_1101-2021_01_02_425006	442	3	75	75	CD
10_1101-2021_01_02_425006	442	4	(	(	-LRB-
10_1101-2021_01_02_425006	442	5	2019	2019	CD
10_1101-2021_01_02_425006	442	6	)	)	-RRB-
10_1101-2021_01_02_425006	442	7	.	.	.
10_1101-2021_01_02_425006	443	1	533	533	CD
10_1101-2021_01_02_425006	443	2	37	37	CD
10_1101-2021_01_02_425006	443	3	.	.	.
10_1101-2021_01_02_425006	444	1	J.	J.	NNP
10_1101-2021_01_02_425006	444	2	Chaitanya	Chaitanya	NNP
10_1101-2021_01_02_425006	444	3	,	,	,
10_1101-2021_01_02_425006	444	4	Degradation	Degradation	NNP
10_1101-2021_01_02_425006	444	5	of	of	IN
10_1101-2021_01_02_425006	444	6	mRNA	mRNA	NNS
10_1101-2021_01_02_425006	444	7	in	in	IN
10_1101-2021_01_02_425006	444	8	Escherichia	Escherichia	NNP
10_1101-2021_01_02_425006	444	9	coli	coli	NNS
10_1101-2021_01_02_425006	444	10	.	.	.
10_1101-2021_01_02_425006	445	1	IUBMB	IUBMB	NNP
10_1101-2021_01_02_425006	445	2	Life	Life	NNP
10_1101-2021_01_02_425006	445	3	54	54	CD
10_1101-2021_01_02_425006	445	4	,	,	,
10_1101-2021_01_02_425006	445	5	315	315	CD
10_1101-2021_01_02_425006	445	6	-	-	SYM
10_1101-2021_01_02_425006	445	7	321	321	CD
10_1101-2021_01_02_425006	445	8	(	(	-LRB-
10_1101-2021_01_02_425006	445	9	2010	2010	CD
10_1101-2021_01_02_425006	445	10	)	)	-RRB-
10_1101-2021_01_02_425006	445	11	.	.	.
10_1101-2021_01_02_425006	446	1	534	534	CD
10_1101-2021_01_02_425006	446	2	38	38	CD
10_1101-2021_01_02_425006	446	3	.	.	.
10_1101-2021_01_02_425006	447	1	X.	X.	NNP
10_1101-2021_01_02_425006	447	2	Mao	Mao	NNP
10_1101-2021_01_02_425006	447	3	,	,	,
10_1101-2021_01_02_425006	447	4	Q.	Q.	NNP
10_1101-2021_01_02_425006	447	5	Ma	Ma	NNP
10_1101-2021_01_02_425006	447	6	,	,	,
10_1101-2021_01_02_425006	447	7	B.	B.	NNP
10_1101-2021_01_02_425006	447	8	Liu	Liu	NNP
10_1101-2021_01_02_425006	447	9	,	,	,
10_1101-2021_01_02_425006	447	10	X.	X.	NNP
10_1101-2021_01_02_425006	447	11	Chen	Chen	NNP
10_1101-2021_01_02_425006	447	12	,	,	,
10_1101-2021_01_02_425006	447	13	H.	H.	NNP
10_1101-2021_01_02_425006	447	14	Zhang	Zhang	NNP
10_1101-2021_01_02_425006	447	15	,	,	,
10_1101-2021_01_02_425006	447	16	Y.	Y.	NNP
10_1101-2021_01_02_425006	447	17	Xu	Xu	NNP
10_1101-2021_01_02_425006	447	18	,	,	,
10_1101-2021_01_02_425006	447	19	Revisiting	Revisiting	NNP
10_1101-2021_01_02_425006	447	20	operons	operon	NNS
10_1101-2021_01_02_425006	447	21	:	:	:
10_1101-2021_01_02_425006	447	22	an	an	DT
10_1101-2021_01_02_425006	447	23	analysis	analysis	NN
10_1101-2021_01_02_425006	447	24	of	of	IN
10_1101-2021_01_02_425006	447	25	the	the	DT
10_1101-2021_01_02_425006	447	26	landscape	landscape	NN
10_1101-2021_01_02_425006	447	27	535	535	CD
10_1101-2021_01_02_425006	447	28	of	of	IN
10_1101-2021_01_02_425006	447	29	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	447	30	units	unit	NNS
10_1101-2021_01_02_425006	447	31	in	in	IN
10_1101-2021_01_02_425006	447	32	E.	E.	NNP
10_1101-2021_01_02_425006	447	33	coli	coli	NNS
10_1101-2021_01_02_425006	447	34	.	.	.
10_1101-2021_01_02_425006	448	1	BMC	BMC	NNP
10_1101-2021_01_02_425006	448	2	Bioinformatics	Bioinformatics	NNP
10_1101-2021_01_02_425006	448	3	16	16	CD
10_1101-2021_01_02_425006	448	4	,	,	,
10_1101-2021_01_02_425006	448	5	356	356	CD
10_1101-2021_01_02_425006	448	6	(	(	-LRB-
10_1101-2021_01_02_425006	448	7	2015	2015	CD
10_1101-2021_01_02_425006	448	8	)	)	-RRB-
10_1101-2021_01_02_425006	448	9	.	.	.
10_1101-2021_01_02_425006	449	1	536	536	CD
10_1101-2021_01_02_425006	449	2	39	39	CD
10_1101-2021_01_02_425006	449	3	.	.	.
10_1101-2021_01_02_425006	450	1	B.	B.	NNP
10_1101-2021_01_02_425006	450	2	Marie	Marie	NNP
10_1101-2021_01_02_425006	450	3	,	,	,
10_1101-2021_01_02_425006	450	4	K.	K.	NNP
10_1101-2021_01_02_425006	450	5	H.	H.	NNP
10_1101-2021_01_02_425006	450	6	Thilo	Thilo	NNP
10_1101-2021_01_02_425006	450	7	,	,	,
10_1101-2021_01_02_425006	450	8	F.	F.	NNP
10_1101-2021_01_02_425006	450	9	Thierry	Thierry	NNP
10_1101-2021_01_02_425006	450	10	,	,	,
10_1101-2021_01_02_425006	450	11	T.	T.	NNP
10_1101-2021_01_02_425006	450	12	Mikael	Mikael	NNP
10_1101-2021_01_02_425006	450	13	,	,	,
10_1101-2021_01_02_425006	450	14	R.	R.	NNP
10_1101-2021_01_02_425006	450	15	Adriana	Adriana	NNP
10_1101-2021_01_02_425006	450	16	,	,	,
10_1101-2021_01_02_425006	450	17	V.	V.	NNP
10_1101-2021_01_02_425006	450	18	D.	D.	NNP
10_1101-2021_01_02_425006	450	19	Christian	Christian	NNP
10_1101-2021_01_02_425006	450	20	,	,	,
10_1101-2021_01_02_425006	450	21	Metabolic	metabolic	JJ
10_1101-2021_01_02_425006	450	22	pathways	pathway	NNS
10_1101-2021_01_02_425006	450	23	of	of	IN
10_1101-2021_01_02_425006	450	24	537	537	CD
10_1101-2021_01_02_425006	450	25	Pseudomonas	Pseudomonas	NNP
10_1101-2021_01_02_425006	450	26	aeruginosa	aeruginosa	RB
10_1101-2021_01_02_425006	450	27	involved	involve	VBN
10_1101-2021_01_02_425006	450	28	in	in	IN
10_1101-2021_01_02_425006	450	29	competition	competition	NN
10_1101-2021_01_02_425006	450	30	with	with	IN
10_1101-2021_01_02_425006	450	31	respiratory	respiratory	JJ
10_1101-2021_01_02_425006	450	32	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	450	33	pathogens	pathogen	NNS
10_1101-2021_01_02_425006	450	34	.	.	.
10_1101-2021_01_02_425006	451	1	Frontiers	frontier	NNS
10_1101-2021_01_02_425006	451	2	538	538	CD
10_1101-2021_01_02_425006	451	3	in	in	IN
10_1101-2021_01_02_425006	451	4	Microbiology	Microbiology	NNP
10_1101-2021_01_02_425006	451	5	6	6	CD
10_1101-2021_01_02_425006	451	6	,	,	,
10_1101-2021_01_02_425006	451	7	321	321	CD
10_1101-2021_01_02_425006	451	8	(	(	-LRB-
10_1101-2021_01_02_425006	451	9	2015	2015	CD
10_1101-2021_01_02_425006	451	10	)	)	-RRB-
10_1101-2021_01_02_425006	451	11	.	.	.
10_1101-2021_01_02_425006	452	1	539	539	CD
10_1101-2021_01_02_425006	452	2	40	40	CD
10_1101-2021_01_02_425006	452	3	.	.	.
10_1101-2021_01_02_425006	453	1	C.	C.	NNP
10_1101-2021_01_02_425006	453	2	Nadiras	Nadiras	NNP
10_1101-2021_01_02_425006	453	3	,	,	,
10_1101-2021_01_02_425006	453	4	E.	E.	NNP
10_1101-2021_01_02_425006	453	5	Eveno	Eveno	NNP
10_1101-2021_01_02_425006	453	6	,	,	,
10_1101-2021_01_02_425006	453	7	A.	A.	NNP
10_1101-2021_01_02_425006	453	8	Schwartz	Schwartz	NNP
10_1101-2021_01_02_425006	453	9	,	,	,
10_1101-2021_01_02_425006	453	10	N.	N.	NNP
10_1101-2021_01_02_425006	453	11	Figueroa	Figueroa	NNP
10_1101-2021_01_02_425006	453	12	-	-	HYPH
10_1101-2021_01_02_425006	453	13	Bossi	Bossi	NNP
10_1101-2021_01_02_425006	453	14	,	,	,
10_1101-2021_01_02_425006	453	15	M.	M.	NNP
10_1101-2021_01_02_425006	453	16	Boudvillain	Boudvillain	NNP
10_1101-2021_01_02_425006	453	17	,	,	,
10_1101-2021_01_02_425006	453	18	A	a	DT
10_1101-2021_01_02_425006	453	19	multivariate	multivariate	JJ
10_1101-2021_01_02_425006	453	20	prediction	prediction	NN
10_1101-2021_01_02_425006	453	21	540	540	CD
10_1101-2021_01_02_425006	453	22	model	model	NN
10_1101-2021_01_02_425006	453	23	for	for	IN
10_1101-2021_01_02_425006	453	24	Rho	Rho	NNP
10_1101-2021_01_02_425006	453	25	-	-	HYPH
10_1101-2021_01_02_425006	453	26	dependent	dependent	JJ
10_1101-2021_01_02_425006	453	27	termination	termination	NN
10_1101-2021_01_02_425006	453	28	of	of	IN
10_1101-2021_01_02_425006	453	29	transcription	transcription	NN
10_1101-2021_01_02_425006	453	30	.	.	.
10_1101-2021_01_02_425006	454	1	Nucleic	Nucleic	NNP
10_1101-2021_01_02_425006	454	2	Acids	Acids	NNPS
10_1101-2021_01_02_425006	454	3	Res	Res	NNP
10_1101-2021_01_02_425006	454	4	.	.	.
10_1101-2021_01_02_425006	455	1	46	46	CD
10_1101-2021_01_02_425006	455	2	,	,	,
10_1101-2021_01_02_425006	455	3	8245	8245	CD
10_1101-2021_01_02_425006	455	4	-	-	SYM
10_1101-2021_01_02_425006	455	5	8260	8260	CD
10_1101-2021_01_02_425006	455	6	(	(	-LRB-
10_1101-2021_01_02_425006	455	7	2018	2018	CD
10_1101-2021_01_02_425006	455	8	)	)	-RRB-
10_1101-2021_01_02_425006	455	9	.	.	.
10_1101-2021_01_02_425006	456	1	541	541	CD
10_1101-2021_01_02_425006	456	2	41	41	CD
10_1101-2021_01_02_425006	456	3	.	.	.
10_1101-2021_01_02_425006	457	1	C.	C.	NNP
10_1101-2021_01_02_425006	457	2	L.	L.	NNP
10_1101-2021_01_02_425006	457	3	Kingsford	Kingsford	NNP
10_1101-2021_01_02_425006	457	4	,	,	,
10_1101-2021_01_02_425006	457	5	K.	K.	NNP
10_1101-2021_01_02_425006	457	6	Ayanbule	Ayanbule	NNP
10_1101-2021_01_02_425006	457	7	,	,	,
10_1101-2021_01_02_425006	457	8	S.	S.	NNP
10_1101-2021_01_02_425006	457	9	L.	L.	NNP
10_1101-2021_01_02_425006	457	10	Salzberg	Salzberg	NNP
10_1101-2021_01_02_425006	457	11	,	,	,
10_1101-2021_01_02_425006	457	12	Rapid	Rapid	NNP
10_1101-2021_01_02_425006	457	13	,	,	,
10_1101-2021_01_02_425006	457	14	accurate	accurate	JJ
10_1101-2021_01_02_425006	457	15	,	,	,
10_1101-2021_01_02_425006	457	16	computational	computational	JJ
10_1101-2021_01_02_425006	457	17	discovery	discovery	NN
10_1101-2021_01_02_425006	457	18	of	of	IN
10_1101-2021_01_02_425006	457	19	Rho-542	rho-542	CD
10_1101-2021_01_02_425006	457	20	independent	independent	JJ
10_1101-2021_01_02_425006	457	21	transcription	transcription	NN
10_1101-2021_01_02_425006	457	22	terminators	terminator	NNS
10_1101-2021_01_02_425006	457	23	illuminates	illuminate	VBZ
10_1101-2021_01_02_425006	457	24	their	-PRON-	PRP$
10_1101-2021_01_02_425006	457	25	relationship	relationship	NN
10_1101-2021_01_02_425006	457	26	to	to	IN
10_1101-2021_01_02_425006	457	27	DNA	DNA	NNP
10_1101-2021_01_02_425006	457	28	uptake	uptake	NN
10_1101-2021_01_02_425006	457	29	.	.	.
10_1101-2021_01_02_425006	458	1	Genome	Genome	NNP
10_1101-2021_01_02_425006	458	2	Biol	Biol	NNP
10_1101-2021_01_02_425006	458	3	.	.	.
10_1101-2021_01_02_425006	459	1	543	543	CD
10_1101-2021_01_02_425006	459	2	8	8	CD
10_1101-2021_01_02_425006	459	3	,	,	,
10_1101-2021_01_02_425006	459	4	R22	R22	NNP
10_1101-2021_01_02_425006	459	5	(	(	-LRB-
10_1101-2021_01_02_425006	459	6	2007	2007	CD
10_1101-2021_01_02_425006	459	7	)	)	-RRB-
10_1101-2021_01_02_425006	459	8	.	.	.
10_1101-2021_01_02_425006	460	1	544	544	CD
10_1101-2021_01_02_425006	460	2	42	42	CD
10_1101-2021_01_02_425006	460	3	.	.	.
10_1101-2021_01_02_425006	461	1	M.	M.	NNP
10_1101-2021_01_02_425006	461	2	Ashburner	Ashburner	NNP
10_1101-2021_01_02_425006	461	3	,	,	,
10_1101-2021_01_02_425006	461	4	S.	S.	NNP
10_1101-2021_01_02_425006	461	5	Lewis	Lewis	NNP
10_1101-2021_01_02_425006	461	6	,	,	,
10_1101-2021_01_02_425006	461	7	On	on	IN
10_1101-2021_01_02_425006	461	8	Ontologies	ontology	NNS
10_1101-2021_01_02_425006	461	9	for	for	IN
10_1101-2021_01_02_425006	461	10	Biologists	Biologists	NNPS
10_1101-2021_01_02_425006	461	11	:	:	:
10_1101-2021_01_02_425006	461	12	The	the	DT
10_1101-2021_01_02_425006	461	13	Gene	Gene	NNP
10_1101-2021_01_02_425006	461	14	Ontology	Ontology	NNP
10_1101-2021_01_02_425006	461	15	—	—	:
10_1101-2021_01_02_425006	461	16	Untangling	untangle	VBG
10_1101-2021_01_02_425006	461	17	the	the	DT
10_1101-2021_01_02_425006	461	18	Web	web	NN
10_1101-2021_01_02_425006	461	19	.	.	.
10_1101-2021_01_02_425006	462	1	545	545	CD
10_1101-2021_01_02_425006	462	2	Novartis	Novartis	NNP
10_1101-2021_01_02_425006	462	3	Found	Found	NNP
10_1101-2021_01_02_425006	462	4	.	.	.
10_1101-2021_01_02_425006	463	1	Symp	Symp	VBN
10_1101-2021_01_02_425006	463	2	.	.	.
10_1101-2021_01_02_425006	464	1	247	247	CD
10_1101-2021_01_02_425006	464	2	,	,	,
10_1101-2021_01_02_425006	464	3	66	66	CD
10_1101-2021_01_02_425006	464	4	-	-	SYM
10_1101-2021_01_02_425006	464	5	80	80	CD
10_1101-2021_01_02_425006	464	6	;	;	:
10_1101-2021_01_02_425006	464	7	discussion	discussion	NN
10_1101-2021_01_02_425006	464	8	80	80	CD
10_1101-2021_01_02_425006	464	9	-	-	SYM
10_1101-2021_01_02_425006	464	10	63	63	CD
10_1101-2021_01_02_425006	464	11	,	,	,
10_1101-2021_01_02_425006	464	12	84	84	CD
10_1101-2021_01_02_425006	464	13	-	-	SYM
10_1101-2021_01_02_425006	464	14	90	90	CD
10_1101-2021_01_02_425006	464	15	,	,	,
10_1101-2021_01_02_425006	464	16	244	244	CD
10_1101-2021_01_02_425006	464	17	-	-	SYM
10_1101-2021_01_02_425006	464	18	252	252	CD
10_1101-2021_01_02_425006	464	19	(	(	-LRB-
10_1101-2021_01_02_425006	464	20	2002	2002	CD
10_1101-2021_01_02_425006	464	21	)	)	-RRB-
10_1101-2021_01_02_425006	464	22	.	.	.
10_1101-2021_01_02_425006	465	1	546	546	CD
10_1101-2021_01_02_425006	465	2	43	43	CD
10_1101-2021_01_02_425006	465	3	.	.	.
10_1101-2021_01_02_425006	466	1	H.	H.	NNP
10_1101-2021_01_02_425006	466	2	Wu	Wu	NNP
10_1101-2021_01_02_425006	466	3	,	,	,
10_1101-2021_01_02_425006	466	4	Z.	Z.	NNP
10_1101-2021_01_02_425006	466	5	Su	Su	NNP
10_1101-2021_01_02_425006	466	6	,	,	,
10_1101-2021_01_02_425006	466	7	F.	F.	NNP
10_1101-2021_01_02_425006	466	8	Mao	Mao	NNP
10_1101-2021_01_02_425006	466	9	,	,	,
10_1101-2021_01_02_425006	466	10	V.	V.	NNP
10_1101-2021_01_02_425006	466	11	Olman	Olman	NNP
10_1101-2021_01_02_425006	466	12	,	,	,
10_1101-2021_01_02_425006	466	13	Y.	Y.	NNP
10_1101-2021_01_02_425006	466	14	Xu	Xu	NNP
10_1101-2021_01_02_425006	466	15	,	,	,
10_1101-2021_01_02_425006	466	16	Prediction	Prediction	NNP
10_1101-2021_01_02_425006	466	17	of	of	IN
10_1101-2021_01_02_425006	466	18	functional	functional	JJ
10_1101-2021_01_02_425006	466	19	modules	module	NNS
10_1101-2021_01_02_425006	466	20	based	base	VBN
10_1101-2021_01_02_425006	466	21	on	on	IN
10_1101-2021_01_02_425006	466	22	comparative	comparative	JJ
10_1101-2021_01_02_425006	466	23	547	547	CD
10_1101-2021_01_02_425006	466	24	genome	genome	JJ
10_1101-2021_01_02_425006	466	25	analysis	analysis	NN
10_1101-2021_01_02_425006	466	26	and	and	CC
10_1101-2021_01_02_425006	466	27	Gene	Gene	NNP
10_1101-2021_01_02_425006	466	28	Ontology	Ontology	NNP
10_1101-2021_01_02_425006	466	29	application	application	NN
10_1101-2021_01_02_425006	466	30	.	.	.
10_1101-2021_01_02_425006	467	1	Nucleic	Nucleic	NNP
10_1101-2021_01_02_425006	467	2	Acids	Acids	NNPS
10_1101-2021_01_02_425006	467	3	Res	Res	NNP
10_1101-2021_01_02_425006	467	4	.	.	.
10_1101-2021_01_02_425006	468	1	33	33	CD
10_1101-2021_01_02_425006	468	2	,	,	,
10_1101-2021_01_02_425006	468	3	2822	2822	CD
10_1101-2021_01_02_425006	468	4	-	-	SYM
10_1101-2021_01_02_425006	468	5	2837	2837	CD
10_1101-2021_01_02_425006	468	6	(	(	-LRB-
10_1101-2021_01_02_425006	468	7	2005	2005	CD
10_1101-2021_01_02_425006	468	8	)	)	-RRB-
10_1101-2021_01_02_425006	468	9	.	.	.
10_1101-2021_01_02_425006	469	1	548	548	CD
10_1101-2021_01_02_425006	469	2	.CC	.CC	:
10_1101-2021_01_02_425006	469	3	-	-	HYPH
10_1101-2021_01_02_425006	469	4	BY	by	IN
10_1101-2021_01_02_425006	469	5	-	-	HYPH
10_1101-2021_01_02_425006	469	6	NC	NC	NNP
10_1101-2021_01_02_425006	469	7	-	-	HYPH
10_1101-2021_01_02_425006	469	8	ND	ND	NNP
10_1101-2021_01_02_425006	469	9	4.0	4.0	CD
10_1101-2021_01_02_425006	469	10	International	International	NNP
10_1101-2021_01_02_425006	469	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	469	12	under	under	IN
10_1101-2021_01_02_425006	469	13	a	a	DT
10_1101-2021_01_02_425006	469	14	(	(	-LRB-
10_1101-2021_01_02_425006	469	15	which	which	WDT
10_1101-2021_01_02_425006	469	16	was	be	VBD
10_1101-2021_01_02_425006	469	17	not	not	RB
10_1101-2021_01_02_425006	469	18	certified	certify	VBN
10_1101-2021_01_02_425006	469	19	by	by	IN
10_1101-2021_01_02_425006	469	20	peer	peer	NN
10_1101-2021_01_02_425006	469	21	review	review	NN
10_1101-2021_01_02_425006	469	22	)	)	-RRB-
10_1101-2021_01_02_425006	469	23	is	be	VBZ
10_1101-2021_01_02_425006	469	24	the	the	DT
10_1101-2021_01_02_425006	469	25	author	author	NN
10_1101-2021_01_02_425006	469	26	/	/	SYM
10_1101-2021_01_02_425006	469	27	funder	funder	NN
10_1101-2021_01_02_425006	469	28	,	,	,
10_1101-2021_01_02_425006	469	29	who	who	WP
10_1101-2021_01_02_425006	469	30	has	have	VBZ
10_1101-2021_01_02_425006	469	31	granted	grant	VBN
10_1101-2021_01_02_425006	469	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	469	33	a	a	DT
10_1101-2021_01_02_425006	469	34	license	license	NN
10_1101-2021_01_02_425006	469	35	to	to	TO
10_1101-2021_01_02_425006	469	36	display	display	VB
10_1101-2021_01_02_425006	469	37	the	the	DT
10_1101-2021_01_02_425006	469	38	preprint	preprint	NN
10_1101-2021_01_02_425006	469	39	in	in	IN
10_1101-2021_01_02_425006	469	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	469	41	.	.	.
