id	sid	tid	token	lemma	pos
pz50gt5705c	1	1	understanding	understand	VERB
pz50gt5705c	1	2	how	how	SCONJ
pz50gt5705c	1	3	a	a	DET
pz50gt5705c	1	4	polypeptide	polypeptide	NOUN
pz50gt5705c	1	5	chain	chain	NOUN
pz50gt5705c	1	6	achieves	achieve	VERB
pz50gt5705c	1	7	its	its	PRON
pz50gt5705c	1	8	native	native	ADJ
pz50gt5705c	1	9	fold	fold	NOUN
pz50gt5705c	1	10	and	and	CCONJ
pz50gt5705c	1	11	the	the	DET
pz50gt5705c	1	12	complex	complex	ADJ
pz50gt5705c	1	13	interplay	interplay	NOUN
pz50gt5705c	1	14	between	between	ADP
pz50gt5705c	1	15	folding	folding	NOUN
pz50gt5705c	1	16	and	and	CCONJ
pz50gt5705c	1	17	aggregation	aggregation	NOUN
pz50gt5705c	1	18	remains	remain	VERB
pz50gt5705c	1	19	,	,	PUNCT
pz50gt5705c	1	20	even	even	ADV
pz50gt5705c	1	21	after	after	ADP
pz50gt5705c	1	22	over	over	ADP
pz50gt5705c	1	23	40	40	NUM
pz50gt5705c	1	24	years	year	NOUN
pz50gt5705c	1	25	,	,	PUNCT
pz50gt5705c	1	26	an	an	DET
pz50gt5705c	1	27	area	area	NOUN
pz50gt5705c	1	28	of	of	ADP
pz50gt5705c	1	29	active	active	ADJ
pz50gt5705c	1	30	research	research	NOUN
pz50gt5705c	1	31	.	.	PUNCT
pz50gt5705c	2	1	particularly	particularly	ADV
pz50gt5705c	2	2	,	,	PUNCT
pz50gt5705c	2	3	understanding	understand	VERB
pz50gt5705c	2	4	how	how	SCONJ
pz50gt5705c	2	5	large	large	ADJ
pz50gt5705c	2	6	,	,	PUNCT
pz50gt5705c	2	7	topologically	topologically	ADV
pz50gt5705c	2	8	complex	complex	ADJ
pz50gt5705c	2	9	proteins	protein	NOUN
pz50gt5705c	2	10	fold	fold	VERB
pz50gt5705c	2	11	and	and	CCONJ
pz50gt5705c	2	12	avoid	avoid	VERB
pz50gt5705c	2	13	aggregation	aggregation	NOUN
pz50gt5705c	2	14	is	be	AUX
pz50gt5705c	2	15	crucial	crucial	ADJ
pz50gt5705c	2	16	for	for	ADP
pz50gt5705c	2	17	the	the	DET
pz50gt5705c	2	18	advancement	advancement	NOUN
pz50gt5705c	2	19	of	of	ADP
pz50gt5705c	2	20	the	the	DET
pz50gt5705c	2	21	field	field	NOUN
pz50gt5705c	2	22	.	.	PUNCT
pz50gt5705c	3	1	this	this	DET
pz50gt5705c	3	2	thesis	thesis	NOUN
pz50gt5705c	3	3	specifically	specifically	ADV
pz50gt5705c	3	4	investigates	investigate	VERB
pz50gt5705c	3	5	the	the	DET
pz50gt5705c	3	6	relationship	relationship	NOUN
pz50gt5705c	3	7	between	between	ADP
pz50gt5705c	3	8	folding	folding	NOUN
pz50gt5705c	3	9	and	and	CCONJ
pz50gt5705c	3	10	aggregation	aggregation	NOUN
pz50gt5705c	3	11	of	of	ADP
pz50gt5705c	3	12	large	large	ADJ
pz50gt5705c	3	13	,	,	PUNCT
pz50gt5705c	3	14	&	&	CCONJ
pz50gt5705c	3	15	#	#	SYM
pz50gt5705c	3	16	946;-sheet	946;-sheet	NUM
pz50gt5705c	3	17	rich	rich	ADJ
pz50gt5705c	3	18	proteins	protein	NOUN
pz50gt5705c	3	19	with	with	ADP
pz50gt5705c	3	20	complex	complex	ADJ
pz50gt5705c	3	21	folding	fold	VERB
pz50gt5705c	3	22	mechanisms	mechanism	NOUN
pz50gt5705c	3	23	with	with	ADP
pz50gt5705c	3	24	an	an	DET
pz50gt5705c	3	25	emphasis	emphasis	NOUN
pz50gt5705c	3	26	on	on	ADP
pz50gt5705c	3	27	&	&	CCONJ
pz50gt5705c	3	28	#	#	SYM
pz50gt5705c	3	29	946;-helical	946;-helical	ADJ
pz50gt5705c	3	30	proteins	protein	NOUN
pz50gt5705c	3	31	such	such	ADJ
