id	sid	tid	token	lemma	pos
zp38w953f1h	1	1	genomics	genomic	NOUN
zp38w953f1h	1	2	,	,	PUNCT
zp38w953f1h	1	3	or	or	CCONJ
zp38w953f1h	1	4	the	the	DET
zp38w953f1h	1	5	study	study	NOUN
zp38w953f1h	1	6	of	of	ADP
zp38w953f1h	1	7	genome	genome	NOUN
zp38w953f1h	1	8	-	-	PUNCT
zp38w953f1h	1	9	derived	derive	VERB
zp38w953f1h	1	10	data	datum	NOUN
zp38w953f1h	1	11	,	,	PUNCT
zp38w953f1h	1	12	has	have	AUX
zp38w953f1h	1	13	had	have	VERB
zp38w953f1h	1	14	widespread	widespread	ADJ
zp38w953f1h	1	15	impact	impact	NOUN
zp38w953f1h	1	16	in	in	ADP
zp38w953f1h	1	17	applications	application	NOUN
zp38w953f1h	1	18	including	include	VERB
zp38w953f1h	1	19	medicine	medicine	NOUN
zp38w953f1h	1	20	,	,	PUNCT
zp38w953f1h	1	21	forensic	forensic	ADJ
zp38w953f1h	1	22	science	science	NOUN
zp38w953f1h	1	23	,	,	PUNCT
zp38w953f1h	1	24	human	human	ADJ
zp38w953f1h	1	25	evolution	evolution	NOUN
zp38w953f1h	1	26	,	,	PUNCT
zp38w953f1h	1	27	environmental	environmental	ADJ
zp38w953f1h	1	28	science	science	NOUN
zp38w953f1h	1	29	,	,	PUNCT
zp38w953f1h	1	30	and	and	CCONJ
zp38w953f1h	1	31	social	social	ADJ
zp38w953f1h	1	32	science	science	NOUN
zp38w953f1h	1	33	.	.	PUNCT
zp38w953f1h	2	1	the	the	DET
zp38w953f1h	2	2	plummeting	plummet	VERB
zp38w953f1h	2	3	cost	cost	NOUN
zp38w953f1h	2	4	of	of	ADP
zp38w953f1h	2	5	genome	genome	NOUN
zp38w953f1h	2	6	sequencing	sequence	VERB
zp38w953f1h	2	7	in	in	ADP
zp38w953f1h	2	8	the	the	DET
zp38w953f1h	2	9	last	last	ADJ
zp38w953f1h	2	10	decade	decade	NOUN
zp38w953f1h	2	11	has	have	AUX
zp38w953f1h	2	12	spurred	spur	VERB
zp38w953f1h	2	13	an	an	DET
zp38w953f1h	2	14	exponential	exponential	ADJ
zp38w953f1h	2	15	growth	growth	NOUN
zp38w953f1h	2	16	of	of	ADP
zp38w953f1h	2	17	genomic	genomic	ADJ
zp38w953f1h	2	18	data	datum	NOUN
zp38w953f1h	2	19	.	.	PUNCT
zp38w953f1h	3	1	the	the	DET
zp38w953f1h	3	2	rate	rate	NOUN
zp38w953f1h	3	3	of	of	ADP
zp38w953f1h	3	4	data	data	NOUN
zp38w953f1h	3	5	generation	generation	NOUN
zp38w953f1h	3	6	from	from	ADP
zp38w953f1h	3	7	these	these	DET
zp38w953f1h	3	8	sequencing	sequence	VERB
zp38w953f1h	3	9	techniques	technique	NOUN
zp38w953f1h	3	10	has	have	AUX
zp38w953f1h	3	11	outpaced	outpace	VERB
zp38w953f1h	3	12	computing	compute	VERB
zp38w953f1h	3	13	throughput	throughput	NOUN
zp38w953f1h	3	14	,	,	PUNCT
zp38w953f1h	3	15	as	as	SCONJ
zp38w953f1h	3	16	predicted	predict	VERB
zp38w953f1h	3	17	by	by	ADP