10_1101-2021_01_02_425006	470	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	470	2	is	be	VBZ
10_1101-2021_01_02_425006	470	3	made	make	VBN
10_1101-2021_01_02_425006	470	4	The	the	DT
10_1101-2021_01_02_425006	470	5	copyright	copyright	NN
10_1101-2021_01_02_425006	470	6	holder	holder	NN
10_1101-2021_01_02_425006	470	7	for	for	IN
10_1101-2021_01_02_425006	470	8	this	this	DT
10_1101-2021_01_02_425006	470	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	470	10	version	version	NN
10_1101-2021_01_02_425006	470	11	posted	post	VBD
10_1101-2021_01_02_425006	470	12	January	January	NNP
10_1101-2021_01_02_425006	470	13	6	6	CD
10_1101-2021_01_02_425006	470	14	,	,	,
10_1101-2021_01_02_425006	470	15	2021	2021	CD
10_1101-2021_01_02_425006	470	16	.	.	.
10_1101-2021_01_02_425006	470	17	;	;	:
10_1101-2021_01_02_425006	470	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	470	19	:	:	:
10_1101-2021_01_02_425006	470	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	470	21	preprint	preprint	NN
10_1101-2021_01_02_425006	470	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	470	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	470	24	32	32	CD
10_1101-2021_01_02_425006	470	25	44	44	CD
10_1101-2021_01_02_425006	470	26	.	.	.
10_1101-2021_01_02_425006	471	1	S.	S.	NNP
10_1101-2021_01_02_425006	471	2	A.	A.	NNP
10_1101-2021_01_02_425006	471	3	Teukolsky	Teukolsky	NNP
10_1101-2021_01_02_425006	471	4	,	,	,
10_1101-2021_01_02_425006	471	5	B.	B.	NNP
10_1101-2021_01_02_425006	471	6	P.	P.	NNP
10_1101-2021_01_02_425006	471	7	Flannery	Flannery	NNP
10_1101-2021_01_02_425006	471	8	,	,	,
10_1101-2021_01_02_425006	471	9	W.	W.	NNP
10_1101-2021_01_02_425006	471	10	Press	Press	NNP
10_1101-2021_01_02_425006	471	11	,	,	,
10_1101-2021_01_02_425006	471	12	W.	W.	NNP
10_1101-2021_01_02_425006	471	13	Vetterling	Vetterling	NNP
10_1101-2021_01_02_425006	471	14	,	,	,
10_1101-2021_01_02_425006	471	15	Numerical	Numerical	NNP
10_1101-2021_01_02_425006	471	16	Recipes	Recipes	NNPS
10_1101-2021_01_02_425006	471	17	in	in	IN
10_1101-2021_01_02_425006	471	18	C	C	NNP
10_1101-2021_01_02_425006	471	19	:	:	:
10_1101-2021_01_02_425006	471	20	The	the	DT
10_1101-2021_01_02_425006	471	21	Art	art	NN
10_1101-2021_01_02_425006	471	22	of	of	IN
10_1101-2021_01_02_425006	471	23	549	549	CD
10_1101-2021_01_02_425006	471	24	Scientific	Scientific	NNP
10_1101-2021_01_02_425006	471	25	Computing	computing	NN
10_1101-2021_01_02_425006	471	26	.	.	.
10_1101-2021_01_02_425006	472	1	Cambridge	Cambridge	NNP
10_1101-2021_01_02_425006	472	2	University	University	NNP
10_1101-2021_01_02_425006	472	3	Press	Press	NNP
10_1101-2021_01_02_425006	472	4	,	,	,
10_1101-2021_01_02_425006	472	5	Cambridge	Cambridge	NNP
10_1101-2021_01_02_425006	472	6	(	(	-LRB-
10_1101-2021_01_02_425006	472	7	1992	1992	CD
10_1101-2021_01_02_425006	472	8	)	)	-RRB-
10_1101-2021_01_02_425006	472	9	.	.	.
10_1101-2021_01_02_425006	473	1	550	550	CD
10_1101-2021_01_02_425006	473	2	45	45	CD
10_1101-2021_01_02_425006	473	3	.	.	.
10_1101-2021_01_02_425006	474	1	L.	L.	NNP
10_1101-2021_01_02_425006	474	2	Wan	Wan	NNP
10_1101-2021_01_02_425006	474	3	,	,	,
10_1101-2021_01_02_425006	474	4	X.	X.	NNP
10_1101-2021_01_02_425006	474	5	Yan	Yan	NNP
10_1101-2021_01_02_425006	474	6	,	,	,
10_1101-2021_01_02_425006	474	7	T.	T.	NNP
10_1101-2021_01_02_425006	474	8	Chen	Chen	NNP
10_1101-2021_01_02_425006	474	9	,	,	,
10_1101-2021_01_02_425006	474	10	F.	F.	NNP
10_1101-2021_01_02_425006	474	11	Sun	Sun	NNP
10_1101-2021_01_02_425006	474	12	,	,	,
10_1101-2021_01_02_425006	474	13	Modeling	Modeling	NNP
10_1101-2021_01_02_425006	474	14	RNA	RNA	NNP
10_1101-2021_01_02_425006	474	15	degradation	degradation	NN
10_1101-2021_01_02_425006	474	16	for	for	IN
10_1101-2021_01_02_425006	474	17	RNA	RNA	NNP
10_1101-2021_01_02_425006	474	18	-	-	HYPH
10_1101-2021_01_02_425006	474	19	Seq	Seq	NNP
10_1101-2021_01_02_425006	474	20	with	with	IN
10_1101-2021_01_02_425006	474	21	applications	application	NNS
10_1101-2021_01_02_425006	474	22	.	.	.
10_1101-2021_01_02_425006	475	1	551	551	CD
10_1101-2021_01_02_425006	475	2	Biostatistics	Biostatistics	NNP
10_1101-2021_01_02_425006	475	3	13	13	CD
10_1101-2021_01_02_425006	475	4	,	,	,
10_1101-2021_01_02_425006	475	5	734	734	CD
10_1101-2021_01_02_425006	475	6	-	-	HYPH
10_1101-2021_01_02_425006	475	7	747	747	CD
10_1101-2021_01_02_425006	475	8	(	(	-LRB-
10_1101-2021_01_02_425006	475	9	2012	2012	CD
10_1101-2021_01_02_425006	475	10	)	)	-RRB-
10_1101-2021_01_02_425006	475	11	.	.	.
10_1101-2021_01_02_425006	476	1	552	552	CD
10_1101-2021_01_02_425006	476	2	46	46	CD
10_1101-2021_01_02_425006	476	3	.	.	.
10_1101-2021_01_02_425006	477	1	C.	C.	NNP
10_1101-2021_01_02_425006	477	2	Yanofsky	Yanofsky	NNP
10_1101-2021_01_02_425006	477	3	,	,	,
10_1101-2021_01_02_425006	477	4	Attenuation	Attenuation	NNP
10_1101-2021_01_02_425006	477	5	in	in	IN
10_1101-2021_01_02_425006	477	6	the	the	DT
10_1101-2021_01_02_425006	477	7	control	control	NN
10_1101-2021_01_02_425006	477	8	of	of	IN
10_1101-2021_01_02_425006	477	9	expression	expression	NN
10_1101-2021_01_02_425006	477	10	of	of	IN
10_1101-2021_01_02_425006	477	11	bacterial	bacterial	JJ
10_1101-2021_01_02_425006	477	12	operons	operon	NNS
10_1101-2021_01_02_425006	477	13	.	.	.
10_1101-2021_01_02_425006	478	1	Nature	nature	NN
10_1101-2021_01_02_425006	478	2	289	289	CD
10_1101-2021_01_02_425006	478	3	,	,	,
10_1101-2021_01_02_425006	478	4	751	751	CD
10_1101-2021_01_02_425006	478	5	(	(	-LRB-
10_1101-2021_01_02_425006	478	6	1981	1981	CD
10_1101-2021_01_02_425006	478	7	)	)	-RRB-
10_1101-2021_01_02_425006	478	8	.	.	.
10_1101-2021_01_02_425006	479	1	553	553	CD
10_1101-2021_01_02_425006	479	2	47	47	CD
10_1101-2021_01_02_425006	479	3	.	.	.
10_1101-2021_01_02_425006	480	1	B.	B.	NNP
10_1101-2021_01_02_425006	480	2	K.	K.	NNP
10_1101-2021_01_02_425006	480	3	Cho	Cho	NNP
10_1101-2021_01_02_425006	480	4	,	,	,
10_1101-2021_01_02_425006	480	5	D.	D.	NNP
10_1101-2021_01_02_425006	480	6	Kim	Kim	NNP
10_1101-2021_01_02_425006	480	7	,	,	,
10_1101-2021_01_02_425006	480	8	E.	E.	NNP
10_1101-2021_01_02_425006	480	9	M.	M.	NNP
10_1101-2021_01_02_425006	480	10	Knight	Knight	NNP
10_1101-2021_01_02_425006	480	11	,	,	,
10_1101-2021_01_02_425006	480	12	K.	K.	NNP
10_1101-2021_01_02_425006	480	13	Zengler	Zengler	NNP
10_1101-2021_01_02_425006	480	14	,	,	,
10_1101-2021_01_02_425006	480	15	B.	B.	NNP
10_1101-2021_01_02_425006	480	16	O.	O.	NNP
10_1101-2021_01_02_425006	480	17	Palsson	Palsson	NNP
10_1101-2021_01_02_425006	480	18	,	,	,
10_1101-2021_01_02_425006	480	19	Genome	Genome	NNP
10_1101-2021_01_02_425006	480	20	-	-	HYPH
10_1101-2021_01_02_425006	480	21	scale	scale	NN
10_1101-2021_01_02_425006	480	22	reconstruction	reconstruction	NN
10_1101-2021_01_02_425006	480	23	of	of	IN
10_1101-2021_01_02_425006	480	24	the	the	DT
10_1101-2021_01_02_425006	480	25	554	554	CD
10_1101-2021_01_02_425006	480	26	sigma	sigma	JJ
10_1101-2021_01_02_425006	480	27	factor	factor	NN
10_1101-2021_01_02_425006	480	28	network	network	NN
10_1101-2021_01_02_425006	480	29	in	in	IN
10_1101-2021_01_02_425006	480	30	Escherichia	Escherichia	NNP
10_1101-2021_01_02_425006	480	31	coli	coli	NNS
10_1101-2021_01_02_425006	480	32	:	:	:
10_1101-2021_01_02_425006	480	33	topology	topology	NN
10_1101-2021_01_02_425006	480	34	and	and	CC
10_1101-2021_01_02_425006	480	35	functional	functional	JJ
10_1101-2021_01_02_425006	480	36	states	state	NNS
10_1101-2021_01_02_425006	480	37	.	.	.
10_1101-2021_01_02_425006	481	1	BMC	BMC	NNP
10_1101-2021_01_02_425006	481	2	Biol	Biol	NNP
10_1101-2021_01_02_425006	481	3	.	.	.
10_1101-2021_01_02_425006	482	1	12	12	CD
10_1101-2021_01_02_425006	482	2	,	,	,
10_1101-2021_01_02_425006	482	3	4	4	CD
10_1101-2021_01_02_425006	482	4	-	-	SYM
10_1101-2021_01_02_425006	482	5	4	4	CD
10_1101-2021_01_02_425006	482	6	(	(	-LRB-
10_1101-2021_01_02_425006	482	7	2014	2014	CD
10_1101-2021_01_02_425006	482	8	)	)	-RRB-
10_1101-2021_01_02_425006	482	9	.	.	.
10_1101-2021_01_02_425006	483	1	555	555	CD
10_1101-2021_01_02_425006	483	2	48	48	CD
10_1101-2021_01_02_425006	483	3	.	.	.
10_1101-2021_01_02_425006	484	1	B.-K.	B.-K.	NNP
10_1101-2021_01_02_425006	484	2	Cho	Cho	NNP
10_1101-2021_01_02_425006	484	3	,	,	,
10_1101-2021_01_02_425006	484	4	P.	P.	NNP
10_1101-2021_01_02_425006	484	5	Charusanti	Charusanti	NNP
10_1101-2021_01_02_425006	484	6	,	,	,
10_1101-2021_01_02_425006	484	7	M.	M.	NNP
10_1101-2021_01_02_425006	484	8	J.	J.	NNP
10_1101-2021_01_02_425006	484	9	Herrgård	Herrgård	NNP
10_1101-2021_01_02_425006	484	10	,	,	,
10_1101-2021_01_02_425006	484	11	Microbial	Microbial	NNP
10_1101-2021_01_02_425006	484	12	regulatory	regulatory	JJ
10_1101-2021_01_02_425006	484	13	and	and	CC
10_1101-2021_01_02_425006	484	14	metabolic	metabolic	JJ
10_1101-2021_01_02_425006	484	15	networks	network	NNS
10_1101-2021_01_02_425006	484	16	.	.	.
10_1101-2021_01_02_425006	485	1	Curr	curr	UH
10_1101-2021_01_02_425006	485	2	.	.	.
10_1101-2021_01_02_425006	486	1	Opin	opin	JJ
10_1101-2021_01_02_425006	486	2	.	.	.
10_1101-2021_01_02_425006	487	1	556	556	CD
10_1101-2021_01_02_425006	487	2	Biotechnol	Biotechnol	NNPS
10_1101-2021_01_02_425006	487	3	.	.	.
10_1101-2021_01_02_425006	488	1	18	18	CD
10_1101-2021_01_02_425006	488	2	,	,	,
10_1101-2021_01_02_425006	488	3	360	360	CD
10_1101-2021_01_02_425006	488	4	-	-	SYM
10_1101-2021_01_02_425006	488	5	364	364	CD
10_1101-2021_01_02_425006	488	6	(	(	-LRB-
10_1101-2021_01_02_425006	488	7	2007	2007	CD
10_1101-2021_01_02_425006	488	8	)	)	-RRB-
10_1101-2021_01_02_425006	488	9	.	.	.
10_1101-2021_01_02_425006	489	1	557	557	CD
10_1101-2021_01_02_425006	489	2	49	49	CD
10_1101-2021_01_02_425006	489	3	.	.	.
10_1101-2021_01_02_425006	490	1	A.	A.	NNP
10_1101-2021_01_02_425006	490	2	Toledo	Toledo	NNP
10_1101-2021_01_02_425006	490	3	-	-	HYPH
10_1101-2021_01_02_425006	490	4	Arana	Arana	NNP
10_1101-2021_01_02_425006	490	5	,	,	,
10_1101-2021_01_02_425006	490	6	O.	O.	NNP
10_1101-2021_01_02_425006	490	7	Dussurget	Dussurget	NNP
10_1101-2021_01_02_425006	490	8	,	,	,
10_1101-2021_01_02_425006	490	9	G.	G.	NNP
10_1101-2021_01_02_425006	490	10	Nikitas	Nikitas	NNP
10_1101-2021_01_02_425006	490	11	,	,	,
10_1101-2021_01_02_425006	490	12	N.	N.	NNP
10_1101-2021_01_02_425006	490	13	Sesto	Sesto	NNP
10_1101-2021_01_02_425006	490	14	,	,	,
10_1101-2021_01_02_425006	490	15	H.	H.	NNP
10_1101-2021_01_02_425006	490	16	Guet	Guet	NNP
10_1101-2021_01_02_425006	490	17	-	-	HYPH
10_1101-2021_01_02_425006	490	18	Revillet	Revillet	NNP
10_1101-2021_01_02_425006	490	19	,	,	,
10_1101-2021_01_02_425006	490	20	D.	D.	NNP
10_1101-2021_01_02_425006	490	21	Balestrino	Balestrino	NNP
10_1101-2021_01_02_425006	490	22	,	,	,
10_1101-2021_01_02_425006	490	23	E.	E.	NNP
10_1101-2021_01_02_425006	490	24	Loh	Loh	NNP
10_1101-2021_01_02_425006	490	25	,	,	,
10_1101-2021_01_02_425006	490	26	J.	J.	NNP
10_1101-2021_01_02_425006	491	1	558	558	CD
10_1101-2021_01_02_425006	491	2	Gripenland	Gripenland	NNP
10_1101-2021_01_02_425006	491	3	,	,	,
10_1101-2021_01_02_425006	491	4	T.	T.	NNP
10_1101-2021_01_02_425006	491	5	Tiensuu	Tiensuu	NNP
10_1101-2021_01_02_425006	491	6	,	,	,
10_1101-2021_01_02_425006	491	7	K.	K.	NNP
10_1101-2021_01_02_425006	491	8	Vaitkevicius	Vaitkevicius	NNP
10_1101-2021_01_02_425006	491	9	,	,	,
10_1101-2021_01_02_425006	491	10	The	the	DT
10_1101-2021_01_02_425006	491	11	Listeria	Listeria	NNP
10_1101-2021_01_02_425006	491	12	transcriptional	transcriptional	JJ
10_1101-2021_01_02_425006	491	13	landscape	landscape	NN
10_1101-2021_01_02_425006	491	14	from	from	IN
10_1101-2021_01_02_425006	491	15	saprophytism	saprophytism	NNP
10_1101-2021_01_02_425006	491	16	559	559	CD
10_1101-2021_01_02_425006	491	17	to	to	IN
10_1101-2021_01_02_425006	491	18	virulence	virulence	NN
10_1101-2021_01_02_425006	491	19	.	.	.
10_1101-2021_01_02_425006	492	1	Nature	nature	NN
10_1101-2021_01_02_425006	492	2	459	459	CD
10_1101-2021_01_02_425006	492	3	,	,	,
10_1101-2021_01_02_425006	492	4	950	950	CD
10_1101-2021_01_02_425006	492	5	-	-	SYM
10_1101-2021_01_02_425006	492	6	956	956	CD
10_1101-2021_01_02_425006	492	7	(	(	-LRB-
10_1101-2021_01_02_425006	492	8	2009	2009	CD
10_1101-2021_01_02_425006	492	9	)	)	-RRB-
10_1101-2021_01_02_425006	492	10	.	.	.
10_1101-2021_01_02_425006	493	1	560	560	CD
10_1101-2021_01_02_425006	493	2	50	50	CD
10_1101-2021_01_02_425006	493	3	.	.	.
10_1101-2021_01_02_425006	494	1	B.	B.	NNP
10_1101-2021_01_02_425006	494	2	Yue	Yue	NNP
10_1101-2021_01_02_425006	494	3	,	,	,
10_1101-2021_01_02_425006	494	4	X.	X.	NNP
10_1101-2021_01_02_425006	494	5	Luo	Luo	NNP
10_1101-2021_01_02_425006	494	6	,	,	,
10_1101-2021_01_02_425006	494	7	Z.	Z.	NNP
10_1101-2021_01_02_425006	494	8	Yu	Yu	NNP
10_1101-2021_01_02_425006	494	9	,	,	,
10_1101-2021_01_02_425006	494	10	S.	S.	NNP
10_1101-2021_01_02_425006	494	11	Mani	Mani	NNP
10_1101-2021_01_02_425006	494	12	,	,	,
10_1101-2021_01_02_425006	494	13	Z.	Z.	NNP
10_1101-2021_01_02_425006	494	14	Wang	Wang	NNP
10_1101-2021_01_02_425006	494	15	,	,	,
10_1101-2021_01_02_425006	494	16	W.	W.	NNP
10_1101-2021_01_02_425006	494	17	Dou	Dou	NNP
10_1101-2021_01_02_425006	494	18	,	,	,
10_1101-2021_01_02_425006	494	19	Inflammatory	Inflammatory	NNP
10_1101-2021_01_02_425006	494	20	bowel	bowel	NN
10_1101-2021_01_02_425006	494	21	disease	disease	NN
10_1101-2021_01_02_425006	494	22	:	:	:
10_1101-2021_01_02_425006	494	23	a	a	DT
10_1101-2021_01_02_425006	494	24	potential	potential	JJ
10_1101-2021_01_02_425006	494	25	result	result	NN
10_1101-2021_01_02_425006	494	26	561	561	CD
10_1101-2021_01_02_425006	494	27	from	from	IN
10_1101-2021_01_02_425006	494	28	the	the	DT
10_1101-2021_01_02_425006	494	29	collusion	collusion	NN
10_1101-2021_01_02_425006	494	30	between	between	IN
10_1101-2021_01_02_425006	494	31	gut	gut	NNP
10_1101-2021_01_02_425006	494	32	microbiota	microbiota	NNP
10_1101-2021_01_02_425006	494	33	and	and	CC
10_1101-2021_01_02_425006	494	34	mucosal	mucosal	NN
10_1101-2021_01_02_425006	494	35	immune	immune	JJ
10_1101-2021_01_02_425006	494	36	system	system	NN
10_1101-2021_01_02_425006	494	37	.	.	.
10_1101-2021_01_02_425006	495	1	Microorganisms	microorganism	NNS
10_1101-2021_01_02_425006	495	2	7	7	CD
10_1101-2021_01_02_425006	495	3	,	,	,
10_1101-2021_01_02_425006	495	4	440	440	CD
10_1101-2021_01_02_425006	495	5	562	562	CD
10_1101-2021_01_02_425006	495	6	(	(	-LRB-
10_1101-2021_01_02_425006	495	7	2019	2019	CD
10_1101-2021_01_02_425006	495	8	)	)	-RRB-
10_1101-2021_01_02_425006	495	9	.	.	.
10_1101-2021_01_02_425006	496	1	563	563	CD
10_1101-2021_01_02_425006	496	2	51	51	CD
10_1101-2021_01_02_425006	496	3	.	.	.