pz50gt5705c	3	32	as	as	ADP
pz50gt5705c	3	33	pertactin	pertactin	NOUN
pz50gt5705c	3	34	.	.	PUNCT
pz50gt5705c	4	1	while	while	SCONJ
pz50gt5705c	4	2	&	&	CCONJ
pz50gt5705c	4	3	#	#	SYM
pz50gt5705c	4	4	946;-sheet	946;-sheet	NUM
pz50gt5705c	4	5	rich	rich	ADJ
pz50gt5705c	4	6	proteins	protein	NOUN
pz50gt5705c	4	7	tend	tend	VERB
pz50gt5705c	4	8	to	to	PART
pz50gt5705c	4	9	have	have	VERB
pz50gt5705c	4	10	slower	slow	ADJ
pz50gt5705c	4	11	folding	fold	VERB
pz50gt5705c	4	12	kinetics	kinetic	NOUN
pz50gt5705c	4	13	and	and	CCONJ
pz50gt5705c	4	14	increased	increase	VERB
pz50gt5705c	4	15	population	population	NOUN
pz50gt5705c	4	16	of	of	ADP
pz50gt5705c	4	17	aggregation	aggregation	NOUN
pz50gt5705c	4	18	prone	prone	ADJ
pz50gt5705c	4	19	intermediates	intermediate	NOUN
pz50gt5705c	4	20	(	(	PUNCT
pz50gt5705c	4	21	1	1	NUM
pz50gt5705c	4	22	,	,	PUNCT
pz50gt5705c	4	23	2	2	NUM
pz50gt5705c	4	24	)	)	PUNCT
pz50gt5705c	4	25	,	,	PUNCT
pz50gt5705c	4	26	&	&	CCONJ
pz50gt5705c	4	27	#	#	SYM
pz50gt5705c	4	28	946;-sheet	946;-sheet	NUM
pz50gt5705c	4	29	rich	rich	ADJ
pz50gt5705c	4	30	proteins	protein	NOUN
pz50gt5705c	4	31	can	can	AUX
pz50gt5705c	4	32	avoid	avoid	VERB
pz50gt5705c	4	33	aggregation	aggregation	NOUN
pz50gt5705c	4	34	and	and	CCONJ
pz50gt5705c	4	35	robustly	robustly	ADV
pz50gt5705c	4	36	fold	fold	ADJ
pz50gt5705c	4	37	(	(	PUNCT
pz50gt5705c	4	38	3	3	NUM
pz50gt5705c	4	39	)	)	PUNCT
pz50gt5705c	4	40	.	.	PUNCT
pz50gt5705c	5	1	specifically	specifically	ADV
pz50gt5705c	5	2	,	,	PUNCT
pz50gt5705c	5	3	&	&	CCONJ
pz50gt5705c	5	4	#	#	SYM
pz50gt5705c	5	5	946;-helical	946;-helical	ADJ
pz50gt5705c	5	6	proteins	protein	NOUN
pz50gt5705c	5	7	possess	possess	VERB
pz50gt5705c	5	8	structural	structural	ADJ
pz50gt5705c	5	9	caps	cap	NOUN
pz50gt5705c	5	10	that	that	PRON
pz50gt5705c	5	11	prevent	prevent	VERB
pz50gt5705c	5	12	aggregation	aggregation	NOUN
pz50gt5705c	5	13	that	that	PRON
pz50gt5705c	5	14	can	can	AUX
pz50gt5705c	5	15	be	be	AUX
pz50gt5705c	5	16	identified	identify	VERB
pz50gt5705c	5	17	by	by	ADP
pz50gt5705c	5	18	our	our	PRON
pz50gt5705c	5	19	structure	structure	NOUN
pz50gt5705c	5	20	-	-	PUNCT
pz50gt5705c	5	21	based	base	VERB
pz50gt5705c	5	22	prediction	prediction	NOUN
pz50gt5705c	5	23	program	program	NOUN
pz50gt5705c	5	24	,	,	PUNCT
pz50gt5705c	5	25	helixcap	helixcap	ADV
pz50gt5705c	5	26	(	(	PUNCT
pz50gt5705c	5	27	4	4	NUM
pz50gt5705c	5	28	)	)	PUNCT
pz50gt5705c	5	29	.	.	PUNCT
pz50gt5705c	6	1	additionally	additionally	ADV
pz50gt5705c	6	2	,	,	PUNCT
pz50gt5705c	6	3	aggregation	aggregation	NOUN
pz50gt5705c	6	4	is	be	AUX
pz50gt5705c	6	5	often	often	ADV
pz50gt5705c	6	6	viewed	view	VERB
pz50gt5705c	6	7	as	as	ADP
pz50gt5705c	6	8	an	an	DET
pz50gt5705c	6	9	irreversible	irreversible	ADJ
pz50gt5705c	6	10	fate	fate	NOUN
pz50gt5705c	6	11	for	for	ADP
pz50gt5705c	6	12	folding	fold	VERB
pz50gt5705c	6	13	polypeptides	polypeptide	NOUN
pz50gt5705c	6	14	,	,	PUNCT
pz50gt5705c	6	15	yet	yet	ADV