zp38w953f1h	3	18	moore	moore	NOUN
zp38w953f1h	3	19	's	's	PART
zp38w953f1h	3	20	law	law	NOUN
zp38w953f1h	3	21	,	,	PUNCT
zp38w953f1h	3	22	causing	cause	VERB
zp38w953f1h	3	23	a	a	DET
zp38w953f1h	3	24	major	major	ADJ
zp38w953f1h	3	25	bottleneck	bottleneck	NOUN
zp38w953f1h	3	26	in	in	ADP
zp38w953f1h	3	27	the	the	DET
zp38w953f1h	3	28	rate	rate	NOUN
zp38w953f1h	3	29	of	of	ADP
zp38w953f1h	3	30	data	datum	NOUN
zp38w953f1h	3	31	processing	processing	NOUN
zp38w953f1h	3	32	and	and	CCONJ
zp38w953f1h	3	33	analysis	analysis	NOUN
zp38w953f1h	3	34	.	.	PUNCT
zp38w953f1h	4	1	emerging	emerge	VERB
zp38w953f1h	4	2	genome	genome	NOUN
zp38w953f1h	4	3	data	datum	NOUN
zp38w953f1h	4	4	is	be	AUX
zp38w953f1h	4	5	also	also	ADV
zp38w953f1h	4	6	characterized	characterize	VERB
zp38w953f1h	4	7	by	by	ADP
zp38w953f1h	4	8	missing	miss	VERB
zp38w953f1h	4	9	and	and	CCONJ
zp38w953f1h	4	10	erroneous	erroneous	ADJ
zp38w953f1h	4	11	values	value	NOUN
zp38w953f1h	4	12	,	,	PUNCT
zp38w953f1h	4	13	that	that	PRON
zp38w953f1h	4	14	reduce	reduce	VERB
zp38w953f1h	4	15	data	datum	NOUN
zp38w953f1h	4	16	fidelity	fidelity	NOUN
zp38w953f1h	4	17	and	and	CCONJ
zp38w953f1h	4	18	limit	limit	VERB
zp38w953f1h	4	19	its	its	PRON
zp38w953f1h	4	20	applicability	applicability	NOUN
zp38w953f1h	4	21	for	for	ADP
zp38w953f1h	4	22	downstream	downstream	ADJ
zp38w953f1h	4	23	analysis	analysis	NOUN
zp38w953f1h	4	24	.	.	PUNCT
zp38w953f1h	5	1	this	this	PRON
zp38w953f1h	5	2	forms	form	VERB
zp38w953f1h	5	3	the	the	DET
zp38w953f1h	5	4	basis	basis	NOUN
zp38w953f1h	5	5	of	of	ADP
zp38w953f1h	5	6	the	the	DET
zp38w953f1h	5	7	following	follow	VERB
zp38w953f1h	5	8	research	research	NOUN
zp38w953f1h	5	9	questions	question	NOUN
zp38w953f1h	5	10	:	:	PUNCT
zp38w953f1h	5	11	(	(	PUNCT
zp38w953f1h	5	12	i	i	NOUN
zp38w953f1h	5	13	)	)	PUNCT
zp38w953f1h	5	14	can	can	AUX
zp38w953f1h	5	15	we	we	PRON
zp38w953f1h	5	16	design	design	VERB
zp38w953f1h	5	17	frameworks	framework	NOUN
zp38w953f1h	5	18	that	that	PRON
zp38w953f1h	5	19	can	can	AUX
zp38w953f1h	5	20	expedite	expedite	VERB
zp38w953f1h	5	21	data	data	NOUN
zp38w953f1h	5	22	analysis	analysis	NOUN
zp38w953f1h	5	23	and	and	CCONJ
zp38w953f1h	5	24	enable	enable	VERB
zp38w953f1h	5	25	efficient	efficient	ADJ
zp38w953f1h	5	26	utilization	utilization	NOUN
zp38w953f1h	5	27	of	of	ADP
zp38w953f1h	5	28	computational	computational	ADJ
zp38w953f1h	5	29	resources	resource	NOUN