10_1101-2021_01_02_425006	497	1	B.	B.	NNP
10_1101-2021_01_02_425006	497	2	H.	H.	NNP
10_1101-2021_01_02_425006	497	3	Mullish	Mullish	NNP
10_1101-2021_01_02_425006	497	4	,	,	,
10_1101-2021_01_02_425006	497	5	H.	H.	NNP
10_1101-2021_01_02_425006	497	6	R.	R.	NNP
10_1101-2021_01_02_425006	497	7	Williams	Williams	NNP
10_1101-2021_01_02_425006	497	8	,	,	,
10_1101-2021_01_02_425006	497	9	Clostridium	Clostridium	NNP
10_1101-2021_01_02_425006	497	10	difficile	difficile	NN
10_1101-2021_01_02_425006	497	11	infection	infection	NN
10_1101-2021_01_02_425006	497	12	and	and	CC
10_1101-2021_01_02_425006	497	13	antibiotic	antibiotic	NN
10_1101-2021_01_02_425006	497	14	-	-	HYPH
10_1101-2021_01_02_425006	497	15	associated	associate	VBN
10_1101-2021_01_02_425006	497	16	diarrhoea	diarrhoea	NNP
10_1101-2021_01_02_425006	497	17	.	.	.
10_1101-2021_01_02_425006	498	1	564	564	CD
10_1101-2021_01_02_425006	498	2	Clin	Clin	NNP
10_1101-2021_01_02_425006	498	3	.	.	.
10_1101-2021_01_02_425006	499	1	Med	Med	NNP
10_1101-2021_01_02_425006	499	2	.	.	.
10_1101-2021_01_02_425006	500	1	18	18	CD
10_1101-2021_01_02_425006	500	2	,	,	,
10_1101-2021_01_02_425006	500	3	237	237	CD
10_1101-2021_01_02_425006	500	4	(	(	-LRB-
10_1101-2021_01_02_425006	500	5	2018	2018	CD
10_1101-2021_01_02_425006	500	6	)	)	-RRB-
10_1101-2021_01_02_425006	500	7	.	.	.
10_1101-2021_01_02_425006	501	1	565	565	CD
10_1101-2021_01_02_425006	501	2	.CC	.CC	:
10_1101-2021_01_02_425006	501	3	-	-	HYPH
10_1101-2021_01_02_425006	501	4	BY	by	IN
10_1101-2021_01_02_425006	501	5	-	-	HYPH
10_1101-2021_01_02_425006	501	6	NC	NC	NNP
10_1101-2021_01_02_425006	501	7	-	-	HYPH
10_1101-2021_01_02_425006	501	8	ND	ND	NNP
10_1101-2021_01_02_425006	501	9	4.0	4.0	CD
10_1101-2021_01_02_425006	501	10	International	International	NNP
10_1101-2021_01_02_425006	501	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	501	12	under	under	IN
10_1101-2021_01_02_425006	501	13	a	a	DT
10_1101-2021_01_02_425006	501	14	(	(	-LRB-
10_1101-2021_01_02_425006	501	15	which	which	WDT
10_1101-2021_01_02_425006	501	16	was	be	VBD
10_1101-2021_01_02_425006	501	17	not	not	RB
10_1101-2021_01_02_425006	501	18	certified	certify	VBN
10_1101-2021_01_02_425006	501	19	by	by	IN
10_1101-2021_01_02_425006	501	20	peer	peer	NN
10_1101-2021_01_02_425006	501	21	review	review	NN
10_1101-2021_01_02_425006	501	22	)	)	-RRB-
10_1101-2021_01_02_425006	501	23	is	be	VBZ
10_1101-2021_01_02_425006	501	24	the	the	DT
10_1101-2021_01_02_425006	501	25	author	author	NN
10_1101-2021_01_02_425006	501	26	/	/	SYM
10_1101-2021_01_02_425006	501	27	funder	funder	NN
10_1101-2021_01_02_425006	501	28	,	,	,
10_1101-2021_01_02_425006	501	29	who	who	WP
10_1101-2021_01_02_425006	501	30	has	have	VBZ
10_1101-2021_01_02_425006	501	31	granted	grant	VBN
10_1101-2021_01_02_425006	501	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	501	33	a	a	DT
10_1101-2021_01_02_425006	501	34	license	license	NN
10_1101-2021_01_02_425006	501	35	to	to	TO
10_1101-2021_01_02_425006	501	36	display	display	VB
10_1101-2021_01_02_425006	501	37	the	the	DT
10_1101-2021_01_02_425006	501	38	preprint	preprint	NN
10_1101-2021_01_02_425006	501	39	in	in	IN
10_1101-2021_01_02_425006	501	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	501	41	.	.	.
10_1101-2021_01_02_425006	502	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	502	2	is	be	VBZ
10_1101-2021_01_02_425006	502	3	made	make	VBN
10_1101-2021_01_02_425006	502	4	The	the	DT
10_1101-2021_01_02_425006	502	5	copyright	copyright	NN
10_1101-2021_01_02_425006	502	6	holder	holder	NN
10_1101-2021_01_02_425006	502	7	for	for	IN
10_1101-2021_01_02_425006	502	8	this	this	DT
10_1101-2021_01_02_425006	502	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	502	10	version	version	NN
10_1101-2021_01_02_425006	502	11	posted	post	VBD
10_1101-2021_01_02_425006	502	12	January	January	NNP
10_1101-2021_01_02_425006	502	13	6	6	CD
10_1101-2021_01_02_425006	502	14	,	,	,
10_1101-2021_01_02_425006	502	15	2021	2021	CD
10_1101-2021_01_02_425006	502	16	.	.	.
10_1101-2021_01_02_425006	502	17	;	;	:
10_1101-2021_01_02_425006	502	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	502	19	:	:	:
10_1101-2021_01_02_425006	502	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	502	21	preprint	preprint	NN
10_1101-2021_01_02_425006	502	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	502	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	502	24	33	33	CD
10_1101-2021_01_02_425006	502	25	52	52	CD
10_1101-2021_01_02_425006	502	26	.	.	.
10_1101-2021_01_02_425006	503	1	M.	M.	NNP
10_1101-2021_01_02_425006	503	2	Maguire	Maguire	NNP
10_1101-2021_01_02_425006	503	3	,	,	,
10_1101-2021_01_02_425006	503	4	G.	G.	NNP
10_1101-2021_01_02_425006	503	5	Maguire	Maguire	NNP
10_1101-2021_01_02_425006	503	6	,	,	,
10_1101-2021_01_02_425006	503	7	Gut	Gut	NNP
10_1101-2021_01_02_425006	503	8	dysbiosis	dysbiosis	NN
10_1101-2021_01_02_425006	503	9	,	,	,
10_1101-2021_01_02_425006	503	10	leaky	leaky	JJ
10_1101-2021_01_02_425006	503	11	gut	gut	NN
10_1101-2021_01_02_425006	503	12	,	,	,
10_1101-2021_01_02_425006	503	13	and	and	CC
10_1101-2021_01_02_425006	503	14	intestinal	intestinal	JJ
10_1101-2021_01_02_425006	503	15	epithelial	epithelial	JJ
10_1101-2021_01_02_425006	503	16	proliferation	proliferation	NN
10_1101-2021_01_02_425006	503	17	in	in	IN
10_1101-2021_01_02_425006	503	18	566	566	CD
10_1101-2021_01_02_425006	503	19	neurological	neurological	JJ
10_1101-2021_01_02_425006	503	20	disorders	disorder	NNS
10_1101-2021_01_02_425006	503	21	:	:	:
10_1101-2021_01_02_425006	503	22	towards	towards	IN
10_1101-2021_01_02_425006	503	23	the	the	DT
10_1101-2021_01_02_425006	503	24	development	development	NN
10_1101-2021_01_02_425006	503	25	of	of	IN
10_1101-2021_01_02_425006	503	26	a	a	DT
10_1101-2021_01_02_425006	503	27	new	new	JJ
10_1101-2021_01_02_425006	503	28	therapeutic	therapeutic	NN
10_1101-2021_01_02_425006	503	29	using	use	VBG
10_1101-2021_01_02_425006	503	30	amino	amino	JJ
10_1101-2021_01_02_425006	503	31	acids	acid	NNS
10_1101-2021_01_02_425006	503	32	,	,	,
10_1101-2021_01_02_425006	503	33	567	567	CD
10_1101-2021_01_02_425006	503	34	prebiotics	prebiotic	NNS
10_1101-2021_01_02_425006	503	35	,	,	,
10_1101-2021_01_02_425006	503	36	probiotics	probiotic	NNS
10_1101-2021_01_02_425006	503	37	,	,	,
10_1101-2021_01_02_425006	503	38	and	and	CC
10_1101-2021_01_02_425006	503	39	postbiotics	postbiotic	NNS
10_1101-2021_01_02_425006	503	40	.	.	.
10_1101-2021_01_02_425006	504	1	Rev.	Rev.	NNP
10_1101-2021_01_02_425006	505	1	Neurosci	Neurosci	NNP
10_1101-2021_01_02_425006	505	2	.	.	.
10_1101-2021_01_02_425006	506	1	30	30	CD
10_1101-2021_01_02_425006	506	2	,	,	,
10_1101-2021_01_02_425006	506	3	179	179	CD
10_1101-2021_01_02_425006	506	4	-	-	SYM
10_1101-2021_01_02_425006	506	5	201	201	CD
10_1101-2021_01_02_425006	506	6	(	(	-LRB-
10_1101-2021_01_02_425006	506	7	2019	2019	CD
10_1101-2021_01_02_425006	506	8	)	)	-RRB-
10_1101-2021_01_02_425006	506	9	.	.	.
10_1101-2021_01_02_425006	507	1	568	568	CD
10_1101-2021_01_02_425006	507	2	53	53	CD
10_1101-2021_01_02_425006	507	3	.	.	.
10_1101-2021_01_02_425006	508	1	S.	S.	NNP
10_1101-2021_01_02_425006	508	2	Vivarelli	Vivarelli	NNP
10_1101-2021_01_02_425006	508	3	,	,	,
10_1101-2021_01_02_425006	508	4	R.	R.	NNP
10_1101-2021_01_02_425006	508	5	Salemi	Salemi	NNP
10_1101-2021_01_02_425006	508	6	,	,	,
10_1101-2021_01_02_425006	508	7	S.	S.	NNP
10_1101-2021_01_02_425006	508	8	Candido	Candido	NNP
10_1101-2021_01_02_425006	508	9	,	,	,
10_1101-2021_01_02_425006	508	10	L.	L.	NNP
10_1101-2021_01_02_425006	508	11	Falzone	Falzone	NNP
10_1101-2021_01_02_425006	508	12	,	,	,
10_1101-2021_01_02_425006	508	13	M.	M.	NNP
10_1101-2021_01_02_425006	508	14	Santagati	Santagati	NNP
10_1101-2021_01_02_425006	508	15	,	,	,
10_1101-2021_01_02_425006	508	16	S.	S.	NNP
10_1101-2021_01_02_425006	508	17	Stefani	Stefani	NNP
10_1101-2021_01_02_425006	508	18	,	,	,
10_1101-2021_01_02_425006	508	19	F.	F.	NNP
10_1101-2021_01_02_425006	508	20	Torino	Torino	NNP
10_1101-2021_01_02_425006	508	21	,	,	,
10_1101-2021_01_02_425006	508	22	G.	G.	NNP
10_1101-2021_01_02_425006	508	23	L.	L.	NNP
10_1101-2021_01_02_425006	508	24	Banna	Banna	NNP
10_1101-2021_01_02_425006	508	25	,	,	,
10_1101-2021_01_02_425006	508	26	569	569	CD
10_1101-2021_01_02_425006	508	27	G.	G.	NNP
10_1101-2021_01_02_425006	508	28	Tonini	Tonini	NNP
10_1101-2021_01_02_425006	508	29	,	,	,
10_1101-2021_01_02_425006	508	30	M.	M.	NNP
10_1101-2021_01_02_425006	508	31	Libra	Libra	NNP
10_1101-2021_01_02_425006	508	32	,	,	,
10_1101-2021_01_02_425006	508	33	Gut	Gut	NNP
10_1101-2021_01_02_425006	508	34	microbiota	microbiota	NNP
10_1101-2021_01_02_425006	508	35	and	and	CC
10_1101-2021_01_02_425006	508	36	cancer	cancer	NN
10_1101-2021_01_02_425006	508	37	:	:	:
10_1101-2021_01_02_425006	508	38	from	from	IN
10_1101-2021_01_02_425006	508	39	pathogenesis	pathogenesis	NN
10_1101-2021_01_02_425006	508	40	to	to	IN
10_1101-2021_01_02_425006	508	41	therapy	therapy	NN
10_1101-2021_01_02_425006	508	42	.	.	.
10_1101-2021_01_02_425006	509	1	Cancers	cancer	NNS
10_1101-2021_01_02_425006	509	2	11	11	CD
10_1101-2021_01_02_425006	509	3	,	,	,
10_1101-2021_01_02_425006	509	4	38	38	CD
10_1101-2021_01_02_425006	509	5	570	570	CD
10_1101-2021_01_02_425006	509	6	(	(	-LRB-
10_1101-2021_01_02_425006	509	7	2019	2019	CD
10_1101-2021_01_02_425006	509	8	)	)	-RRB-
10_1101-2021_01_02_425006	509	9	.	.	.
10_1101-2021_01_02_425006	510	1	571	571	CD
10_1101-2021_01_02_425006	510	2	54	54	CD
10_1101-2021_01_02_425006	510	3	.	.	.
10_1101-2021_01_02_425006	511	1	G.	G.	NNP
10_1101-2021_01_02_425006	511	2	Cammarota	Cammarota	NNP
10_1101-2021_01_02_425006	511	3	,	,	,
10_1101-2021_01_02_425006	511	4	G.	G.	NNP
10_1101-2021_01_02_425006	511	5	Ianiro	Ianiro	NNP
10_1101-2021_01_02_425006	511	6	,	,	,
10_1101-2021_01_02_425006	511	7	A.	A.	NNP
10_1101-2021_01_02_425006	511	8	Ahern	Ahern	NNP
10_1101-2021_01_02_425006	511	9	,	,	,
10_1101-2021_01_02_425006	511	10	C.	C.	NNP
10_1101-2021_01_02_425006	511	11	Carbone	Carbone	NNP
10_1101-2021_01_02_425006	511	12	,	,	,
10_1101-2021_01_02_425006	511	13	A.	A.	NNP
10_1101-2021_01_02_425006	511	14	Temko	Temko	NNP
10_1101-2021_01_02_425006	511	15	,	,	,
10_1101-2021_01_02_425006	511	16	M.	M.	NNP
10_1101-2021_01_02_425006	511	17	J.	J.	NNP
10_1101-2021_01_02_425006	511	18	Claesson	Claesson	NNP
10_1101-2021_01_02_425006	511	19	,	,	,
10_1101-2021_01_02_425006	511	20	A.	A.	NNP
10_1101-2021_01_02_425006	511	21	Gasbarrini	Gasbarrini	NNP
10_1101-2021_01_02_425006	511	22	,	,	,
10_1101-2021_01_02_425006	511	23	G.	G.	NNP
10_1101-2021_01_02_425006	511	24	572	572	CD
10_1101-2021_01_02_425006	511	25	Tortora	Tortora	NNP
10_1101-2021_01_02_425006	511	26	,	,	,
10_1101-2021_01_02_425006	511	27	Gut	Gut	NNP
10_1101-2021_01_02_425006	511	28	microbiome	microbiome	NN
10_1101-2021_01_02_425006	511	29	,	,	,
10_1101-2021_01_02_425006	511	30	big	big	JJ
10_1101-2021_01_02_425006	511	31	data	datum	NNS
10_1101-2021_01_02_425006	511	32	and	and	CC
10_1101-2021_01_02_425006	511	33	machine	machine	NN
10_1101-2021_01_02_425006	511	34	learning	learn	VBG
10_1101-2021_01_02_425006	511	35	to	to	TO
10_1101-2021_01_02_425006	511	36	promote	promote	VB
10_1101-2021_01_02_425006	511	37	precision	precision	NN
10_1101-2021_01_02_425006	511	38	medicine	medicine	NN
10_1101-2021_01_02_425006	511	39	for	for	IN
10_1101-2021_01_02_425006	511	40	cancer	cancer	NN
10_1101-2021_01_02_425006	511	41	.	.	.
10_1101-2021_01_02_425006	512	1	573	573	CD
10_1101-2021_01_02_425006	512	2	Nature	Nature	NNP
10_1101-2021_01_02_425006	512	3	Reviews	Reviews	NNPS
10_1101-2021_01_02_425006	512	4	Gastroenterology	Gastroenterology	NNP
10_1101-2021_01_02_425006	512	5	&	&	CC
10_1101-2021_01_02_425006	512	6	Hepatology	Hepatology	NNP
10_1101-2021_01_02_425006	512	7	17	17	CD
10_1101-2021_01_02_425006	512	8	,	,	,
10_1101-2021_01_02_425006	512	9	635	635	CD
10_1101-2021_01_02_425006	512	10	-	-	SYM
10_1101-2021_01_02_425006	512	11	648	648	CD
10_1101-2021_01_02_425006	512	12	(	(	-LRB-
10_1101-2021_01_02_425006	512	13	2020	2020	CD
10_1101-2021_01_02_425006	512	14	)	)	-RRB-
10_1101-2021_01_02_425006	512	15	.	.	.
10_1101-2021_01_02_425006	513	1	574	574	CD
10_1101-2021_01_02_425006	513	2	55	55	CD
10_1101-2021_01_02_425006	513	3	.	.	.
10_1101-2021_01_02_425006	514	1	S.	S.	NNP
10_1101-2021_01_02_425006	514	2	S.	S.	NNP
10_1101-2021_01_02_425006	514	3	A.	a.	NN
10_1101-2021_01_02_425006	514	4	Zaidi	Zaidi	NNP
10_1101-2021_01_02_425006	514	5	,	,	,
10_1101-2021_01_02_425006	514	6	X.	X.	NNP
10_1101-2021_01_02_425006	514	7	Zhang	Zhang	NNP
10_1101-2021_01_02_425006	514	8	,	,	,
10_1101-2021_01_02_425006	514	9	Computational	Computational	NNP
10_1101-2021_01_02_425006	514	10	operon	operon	NN
10_1101-2021_01_02_425006	514	11	prediction	prediction	NN
10_1101-2021_01_02_425006	514	12	in	in	IN
10_1101-2021_01_02_425006	514	13	whole	whole	JJ
10_1101-2021_01_02_425006	514	14	-	-	HYPH
10_1101-2021_01_02_425006	514	15	genomes	genome	NNS
10_1101-2021_01_02_425006	514	16	and	and	CC
10_1101-2021_01_02_425006	514	17	metagenomes	metagenome	NNS
10_1101-2021_01_02_425006	514	18	.	.	.
10_1101-2021_01_02_425006	515	1	575	575	CD
10_1101-2021_01_02_425006	515	2	Briefings	briefing	NNS
10_1101-2021_01_02_425006	515	3	in	in	IN
10_1101-2021_01_02_425006	515	4	functional	functional	JJ
10_1101-2021_01_02_425006	515	5	genomics	genomic	NNS
10_1101-2021_01_02_425006	515	6	16	16	CD
10_1101-2021_01_02_425006	515	7	,	,	,
10_1101-2021_01_02_425006	515	8	181	181	CD
10_1101-2021_01_02_425006	515	9	-	-	SYM
10_1101-2021_01_02_425006	515	10	193	193	CD
10_1101-2021_01_02_425006	515	11	(	(	-LRB-
10_1101-2021_01_02_425006	515	12	2017	2017	CD
10_1101-2021_01_02_425006	515	13	)	)	-RRB-
10_1101-2021_01_02_425006	515	14	.	.	.
10_1101-2021_01_02_425006	516	1	576	576	CD
10_1101-2021_01_02_425006	516	2	ACKNOWLEDGEMENTS	acknowledgement	NNS
10_1101-2021_01_02_425006	516	3	577	577	CD
10_1101-2021_01_02_425006	516	4	Funding	funding	NN
10_1101-2021_01_02_425006	516	5	:	:	:
10_1101-2021_01_02_425006	516	6	This	this	DT
10_1101-2021_01_02_425006	516	7	work	work	NN
10_1101-2021_01_02_425006	516	8	was	be	VBD
10_1101-2021_01_02_425006	516	9	supported	support	VBN
10_1101-2021_01_02_425006	516	10	by	by	IN
10_1101-2021_01_02_425006	516	11	the	the	DT
10_1101-2021_01_02_425006	516	12	National	National	NNP
10_1101-2021_01_02_425006	516	13	Nature	Nature	NNP
10_1101-2021_01_02_425006	516	14	Science	Science	NNP
10_1101-2021_01_02_425006	516	15	Foundation	Foundation	NNP
10_1101-2021_01_02_425006	516	16	of	of	IN
10_1101-2021_01_02_425006	516	17	China	China	NNP
10_1101-2021_01_02_425006	516	18	(	(	-LRB-
10_1101-2021_01_02_425006	516	19	NSFC	NSFC	NNP
10_1101-2021_01_02_425006	516	20	)	)	-RRB-
10_1101-2021_01_02_425006	516	21	578	578	CD
10_1101-2021_01_02_425006	516	22	[	[	-LRB-
10_1101-2021_01_02_425006	516	23	61772313	61772313	CD
10_1101-2021_01_02_425006	516	24	to	to	IN
10_1101-2021_01_02_425006	516	25	B.L.	B.L.	NNP
10_1101-2021_01_02_425006	516	26	,	,	,
10_1101-2021_01_02_425006	516	27	11931008	11931008	CD
10_1101-2021_01_02_425006	516	28	to	to	IN
10_1101-2021_01_02_425006	516	29	B.L.	B.L.	NNP
10_1101-2021_01_02_425006	517	1	]	]	-RRB-
10_1101-2021_01_02_425006	517	2	;	;	:
10_1101-2021_01_02_425006	517	3	Interdisciplinary	Interdisciplinary	NNP
10_1101-2021_01_02_425006	517	4	Science	Science	NNP
10_1101-2021_01_02_425006	517	5	Innovation	Innovation	NNP
10_1101-2021_01_02_425006	517	6	Group	Group	NNP
10_1101-2021_01_02_425006	517	7	Project	Project	NNP
10_1101-2021_01_02_425006	517	8	of	of	IN
10_1101-2021_01_02_425006	517	9	Shandong	Shandong	NNP
10_1101-2021_01_02_425006	517	10	579	579	CD
10_1101-2021_01_02_425006	517	11	University	University	NNP
10_1101-2021_01_02_425006	517	12	(	(	-LRB-
10_1101-2021_01_02_425006	517	13	2019	2019	CD
10_1101-2021_01_02_425006	517	14	)	)	-RRB-
10_1101-2021_01_02_425006	517	15	;	;	:
10_1101-2021_01_02_425006	517	16	and	and	CC
10_1101-2021_01_02_425006	517	17	the	the	DT
10_1101-2021_01_02_425006	517	18	Innovation	Innovation	NNP
10_1101-2021_01_02_425006	517	19	Method	Method	NNP
10_1101-2021_01_02_425006	517	20	Fund	Fund	NNP
10_1101-2021_01_02_425006	517	21	of	of	IN
10_1101-2021_01_02_425006	517	22	China	China	NNP
10_1101-2021_01_02_425006	517	23	[	[	-LRB-
10_1101-2021_01_02_425006	517	24	2018IM020200	2018im020200	CD
10_1101-2021_01_02_425006	517	25	to	to	IN
10_1101-2021_01_02_425006	517	26	B.L.	B.L.	NNP
10_1101-2021_01_02_425006	517	27	]	]	-RRB-
10_1101-2021_01_02_425006	517	28	.	.	.