pz50gt5705c	6	16	as	as	SCONJ
pz50gt5705c	6	17	demonstrated	demonstrate	VERB
pz50gt5705c	6	18	by	by	ADP
pz50gt5705c	6	19	this	this	DET
pz50gt5705c	6	20	work	work	NOUN
pz50gt5705c	6	21	,	,	PUNCT
pz50gt5705c	6	22	it	it	PRON
pz50gt5705c	6	23	can	can	AUX
pz50gt5705c	6	24	be	be	AUX
pz50gt5705c	6	25	a	a	DET
pz50gt5705c	6	26	dynamic	dynamic	ADJ
pz50gt5705c	6	27	process	process	NOUN
pz50gt5705c	6	28	.	.	PUNCT
pz50gt5705c	7	1	during	during	ADP
pz50gt5705c	7	2	refolding	refolding	NOUN
pz50gt5705c	7	3	,	,	PUNCT
pz50gt5705c	7	4	pertactin	pertactin	ADJ
pz50gt5705c	7	5	forms	form	NOUN
pz50gt5705c	7	6	loose	loose	ADJ
pz50gt5705c	7	7	,	,	PUNCT
pz50gt5705c	7	8	unstructured	unstructured	ADJ
pz50gt5705c	7	9	transient	transient	ADJ
pz50gt5705c	7	10	insoluble	insoluble	ADJ
pz50gt5705c	7	11	aggregates	aggregate	NOUN
pz50gt5705c	7	12	(	(	PUNCT
pz50gt5705c	7	13	tia	tia	PROPN
pz50gt5705c	7	14	)	)	PUNCT
pz50gt5705c	7	15	that	that	PRON
pz50gt5705c	7	16	disassemble	disassemble	VERB
pz50gt5705c	7	17	without	without	ADP
pz50gt5705c	7	18	the	the	DET
pz50gt5705c	7	19	aid	aid	NOUN
pz50gt5705c	7	20	of	of	ADP
pz50gt5705c	7	21	molecular	molecular	ADJ
pz50gt5705c	7	22	chaperones	chaperone	NOUN
pz50gt5705c	7	23	to	to	PART
pz50gt5705c	7	24	productively	productively	ADV
pz50gt5705c	7	25	fold	fold	VERB
pz50gt5705c	7	26	to	to	ADP
pz50gt5705c	7	27	the	the	DET
pz50gt5705c	7	28	native	native	ADJ
pz50gt5705c	7	29	state	state	NOUN
pz50gt5705c	7	30	.	.	PUNCT
pz50gt5705c	8	1	understanding	understand	VERB
pz50gt5705c	8	2	how	how	SCONJ
pz50gt5705c	8	3	proteins	protein	NOUN
pz50gt5705c	8	4	assemble	assemble	VERB
pz50gt5705c	8	5	into	into	ADP
pz50gt5705c	8	6	aggregate	aggregate	ADJ
pz50gt5705c	8	7	structures	structure	NOUN
pz50gt5705c	8	8	,	,	PUNCT
pz50gt5705c	8	9	such	such	ADJ
pz50gt5705c	8	10	as	as	ADP
pz50gt5705c	8	11	the	the	DET
pz50gt5705c	8	12	unstructured	unstructured	ADJ
pz50gt5705c	8	13	tia	tia	PROPN
pz50gt5705c	8	14	or	or	CCONJ
pz50gt5705c	8	15	the	the	DET
pz50gt5705c	8	16	large	large	ADJ
pz50gt5705c	8	17	rope	rope	NOUN
pz50gt5705c	8	18	-	-	PUNCT
pz50gt5705c	8	19	like	like	ADJ
pz50gt5705c	8	20	fibril	fibril	ADJ
pz50gt5705c	8	21	aggregates	aggregate	NOUN
pz50gt5705c	8	22	(	(	PUNCT
pz50gt5705c	8	23	5	5	NUM
pz50gt5705c	8	24	)	)	PUNCT
pz50gt5705c	8	25	described	describe	VERB
pz50gt5705c	8	26	in	in	ADP
pz50gt5705c	8	27	this	this	DET
pz50gt5705c	8	28	thesis	thesis	NOUN
pz50gt5705c	8	29	,	,	PUNCT
pz50gt5705c	8	30	can	can	AUX
pz50gt5705c	8	31	lead	lead	VERB
pz50gt5705c	8	32	to	to	ADP
pz50gt5705c	8	33	controlled	control	VERB
pz50gt5705c	8	34	assembly	assembly	NOUN
pz50gt5705c	8	35	for	for	ADP
pz50gt5705c	8	36	biomaterials	biomaterial	NOUN
pz50gt5705c	8	37	applications	application	NOUN
pz50gt5705c	8	38	and/or	and/or	CCONJ
pz50gt5705c	8	39	prevention	prevention	NOUN
pz50gt5705c	8	40	of	of	ADP
pz50gt5705c	8	41	unwanted	unwanted	ADJ
pz50gt5705c	8	42	aggregation	aggregation	NOUN
pz50gt5705c	8	43	.	.	PUNCT