zp38w953f1h	5	30	?	?	PUNCT
zp38w953f1h	6	1	(	(	PUNCT
zp38w953f1h	6	2	ii	ii	PROPN
zp38w953f1h	6	3	)	)	PUNCT
zp38w953f1h	6	4	can	can	AUX
zp38w953f1h	6	5	we	we	PRON
zp38w953f1h	6	6	develop	develop	VERB
zp38w953f1h	6	7	accurate	accurate	ADJ
zp38w953f1h	6	8	and	and	CCONJ
zp38w953f1h	6	9	efficient	efficient	ADJ
zp38w953f1h	6	10	algorithms	algorithm	NOUN
zp38w953f1h	6	11	to	to	PART
zp38w953f1h	6	12	improve	improve	VERB
zp38w953f1h	6	13	data	data	NOUN
zp38w953f1h	6	14	fidelity	fidelity	NOUN
zp38w953f1h	6	15	in	in	ADP
zp38w953f1h	6	16	genomic	genomic	PROPN
zp38w953f1h	6	17	applications?we	applications?we	PUNCT
zp38w953f1h	6	18	address	address	VERB
zp38w953f1h	6	19	the	the	DET
zp38w953f1h	6	20	first	first	ADJ
zp38w953f1h	6	21	problem	problem	NOUN
zp38w953f1h	6	22	by	by	ADP
zp38w953f1h	6	23	developing	develop	VERB
zp38w953f1h	6	24	a	a	DET
zp38w953f1h	6	25	parallel	parallel	ADJ
zp38w953f1h	6	26	data	datum	NOUN
zp38w953f1h	6	27	analysis	analysis	NOUN
zp38w953f1h	6	28	framework	framework	NOUN
zp38w953f1h	6	29	that	that	PRON
zp38w953f1h	6	30	accelerates	accelerate	VERB
zp38w953f1h	6	31	large	large	ADJ
zp38w953f1h	6	32	-	-	PUNCT
zp38w953f1h	6	33	scale	scale	NOUN
zp38w953f1h	6	34	comparative	comparative	ADJ
zp38w953f1h	6	35	genomics	genomic	NOUN
zp38w953f1h	6	36	applications	application	NOUN
zp38w953f1h	6	37	.	.	PUNCT
zp38w953f1h	7	1	we	we	PRON
zp38w953f1h	7	2	identify	identify	VERB
zp38w953f1h	7	3	that	that	DET
zp38w953f1h	7	4	optimal	optimal	ADJ
zp38w953f1h	7	5	data	datum	NOUN
zp38w953f1h	7	6	partitioning	partition	VERB
zp38w953f1h	7	7	and	and	CCONJ
zp38w953f1h	7	8	caching	caching	NOUN
zp38w953f1h	7	9	significantly	significantly	ADV
zp38w953f1h	7	10	improve	improve	VERB
zp38w953f1h	7	11	the	the	DET
zp38w953f1h	7	12	performance	performance	NOUN
zp38w953f1h	7	13	of	of	ADP
zp38w953f1h	7	14	such	such	ADJ
zp38w953f1h	7	15	framework	framework	NOUN
zp38w953f1h	7	16	.	.	PUNCT
zp38w953f1h	8	1	we	we	PRON
zp38w953f1h	8	2	further	far	ADV
zp38w953f1h	8	3	construct	construct	VERB
zp38w953f1h	8	4	a	a	DET
zp38w953f1h	8	5	predictive	predictive	ADJ
zp38w953f1h	8	6	model	model	NOUN
zp38w953f1h	8	7	to	to	PART
zp38w953f1h	8	8	estimate	estimate	VERB
zp38w953f1h	8	9	runtime	runtime	NOUN
zp38w953f1h	8	10	configurations	configuration	NOUN
zp38w953f1h	8	11	that	that	PRON
zp38w953f1h	8	12	facilitate	facilitate	VERB