10_1101-2021_01_02_425006	518	1	The	the	DT
10_1101-2021_01_02_425006	518	2	authors	author	NNS
10_1101-2021_01_02_425006	518	3	580	580	CD
10_1101-2021_01_02_425006	518	4	would	would	MD
10_1101-2021_01_02_425006	518	5	like	like	VB
10_1101-2021_01_02_425006	518	6	to	to	TO
10_1101-2021_01_02_425006	518	7	thank	thank	VB
10_1101-2021_01_02_425006	518	8	Yang	Yang	NNP
10_1101-2021_01_02_425006	518	9	Li	Li	NNP
10_1101-2021_01_02_425006	518	10	for	for	IN
10_1101-2021_01_02_425006	518	11	his	-PRON-	PRP$
10_1101-2021_01_02_425006	518	12	assistance	assistance	NN
10_1101-2021_01_02_425006	518	13	in	in	IN
10_1101-2021_01_02_425006	518	14	language	language	NN
10_1101-2021_01_02_425006	518	15	polishing	polishing	NN
10_1101-2021_01_02_425006	518	16	.	.	.
10_1101-2021_01_02_425006	519	1	Authors	author	NNS
10_1101-2021_01_02_425006	519	2	’	’	POS
10_1101-2021_01_02_425006	519	3	contributions	contribution	NNS
10_1101-2021_01_02_425006	519	4	:	:	:
10_1101-2021_01_02_425006	519	5	B.L.	B.L.	NNP
10_1101-2021_01_02_425006	519	6	,	,	,
10_1101-2021_01_02_425006	519	7	581	581	CD
10_1101-2021_01_02_425006	519	8	Q.M.	Q.M.	NNP
10_1101-2021_01_02_425006	520	1	and	and	CC
10_1101-2021_01_02_425006	520	2	W.C.	W.C.	NNP
10_1101-2021_01_02_425006	520	3	conceived	conceive	VBD
10_1101-2021_01_02_425006	520	4	the	the	DT
10_1101-2021_01_02_425006	520	5	basic	basic	JJ
10_1101-2021_01_02_425006	520	6	idea	idea	NN
10_1101-2021_01_02_425006	520	7	and	and	CC
10_1101-2021_01_02_425006	520	8	designed	design	VBD
10_1101-2021_01_02_425006	520	9	the	the	DT
10_1101-2021_01_02_425006	520	10	overall	overall	JJ
10_1101-2021_01_02_425006	520	11	analyses	analysis	NNS
10_1101-2021_01_02_425006	520	12	.	.	.
10_1101-2021_01_02_425006	521	1	Q.W.	Q.W.	NNP
10_1101-2021_01_02_425006	522	1	carried	carry	VBN
10_1101-2021_01_02_425006	522	2	out	out	RP
10_1101-2021_01_02_425006	522	3	most	most	JJS
10_1101-2021_01_02_425006	522	4	of	of	IN
10_1101-2021_01_02_425006	522	5	the	the	DT
10_1101-2021_01_02_425006	522	6	582	582	CD
10_1101-2021_01_02_425006	522	7	computational	computational	JJ
10_1101-2021_01_02_425006	522	8	analysis	analysis	NN
10_1101-2021_01_02_425006	522	9	and	and	CC
10_1101-2021_01_02_425006	522	10	data	datum	NNS
10_1101-2021_01_02_425006	522	11	interpretation	interpretation	NN
10_1101-2021_01_02_425006	522	12	.	.	.
10_1101-2021_01_02_425006	523	1	All	all	PDT
10_1101-2021_01_02_425006	523	2	the	the	DT
10_1101-2021_01_02_425006	523	3	authors	author	NNS
10_1101-2021_01_02_425006	523	4	wrote	write	VBD
10_1101-2021_01_02_425006	523	5	the	the	DT
10_1101-2021_01_02_425006	523	6	manuscript	manuscript	NN
10_1101-2021_01_02_425006	523	7	.	.	.
10_1101-2021_01_02_425006	524	1	Competing	compete	VBG
10_1101-2021_01_02_425006	524	2	583	583	CD
10_1101-2021_01_02_425006	524	3	.CC	.CC	,
10_1101-2021_01_02_425006	524	4	-	-	HYPH
10_1101-2021_01_02_425006	524	5	BY	by	IN
10_1101-2021_01_02_425006	524	6	-	-	HYPH
10_1101-2021_01_02_425006	524	7	NC	NC	NNP
10_1101-2021_01_02_425006	524	8	-	-	HYPH
10_1101-2021_01_02_425006	524	9	ND	ND	NNP
10_1101-2021_01_02_425006	524	10	4.0	4.0	CD
10_1101-2021_01_02_425006	524	11	International	International	NNP
10_1101-2021_01_02_425006	524	12	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	524	13	under	under	IN
10_1101-2021_01_02_425006	524	14	a	a	DT
10_1101-2021_01_02_425006	524	15	(	(	-LRB-
10_1101-2021_01_02_425006	524	16	which	which	WDT
10_1101-2021_01_02_425006	524	17	was	be	VBD
10_1101-2021_01_02_425006	524	18	not	not	RB
10_1101-2021_01_02_425006	524	19	certified	certify	VBN
10_1101-2021_01_02_425006	524	20	by	by	IN
10_1101-2021_01_02_425006	524	21	peer	peer	NN
10_1101-2021_01_02_425006	524	22	review	review	NN
10_1101-2021_01_02_425006	524	23	)	)	-RRB-
10_1101-2021_01_02_425006	524	24	is	be	VBZ
10_1101-2021_01_02_425006	524	25	the	the	DT
10_1101-2021_01_02_425006	524	26	author	author	NN
10_1101-2021_01_02_425006	524	27	/	/	SYM
10_1101-2021_01_02_425006	524	28	funder	funder	NN
10_1101-2021_01_02_425006	524	29	,	,	,
10_1101-2021_01_02_425006	524	30	who	who	WP
10_1101-2021_01_02_425006	524	31	has	have	VBZ
10_1101-2021_01_02_425006	524	32	granted	grant	VBN
10_1101-2021_01_02_425006	524	33	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	524	34	a	a	DT
10_1101-2021_01_02_425006	524	35	license	license	NN
10_1101-2021_01_02_425006	524	36	to	to	TO
10_1101-2021_01_02_425006	524	37	display	display	VB
10_1101-2021_01_02_425006	524	38	the	the	DT
10_1101-2021_01_02_425006	524	39	preprint	preprint	NN
10_1101-2021_01_02_425006	524	40	in	in	IN
10_1101-2021_01_02_425006	524	41	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	524	42	.	.	.
10_1101-2021_01_02_425006	525	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	525	2	is	be	VBZ
10_1101-2021_01_02_425006	525	3	made	make	VBN
10_1101-2021_01_02_425006	525	4	The	the	DT
10_1101-2021_01_02_425006	525	5	copyright	copyright	NN
10_1101-2021_01_02_425006	525	6	holder	holder	NN
10_1101-2021_01_02_425006	525	7	for	for	IN
10_1101-2021_01_02_425006	525	8	this	this	DT
10_1101-2021_01_02_425006	525	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	525	10	version	version	NN
10_1101-2021_01_02_425006	525	11	posted	post	VBD
10_1101-2021_01_02_425006	525	12	January	January	NNP
10_1101-2021_01_02_425006	525	13	6	6	CD
10_1101-2021_01_02_425006	525	14	,	,	,
10_1101-2021_01_02_425006	525	15	2021	2021	CD
10_1101-2021_01_02_425006	525	16	.	.	.
10_1101-2021_01_02_425006	525	17	;	;	:
10_1101-2021_01_02_425006	525	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	525	19	:	:	:
10_1101-2021_01_02_425006	525	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	525	21	preprint	preprint	NN
10_1101-2021_01_02_425006	525	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	525	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	525	24	34	34	CD
10_1101-2021_01_02_425006	525	25	interests	interest	NNS
10_1101-2021_01_02_425006	525	26	:	:	:
10_1101-2021_01_02_425006	525	27	The	the	DT
10_1101-2021_01_02_425006	525	28	authors	author	NNS
10_1101-2021_01_02_425006	525	29	declare	declare	VBP
10_1101-2021_01_02_425006	525	30	that	that	IN
10_1101-2021_01_02_425006	525	31	they	-PRON-	PRP
10_1101-2021_01_02_425006	525	32	have	have	VBP
10_1101-2021_01_02_425006	525	33	no	no	DT
10_1101-2021_01_02_425006	525	34	competing	compete	VBG
10_1101-2021_01_02_425006	525	35	interests	interest	NNS
10_1101-2021_01_02_425006	525	36	.	.	.
10_1101-2021_01_02_425006	526	1	Data	datum	NNS
10_1101-2021_01_02_425006	526	2	and	and	CC
10_1101-2021_01_02_425006	526	3	materials	material	NNS
10_1101-2021_01_02_425006	526	4	availability	availability	NN
10_1101-2021_01_02_425006	526	5	:	:	:
10_1101-2021_01_02_425006	526	6	584	584	CD
10_1101-2021_01_02_425006	526	7	The	the	DT
10_1101-2021_01_02_425006	526	8	raw	raw	JJ
10_1101-2021_01_02_425006	526	9	data	datum	NNS
10_1101-2021_01_02_425006	526	10	and	and	CC
10_1101-2021_01_02_425006	526	11	source	source	NN
10_1101-2021_01_02_425006	526	12	code	code	NN
10_1101-2021_01_02_425006	526	13	of	of	IN
10_1101-2021_01_02_425006	526	14	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	526	15	and	and	CC
10_1101-2021_01_02_425006	526	16	a	a	DT
10_1101-2021_01_02_425006	526	17	detailed	detailed	JJ
10_1101-2021_01_02_425006	526	18	tutorial	tutorial	NN
10_1101-2021_01_02_425006	526	19	can	can	MD
10_1101-2021_01_02_425006	526	20	be	be	VB
10_1101-2021_01_02_425006	526	21	found	find	VBN
10_1101-2021_01_02_425006	526	22	at	at	IN
10_1101-2021_01_02_425006	526	23	585	585	CD
10_1101-2021_01_02_425006	526	24	https://github.com/OSU-BMBL/SeqATU	https://github.com/OSU-BMBL/SeqATU	NNS
10_1101-2021_01_02_425006	526	25	.	.	.
10_1101-2021_01_02_425006	527	1	586	586	CD
10_1101-2021_01_02_425006	527	2	FIGURES	figure	NNS
10_1101-2021_01_02_425006	527	3	AND	and	CC
10_1101-2021_01_02_425006	527	4	TABLES	tables	NN
10_1101-2021_01_02_425006	527	5	587	587	CD
10_1101-2021_01_02_425006	527	6	Table	table	NN
10_1101-2021_01_02_425006	527	7	1	1	CD
10_1101-2021_01_02_425006	527	8	.	.	.
10_1101-2021_01_02_425006	528	1	Results	result	NNS
10_1101-2021_01_02_425006	528	2	of	of	IN
10_1101-2021_01_02_425006	528	3	predicted	predict	VBN
10_1101-2021_01_02_425006	528	4	ATUs	atu	NNS
10_1101-2021_01_02_425006	528	5	verified	verify	VBN
10_1101-2021_01_02_425006	528	6	by	by	IN
10_1101-2021_01_02_425006	528	7	experimental	experimental	JJ
10_1101-2021_01_02_425006	528	8	TSSs	tss	NNS
10_1101-2021_01_02_425006	528	9	or	or	CC
10_1101-2021_01_02_425006	528	10	TF	TF	NNP
10_1101-2021_01_02_425006	528	11	binding	bind	VBG
10_1101-2021_01_02_425006	528	12	sites	site	NNS
10_1101-2021_01_02_425006	528	13	.	.	.
10_1101-2021_01_02_425006	529	1	Overview	overview	NN
10_1101-2021_01_02_425006	529	2	of	of	IN
10_1101-2021_01_02_425006	529	3	588	588	CD
10_1101-2021_01_02_425006	529	4	the	the	DT
10_1101-2021_01_02_425006	529	5	experimental	experimental	JJ
10_1101-2021_01_02_425006	529	6	TSS	TSS	NNP
10_1101-2021_01_02_425006	529	7	and	and	CC
10_1101-2021_01_02_425006	529	8	TF	TF	NNP
10_1101-2021_01_02_425006	529	9	binding	bind	VBG
10_1101-2021_01_02_425006	529	10	site	site	NN
10_1101-2021_01_02_425006	529	11	datasets	dataset	NNS
10_1101-2021_01_02_425006	529	12	(	(	-LRB-
10_1101-2021_01_02_425006	529	13	dataset	dataset	NNP
10_1101-2021_01_02_425006	529	14	1	1	CD
10_1101-2021_01_02_425006	529	15	and	and	CC
10_1101-2021_01_02_425006	529	16	dataset	dataset	NNP
10_1101-2021_01_02_425006	529	17	2	2	CD
10_1101-2021_01_02_425006	529	18	)	)	-RRB-
10_1101-2021_01_02_425006	529	19	and	and	CC
10_1101-2021_01_02_425006	529	20	the	the	DT
10_1101-2021_01_02_425006	529	21	proportion	proportion	NN
10_1101-2021_01_02_425006	529	22	of	of	IN
10_1101-2021_01_02_425006	529	23	5’-end	5’-end	CD
10_1101-2021_01_02_425006	529	24	589	589	CD
10_1101-2021_01_02_425006	529	25	genes	gene	NNS
10_1101-2021_01_02_425006	529	26	and	and	CC
10_1101-2021_01_02_425006	529	27	no	no	DT
10_1101-2021_01_02_425006	529	28	5’-end	5’-end	CD
10_1101-2021_01_02_425006	529	29	genes	gene	NNS
10_1101-2021_01_02_425006	529	30	of	of	IN
10_1101-2021_01_02_425006	529	31	the	the	DT
10_1101-2021_01_02_425006	529	32	predicted	predict	VBN
10_1101-2021_01_02_425006	529	33	ATUs	atu	NNS
10_1101-2021_01_02_425006	529	34	by	by	IN
10_1101-2021_01_02_425006	529	35	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	529	36	for	for	IN
10_1101-2021_01_02_425006	529	37	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	529	38	and	and	CC
10_1101-2021_01_02_425006	529	39	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	529	40	,	,	,
10_1101-2021_01_02_425006	529	41	which	which	WDT
10_1101-2021_01_02_425006	529	42	590	590	CD
10_1101-2021_01_02_425006	529	43	were	be	VBD
10_1101-2021_01_02_425006	529	44	validated	validate	VBN
10_1101-2021_01_02_425006	529	45	by	by	IN
10_1101-2021_01_02_425006	529	46	experimental	experimental	JJ
10_1101-2021_01_02_425006	529	47	TSSs	tss	NNS
10_1101-2021_01_02_425006	529	48	or	or	CC
10_1101-2021_01_02_425006	529	49	TF	TF	NNP
10_1101-2021_01_02_425006	529	50	binding	bind	VBG
10_1101-2021_01_02_425006	529	51	sites	site	NNS
10_1101-2021_01_02_425006	529	52	.	.	.
10_1101-2021_01_02_425006	530	1	591	591	CD
10_1101-2021_01_02_425006	530	2	dataset	dataset	VBD
10_1101-2021_01_02_425006	530	3	1	1	CD
10_1101-2021_01_02_425006	530	4	dataset	dataset	NN
10_1101-2021_01_02_425006	530	5	2	2	CD
10_1101-2021_01_02_425006	530	6	Source	Source	NNP
10_1101-2021_01_02_425006	530	7	Ju	Ju	NNP
10_1101-2021_01_02_425006	530	8	et	et	NNP
10_1101-2021_01_02_425006	530	9	al	al	NNP
10_1101-2021_01_02_425006	530	10	.	.	.
10_1101-2021_01_02_425006	531	1	(	(	-LRB-
10_1101-2021_01_02_425006	531	2	7	7	LS
10_1101-2021_01_02_425006	531	3	)	)	-RRB-
10_1101-2021_01_02_425006	531	4	RegulonDB	regulondb	NN
10_1101-2021_01_02_425006	531	5	TF	TF	NNP
10_1101-2021_01_02_425006	531	6	binding	bind	VBG
10_1101-2021_01_02_425006	531	7	sites	site	NNS
10_1101-2021_01_02_425006	531	8	Technique	Technique	NNP
10_1101-2021_01_02_425006	531	9	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	531	10	-	-	HYPH
10_1101-2021_01_02_425006	531	11	seq	seq	NNP
10_1101-2021_01_02_425006	531	12	Collection	Collection	NNP
10_1101-2021_01_02_425006	531	13	TSSs	TSSs	NNP
10_1101-2021_01_02_425006	531	14	/	/	SYM
10_1101-2021_01_02_425006	531	15	TF	TF	NNP
10_1101-2021_01_02_425006	531	16	binding	bind	VBG
10_1101-2021_01_02_425006	531	17	sites	site	NNS
10_1101-2021_01_02_425006	531	18	5,512	5,512	CD
10_1101-2021_01_02_425006	531	19	3,220	3,220	CD
10_1101-2021_01_02_425006	531	20	M9Enrich_Se	M9Enrich_Se	NNP
10_1101-2021_01_02_425006	531	21	q	q	NNP
10_1101-2021_01_02_425006	531	22	5’-end	5’-end	CD
10_1101-2021_01_02_425006	531	23	genes	gene	NNS
10_1101-2021_01_02_425006	531	24	83	83	CD
10_1101-2021_01_02_425006	531	25	%	%	NN
10_1101-2021_01_02_425006	531	26	29	29	CD
10_1101-2021_01_02_425006	531	27	%	%	NN
10_1101-2021_01_02_425006	531	28	no	no	DT
10_1101-2021_01_02_425006	531	29	5’-end	5’-end	CD
10_1101-2021_01_02_425006	531	30	genes	gene	NNS
10_1101-2021_01_02_425006	531	31	47	47	CD
10_1101-2021_01_02_425006	531	32	%	%	NN
10_1101-2021_01_02_425006	531	33	9.2	9.2	CD
10_1101-2021_01_02_425006	531	34	%	%	NN
10_1101-2021_01_02_425006	531	35	RiEnrich_Seq	rienrich_seq	NN
10_1101-2021_01_02_425006	531	36	5’-end	5’-end	CD
10_1101-2021_01_02_425006	531	37	genes	gene	NNS
10_1101-2021_01_02_425006	531	38	89	89	CD
10_1101-2021_01_02_425006	531	39	%	%	NN
10_1101-2021_01_02_425006	531	40	30	30	CD
10_1101-2021_01_02_425006	531	41	%	%	NN
10_1101-2021_01_02_425006	531	42	no	no	DT
10_1101-2021_01_02_425006	531	43	5’-end	5’-end	CD
10_1101-2021_01_02_425006	531	44	genes	gene	NNS
10_1101-2021_01_02_425006	531	45	44	44	CD
10_1101-2021_01_02_425006	531	46	%	%	NN
10_1101-2021_01_02_425006	531	47	9.0	9.0	CD
10_1101-2021_01_02_425006	531	48	%	%	NN
10_1101-2021_01_02_425006	531	49	592	592	CD
10_1101-2021_01_02_425006	531	50	593	593	CD
10_1101-2021_01_02_425006	531	51	Table	table	NN
10_1101-2021_01_02_425006	531	52	2	2	CD
10_1101-2021_01_02_425006	531	53	.	.	.
10_1101-2021_01_02_425006	532	1	Results	result	NNS
10_1101-2021_01_02_425006	532	2	of	of	IN
10_1101-2021_01_02_425006	532	3	predicted	predict	VBN
10_1101-2021_01_02_425006	532	4	ATUs	atu	NNS
10_1101-2021_01_02_425006	532	5	verified	verify	VBN
10_1101-2021_01_02_425006	532	6	by	by	IN
10_1101-2021_01_02_425006	532	7	experimental	experimental	JJ
10_1101-2021_01_02_425006	532	8	TTSs	tts	NNS
10_1101-2021_01_02_425006	532	9	.	.	.
10_1101-2021_01_02_425006	533	1	Overview	overview	NN
10_1101-2021_01_02_425006	533	2	of	of	IN
10_1101-2021_01_02_425006	533	3	the	the	DT
10_1101-2021_01_02_425006	533	4	experimental	experimental	JJ
10_1101-2021_01_02_425006	533	5	594	594	CD
10_1101-2021_01_02_425006	533	6	TTS	TTS	NNP
10_1101-2021_01_02_425006	533	7	datasets	dataset	NNS
10_1101-2021_01_02_425006	533	8	(	(	-LRB-
10_1101-2021_01_02_425006	533	9	dataset	dataset	NNP
10_1101-2021_01_02_425006	533	10	3	3	CD
10_1101-2021_01_02_425006	533	11	and	and	CC
10_1101-2021_01_02_425006	533	12	dataset	dataset	VBD
10_1101-2021_01_02_425006	533	13	4	4	CD
10_1101-2021_01_02_425006	533	14	)	)	-RRB-
10_1101-2021_01_02_425006	533	15	and	and	CC
10_1101-2021_01_02_425006	533	16	the	the	DT
10_1101-2021_01_02_425006	533	17	proportion	proportion	NN
10_1101-2021_01_02_425006	533	18	of	of	IN
10_1101-2021_01_02_425006	533	19	3’-end	3’-end	CD
10_1101-2021_01_02_425006	533	20	genes	gene	NNS
10_1101-2021_01_02_425006	533	21	and	and	CC
10_1101-2021_01_02_425006	533	22	no	no	DT
10_1101-2021_01_02_425006	533	23	3’-end	3’-end	CD
10_1101-2021_01_02_425006	533	24	genes	gene	NNS
10_1101-2021_01_02_425006	533	25	of	of	IN
10_1101-2021_01_02_425006	533	26	the	the	DT
10_1101-2021_01_02_425006	533	27	595	595	CD
10_1101-2021_01_02_425006	533	28	predicted	predict	VBN
10_1101-2021_01_02_425006	533	29	ATUs	atu	NNS
10_1101-2021_01_02_425006	533	30	by	by	IN
10_1101-2021_01_02_425006	533	31	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	533	32	for	for	IN
10_1101-2021_01_02_425006	533	33	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	533	34	and	and	CC
10_1101-2021_01_02_425006	533	35	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	533	36	,	,	,
10_1101-2021_01_02_425006	533	37	which	which	WDT
10_1101-2021_01_02_425006	533	38	were	be	VBD
10_1101-2021_01_02_425006	533	39	validated	validate	VBN
10_1101-2021_01_02_425006	533	40	by	by	IN
10_1101-2021_01_02_425006	533	41	596	596	CD
10_1101-2021_01_02_425006	533	42	experimental	experimental	JJ
10_1101-2021_01_02_425006	533	43	TTSs	tts	NNS
10_1101-2021_01_02_425006	533	44	.	.	.