zp38w953f1h	8	13	optimal	optimal	ADJ
zp38w953f1h	8	14	utilization	utilization	NOUN
zp38w953f1h	8	15	of	of	ADP
zp38w953f1h	8	16	cloud	cloud	NOUN
zp38w953f1h	8	17	and	and	CCONJ
zp38w953f1h	8	18	cluster	cluster	NOUN
zp38w953f1h	8	19	-	-	PUNCT
zp38w953f1h	8	20	based	base	VERB
zp38w953f1h	8	21	resources	resource	NOUN
zp38w953f1h	8	22	while	while	SCONJ
zp38w953f1h	8	23	executing	execute	VERB
zp38w953f1h	8	24	data	data	NOUN
zp38w953f1h	8	25	-	-	PUNCT
zp38w953f1h	8	26	intensive	intensive	ADJ
zp38w953f1h	8	27	applications	application	NOUN
zp38w953f1h	8	28	.	.	PUNCT
zp38w953f1h	9	1	the	the	DET
zp38w953f1h	9	2	fidelity	fidelity	NOUN
zp38w953f1h	9	3	of	of	ADP
zp38w953f1h	9	4	genomic	genomic	ADJ
zp38w953f1h	9	5	data	datum	NOUN
zp38w953f1h	9	6	derived	derive	VERB
zp38w953f1h	9	7	from	from	ADP
zp38w953f1h	9	8	next	next	ADJ
zp38w953f1h	9	9	-	-	PUNCT
zp38w953f1h	9	10	generation	generation	NOUN
zp38w953f1h	9	11	sequencing	sequence	VERB
zp38w953f1h	9	12	techniques	technique	NOUN
zp38w953f1h	9	13	impacts	impact	VERB
zp38w953f1h	9	14	downstream	downstream	ADJ
zp38w953f1h	9	15	applications	application	NOUN
zp38w953f1h	9	16	like	like	ADP
zp38w953f1h	9	17	genome	genome	NOUN
zp38w953f1h	9	18	-	-	PUNCT
zp38w953f1h	9	19	wide	wide	ADJ
zp38w953f1h	9	20	association	association	NOUN
zp38w953f1h	9	21	study	study	NOUN
zp38w953f1h	9	22	(	(	PUNCT
zp38w953f1h	9	23	gwas	gwas	PROPN
zp38w953f1h	9	24	)	)	PUNCT
zp38w953f1h	9	25	and	and	CCONJ
zp38w953f1h	9	26	genome	genome	NOUN
zp38w953f1h	9	27	assembly	assembly	NOUN
zp38w953f1h	9	28	.	.	PUNCT
zp38w953f1h	10	1	for	for	ADP
zp38w953f1h	10	2	imputation	imputation	NOUN
zp38w953f1h	10	3	of	of	ADP
zp38w953f1h	10	4	missing	miss	VERB
zp38w953f1h	10	5	genotype	genotype	NOUN
zp38w953f1h	10	6	data	datum	NOUN
zp38w953f1h	10	7	,	,	PUNCT
zp38w953f1h	10	8	we	we	PRON
zp38w953f1h	10	9	design	design	VERB
zp38w953f1h	10	10	an	an	DET
zp38w953f1h	10	11	accurate	accurate	ADJ
zp38w953f1h	10	12	,	,	PUNCT
zp38w953f1h	10	13	fast	fast	ADJ
zp38w953f1h	10	14	,	,	PUNCT
zp38w953f1h	10	15	and	and	CCONJ
zp38w953f1h	10	16	lightweight	lightweight	ADJ
zp38w953f1h	10	17	algorithm	algorithm	PROPN
zp38w953f1h	10	18	for	for	ADP
zp38w953f1h	10	19	both	both	DET
zp38w953f1h	10	20	model	model	NOUN
zp38w953f1h	10	21	(	(	PUNCT
zp38w953f1h	10	22	with	with	ADP
zp38w953f1h	10	23	a	a	DET
zp38w953f1h	10	24	reference	reference	NOUN
zp38w953f1h	10	25	genotype	genotype	NOUN
zp38w953f1h	10	26	panel	panel	NOUN
zp38w953f1h	10	27	)	)	PUNCT
zp38w953f1h	10	28	and	and	CCONJ
zp38w953f1h	10	29	non	non	ADJ
zp38w953f1h	10	30	-	-	ADJ
zp38w953f1h	10	31	model	model	ADJ
zp38w953f1h	10	32	(	(	PUNCT
zp38w953f1h	10	33	without	without	ADP
zp38w953f1h	10	34	a	a	DET
zp38w953f1h	10	35	reference	reference	NOUN
zp38w953f1h	10	36	genotype	genotype	NOUN
zp38w953f1h	10	37	panel	panel	NOUN
zp38w953f1h	10	38	)	)	PUNCT
zp38w953f1h	10	39	organisms	organism	NOUN
zp38w953f1h	10	40	.	.	PUNCT
zp38w953f1h	11	1	to	to	PART
zp38w953f1h	11	2	correct	correct	VERB
zp38w953f1h	11	3	erroneous	erroneous	ADJ
zp38w953f1h	11	4	long	long	ADJ
zp38w953f1h	11	5	reads	read	NOUN
zp38w953f1h	11	6	generated	generate	VERB
zp38w953f1h	11	7	by	by	ADP
zp38w953f1h	11	8	emerging	emerge	VERB
zp38w953f1h	11	9	sequencing	sequence	VERB
zp38w953f1h	11	10	techniques	technique	NOUN
zp38w953f1h	11	11	,	,	PUNCT
zp38w953f1h	11	12	we	we	PRON
zp38w953f1h	11	13	formulate	formulate	VERB
zp38w953f1h	11	14	a	a	DET
zp38w953f1h	11	15	hybrid	hybrid	ADJ
zp38w953f1h	11	16	correction	correction	NOUN
zp38w953f1h	11	17	algorithm	algorithm	X
zp38w953f1h	11	18	that	that	PRON
zp38w953f1h	11	19	determines	determine	VERB
zp38w953f1h	11	20	a	a	DET
zp38w953f1h	11	21	correction	correction	NOUN
zp38w953f1h	11	22	policy	policy	NOUN
zp38w953f1h	11	23	based	base	VERB
zp38w953f1h	11	24	on	on	ADP
zp38w953f1h	11	25	an	an	DET
zp38w953f1h	11	26	optimal	optimal	ADJ
zp38w953f1h	11	27	combination	combination	NOUN
zp38w953f1h	11	28	of	of	ADP
zp38w953f1h	11	29	base	base	ADJ
zp38w953f1h	11	30	quality	quality	NOUN
zp38w953f1h	11	31	and	and	CCONJ
zp38w953f1h	11	32	similarity	similarity	NOUN
zp38w953f1h	11	33	of	of	ADP
zp38w953f1h	11	34	aligned	align	VERB
zp38w953f1h	11	35	short	short	ADJ
zp38w953f1h	11	36	reads	read	NOUN
zp38w953f1h	11	37	.	.	PUNCT
zp38w953f1h	12	1	we	we	PRON
zp38w953f1h	12	2	extend	extend	VERB
zp38w953f1h	12	3	the	the	DET
zp38w953f1h	12	4	core	core	NOUN
zp38w953f1h	12	5	algorithm	algorithm	NOUN
zp38w953f1h	12	6	by	by	ADP
zp38w953f1h	12	7	proposing	propose	VERB
zp38w953f1h	12	8	an	an	DET
zp38w953f1h	12	9	iterative	iterative	ADJ
zp38w953f1h	12	10	learning	learning	NOUN
zp38w953f1h	12	11	paradigm	paradigm	NOUN
zp38w953f1h	12	12	that	that	PRON
zp38w953f1h	12	13	further	far	ADV
zp38w953f1h	12	14	improves	improve	VERB
zp38w953f1h	12	15	its	its	PRON