10_1101-2021_01_02_425006	534	1	597	597	CD
10_1101-2021_01_02_425006	534	2	.CC	.CC	:
10_1101-2021_01_02_425006	534	3	-	-	HYPH
10_1101-2021_01_02_425006	534	4	BY	by	IN
10_1101-2021_01_02_425006	534	5	-	-	HYPH
10_1101-2021_01_02_425006	534	6	NC	NC	NNP
10_1101-2021_01_02_425006	534	7	-	-	HYPH
10_1101-2021_01_02_425006	534	8	ND	ND	NNP
10_1101-2021_01_02_425006	534	9	4.0	4.0	CD
10_1101-2021_01_02_425006	534	10	International	International	NNP
10_1101-2021_01_02_425006	534	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	534	12	under	under	IN
10_1101-2021_01_02_425006	534	13	a	a	DT
10_1101-2021_01_02_425006	534	14	(	(	-LRB-
10_1101-2021_01_02_425006	534	15	which	which	WDT
10_1101-2021_01_02_425006	534	16	was	be	VBD
10_1101-2021_01_02_425006	534	17	not	not	RB
10_1101-2021_01_02_425006	534	18	certified	certify	VBN
10_1101-2021_01_02_425006	534	19	by	by	IN
10_1101-2021_01_02_425006	534	20	peer	peer	NN
10_1101-2021_01_02_425006	534	21	review	review	NN
10_1101-2021_01_02_425006	534	22	)	)	-RRB-
10_1101-2021_01_02_425006	534	23	is	be	VBZ
10_1101-2021_01_02_425006	534	24	the	the	DT
10_1101-2021_01_02_425006	534	25	author	author	NN
10_1101-2021_01_02_425006	534	26	/	/	SYM
10_1101-2021_01_02_425006	534	27	funder	funder	NN
10_1101-2021_01_02_425006	534	28	,	,	,
10_1101-2021_01_02_425006	534	29	who	who	WP
10_1101-2021_01_02_425006	534	30	has	have	VBZ
10_1101-2021_01_02_425006	534	31	granted	grant	VBN
10_1101-2021_01_02_425006	534	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	534	33	a	a	DT
10_1101-2021_01_02_425006	534	34	license	license	NN
10_1101-2021_01_02_425006	534	35	to	to	TO
10_1101-2021_01_02_425006	534	36	display	display	VB
10_1101-2021_01_02_425006	534	37	the	the	DT
10_1101-2021_01_02_425006	534	38	preprint	preprint	NN
10_1101-2021_01_02_425006	534	39	in	in	IN
10_1101-2021_01_02_425006	534	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	534	41	.	.	.
10_1101-2021_01_02_425006	535	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	535	2	is	be	VBZ
10_1101-2021_01_02_425006	535	3	made	make	VBN
10_1101-2021_01_02_425006	535	4	The	the	DT
10_1101-2021_01_02_425006	535	5	copyright	copyright	NN
10_1101-2021_01_02_425006	535	6	holder	holder	NN
10_1101-2021_01_02_425006	535	7	for	for	IN
10_1101-2021_01_02_425006	535	8	this	this	DT
10_1101-2021_01_02_425006	535	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	535	10	version	version	NN
10_1101-2021_01_02_425006	535	11	posted	post	VBD
10_1101-2021_01_02_425006	535	12	January	January	NNP
10_1101-2021_01_02_425006	535	13	6	6	CD
10_1101-2021_01_02_425006	535	14	,	,	,
10_1101-2021_01_02_425006	535	15	2021	2021	CD
10_1101-2021_01_02_425006	535	16	.	.	.
10_1101-2021_01_02_425006	535	17	;	;	:
10_1101-2021_01_02_425006	535	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	535	19	:	:	:
10_1101-2021_01_02_425006	535	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	535	21	preprint	preprint	NN
10_1101-2021_01_02_425006	535	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	535	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	535	24	35	35	CD
10_1101-2021_01_02_425006	535	25	dataset	dataset	NN
10_1101-2021_01_02_425006	535	26	3	3	CD
10_1101-2021_01_02_425006	535	27	dataset	dataset	NN
10_1101-2021_01_02_425006	535	28	4	4	CD
10_1101-2021_01_02_425006	535	29	Source	Source	NNP
10_1101-2021_01_02_425006	535	30	Ju	Ju	NNP
10_1101-2021_01_02_425006	535	31	et	et	NNP
10_1101-2021_01_02_425006	535	32	al	al	NNP
10_1101-2021_01_02_425006	535	33	.	.	.
10_1101-2021_01_02_425006	536	1	(	(	-LRB-
10_1101-2021_01_02_425006	536	2	7	7	LS
10_1101-2021_01_02_425006	536	3	)	)	-RRB-
10_1101-2021_01_02_425006	536	4	RegulonDB	regulondb	NN
10_1101-2021_01_02_425006	536	5	TTSs	TTSs	NNPS
10_1101-2021_01_02_425006	536	6	Technique	Technique	NNP
10_1101-2021_01_02_425006	536	7	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	536	8	-	-	HYPH
10_1101-2021_01_02_425006	536	9	seq	seq	NNP
10_1101-2021_01_02_425006	536	10	Collection	Collection	NNP
10_1101-2021_01_02_425006	536	11	TTSs	TTSs	NNPS
10_1101-2021_01_02_425006	536	12	1,540	1,540	CD
10_1101-2021_01_02_425006	536	13	3,67	3,67	CD
10_1101-2021_01_02_425006	536	14	M9Enrich_Se	M9Enrich_Se	NNP
10_1101-2021_01_02_425006	536	15	q	q	NNP
10_1101-2021_01_02_425006	536	16	3’-end	3’-end	CD
10_1101-2021_01_02_425006	536	17	genes	gene	NNS
10_1101-2021_01_02_425006	536	18	51	51	CD
10_1101-2021_01_02_425006	536	19	%	%	NN
10_1101-2021_01_02_425006	536	20	11	11	CD
10_1101-2021_01_02_425006	536	21	%	%	NN
10_1101-2021_01_02_425006	536	22	no	no	DT
10_1101-2021_01_02_425006	536	23	3’-end	3’-end	CD
10_1101-2021_01_02_425006	536	24	genes	gene	NNS
10_1101-2021_01_02_425006	536	25	15	15	CD
10_1101-2021_01_02_425006	536	26	%	%	NN
10_1101-2021_01_02_425006	536	27	5.2	5.2	CD
10_1101-2021_01_02_425006	536	28	%	%	NN
10_1101-2021_01_02_425006	536	29	RiEnrich_Seq	rienrich_seq	NN
10_1101-2021_01_02_425006	536	30	3’-end	3’-end	CD
10_1101-2021_01_02_425006	536	31	genes	gene	NNS
10_1101-2021_01_02_425006	536	32	53	53	CD
10_1101-2021_01_02_425006	536	33	%	%	NN
10_1101-2021_01_02_425006	536	34	11	11	CD
10_1101-2021_01_02_425006	536	35	%	%	NN
10_1101-2021_01_02_425006	536	36	no	no	DT
10_1101-2021_01_02_425006	536	37	3’-end	3’-end	CD
10_1101-2021_01_02_425006	536	38	genes	gene	NNS
10_1101-2021_01_02_425006	536	39	14	14	CD
10_1101-2021_01_02_425006	536	40	%	%	NN
10_1101-2021_01_02_425006	536	41	4.8	4.8	CD
10_1101-2021_01_02_425006	536	42	%	%	NN
10_1101-2021_01_02_425006	536	43	598	598	CD
10_1101-2021_01_02_425006	536	44	599	599	CD
10_1101-2021_01_02_425006	536	45	600	600	CD
10_1101-2021_01_02_425006	536	46	Fig	Fig	NNP
10_1101-2021_01_02_425006	536	47	.	.	.
10_1101-2021_01_02_425006	537	1	1	1	LS
10_1101-2021_01_02_425006	537	2	.	.	.
10_1101-2021_01_02_425006	538	1	Schematic	schematic	JJ
10_1101-2021_01_02_425006	538	2	overview	overview	NN
10_1101-2021_01_02_425006	538	3	of	of	IN
10_1101-2021_01_02_425006	538	4	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	538	5	.	.	.
10_1101-2021_01_02_425006	539	1	The	the	DT
10_1101-2021_01_02_425006	539	2	blue	blue	JJ
10_1101-2021_01_02_425006	539	3	arrow	arrow	NN
10_1101-2021_01_02_425006	539	4	and	and	CC
10_1101-2021_01_02_425006	539	5	orange	orange	JJ
10_1101-2021_01_02_425006	539	6	line	line	NN
10_1101-2021_01_02_425006	539	7	denote	denote	NN
10_1101-2021_01_02_425006	539	8	gene	gene	NN
10_1101-2021_01_02_425006	539	9	and	and	CC
10_1101-2021_01_02_425006	539	10	RNA	RNA	NNP
10_1101-2021_01_02_425006	539	11	-	-	HYPH
10_1101-2021_01_02_425006	539	12	Seq	Seq	NNP
10_1101-2021_01_02_425006	539	13	601	601	CD
10_1101-2021_01_02_425006	539	14	read	read	VBD
10_1101-2021_01_02_425006	539	15	,	,	,
10_1101-2021_01_02_425006	539	16	respectively	respectively	RB
10_1101-2021_01_02_425006	539	17	.	.	.
10_1101-2021_01_02_425006	540	1	The	the	DT
10_1101-2021_01_02_425006	540	2	preprocessing	preprocessing	NN
10_1101-2021_01_02_425006	540	3	stage	stage	NN
10_1101-2021_01_02_425006	540	4	requires	require	VBZ
10_1101-2021_01_02_425006	540	5	RNA	RNA	NNP
10_1101-2021_01_02_425006	540	6	-	-	HYPH
10_1101-2021_01_02_425006	540	7	Seq	Seq	NNP
10_1101-2021_01_02_425006	540	8	data	datum	NNS
10_1101-2021_01_02_425006	540	9	in	in	IN
10_1101-2021_01_02_425006	540	10	the	the	DT
10_1101-2021_01_02_425006	540	11	FASTQ	FASTQ	NNP
10_1101-2021_01_02_425006	540	12	format	format	NN
10_1101-2021_01_02_425006	540	13	,	,	,
10_1101-2021_01_02_425006	540	14	the	the	DT
10_1101-2021_01_02_425006	540	15	reference	reference	NN
10_1101-2021_01_02_425006	540	16	602	602	CD
10_1101-2021_01_02_425006	540	17	.CC	.CC	:
10_1101-2021_01_02_425006	540	18	-	-	HYPH
10_1101-2021_01_02_425006	540	19	BY	by	IN
10_1101-2021_01_02_425006	540	20	-	-	HYPH
10_1101-2021_01_02_425006	540	21	NC	NC	NNP
10_1101-2021_01_02_425006	540	22	-	-	HYPH
10_1101-2021_01_02_425006	540	23	ND	ND	NNP
10_1101-2021_01_02_425006	540	24	4.0	4.0	CD
10_1101-2021_01_02_425006	540	25	International	International	NNP
10_1101-2021_01_02_425006	540	26	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	540	27	under	under	IN
10_1101-2021_01_02_425006	540	28	a	a	DT
10_1101-2021_01_02_425006	540	29	(	(	-LRB-
10_1101-2021_01_02_425006	540	30	which	which	WDT
10_1101-2021_01_02_425006	540	31	was	be	VBD
10_1101-2021_01_02_425006	540	32	not	not	RB
10_1101-2021_01_02_425006	540	33	certified	certify	VBN
10_1101-2021_01_02_425006	540	34	by	by	IN
10_1101-2021_01_02_425006	540	35	peer	peer	NN
10_1101-2021_01_02_425006	540	36	review	review	NN
10_1101-2021_01_02_425006	540	37	)	)	-RRB-
10_1101-2021_01_02_425006	540	38	is	be	VBZ
10_1101-2021_01_02_425006	540	39	the	the	DT
10_1101-2021_01_02_425006	540	40	author	author	NN
10_1101-2021_01_02_425006	540	41	/	/	SYM
10_1101-2021_01_02_425006	540	42	funder	funder	NN
10_1101-2021_01_02_425006	540	43	,	,	,
10_1101-2021_01_02_425006	540	44	who	who	WP
10_1101-2021_01_02_425006	540	45	has	have	VBZ
10_1101-2021_01_02_425006	540	46	granted	grant	VBN
10_1101-2021_01_02_425006	540	47	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	540	48	a	a	DT
10_1101-2021_01_02_425006	540	49	license	license	NN
10_1101-2021_01_02_425006	540	50	to	to	TO
10_1101-2021_01_02_425006	540	51	display	display	VB
10_1101-2021_01_02_425006	540	52	the	the	DT
10_1101-2021_01_02_425006	540	53	preprint	preprint	NN
10_1101-2021_01_02_425006	540	54	in	in	IN
10_1101-2021_01_02_425006	540	55	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	540	56	.	.	.
10_1101-2021_01_02_425006	541	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	541	2	is	be	VBZ
10_1101-2021_01_02_425006	541	3	made	make	VBN
10_1101-2021_01_02_425006	541	4	The	the	DT
10_1101-2021_01_02_425006	541	5	copyright	copyright	NN
10_1101-2021_01_02_425006	541	6	holder	holder	NN
10_1101-2021_01_02_425006	541	7	for	for	IN
10_1101-2021_01_02_425006	541	8	this	this	DT
10_1101-2021_01_02_425006	541	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	541	10	version	version	NN
10_1101-2021_01_02_425006	541	11	posted	post	VBD
10_1101-2021_01_02_425006	541	12	January	January	NNP
10_1101-2021_01_02_425006	541	13	6	6	CD
10_1101-2021_01_02_425006	541	14	,	,	,
10_1101-2021_01_02_425006	541	15	2021	2021	CD
10_1101-2021_01_02_425006	541	16	.	.	.
10_1101-2021_01_02_425006	541	17	;	;	:
10_1101-2021_01_02_425006	541	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	541	19	:	:	:
10_1101-2021_01_02_425006	541	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	541	21	preprint	preprint	NN
10_1101-2021_01_02_425006	541	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	541	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	541	24	36	36	CD
10_1101-2021_01_02_425006	541	25	genome	genome	JJ
10_1101-2021_01_02_425006	541	26	sequence	sequence	NN
10_1101-2021_01_02_425006	541	27	in	in	IN
10_1101-2021_01_02_425006	541	28	the	the	DT
10_1101-2021_01_02_425006	541	29	FASTA	FASTA	NNP
10_1101-2021_01_02_425006	541	30	format	format	NN
10_1101-2021_01_02_425006	541	31	,	,	,
10_1101-2021_01_02_425006	541	32	and	and	CC
10_1101-2021_01_02_425006	541	33	gene	gene	NN
10_1101-2021_01_02_425006	541	34	annotations	annotation	NNS
10_1101-2021_01_02_425006	541	35	in	in	IN
10_1101-2021_01_02_425006	541	36	the	the	DT
10_1101-2021_01_02_425006	541	37	GFF	GFF	NNP
10_1101-2021_01_02_425006	541	38	format	format	NN
10_1101-2021_01_02_425006	541	39	,	,	,
10_1101-2021_01_02_425006	541	40	generating	generate	VBG
10_1101-2021_01_02_425006	541	41	linear	linear	JJ
10_1101-2021_01_02_425006	541	42	603	603	CD
10_1101-2021_01_02_425006	541	43	constraints	constraint	NNS
10_1101-2021_01_02_425006	541	44	for	for	IN
10_1101-2021_01_02_425006	541	45	the	the	DT
10_1101-2021_01_02_425006	541	46	next	next	JJ
10_1101-2021_01_02_425006	541	47	convex	convex	NNP
10_1101-2021_01_02_425006	541	48	quadratic	quadratic	NNP
10_1101-2021_01_02_425006	541	49	programming	programming	NN
10_1101-2021_01_02_425006	541	50	(	(	-LRB-
10_1101-2021_01_02_425006	541	51	CQP	CQP	NNP
10_1101-2021_01_02_425006	541	52	)	)	-RRB-
10_1101-2021_01_02_425006	541	53	stage	stage	NN
10_1101-2021_01_02_425006	541	54	.	.	.
10_1101-2021_01_02_425006	542	1	There	there	EX
10_1101-2021_01_02_425006	542	2	are	be	VBP
10_1101-2021_01_02_425006	542	3	two	two	CD
10_1101-2021_01_02_425006	542	4	steps	step	NNS
10_1101-2021_01_02_425006	542	5	in	in	IN
10_1101-2021_01_02_425006	542	6	the	the	DT
10_1101-2021_01_02_425006	542	7	604	604	CD
10_1101-2021_01_02_425006	542	8	preprocessing	preprocessing	NN
10_1101-2021_01_02_425006	542	9	stage	stage	NN
10_1101-2021_01_02_425006	542	10	:	:	:
10_1101-2021_01_02_425006	542	11	(	(	-LRB-
10_1101-2021_01_02_425006	542	12	i	i	NN
10_1101-2021_01_02_425006	542	13	)	)	-RRB-
10_1101-2021_01_02_425006	542	14	calculating	calculate	VBG
10_1101-2021_01_02_425006	542	15	the	the	DT
10_1101-2021_01_02_425006	542	16	expression	expression	NN
10_1101-2021_01_02_425006	542	17	value	value	NN
10_1101-2021_01_02_425006	542	18	of	of	IN
10_1101-2021_01_02_425006	542	19	the	the	DT
10_1101-2021_01_02_425006	542	20	genetic	genetic	JJ
10_1101-2021_01_02_425006	542	21	region	region	NN
10_1101-2021_01_02_425006	542	22	�	�	.
10_1101-2021_01_02_425006	542	23	�	�	NN
10_1101-2021_01_02_425006	542	24	and	and	CC
10_1101-2021_01_02_425006	542	25	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	542	26	region	region	NN
10_1101-2021_01_02_425006	542	27	605	605	CD
10_1101-2021_01_02_425006	542	28	�	�	NNP
10_1101-2021_01_02_425006	542	29	�	�	NNP
10_1101-2021_01_02_425006	542	30	,	,	,
10_1101-2021_01_02_425006	542	31	�	�	NNP
10_1101-2021_01_02_425006	542	32	and	and	CC
10_1101-2021_01_02_425006	542	33	(	(	-LRB-
10_1101-2021_01_02_425006	542	34	ii	ii	NNP
10_1101-2021_01_02_425006	542	35	)	)	-RRB-
10_1101-2021_01_02_425006	542	36	modelling	model	VBG
10_1101-2021_01_02_425006	542	37	non	non	JJ
10_1101-2021_01_02_425006	542	38	-	-	JJ
10_1101-2021_01_02_425006	542	39	uniform	uniform	JJ
10_1101-2021_01_02_425006	542	40	read	read	VB
10_1101-2021_01_02_425006	542	41	distribution	distribution	NN
10_1101-2021_01_02_425006	542	42	along	along	IN
10_1101-2021_01_02_425006	542	43	mRNA	mRNA	NNS
10_1101-2021_01_02_425006	542	44	transcripts	transcript	NNS
10_1101-2021_01_02_425006	542	45	;	;	,
10_1101-2021_01_02_425006	542	46	specifically	specifically	RB
10_1101-2021_01_02_425006	542	47	,	,	,
10_1101-2021_01_02_425006	542	48	we	-PRON-	PRP
10_1101-2021_01_02_425006	542	49	acquired	acquire	VBD
10_1101-2021_01_02_425006	542	50	606	606	CD
10_1101-2021_01_02_425006	542	51	a	a	DT
10_1101-2021_01_02_425006	542	52	bias	bias	NN
10_1101-2021_01_02_425006	542	53	rate	rate	NN
10_1101-2021_01_02_425006	542	54	function	function	NN
10_1101-2021_01_02_425006	542	55	�	�	,
10_1101-2021_01_02_425006	542	56	(	(	-LRB-
10_1101-2021_01_02_425006	542	57	�	�	NNP
10_1101-2021_01_02_425006	542	58	)	)	-RRB-
10_1101-2021_01_02_425006	542	59	=	=	NFP
10_1101-2021_01_02_425006	542	60	�	�	ADD
10_1101-2021_01_02_425006	542	61	�	�	,
10_1101-2021_01_02_425006	542	62	�	�	NNP
10_1101-2021_01_02_425006	542	63	using	use	VBG
10_1101-2021_01_02_425006	542	64	nonlinear	nonlinear	JJ
10_1101-2021_01_02_425006	542	65	regression	regression	NN
10_1101-2021_01_02_425006	542	66	and	and	CC
10_1101-2021_01_02_425006	542	67	then	then	RB
10_1101-2021_01_02_425006	542	68	constructed	construct	VBN
10_1101-2021_01_02_425006	542	69	genetic	genetic	JJ
10_1101-2021_01_02_425006	542	70	or	or	CC
10_1101-2021_01_02_425006	542	71	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	542	72	607	607	CD
10_1101-2021_01_02_425006	542	73	region	region	NN
10_1101-2021_01_02_425006	542	74	bias	bias	NN
10_1101-2021_01_02_425006	542	75	rate	rate	NN
10_1101-2021_01_02_425006	542	76	vectors	vector	NNS
10_1101-2021_01_02_425006	542	77	.	.	.