zp38w953f1h	12	16	performance.our	performance.our	PRON
zp38w953f1h	12	17	proposed	propose	VERB
zp38w953f1h	12	18	data	datum	NOUN
zp38w953f1h	12	19	analysis	analysis	NOUN
zp38w953f1h	12	20	framework	framework	NOUN
zp38w953f1h	12	21	is	be	AUX
zp38w953f1h	12	22	accessible	accessible	ADJ
zp38w953f1h	12	23	to	to	ADP
zp38w953f1h	12	24	the	the	DET
zp38w953f1h	12	25	scientific	scientific	ADJ
zp38w953f1h	12	26	community	community	NOUN
zp38w953f1h	12	27	and	and	CCONJ
zp38w953f1h	12	28	has	have	AUX
zp38w953f1h	12	29	been	be	AUX
zp38w953f1h	12	30	used	use	VERB
zp38w953f1h	12	31	to	to	PART
zp38w953f1h	12	32	study	study	VERB
zp38w953f1h	12	33	the	the	DET
zp38w953f1h	12	34	genomes	genome	NOUN
zp38w953f1h	12	35	of	of	ADP
zp38w953f1h	12	36	important	important	ADJ
zp38w953f1h	12	37	plant	plant	NOUN
zp38w953f1h	12	38	species	specie	NOUN
zp38w953f1h	12	39	and	and	CCONJ
zp38w953f1h	12	40	malaria	malaria	PROPN
zp38w953f1h	12	41	vector	vector	NOUN
zp38w953f1h	12	42	mosquitoes	mosquito	NOUN
zp38w953f1h	12	43	.	.	PUNCT
zp38w953f1h	13	1	the	the	DET
zp38w953f1h	13	2	predictive	predictive	ADJ
zp38w953f1h	13	3	models	model	NOUN
zp38w953f1h	13	4	exhibit	exhibit	VERB
zp38w953f1h	13	5	high	high	ADJ
zp38w953f1h	13	6	accuracy	accuracy	NOUN
zp38w953f1h	13	7	in	in	ADP
zp38w953f1h	13	8	determining	determine	VERB
zp38w953f1h	13	9	optimal	optimal	ADJ
zp38w953f1h	13	10	parameters	parameter	NOUN
zp38w953f1h	13	11	of	of	ADP
zp38w953f1h	13	12	operation	operation	NOUN
zp38w953f1h	13	13	on	on	ADP
zp38w953f1h	13	14	commercial	commercial	ADJ
zp38w953f1h	13	15	cloud	cloud	NOUN
zp38w953f1h	13	16	services	service	NOUN
zp38w953f1h	13	17	like	like	ADP
zp38w953f1h	13	18	amazon	amazon	PROPN
zp38w953f1h	13	19	ec2	ec2	PROPN
zp38w953f1h	13	20	and	and	CCONJ
zp38w953f1h	13	21	microsoft	microsoft	PROPN
zp38w953f1h	13	22	azure	azure	PROPN
zp38w953f1h	13	23	.	.	PUNCT
zp38w953f1h	14	1	finally	finally	ADV
zp38w953f1h	14	2	,	,	PUNCT
zp38w953f1h	14	3	the	the	DET
zp38w953f1h	14	4	imputation	imputation	NOUN
zp38w953f1h	14	5	and	and	CCONJ
zp38w953f1h	14	6	error	error	NOUN
zp38w953f1h	14	7	correction	correction	NOUN
zp38w953f1h	14	8	algorithms	algorithm	NOUN
zp38w953f1h	14	9	outperform	outperform	VERB
zp38w953f1h	14	10	state	state	NOUN
zp38w953f1h	14	11	-	-	PUNCT
zp38w953f1h	14	12	of	of	ADP
zp38w953f1h	14	13	-	-	PUNCT
zp38w953f1h	14	14	the	the	DET