10_1101-2021_01_02_425006	543	1	The	the	DT
10_1101-2021_01_02_425006	543	2	maximal	maximal	JJ
10_1101-2021_01_02_425006	543	3	ATU	ATU	NNP
10_1101-2021_01_02_425006	543	4	cluster	cluster	NN
10_1101-2021_01_02_425006	543	5	data	datum	NNS
10_1101-2021_01_02_425006	543	6	determined	determine	VBN
10_1101-2021_01_02_425006	543	7	by	by	IN
10_1101-2021_01_02_425006	543	8	rSeqTU	rseqtu	CD
10_1101-2021_01_02_425006	543	9	and	and	CC
10_1101-2021_01_02_425006	543	10	the	the	DT
10_1101-2021_01_02_425006	543	11	linear	linear	JJ
10_1101-2021_01_02_425006	543	12	constraints	constraint	NNS
10_1101-2021_01_02_425006	543	13	608	608	CD
10_1101-2021_01_02_425006	543	14	from	from	IN
10_1101-2021_01_02_425006	543	15	preprocessing	preprocesse	VBG
10_1101-2021_01_02_425006	543	16	are	be	VBP
10_1101-2021_01_02_425006	543	17	both	both	DT
10_1101-2021_01_02_425006	543	18	taken	take	VBN
10_1101-2021_01_02_425006	543	19	as	as	IN
10_1101-2021_01_02_425006	543	20	inputs	input	NNS
10_1101-2021_01_02_425006	543	21	of	of	IN
10_1101-2021_01_02_425006	543	22	CQP	CQP	NNP
10_1101-2021_01_02_425006	543	23	.	.	.
10_1101-2021_01_02_425006	544	1	CQP	CQP	NNP
10_1101-2021_01_02_425006	544	2	seeks	seek	VBZ
10_1101-2021_01_02_425006	544	3	the	the	DT
10_1101-2021_01_02_425006	544	4	optimum	optimum	JJ
10_1101-2021_01_02_425006	544	5	expression	expression	NN
10_1101-2021_01_02_425006	544	6	combination	combination	NN
10_1101-2021_01_02_425006	544	7	of	of	IN
10_1101-2021_01_02_425006	544	8	609	609	CD
10_1101-2021_01_02_425006	544	9	all	all	DT
10_1101-2021_01_02_425006	544	10	of	of	IN
10_1101-2021_01_02_425006	544	11	the	the	DT
10_1101-2021_01_02_425006	544	12	to	to	TO
10_1101-2021_01_02_425006	544	13	-	-	HYPH
10_1101-2021_01_02_425006	544	14	be	be	VB
10_1101-2021_01_02_425006	544	15	-	-	HYPH
10_1101-2021_01_02_425006	544	16	identified	identify	VBN
10_1101-2021_01_02_425006	544	17	ATUs	atu	NNS
10_1101-2021_01_02_425006	544	18	to	to	TO
10_1101-2021_01_02_425006	544	19	minimize	minimize	VB
10_1101-2021_01_02_425006	544	20	the	the	DT
10_1101-2021_01_02_425006	544	21	gap	gap	NN
10_1101-2021_01_02_425006	544	22	�	�	NN
10_1101-2021_01_02_425006	544	23	�	�	NNP
10_1101-2021_01_02_425006	544	24	�	�	NNS
10_1101-2021_01_02_425006	544	25	between	between	IN
10_1101-2021_01_02_425006	544	26	the	the	DT
10_1101-2021_01_02_425006	544	27	predicted	predict	VBN
10_1101-2021_01_02_425006	544	28	ATU	ATU	NNP
10_1101-2021_01_02_425006	544	29	expression	expression	NN
10_1101-2021_01_02_425006	544	30	profile	profile	NN
10_1101-2021_01_02_425006	544	31	610	610	CD
10_1101-2021_01_02_425006	544	32	and	and	CC
10_1101-2021_01_02_425006	544	33	the	the	DT
10_1101-2021_01_02_425006	544	34	genetic	genetic	JJ
10_1101-2021_01_02_425006	544	35	and	and	CC
10_1101-2021_01_02_425006	544	36	intergenic	intergenic	JJ
10_1101-2021_01_02_425006	544	37	region	region	NN
10_1101-2021_01_02_425006	544	38	expression	expression	NN
10_1101-2021_01_02_425006	544	39	profile	profile	NN
10_1101-2021_01_02_425006	544	40	.	.	.
10_1101-2021_01_02_425006	545	1	Finally	finally	RB
10_1101-2021_01_02_425006	545	2	,	,	,
10_1101-2021_01_02_425006	545	3	the	the	DT
10_1101-2021_01_02_425006	545	4	output	output	NN
10_1101-2021_01_02_425006	545	5	of	of	IN
10_1101-2021_01_02_425006	545	6	CQP	CQP	NNP
10_1101-2021_01_02_425006	545	7	is	be	VBZ
10_1101-2021_01_02_425006	545	8	the	the	DT
10_1101-2021_01_02_425006	545	9	predicted	predict	VBN
10_1101-2021_01_02_425006	545	10	611	611	CD
10_1101-2021_01_02_425006	545	11	ATUs	atu	NNS
10_1101-2021_01_02_425006	545	12	.	.	.
10_1101-2021_01_02_425006	546	1	612	612	CD
10_1101-2021_01_02_425006	546	2	.CC	.CC	:
10_1101-2021_01_02_425006	546	3	-	-	HYPH
10_1101-2021_01_02_425006	546	4	BY	by	IN
10_1101-2021_01_02_425006	546	5	-	-	HYPH
10_1101-2021_01_02_425006	546	6	NC	NC	NNP
10_1101-2021_01_02_425006	546	7	-	-	HYPH
10_1101-2021_01_02_425006	546	8	ND	ND	NNP
10_1101-2021_01_02_425006	546	9	4.0	4.0	CD
10_1101-2021_01_02_425006	546	10	International	International	NNP
10_1101-2021_01_02_425006	546	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	546	12	under	under	IN
10_1101-2021_01_02_425006	546	13	a	a	DT
10_1101-2021_01_02_425006	546	14	(	(	-LRB-
10_1101-2021_01_02_425006	546	15	which	which	WDT
10_1101-2021_01_02_425006	546	16	was	be	VBD
10_1101-2021_01_02_425006	546	17	not	not	RB
10_1101-2021_01_02_425006	546	18	certified	certify	VBN
10_1101-2021_01_02_425006	546	19	by	by	IN
10_1101-2021_01_02_425006	546	20	peer	peer	NN
10_1101-2021_01_02_425006	546	21	review	review	NN
10_1101-2021_01_02_425006	546	22	)	)	-RRB-
10_1101-2021_01_02_425006	546	23	is	be	VBZ
10_1101-2021_01_02_425006	546	24	the	the	DT
10_1101-2021_01_02_425006	546	25	author	author	NN
10_1101-2021_01_02_425006	546	26	/	/	SYM
10_1101-2021_01_02_425006	546	27	funder	funder	NN
10_1101-2021_01_02_425006	546	28	,	,	,
10_1101-2021_01_02_425006	546	29	who	who	WP
10_1101-2021_01_02_425006	546	30	has	have	VBZ
10_1101-2021_01_02_425006	546	31	granted	grant	VBN
10_1101-2021_01_02_425006	546	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	546	33	a	a	DT
10_1101-2021_01_02_425006	546	34	license	license	NN
10_1101-2021_01_02_425006	546	35	to	to	TO
10_1101-2021_01_02_425006	546	36	display	display	VB
10_1101-2021_01_02_425006	546	37	the	the	DT
10_1101-2021_01_02_425006	546	38	preprint	preprint	NN
10_1101-2021_01_02_425006	546	39	in	in	IN
10_1101-2021_01_02_425006	546	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	546	41	.	.	.
10_1101-2021_01_02_425006	547	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	547	2	is	be	VBZ
10_1101-2021_01_02_425006	547	3	made	make	VBN
10_1101-2021_01_02_425006	547	4	The	the	DT
10_1101-2021_01_02_425006	547	5	copyright	copyright	NN
10_1101-2021_01_02_425006	547	6	holder	holder	NN
10_1101-2021_01_02_425006	547	7	for	for	IN
10_1101-2021_01_02_425006	547	8	this	this	DT
10_1101-2021_01_02_425006	547	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	547	10	version	version	NN
10_1101-2021_01_02_425006	547	11	posted	post	VBD
10_1101-2021_01_02_425006	547	12	January	January	NNP
10_1101-2021_01_02_425006	547	13	6	6	CD
10_1101-2021_01_02_425006	547	14	,	,	,
10_1101-2021_01_02_425006	547	15	2021	2021	CD
10_1101-2021_01_02_425006	547	16	.	.	.
10_1101-2021_01_02_425006	547	17	;	;	:
10_1101-2021_01_02_425006	547	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	547	19	:	:	:
10_1101-2021_01_02_425006	547	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	547	21	preprint	preprint	NN
10_1101-2021_01_02_425006	547	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	547	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	547	24	37	37	CD
10_1101-2021_01_02_425006	547	25	613	613	CD
10_1101-2021_01_02_425006	547	26	Fig	Fig	NNP
10_1101-2021_01_02_425006	547	27	.	.	.
10_1101-2021_01_02_425006	548	1	2	2	LS
10_1101-2021_01_02_425006	548	2	.	.	.
10_1101-2021_01_02_425006	549	1	Results	result	NNS
10_1101-2021_01_02_425006	549	2	of	of	IN
10_1101-2021_01_02_425006	549	3	modelling	model	VBG
10_1101-2021_01_02_425006	549	4	non	non	JJ
10_1101-2021_01_02_425006	549	5	-	-	JJ
10_1101-2021_01_02_425006	549	6	uniform	uniform	JJ
10_1101-2021_01_02_425006	549	7	read	read	VB
10_1101-2021_01_02_425006	549	8	distribution	distribution	NN
10_1101-2021_01_02_425006	549	9	along	along	IN
10_1101-2021_01_02_425006	549	10	mRNA	mRNA	NNP
10_1101-2021_01_02_425006	549	11	transcripts	transcript	NNS
10_1101-2021_01_02_425006	549	12	.	.	.
10_1101-2021_01_02_425006	550	1	The	the	DT
10_1101-2021_01_02_425006	550	2	four	four	CD
10_1101-2021_01_02_425006	550	3	bias	bias	NN
10_1101-2021_01_02_425006	550	4	614	614	CD
10_1101-2021_01_02_425006	550	5	rate	rate	NN
10_1101-2021_01_02_425006	550	6	functions	function	NNS
10_1101-2021_01_02_425006	550	7	(	(	-LRB-
10_1101-2021_01_02_425006	550	8	�	�	NNP
10_1101-2021_01_02_425006	550	9	=	=	SYM
10_1101-2021_01_02_425006	550	10	�	�	NNP
10_1101-2021_01_02_425006	550	11	�	�	VBZ
10_1101-2021_01_02_425006	550	12	�	�	NNS
10_1101-2021_01_02_425006	550	13	�	�	NN
10_1101-2021_01_02_425006	550	14	)	)	-RRB-
10_1101-2021_01_02_425006	550	15	by	by	IN
10_1101-2021_01_02_425006	550	16	nonlinear	nonlinear	JJ
10_1101-2021_01_02_425006	550	17	regression	regression	NN
10_1101-2021_01_02_425006	550	18	had	have	VBD
10_1101-2021_01_02_425006	550	19	similar	similar	JJ
10_1101-2021_01_02_425006	550	20	coefficients	coefficient	NNS
10_1101-2021_01_02_425006	550	21	(	(	-LRB-
10_1101-2021_01_02_425006	550	22	�	�	NNP
10_1101-2021_01_02_425006	550	23	and	and	CC
10_1101-2021_01_02_425006	550	24	�	�	NNP
10_1101-2021_01_02_425006	550	25	)	)	-RRB-
10_1101-2021_01_02_425006	550	26	across	across	IN
10_1101-2021_01_02_425006	550	27	the	the	DT
10_1101-2021_01_02_425006	550	28	four	four	CD
10_1101-2021_01_02_425006	550	29	615	615	CD
10_1101-2021_01_02_425006	550	30	datasets	dataset	NNS
10_1101-2021_01_02_425006	550	31	M9Enrich_1	M9Enrich_1	NNP
10_1101-2021_01_02_425006	550	32	,	,	,
10_1101-2021_01_02_425006	550	33	M9Enrich_2	M9Enrich_2	NNP
10_1101-2021_01_02_425006	550	34	,	,	,
10_1101-2021_01_02_425006	550	35	RiEnrich_1	RiEnrich_1	NNP
10_1101-2021_01_02_425006	550	36	and	and	CC
10_1101-2021_01_02_425006	550	37	RiEnrich_2	RiEnrich_2	NNP
10_1101-2021_01_02_425006	550	38	.	.	.
10_1101-2021_01_02_425006	551	1	616	616	CD
10_1101-2021_01_02_425006	551	2	.CC	.CC	:
10_1101-2021_01_02_425006	551	3	-	-	HYPH
10_1101-2021_01_02_425006	551	4	BY	by	IN
10_1101-2021_01_02_425006	551	5	-	-	HYPH
10_1101-2021_01_02_425006	551	6	NC	NC	NNP
10_1101-2021_01_02_425006	551	7	-	-	HYPH
10_1101-2021_01_02_425006	551	8	ND	ND	NNP
10_1101-2021_01_02_425006	551	9	4.0	4.0	CD
10_1101-2021_01_02_425006	551	10	International	International	NNP
10_1101-2021_01_02_425006	551	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	551	12	under	under	IN
10_1101-2021_01_02_425006	551	13	a	a	DT
10_1101-2021_01_02_425006	551	14	(	(	-LRB-
10_1101-2021_01_02_425006	551	15	which	which	WDT
10_1101-2021_01_02_425006	551	16	was	be	VBD
10_1101-2021_01_02_425006	551	17	not	not	RB
10_1101-2021_01_02_425006	551	18	certified	certify	VBN
10_1101-2021_01_02_425006	551	19	by	by	IN
10_1101-2021_01_02_425006	551	20	peer	peer	NN
10_1101-2021_01_02_425006	551	21	review	review	NN
10_1101-2021_01_02_425006	551	22	)	)	-RRB-
10_1101-2021_01_02_425006	551	23	is	be	VBZ
10_1101-2021_01_02_425006	551	24	the	the	DT
10_1101-2021_01_02_425006	551	25	author	author	NN
10_1101-2021_01_02_425006	551	26	/	/	SYM
10_1101-2021_01_02_425006	551	27	funder	funder	NN
10_1101-2021_01_02_425006	551	28	,	,	,
10_1101-2021_01_02_425006	551	29	who	who	WP
10_1101-2021_01_02_425006	551	30	has	have	VBZ
10_1101-2021_01_02_425006	551	31	granted	grant	VBN
10_1101-2021_01_02_425006	551	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	551	33	a	a	DT
10_1101-2021_01_02_425006	551	34	license	license	NN
10_1101-2021_01_02_425006	551	35	to	to	TO
10_1101-2021_01_02_425006	551	36	display	display	VB
10_1101-2021_01_02_425006	551	37	the	the	DT
10_1101-2021_01_02_425006	551	38	preprint	preprint	NN
10_1101-2021_01_02_425006	551	39	in	in	IN
10_1101-2021_01_02_425006	551	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	551	41	.	.	.
10_1101-2021_01_02_425006	552	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	552	2	is	be	VBZ
10_1101-2021_01_02_425006	552	3	made	make	VBN
10_1101-2021_01_02_425006	552	4	The	the	DT
10_1101-2021_01_02_425006	552	5	copyright	copyright	NN
10_1101-2021_01_02_425006	552	6	holder	holder	NN
10_1101-2021_01_02_425006	552	7	for	for	IN
10_1101-2021_01_02_425006	552	8	this	this	DT
10_1101-2021_01_02_425006	552	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	552	10	version	version	NN
10_1101-2021_01_02_425006	552	11	posted	post	VBD
10_1101-2021_01_02_425006	552	12	January	January	NNP
10_1101-2021_01_02_425006	552	13	6	6	CD
10_1101-2021_01_02_425006	552	14	,	,	,
10_1101-2021_01_02_425006	552	15	2021	2021	CD
10_1101-2021_01_02_425006	552	16	.	.	.
10_1101-2021_01_02_425006	552	17	;	;	:
10_1101-2021_01_02_425006	552	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	552	19	:	:	:
10_1101-2021_01_02_425006	552	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	552	21	preprint	preprint	NN
10_1101-2021_01_02_425006	552	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	552	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	552	24	38	38	CD
10_1101-2021_01_02_425006	552	25	617	617	CD
10_1101-2021_01_02_425006	552	26	Fig	fig	NN
10_1101-2021_01_02_425006	552	27	.	.	.
10_1101-2021_01_02_425006	553	1	3	3	LS
10_1101-2021_01_02_425006	553	2	.	.	.
10_1101-2021_01_02_425006	554	1	Overall	overall	JJ
10_1101-2021_01_02_425006	554	2	evaluation	evaluation	NN
10_1101-2021_01_02_425006	554	3	results	result	NNS
10_1101-2021_01_02_425006	554	4	of	of	IN
10_1101-2021_01_02_425006	554	5	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	554	6	.	.	.
10_1101-2021_01_02_425006	555	1	(	(	-LRB-
10_1101-2021_01_02_425006	555	2	A	a	DT
10_1101-2021_01_02_425006	555	3	)	)	-RRB-
10_1101-2021_01_02_425006	555	4	Precision	precision	NN
10_1101-2021_01_02_425006	555	5	and	and	CC
10_1101-2021_01_02_425006	555	6	recall	recall	NN
10_1101-2021_01_02_425006	555	7	based	base	VBN
10_1101-2021_01_02_425006	555	8	on	on	IN
10_1101-2021_01_02_425006	555	9	perfect	perfect	JJ
10_1101-2021_01_02_425006	555	10	matching	matching	NN
10_1101-2021_01_02_425006	555	11	and	and	CC
10_1101-2021_01_02_425006	555	12	618	618	CD
10_1101-2021_01_02_425006	555	13	relaxed	relaxed	JJ
10_1101-2021_01_02_425006	555	14	matching	matching	NN
10_1101-2021_01_02_425006	555	15	for	for	IN
10_1101-2021_01_02_425006	555	16	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	555	17	(	(	-LRB-
10_1101-2021_01_02_425006	555	18	left	left	RB
10_1101-2021_01_02_425006	555	19	)	)	-RRB-
10_1101-2021_01_02_425006	555	20	and	and	CC
10_1101-2021_01_02_425006	555	21	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	555	22	(	(	-LRB-
10_1101-2021_01_02_425006	555	23	right	right	UH
10_1101-2021_01_02_425006	555	24	)	)	-RRB-
10_1101-2021_01_02_425006	555	25	using	use	VBG
10_1101-2021_01_02_425006	555	26	evaluated	evaluate	VBN
10_1101-2021_01_02_425006	555	27	ATUs	atu	NNS
10_1101-2021_01_02_425006	555	28	from	from	IN
10_1101-2021_01_02_425006	555	29	SMRT-619	smrt-619	JJ
10_1101-2021_01_02_425006	555	30	.CC	.CC	NFP
10_1101-2021_01_02_425006	555	31	-	-	HYPH
10_1101-2021_01_02_425006	555	32	BY	by	IN
10_1101-2021_01_02_425006	555	33	-	-	HYPH
10_1101-2021_01_02_425006	555	34	NC	NC	NNP
10_1101-2021_01_02_425006	555	35	-	-	HYPH
10_1101-2021_01_02_425006	555	36	ND	ND	NNP
10_1101-2021_01_02_425006	555	37	4.0	4.0	CD
10_1101-2021_01_02_425006	555	38	International	International	NNP
10_1101-2021_01_02_425006	555	39	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	555	40	under	under	IN
10_1101-2021_01_02_425006	555	41	a	a	DT
10_1101-2021_01_02_425006	555	42	(	(	-LRB-
10_1101-2021_01_02_425006	555	43	which	which	WDT
10_1101-2021_01_02_425006	555	44	was	be	VBD
10_1101-2021_01_02_425006	555	45	not	not	RB
10_1101-2021_01_02_425006	555	46	certified	certify	VBN
10_1101-2021_01_02_425006	555	47	by	by	IN
10_1101-2021_01_02_425006	555	48	peer	peer	NN
10_1101-2021_01_02_425006	555	49	review	review	NN
10_1101-2021_01_02_425006	555	50	)	)	-RRB-
10_1101-2021_01_02_425006	555	51	is	be	VBZ
10_1101-2021_01_02_425006	555	52	the	the	DT
10_1101-2021_01_02_425006	555	53	author	author	NN
10_1101-2021_01_02_425006	555	54	/	/	SYM
10_1101-2021_01_02_425006	555	55	funder	funder	NN
10_1101-2021_01_02_425006	555	56	,	,	,
10_1101-2021_01_02_425006	555	57	who	who	WP
10_1101-2021_01_02_425006	555	58	has	have	VBZ
10_1101-2021_01_02_425006	555	59	granted	grant	VBN
10_1101-2021_01_02_425006	555	60	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	555	61	a	a	DT
10_1101-2021_01_02_425006	555	62	license	license	NN
10_1101-2021_01_02_425006	555	63	to	to	TO
10_1101-2021_01_02_425006	555	64	display	display	VB
10_1101-2021_01_02_425006	555	65	the	the	DT
10_1101-2021_01_02_425006	555	66	preprint	preprint	NN
10_1101-2021_01_02_425006	555	67	in	in	IN
10_1101-2021_01_02_425006	555	68	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	555	69	.	.	.
10_1101-2021_01_02_425006	556	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	556	2	is	be	VBZ
10_1101-2021_01_02_425006	556	3	made	make	VBN
10_1101-2021_01_02_425006	556	4	The	the	DT
10_1101-2021_01_02_425006	556	5	copyright	copyright	NN
10_1101-2021_01_02_425006	556	6	holder	holder	NN
10_1101-2021_01_02_425006	556	7	for	for	IN
10_1101-2021_01_02_425006	556	8	this	this	DT
10_1101-2021_01_02_425006	556	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	556	10	version	version	NN
10_1101-2021_01_02_425006	556	11	posted	post	VBD
10_1101-2021_01_02_425006	556	12	January	January	NNP
10_1101-2021_01_02_425006	556	13	6	6	CD
10_1101-2021_01_02_425006	556	14	,	,	,
10_1101-2021_01_02_425006	556	15	2021	2021	CD
10_1101-2021_01_02_425006	556	16	.	.	.