zp38w953f1h	14	15	-	-	PUNCT
zp38w953f1h	14	16	art	art	NOUN
zp38w953f1h	14	17	alternatives	alternative	NOUN
zp38w953f1h	14	18	when	when	SCONJ
zp38w953f1h	14	19	tested	test	VERB
zp38w953f1h	14	20	on	on	ADP
zp38w953f1h	14	21	real	real	ADJ
zp38w953f1h	14	22	data	data	NOUN
zp38w953f1h	14	23	sets	set	NOUN
zp38w953f1h	14	24	of	of	ADP
zp38w953f1h	14	25	plants	plant	NOUN
zp38w953f1h	14	26	,	,	PUNCT
zp38w953f1h	14	27	malarial	malarial	ADJ
zp38w953f1h	14	28	mosquitoes	mosquito	NOUN
zp38w953f1h	14	29	,	,	PUNCT
zp38w953f1h	14	30	and	and	CCONJ
zp38w953f1h	14	31	humans	human	NOUN
zp38w953f1h	14	32	.	.	PUNCT
zp38w953f1h	15	1	hence	hence	ADV
zp38w953f1h	15	2	,	,	PUNCT
zp38w953f1h	15	3	in	in	ADP
zp38w953f1h	15	4	this	this	DET
zp38w953f1h	15	5	thesis	thesis	NOUN
zp38w953f1h	15	6	,	,	PUNCT
zp38w953f1h	15	7	we	we	PRON
zp38w953f1h	15	8	present	present	VERB
zp38w953f1h	15	9	novel	novel	ADJ
zp38w953f1h	15	10	solutions	solution	NOUN
zp38w953f1h	15	11	to	to	PART
zp38w953f1h	15	12	expedite	expedite	VERB
zp38w953f1h	15	13	data	data	NOUN
zp38w953f1h	15	14	-	-	PUNCT
zp38w953f1h	15	15	parallel	parallel	NOUN
zp38w953f1h	15	16	genomic	genomic	NOUN
zp38w953f1h	15	17	applications	application	NOUN
zp38w953f1h	15	18	while	while	SCONJ
zp38w953f1h	15	19	optimizing	optimize	VERB
zp38w953f1h	15	20	cloud	cloud	NOUN
zp38w953f1h	15	21	and	and	CCONJ
zp38w953f1h	15	22	cluster	cluster	NOUN
zp38w953f1h	15	23	-	-	PUNCT
zp38w953f1h	15	24	based	base	VERB
zp38w953f1h	15	25	resource	resource	NOUN
zp38w953f1h	15	26	utilization	utilization	NOUN
zp38w953f1h	15	27	.	.	PUNCT
zp38w953f1h	16	1	we	we	PRON
zp38w953f1h	16	2	also	also	ADV
zp38w953f1h	16	3	design	design	VERB
zp38w953f1h	16	4	novel	novel	NOUN
zp38w953f1h	16	5	,	,	PUNCT
zp38w953f1h	16	6	accurate	accurate	ADJ
zp38w953f1h	16	7	,	,	PUNCT
zp38w953f1h	16	8	and	and	CCONJ
zp38w953f1h	16	9	efficient	efficient	ADJ
zp38w953f1h	16	10	algorithms	algorithm	NOUN
zp38w953f1h	16	11	to	to	PART
zp38w953f1h	16	12	impute	impute	VERB
zp38w953f1h	16	13	missing	miss	VERB
zp38w953f1h	16	14	data	datum	NOUN
zp38w953f1h	16	15	and	and	CCONJ
zp38w953f1h	16	16	correct	correct	VERB
zp38w953f1h	16	17	erroneous	erroneous	ADJ
zp38w953f1h	16	18	data	datum	NOUN
zp38w953f1h	16	19	in	in	ADP
zp38w953f1h	16	20	emerging	emerge	VERB
zp38w953f1h	16	21	genomic	genomic	ADJ
zp38w953f1h	16	22	applications	application	NOUN
zp38w953f1h	16	23	.	.	PUNCT