10_1101-2021_01_02_425006	556	17	;	;	:
10_1101-2021_01_02_425006	556	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	556	19	:	:	:
10_1101-2021_01_02_425006	556	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	556	21	preprint	preprint	NN
10_1101-2021_01_02_425006	556	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	556	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	556	24	39	39	CD
10_1101-2021_01_02_425006	556	25	Cappable	cappable	JJ
10_1101-2021_01_02_425006	556	26	-	-	HYPH
10_1101-2021_01_02_425006	556	27	seq	seq	NN
10_1101-2021_01_02_425006	556	28	.	.	.
10_1101-2021_01_02_425006	557	1	(	(	-LRB-
10_1101-2021_01_02_425006	557	2	B	b	NN
10_1101-2021_01_02_425006	557	3	)	)	-RRB-
10_1101-2021_01_02_425006	557	4	Average	average	JJ
10_1101-2021_01_02_425006	557	5	precision	precision	NN
10_1101-2021_01_02_425006	557	6	based	base	VBN
10_1101-2021_01_02_425006	557	7	on	on	IN
10_1101-2021_01_02_425006	557	8	perfect	perfect	JJ
10_1101-2021_01_02_425006	557	9	matching	matching	NN
10_1101-2021_01_02_425006	557	10	for	for	IN
10_1101-2021_01_02_425006	557	11	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	557	12	(	(	-LRB-
10_1101-2021_01_02_425006	557	13	left	left	RB
10_1101-2021_01_02_425006	557	14	)	)	-RRB-
10_1101-2021_01_02_425006	557	15	and	and	CC
10_1101-2021_01_02_425006	557	16	620	620	CD
10_1101-2021_01_02_425006	557	17	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	557	18	(	(	-LRB-
10_1101-2021_01_02_425006	557	19	right	right	UH
10_1101-2021_01_02_425006	557	20	)	)	-RRB-
10_1101-2021_01_02_425006	557	21	using	use	VBG
10_1101-2021_01_02_425006	557	22	evaluated	evaluate	VBN
10_1101-2021_01_02_425006	557	23	ATUs	atu	NNS
10_1101-2021_01_02_425006	557	24	from	from	IN
10_1101-2021_01_02_425006	557	25	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	557	26	-	-	HYPH
10_1101-2021_01_02_425006	557	27	Cappable	cappable	JJ
10_1101-2021_01_02_425006	557	28	-	-	HYPH
10_1101-2021_01_02_425006	557	29	seq	seq	NN
10_1101-2021_01_02_425006	557	30	(	(	-LRB-
10_1101-2021_01_02_425006	557	31	black	black	JJ
10_1101-2021_01_02_425006	557	32	)	)	-RRB-
10_1101-2021_01_02_425006	557	33	and	and	CC
10_1101-2021_01_02_425006	557	34	evaluated	evaluate	VBN
10_1101-2021_01_02_425006	557	35	ATUs	atu	NNS
10_1101-2021_01_02_425006	557	36	from	from	IN
10_1101-2021_01_02_425006	557	37	621	621	CD
10_1101-2021_01_02_425006	557	38	SMRT	smrt	JJ
10_1101-2021_01_02_425006	557	39	-	-	HYPH
10_1101-2021_01_02_425006	557	40	Cappable	cappable	JJ
10_1101-2021_01_02_425006	557	41	-	-	HYPH
10_1101-2021_01_02_425006	557	42	seq	seq	NN
10_1101-2021_01_02_425006	557	43	and	and	CC
10_1101-2021_01_02_425006	557	44	SEnd	SEnd	NNP
10_1101-2021_01_02_425006	557	45	-	-	HYPH
10_1101-2021_01_02_425006	557	46	seq	seq	NNP
10_1101-2021_01_02_425006	557	47	(	(	-LRB-
10_1101-2021_01_02_425006	557	48	red	red	NNP
10_1101-2021_01_02_425006	557	49	)	)	-RRB-
10_1101-2021_01_02_425006	557	50	.	.	.
10_1101-2021_01_02_425006	558	1	The	the	DT
10_1101-2021_01_02_425006	558	2	magnitude	magnitude	NN
10_1101-2021_01_02_425006	558	3	of	of	IN
10_1101-2021_01_02_425006	558	4	the	the	DT
10_1101-2021_01_02_425006	558	5	point	point	NN
10_1101-2021_01_02_425006	558	6	denotes	denote	VBZ
10_1101-2021_01_02_425006	558	7	the	the	DT
10_1101-2021_01_02_425006	558	8	number	number	NN
10_1101-2021_01_02_425006	558	9	of	of	IN
10_1101-2021_01_02_425006	558	10	maximal	maximal	JJ
10_1101-2021_01_02_425006	558	11	622	622	CD
10_1101-2021_01_02_425006	558	12	ATU	ATU	NNP
10_1101-2021_01_02_425006	558	13	clusters	cluster	NNS
10_1101-2021_01_02_425006	558	14	with	with	IN
10_1101-2021_01_02_425006	558	15	same	same	JJ
10_1101-2021_01_02_425006	558	16	size	size	NN
10_1101-2021_01_02_425006	558	17	.	.	.
10_1101-2021_01_02_425006	559	1	(	(	-LRB-
10_1101-2021_01_02_425006	559	2	C	c	NN
10_1101-2021_01_02_425006	559	3	)	)	-RRB-
10_1101-2021_01_02_425006	559	4	Average	average	JJ
10_1101-2021_01_02_425006	559	5	number	number	NN
10_1101-2021_01_02_425006	559	6	of	of	IN
10_1101-2021_01_02_425006	559	7	ATUs	atu	NNS
10_1101-2021_01_02_425006	559	8	across	across	IN
10_1101-2021_01_02_425006	559	9	different	different	JJ
10_1101-2021_01_02_425006	559	10	sizes	size	NNS
10_1101-2021_01_02_425006	559	11	of	of	IN
10_1101-2021_01_02_425006	559	12	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	559	13	maximal	maximal	JJ
10_1101-2021_01_02_425006	559	14	623	623	CD
10_1101-2021_01_02_425006	559	15	ATU	ATU	NNP
10_1101-2021_01_02_425006	559	16	clusters	cluster	NNS
10_1101-2021_01_02_425006	559	17	for	for	IN
10_1101-2021_01_02_425006	559	18	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	559	19	(	(	-LRB-
10_1101-2021_01_02_425006	559	20	left	left	RB
10_1101-2021_01_02_425006	559	21	)	)	-RRB-
10_1101-2021_01_02_425006	559	22	and	and	CC
10_1101-2021_01_02_425006	559	23	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	559	24	(	(	-LRB-
10_1101-2021_01_02_425006	559	25	right	right	RB
10_1101-2021_01_02_425006	559	26	)	)	-RRB-
10_1101-2021_01_02_425006	559	27	.	.	.
10_1101-2021_01_02_425006	560	1	624	624	CD
10_1101-2021_01_02_425006	560	2	.CC	.CC	:
10_1101-2021_01_02_425006	560	3	-	-	HYPH
10_1101-2021_01_02_425006	560	4	BY	by	IN
10_1101-2021_01_02_425006	560	5	-	-	HYPH
10_1101-2021_01_02_425006	560	6	NC	NC	NNP
10_1101-2021_01_02_425006	560	7	-	-	HYPH
10_1101-2021_01_02_425006	560	8	ND	ND	NNP
10_1101-2021_01_02_425006	560	9	4.0	4.0	CD
10_1101-2021_01_02_425006	560	10	International	International	NNP
10_1101-2021_01_02_425006	560	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	560	12	under	under	IN
10_1101-2021_01_02_425006	560	13	a	a	DT
10_1101-2021_01_02_425006	560	14	(	(	-LRB-
10_1101-2021_01_02_425006	560	15	which	which	WDT
10_1101-2021_01_02_425006	560	16	was	be	VBD
10_1101-2021_01_02_425006	560	17	not	not	RB
10_1101-2021_01_02_425006	560	18	certified	certify	VBN
10_1101-2021_01_02_425006	560	19	by	by	IN
10_1101-2021_01_02_425006	560	20	peer	peer	NN
10_1101-2021_01_02_425006	560	21	review	review	NN
10_1101-2021_01_02_425006	560	22	)	)	-RRB-
10_1101-2021_01_02_425006	560	23	is	be	VBZ
10_1101-2021_01_02_425006	560	24	the	the	DT
10_1101-2021_01_02_425006	560	25	author	author	NN
10_1101-2021_01_02_425006	560	26	/	/	SYM
10_1101-2021_01_02_425006	560	27	funder	funder	NN
10_1101-2021_01_02_425006	560	28	,	,	,
10_1101-2021_01_02_425006	560	29	who	who	WP
10_1101-2021_01_02_425006	560	30	has	have	VBZ
10_1101-2021_01_02_425006	560	31	granted	grant	VBN
10_1101-2021_01_02_425006	560	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	560	33	a	a	DT
10_1101-2021_01_02_425006	560	34	license	license	NN
10_1101-2021_01_02_425006	560	35	to	to	TO
10_1101-2021_01_02_425006	560	36	display	display	VB
10_1101-2021_01_02_425006	560	37	the	the	DT
10_1101-2021_01_02_425006	560	38	preprint	preprint	NN
10_1101-2021_01_02_425006	560	39	in	in	IN
10_1101-2021_01_02_425006	560	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	560	41	.	.	.
10_1101-2021_01_02_425006	561	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	561	2	is	be	VBZ
10_1101-2021_01_02_425006	561	3	made	make	VBN
10_1101-2021_01_02_425006	561	4	The	the	DT
10_1101-2021_01_02_425006	561	5	copyright	copyright	NN
10_1101-2021_01_02_425006	561	6	holder	holder	NN
10_1101-2021_01_02_425006	561	7	for	for	IN
10_1101-2021_01_02_425006	561	8	this	this	DT
10_1101-2021_01_02_425006	561	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	561	10	version	version	NN
10_1101-2021_01_02_425006	561	11	posted	post	VBD
10_1101-2021_01_02_425006	561	12	January	January	NNP
10_1101-2021_01_02_425006	561	13	6	6	CD
10_1101-2021_01_02_425006	561	14	,	,	,
10_1101-2021_01_02_425006	561	15	2021	2021	CD
10_1101-2021_01_02_425006	561	16	.	.	.
10_1101-2021_01_02_425006	561	17	;	;	:
10_1101-2021_01_02_425006	561	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	561	19	:	:	:
10_1101-2021_01_02_425006	561	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	561	21	preprint	preprint	NN
10_1101-2021_01_02_425006	561	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	561	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	561	24	40	40	CD
10_1101-2021_01_02_425006	561	25	625	625	CD
10_1101-2021_01_02_425006	561	26	Fig	fig	NN
10_1101-2021_01_02_425006	561	27	.	.	.
10_1101-2021_01_02_425006	562	1	4	4	LS
10_1101-2021_01_02_425006	562	2	.	.	.
10_1101-2021_01_02_425006	563	1	Comparative	comparative	JJ
10_1101-2021_01_02_425006	563	2	analysis	analysis	NN
10_1101-2021_01_02_425006	563	3	of	of	IN
10_1101-2021_01_02_425006	563	4	the	the	DT
10_1101-2021_01_02_425006	563	5	performance	performance	NN
10_1101-2021_01_02_425006	563	6	between	between	IN
10_1101-2021_01_02_425006	563	7	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	563	8	and	and	CC
10_1101-2021_01_02_425006	563	9	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	563	10	without	without	IN
10_1101-2021_01_02_425006	563	11	the	the	DT
10_1101-2021_01_02_425006	563	12	bias	bias	NN
10_1101-2021_01_02_425006	563	13	626	626	CD
10_1101-2021_01_02_425006	563	14	rate	rate	NN
10_1101-2021_01_02_425006	563	15	constrains	constrain	NNS
10_1101-2021_01_02_425006	563	16	for	for	IN
10_1101-2021_01_02_425006	563	17	SMRT	SMRT	NNP
10_1101-2021_01_02_425006	563	18	maximal	maximal	JJ
10_1101-2021_01_02_425006	563	19	ATU	ATU	NNP
10_1101-2021_01_02_425006	563	20	clusters	cluster	NNS
10_1101-2021_01_02_425006	563	21	.	.	.
10_1101-2021_01_02_425006	564	1	(	(	-LRB-
10_1101-2021_01_02_425006	564	2	A	a	DT
10_1101-2021_01_02_425006	564	3	)	)	-RRB-
10_1101-2021_01_02_425006	564	4	Precision	precision	NN
10_1101-2021_01_02_425006	564	5	,	,	,
10_1101-2021_01_02_425006	564	6	recall	recall	NN
10_1101-2021_01_02_425006	564	7	and	and	CC
10_1101-2021_01_02_425006	564	8	F	f	NN
10_1101-2021_01_02_425006	564	9	-	-	HYPH
10_1101-2021_01_02_425006	564	10	score	score	NN
10_1101-2021_01_02_425006	564	11	based	base	VBN
10_1101-2021_01_02_425006	564	12	on	on	IN
10_1101-2021_01_02_425006	564	13	perfect	perfect	JJ
10_1101-2021_01_02_425006	564	14	627	627	CD
10_1101-2021_01_02_425006	564	15	matching	matching	NN
10_1101-2021_01_02_425006	564	16	for	for	IN
10_1101-2021_01_02_425006	564	17	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	564	18	and	and	CC
10_1101-2021_01_02_425006	564	19	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	564	20	.	.	.
10_1101-2021_01_02_425006	565	1	(	(	-LRB-
10_1101-2021_01_02_425006	565	2	B	B	NNP
10_1101-2021_01_02_425006	565	3	)	)	-RRB-
10_1101-2021_01_02_425006	565	4	Precision	Precision	NNP
10_1101-2021_01_02_425006	565	5	,	,	,
10_1101-2021_01_02_425006	565	6	recall	recall	NN
10_1101-2021_01_02_425006	565	7	and	and	CC
10_1101-2021_01_02_425006	565	8	F	f	NN
10_1101-2021_01_02_425006	565	9	-	-	HYPH
10_1101-2021_01_02_425006	565	10	score	score	NN
10_1101-2021_01_02_425006	565	11	based	base	VBN
10_1101-2021_01_02_425006	565	12	on	on	IN
10_1101-2021_01_02_425006	565	13	relaxed	relaxed	JJ
10_1101-2021_01_02_425006	565	14	628	628	CD
10_1101-2021_01_02_425006	565	15	matching	match	VBG
10_1101-2021_01_02_425006	565	16	for	for	IN
10_1101-2021_01_02_425006	565	17	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	565	18	and	and	CC
10_1101-2021_01_02_425006	565	19	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	565	20	.	.	.
10_1101-2021_01_02_425006	566	1	629	629	CD
10_1101-2021_01_02_425006	566	2	.CC	.CC	:
10_1101-2021_01_02_425006	566	3	-	-	HYPH
10_1101-2021_01_02_425006	566	4	BY	by	IN
10_1101-2021_01_02_425006	566	5	-	-	HYPH
10_1101-2021_01_02_425006	566	6	NC	NC	NNP
10_1101-2021_01_02_425006	566	7	-	-	HYPH
10_1101-2021_01_02_425006	566	8	ND	ND	NNP
10_1101-2021_01_02_425006	566	9	4.0	4.0	CD
10_1101-2021_01_02_425006	566	10	International	International	NNP
10_1101-2021_01_02_425006	566	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	566	12	under	under	IN
10_1101-2021_01_02_425006	566	13	a	a	DT
10_1101-2021_01_02_425006	566	14	(	(	-LRB-
10_1101-2021_01_02_425006	566	15	which	which	WDT
10_1101-2021_01_02_425006	566	16	was	be	VBD
10_1101-2021_01_02_425006	566	17	not	not	RB
10_1101-2021_01_02_425006	566	18	certified	certify	VBN
10_1101-2021_01_02_425006	566	19	by	by	IN
10_1101-2021_01_02_425006	566	20	peer	peer	NN
10_1101-2021_01_02_425006	566	21	review	review	NN
10_1101-2021_01_02_425006	566	22	)	)	-RRB-
10_1101-2021_01_02_425006	566	23	is	be	VBZ
10_1101-2021_01_02_425006	566	24	the	the	DT
10_1101-2021_01_02_425006	566	25	author	author	NN
10_1101-2021_01_02_425006	566	26	/	/	SYM
10_1101-2021_01_02_425006	566	27	funder	funder	NN
10_1101-2021_01_02_425006	566	28	,	,	,
10_1101-2021_01_02_425006	566	29	who	who	WP
10_1101-2021_01_02_425006	566	30	has	have	VBZ
10_1101-2021_01_02_425006	566	31	granted	grant	VBN
10_1101-2021_01_02_425006	566	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	566	33	a	a	DT
10_1101-2021_01_02_425006	566	34	license	license	NN
10_1101-2021_01_02_425006	566	35	to	to	TO
10_1101-2021_01_02_425006	566	36	display	display	VB
10_1101-2021_01_02_425006	566	37	the	the	DT
10_1101-2021_01_02_425006	566	38	preprint	preprint	NN
10_1101-2021_01_02_425006	566	39	in	in	IN
10_1101-2021_01_02_425006	566	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	566	41	.	.	.
10_1101-2021_01_02_425006	567	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	567	2	is	be	VBZ
10_1101-2021_01_02_425006	567	3	made	make	VBN
10_1101-2021_01_02_425006	567	4	The	the	DT
10_1101-2021_01_02_425006	567	5	copyright	copyright	NN
10_1101-2021_01_02_425006	567	6	holder	holder	NN
10_1101-2021_01_02_425006	567	7	for	for	IN
10_1101-2021_01_02_425006	567	8	this	this	DT
10_1101-2021_01_02_425006	567	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	567	10	version	version	NN
10_1101-2021_01_02_425006	567	11	posted	post	VBD
10_1101-2021_01_02_425006	567	12	January	January	NNP
10_1101-2021_01_02_425006	567	13	6	6	CD
10_1101-2021_01_02_425006	567	14	,	,	,
10_1101-2021_01_02_425006	567	15	2021	2021	CD
10_1101-2021_01_02_425006	567	16	.	.	.
10_1101-2021_01_02_425006	567	17	;	;	:
10_1101-2021_01_02_425006	567	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	567	19	:	:	:
10_1101-2021_01_02_425006	567	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	567	21	preprint	preprint	NN
10_1101-2021_01_02_425006	567	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	567	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	567	24	41	41	CD
10_1101-2021_01_02_425006	567	25	630	630	CD
10_1101-2021_01_02_425006	567	26	Fig	Fig	NNP
10_1101-2021_01_02_425006	567	27	.	.	.
10_1101-2021_01_02_425006	568	1	5	5	CD
10_1101-2021_01_02_425006	568	2	.	.	.
10_1101-2021_01_02_425006	569	1	Comprehensive	comprehensive	JJ
10_1101-2021_01_02_425006	569	2	analysis	analysis	NN
10_1101-2021_01_02_425006	569	3	of	of	IN
10_1101-2021_01_02_425006	569	4	the	the	DT
10_1101-2021_01_02_425006	569	5	predicted	predict	VBN
10_1101-2021_01_02_425006	569	6	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	569	7	by	by	IN
10_1101-2021_01_02_425006	569	8	SeqATU	SeqATU	NNP
10_1101-2021_01_02_425006	569	9	.	.	.
10_1101-2021_01_02_425006	570	1	(	(	-LRB-
10_1101-2021_01_02_425006	570	2	A	a	DT
10_1101-2021_01_02_425006	570	3	)	)	-RRB-
10_1101-2021_01_02_425006	570	4	Number	number	NN
10_1101-2021_01_02_425006	570	5	of	of	IN
10_1101-2021_01_02_425006	570	6	ATUs	ATUs	NNPS
10_1101-2021_01_02_425006	570	7	across	across	IN
10_1101-2021_01_02_425006	570	8	631	631	CD
10_1101-2021_01_02_425006	570	9	different	different	JJ
10_1101-2021_01_02_425006	570	10	sizes	size	NNS
10_1101-2021_01_02_425006	570	11	.	.	.
10_1101-2021_01_02_425006	571	1	The	the	DT
10_1101-2021_01_02_425006	571	2	size	size	NN
10_1101-2021_01_02_425006	571	3	of	of	IN
10_1101-2021_01_02_425006	571	4	an	an	DT
10_1101-2021_01_02_425006	571	5	ATU	ATU	NNP
10_1101-2021_01_02_425006	571	6	is	be	VBZ
10_1101-2021_01_02_425006	571	7	the	the	DT
10_1101-2021_01_02_425006	571	8	number	number	NN
10_1101-2021_01_02_425006	571	9	of	of	IN
10_1101-2021_01_02_425006	571	10	its	-PRON-	PRP$
10_1101-2021_01_02_425006	571	11	component	component	NN
10_1101-2021_01_02_425006	571	12	genes	gene	NNS
10_1101-2021_01_02_425006	571	13	.	.	.
10_1101-2021_01_02_425006	572	1	(	(	-LRB-
10_1101-2021_01_02_425006	572	2	B	b	NN
10_1101-2021_01_02_425006	572	3	)	)	-RRB-
10_1101-2021_01_02_425006	572	4	Distribution	distribution	NN
10_1101-2021_01_02_425006	572	5	of	of	IN
10_1101-2021_01_02_425006	572	6	the	the	DT
10_1101-2021_01_02_425006	572	7	number	number	NN
10_1101-2021_01_02_425006	572	8	632	632	CD
10_1101-2021_01_02_425006	572	9	of	of	IN
10_1101-2021_01_02_425006	572	10	ATUs	atu	NNS
10_1101-2021_01_02_425006	572	11	per	per	IN
10_1101-2021_01_02_425006	572	12	gene	gene	NN
10_1101-2021_01_02_425006	572	13	.	.	.
10_1101-2021_01_02_425006	573	1	633	633	CD
10_1101-2021_01_02_425006	573	2	.CC	.CC	:
10_1101-2021_01_02_425006	573	3	-	-	HYPH
10_1101-2021_01_02_425006	573	4	BY	by	IN
10_1101-2021_01_02_425006	573	5	-	-	HYPH
10_1101-2021_01_02_425006	573	6	NC	NC	NNP
10_1101-2021_01_02_425006	573	7	-	-	HYPH
10_1101-2021_01_02_425006	573	8	ND	ND	NNP
10_1101-2021_01_02_425006	573	9	4.0	4.0	CD
10_1101-2021_01_02_425006	573	10	International	International	NNP
10_1101-2021_01_02_425006	573	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	573	12	under	under	IN
10_1101-2021_01_02_425006	573	13	a	a	DT
10_1101-2021_01_02_425006	573	14	(	(	-LRB-
10_1101-2021_01_02_425006	573	15	which	which	WDT
10_1101-2021_01_02_425006	573	16	was	be	VBD
10_1101-2021_01_02_425006	573	17	not	not	RB
10_1101-2021_01_02_425006	573	18	certified	certify	VBN
10_1101-2021_01_02_425006	573	19	by	by	IN
10_1101-2021_01_02_425006	573	20	peer	peer	NN
10_1101-2021_01_02_425006	573	21	review	review	NN
10_1101-2021_01_02_425006	573	22	)	)	-RRB-
10_1101-2021_01_02_425006	573	23	is	be	VBZ
10_1101-2021_01_02_425006	573	24	the	the	DT
10_1101-2021_01_02_425006	573	25	author	author	NN
10_1101-2021_01_02_425006	573	26	/	/	SYM
10_1101-2021_01_02_425006	573	27	funder	funder	NN
10_1101-2021_01_02_425006	573	28	,	,	,
10_1101-2021_01_02_425006	573	29	who	who	WP
10_1101-2021_01_02_425006	573	30	has	have	VBZ
10_1101-2021_01_02_425006	573	31	granted	grant	VBN
10_1101-2021_01_02_425006	573	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	573	33	a	a	DT
10_1101-2021_01_02_425006	573	34	license	license	NN
10_1101-2021_01_02_425006	573	35	to	to	TO
10_1101-2021_01_02_425006	573	36	display	display	VB
10_1101-2021_01_02_425006	573	37	the	the	DT
10_1101-2021_01_02_425006	573	38	preprint	preprint	NN
10_1101-2021_01_02_425006	573	39	in	in	IN
10_1101-2021_01_02_425006	573	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	573	41	.	.	.
10_1101-2021_01_02_425006	574	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	574	2	is	be	VBZ
10_1101-2021_01_02_425006	574	3	made	make	VBN
10_1101-2021_01_02_425006	574	4	The	the	DT
10_1101-2021_01_02_425006	574	5	copyright	copyright	NN
10_1101-2021_01_02_425006	574	6	holder	holder	NN
10_1101-2021_01_02_425006	574	7	for	for	IN
10_1101-2021_01_02_425006	574	8	this	this	DT
10_1101-2021_01_02_425006	574	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	574	10	version	version	NN
10_1101-2021_01_02_425006	574	11	posted	post	VBD
10_1101-2021_01_02_425006	574	12	January	January	NNP
10_1101-2021_01_02_425006	574	13	6	6	CD
10_1101-2021_01_02_425006	574	14	,	,	,
10_1101-2021_01_02_425006	574	15	2021	2021	CD
10_1101-2021_01_02_425006	574	16	.	.	.
10_1101-2021_01_02_425006	574	17	;	;	:
10_1101-2021_01_02_425006	574	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	574	19	:	:	:
10_1101-2021_01_02_425006	574	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	574	21	preprint	preprint	NN
10_1101-2021_01_02_425006	574	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	574	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	574	24	42	42	CD
10_1101-2021_01_02_425006	574	25	634	634	CD
10_1101-2021_01_02_425006	574	26	Fig	fig	NN
10_1101-2021_01_02_425006	574	27	.	.	.
10_1101-2021_01_02_425006	575	1	6	6	CD
10_1101-2021_01_02_425006	575	2	.	.	.
10_1101-2021_01_02_425006	576	1	Integrative	Integrative	NNP
10_1101-2021_01_02_425006	576	2	Genomics	Genomics	NNP
10_1101-2021_01_02_425006	576	3	Viewer	Viewer	NNP
10_1101-2021_01_02_425006	576	4	(	(	-LRB-
10_1101-2021_01_02_425006	576	5	IGV	IGV	NNP
10_1101-2021_01_02_425006	576	6	)	)	-RRB-
10_1101-2021_01_02_425006	576	7	representation	representation	NN
10_1101-2021_01_02_425006	576	8	of	of	IN
10_1101-2021_01_02_425006	576	9	the	the	DT
10_1101-2021_01_02_425006	576	10	mapping	mapping	NN
10_1101-2021_01_02_425006	576	11	and	and	CC
10_1101-2021_01_02_425006	576	12	ATUs	atu	NNS
10_1101-2021_01_02_425006	576	13	.	.	.
10_1101-2021_01_02_425006	577	1	Mapping	mapping	NN
10_1101-2021_01_02_425006	577	2	and	and	CC
10_1101-2021_01_02_425006	577	3	635	635	CD
10_1101-2021_01_02_425006	577	4	ATUs	atu	NNS
10_1101-2021_01_02_425006	577	5	of	of	IN
10_1101-2021_01_02_425006	577	6	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	577	7	(	(	-LRB-
10_1101-2021_01_02_425006	577	8	orange	orange	NNP
10_1101-2021_01_02_425006	577	9	)	)	-RRB-
10_1101-2021_01_02_425006	577	10	and	and	CC
10_1101-2021_01_02_425006	577	11	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	577	12	(	(	-LRB-
10_1101-2021_01_02_425006	577	13	blue	blue	NNP
10_1101-2021_01_02_425006	577	14	)	)	-RRB-
10_1101-2021_01_02_425006	577	15	were	be	VBD
10_1101-2021_01_02_425006	577	16	shown	show	VBN
10_1101-2021_01_02_425006	577	17	for	for	IN
10_1101-2021_01_02_425006	577	18	the	the	DT
10_1101-2021_01_02_425006	577	19	maximal	maximal	JJ
10_1101-2021_01_02_425006	577	20	ATU	ATU	NNP
10_1101-2021_01_02_425006	577	21	cluster	cluster	NN
10_1101-2021_01_02_425006	577	22	636	636	CD
10_1101-2021_01_02_425006	577	23	containing	contain	VBG
10_1101-2021_01_02_425006	577	24	the	the	DT
10_1101-2021_01_02_425006	577	25	bioB	bioB	NNS
10_1101-2021_01_02_425006	577	26	,	,	,
10_1101-2021_01_02_425006	577	27	bioF	biof	NN
10_1101-2021_01_02_425006	577	28	,	,	,
10_1101-2021_01_02_425006	577	29	bioC	bioC	NNS
10_1101-2021_01_02_425006	577	30	,	,	,
10_1101-2021_01_02_425006	577	31	bioD	bioD	NNS
10_1101-2021_01_02_425006	577	32	and	and	CC
10_1101-2021_01_02_425006	577	33	uvrB	uvrb	JJ
10_1101-2021_01_02_425006	577	34	genes	gene	NNS
10_1101-2021_01_02_425006	577	35	.	.	.
10_1101-2021_01_02_425006	578	1	637	637	CD
10_1101-2021_01_02_425006	578	2	.CC	.CC	:
10_1101-2021_01_02_425006	578	3	-	-	HYPH
10_1101-2021_01_02_425006	578	4	BY	by	IN
10_1101-2021_01_02_425006	578	5	-	-	HYPH
10_1101-2021_01_02_425006	578	6	NC	NC	NNP
10_1101-2021_01_02_425006	578	7	-	-	HYPH
10_1101-2021_01_02_425006	578	8	ND	ND	NNP
10_1101-2021_01_02_425006	578	9	4.0	4.0	CD
10_1101-2021_01_02_425006	578	10	International	International	NNP
10_1101-2021_01_02_425006	578	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	578	12	under	under	IN
10_1101-2021_01_02_425006	578	13	a	a	DT
10_1101-2021_01_02_425006	578	14	(	(	-LRB-
10_1101-2021_01_02_425006	578	15	which	which	WDT
10_1101-2021_01_02_425006	578	16	was	be	VBD
10_1101-2021_01_02_425006	578	17	not	not	RB
10_1101-2021_01_02_425006	578	18	certified	certify	VBN
10_1101-2021_01_02_425006	578	19	by	by	IN
10_1101-2021_01_02_425006	578	20	peer	peer	NN
10_1101-2021_01_02_425006	578	21	review	review	NN
10_1101-2021_01_02_425006	578	22	)	)	-RRB-
10_1101-2021_01_02_425006	578	23	is	be	VBZ
10_1101-2021_01_02_425006	578	24	the	the	DT
10_1101-2021_01_02_425006	578	25	author	author	NN
10_1101-2021_01_02_425006	578	26	/	/	SYM
10_1101-2021_01_02_425006	578	27	funder	funder	NN
10_1101-2021_01_02_425006	578	28	,	,	,
10_1101-2021_01_02_425006	578	29	who	who	WP
10_1101-2021_01_02_425006	578	30	has	have	VBZ
10_1101-2021_01_02_425006	578	31	granted	grant	VBN
10_1101-2021_01_02_425006	578	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	578	33	a	a	DT
10_1101-2021_01_02_425006	578	34	license	license	NN
10_1101-2021_01_02_425006	578	35	to	to	TO
10_1101-2021_01_02_425006	578	36	display	display	VB
10_1101-2021_01_02_425006	578	37	the	the	DT
10_1101-2021_01_02_425006	578	38	preprint	preprint	NN
10_1101-2021_01_02_425006	578	39	in	in	IN
10_1101-2021_01_02_425006	578	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	578	41	.	.	.
10_1101-2021_01_02_425006	579	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	579	2	is	be	VBZ
10_1101-2021_01_02_425006	579	3	made	make	VBN
10_1101-2021_01_02_425006	579	4	The	the	DT
10_1101-2021_01_02_425006	579	5	copyright	copyright	NN
10_1101-2021_01_02_425006	579	6	holder	holder	NN
10_1101-2021_01_02_425006	579	7	for	for	IN
10_1101-2021_01_02_425006	579	8	this	this	DT
10_1101-2021_01_02_425006	579	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	579	10	version	version	NN
10_1101-2021_01_02_425006	579	11	posted	post	VBD
10_1101-2021_01_02_425006	579	12	January	January	NNP
10_1101-2021_01_02_425006	579	13	6	6	CD
10_1101-2021_01_02_425006	579	14	,	,	,
10_1101-2021_01_02_425006	579	15	2021	2021	CD
10_1101-2021_01_02_425006	579	16	.	.	.
10_1101-2021_01_02_425006	579	17	;	;	:
10_1101-2021_01_02_425006	579	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	579	19	:	:	:
10_1101-2021_01_02_425006	579	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	579	21	preprint	preprint	NN
10_1101-2021_01_02_425006	579	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	579	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	CD
10_1101-2021_01_02_425006	579	24	43	43	CD
10_1101-2021_01_02_425006	579	25	638	638	CD
10_1101-2021_01_02_425006	579	26	Fig	fig	NN
10_1101-2021_01_02_425006	579	27	.	.	.
10_1101-2021_01_02_425006	580	1	7	7	LS
10_1101-2021_01_02_425006	580	2	.	.	.
10_1101-2021_01_02_425006	581	1	Interpretation	interpretation	NN
10_1101-2021_01_02_425006	581	2	and	and	CC
10_1101-2021_01_02_425006	581	3	results	result	NNS
10_1101-2021_01_02_425006	581	4	of	of	IN
10_1101-2021_01_02_425006	581	5	the	the	DT
10_1101-2021_01_02_425006	581	6	functional	functional	JJ
10_1101-2021_01_02_425006	581	7	relatedness	relatedness	NN
10_1101-2021_01_02_425006	581	8	of	of	IN
10_1101-2021_01_02_425006	581	9	different	different	JJ
10_1101-2021_01_02_425006	581	10	gene	gene	NN
10_1101-2021_01_02_425006	581	11	pairs	pair	NNS
10_1101-2021_01_02_425006	581	12	based	base	VBN
10_1101-2021_01_02_425006	581	13	on	on	IN
10_1101-2021_01_02_425006	581	14	GO	GO	NNP
10_1101-2021_01_02_425006	581	15	639	639	CD
10_1101-2021_01_02_425006	581	16	and	and	CC
10_1101-2021_01_02_425006	581	17	KEGG	KEGG	NNP
10_1101-2021_01_02_425006	581	18	enrichment	enrichment	NN
10_1101-2021_01_02_425006	581	19	analyses	analysis	NNS
10_1101-2021_01_02_425006	581	20	.	.	.
10_1101-2021_01_02_425006	582	1	(	(	-LRB-
10_1101-2021_01_02_425006	582	2	A	a	NN
10_1101-2021_01_02_425006	582	3	)	)	-RRB-
10_1101-2021_01_02_425006	582	4	Illustration	illustration	NN
10_1101-2021_01_02_425006	582	5	of	of	IN
10_1101-2021_01_02_425006	582	6	two	two	CD
10_1101-2021_01_02_425006	582	7	different	different	JJ
10_1101-2021_01_02_425006	582	8	gene	gene	NN
10_1101-2021_01_02_425006	582	9	pairs	pair	NNS
10_1101-2021_01_02_425006	582	10	i	i	PRP
10_1101-2021_01_02_425006	582	11	and	and	CC
10_1101-2021_01_02_425006	582	12	ii	ii	NNP
10_1101-2021_01_02_425006	582	13	.	.	.
10_1101-2021_01_02_425006	583	1	(	(	-LRB-
10_1101-2021_01_02_425006	583	2	B	B	NNP
10_1101-2021_01_02_425006	583	3	)	)	-RRB-
10_1101-2021_01_02_425006	583	4	Functional	Functional	NNP
10_1101-2021_01_02_425006	583	5	640	640	CD
10_1101-2021_01_02_425006	583	6	relatedness	relatedness	NN
10_1101-2021_01_02_425006	583	7	results	result	NNS
10_1101-2021_01_02_425006	583	8	based	base	VBN
10_1101-2021_01_02_425006	583	9	on	on	IN
10_1101-2021_01_02_425006	583	10	GO	GO	NNP
10_1101-2021_01_02_425006	583	11	enrichment	enrichment	NN
10_1101-2021_01_02_425006	583	12	analysis	analysis	NN
10_1101-2021_01_02_425006	583	13	for	for	IN
10_1101-2021_01_02_425006	583	14	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	583	15	(	(	-LRB-
10_1101-2021_01_02_425006	583	16	left	left	RB
10_1101-2021_01_02_425006	583	17	)	)	-RRB-
10_1101-2021_01_02_425006	583	18	and	and	CC
10_1101-2021_01_02_425006	583	19	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	583	20	(	(	-LRB-
10_1101-2021_01_02_425006	583	21	right	right	RB
10_1101-2021_01_02_425006	583	22	)	)	-RRB-
10_1101-2021_01_02_425006	583	23	.	.	.
10_1101-2021_01_02_425006	584	1	641	641	CD
10_1101-2021_01_02_425006	584	2	(	(	-LRB-
10_1101-2021_01_02_425006	584	3	C	C	NNP
10_1101-2021_01_02_425006	584	4	)	)	-RRB-
10_1101-2021_01_02_425006	584	5	The	the	DT
10_1101-2021_01_02_425006	584	6	proportion	proportion	NN
10_1101-2021_01_02_425006	584	7	of	of	IN
10_1101-2021_01_02_425006	584	8	two	two	CD
10_1101-2021_01_02_425006	584	9	different	different	JJ
10_1101-2021_01_02_425006	584	10	gene	gene	NN
10_1101-2021_01_02_425006	584	11	pairs	pair	NNS
10_1101-2021_01_02_425006	584	12	whose	whose	WP$
10_1101-2021_01_02_425006	584	13	genes	gene	NNS
10_1101-2021_01_02_425006	584	14	are	be	VBP
10_1101-2021_01_02_425006	584	15	contained	contain	VBN
10_1101-2021_01_02_425006	584	16	in	in	IN
10_1101-2021_01_02_425006	584	17	the	the	DT
10_1101-2021_01_02_425006	584	18	same	same	JJ
10_1101-2021_01_02_425006	584	19	KEGG	KEGG	NNP
10_1101-2021_01_02_425006	584	20	pathway	pathway	NN
10_1101-2021_01_02_425006	584	21	642	642	CD
10_1101-2021_01_02_425006	584	22	for	for	IN
10_1101-2021_01_02_425006	584	23	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	584	24	(	(	-LRB-
10_1101-2021_01_02_425006	584	25	left	left	RB
10_1101-2021_01_02_425006	584	26	)	)	-RRB-
10_1101-2021_01_02_425006	584	27	and	and	CC
10_1101-2021_01_02_425006	584	28	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	584	29	(	(	-LRB-
10_1101-2021_01_02_425006	584	30	right	right	RB
10_1101-2021_01_02_425006	584	31	)	)	-RRB-
10_1101-2021_01_02_425006	584	32	.	.	.
10_1101-2021_01_02_425006	585	1	(	(	-LRB-
10_1101-2021_01_02_425006	585	2	D	d	NN
10_1101-2021_01_02_425006	585	3	)	)	-RRB-
10_1101-2021_01_02_425006	585	4	The	the	DT
10_1101-2021_01_02_425006	585	5	functional	functional	JJ
10_1101-2021_01_02_425006	585	6	relatedness	relatedness	NN
10_1101-2021_01_02_425006	585	7	results	result	NNS
10_1101-2021_01_02_425006	585	8	based	base	VBN
10_1101-2021_01_02_425006	585	9	on	on	IN
10_1101-2021_01_02_425006	585	10	643	643	CD
10_1101-2021_01_02_425006	585	11	KEGG	KEGG	NNP
10_1101-2021_01_02_425006	585	12	enrichment	enrichment	NN
10_1101-2021_01_02_425006	585	13	analysis	analysis	NN
10_1101-2021_01_02_425006	585	14	for	for	IN
10_1101-2021_01_02_425006	585	15	M9Enrich_Seq	M9Enrich_Seq	NNP
10_1101-2021_01_02_425006	585	16	(	(	-LRB-
10_1101-2021_01_02_425006	585	17	left	left	RB
10_1101-2021_01_02_425006	585	18	)	)	-RRB-
10_1101-2021_01_02_425006	585	19	and	and	CC
10_1101-2021_01_02_425006	585	20	RiEnrich_Seq	RiEnrich_Seq	NNP
10_1101-2021_01_02_425006	585	21	(	(	-LRB-
10_1101-2021_01_02_425006	585	22	right	right	RB
10_1101-2021_01_02_425006	585	23	)	)	-RRB-
10_1101-2021_01_02_425006	585	24	.	.	.
10_1101-2021_01_02_425006	586	1	644	644	CD
10_1101-2021_01_02_425006	586	2	.CC	.CC	NFP
10_1101-2021_01_02_425006	586	3	-	-	HYPH
10_1101-2021_01_02_425006	586	4	BY	by	IN
10_1101-2021_01_02_425006	586	5	-	-	HYPH
10_1101-2021_01_02_425006	586	6	NC	NC	NNP
10_1101-2021_01_02_425006	586	7	-	-	HYPH
10_1101-2021_01_02_425006	586	8	ND	ND	NNP
10_1101-2021_01_02_425006	586	9	4.0	4.0	CD
10_1101-2021_01_02_425006	586	10	International	International	NNP
10_1101-2021_01_02_425006	586	11	licenseavailable	licenseavailable	NN
10_1101-2021_01_02_425006	586	12	under	under	IN
10_1101-2021_01_02_425006	586	13	a	a	DT
10_1101-2021_01_02_425006	586	14	(	(	-LRB-
10_1101-2021_01_02_425006	586	15	which	which	WDT
10_1101-2021_01_02_425006	586	16	was	be	VBD
10_1101-2021_01_02_425006	586	17	not	not	RB
10_1101-2021_01_02_425006	586	18	certified	certify	VBN
10_1101-2021_01_02_425006	586	19	by	by	IN
10_1101-2021_01_02_425006	586	20	peer	peer	NN
10_1101-2021_01_02_425006	586	21	review	review	NN
10_1101-2021_01_02_425006	586	22	)	)	-RRB-
10_1101-2021_01_02_425006	586	23	is	be	VBZ
10_1101-2021_01_02_425006	586	24	the	the	DT
10_1101-2021_01_02_425006	586	25	author	author	NN
10_1101-2021_01_02_425006	586	26	/	/	SYM
10_1101-2021_01_02_425006	586	27	funder	funder	NN
10_1101-2021_01_02_425006	586	28	,	,	,
10_1101-2021_01_02_425006	586	29	who	who	WP
10_1101-2021_01_02_425006	586	30	has	have	VBZ
10_1101-2021_01_02_425006	586	31	granted	grant	VBN
10_1101-2021_01_02_425006	586	32	bioRxiv	biorxiv	IN
10_1101-2021_01_02_425006	586	33	a	a	DT
10_1101-2021_01_02_425006	586	34	license	license	NN
10_1101-2021_01_02_425006	586	35	to	to	TO
10_1101-2021_01_02_425006	586	36	display	display	VB
10_1101-2021_01_02_425006	586	37	the	the	DT
10_1101-2021_01_02_425006	586	38	preprint	preprint	NN
10_1101-2021_01_02_425006	586	39	in	in	IN
10_1101-2021_01_02_425006	586	40	perpetuity	perpetuity	NN
10_1101-2021_01_02_425006	586	41	.	.	.
10_1101-2021_01_02_425006	587	1	It	-PRON-	PRP
10_1101-2021_01_02_425006	587	2	is	be	VBZ
10_1101-2021_01_02_425006	587	3	made	make	VBN
10_1101-2021_01_02_425006	587	4	The	the	DT
10_1101-2021_01_02_425006	587	5	copyright	copyright	NN
10_1101-2021_01_02_425006	587	6	holder	holder	NN
10_1101-2021_01_02_425006	587	7	for	for	IN
10_1101-2021_01_02_425006	587	8	this	this	DT
10_1101-2021_01_02_425006	587	9	preprintthis	preprintthis	NN
10_1101-2021_01_02_425006	587	10	version	version	NN
10_1101-2021_01_02_425006	587	11	posted	post	VBD
10_1101-2021_01_02_425006	587	12	January	January	NNP
10_1101-2021_01_02_425006	587	13	6	6	CD
10_1101-2021_01_02_425006	587	14	,	,	,
10_1101-2021_01_02_425006	587	15	2021	2021	CD
10_1101-2021_01_02_425006	587	16	.	.	.
10_1101-2021_01_02_425006	587	17	;	;	:
10_1101-2021_01_02_425006	587	18	https://doi.org/10.1101/2021.01.02.425006doi	https://doi.org/10.1101/2021.01.02.425006doi	XX
10_1101-2021_01_02_425006	587	19	:	:	:
10_1101-2021_01_02_425006	587	20	bioRxiv	biorxiv	VB
10_1101-2021_01_02_425006	587	21	preprint	preprint	NN
10_1101-2021_01_02_425006	587	22	https://doi.org/10.1101/2021.01.02.425006	https://doi.org/10.1101/2021.01.02.425006	CD
10_1101-2021_01_02_425006	587	23	http://creativecommons.org/licenses/by-nc-nd/4.0/	http://creativecommons.org/licenses/by-nc-nd/4.0/	NN