id	sid	tid	token	lemma	pos
istl-2566	1	1	article	article	NOUN
istl-2566	1	2	title	title	NOUN
istl-2566	1	3	abstract	abstract	ADJ
istl-2566	1	4	introduction	introduction	NOUN
istl-2566	1	5	and	and	CCONJ
istl-2566	1	6	literature	literature	NOUN
istl-2566	1	7	review	review	NOUN
istl-2566	1	8	methods	method	NOUN
istl-2566	1	9	results	result	VERB
istl-2566	1	10	discussion	discussion	NOUN
istl-2566	1	11	conclusions	conclusion	NOUN
istl-2566	1	12	supporting	support	VERB
istl-2566	1	13	information	information	NOUN
istl-2566	1	14	acknowledgments	acknowledgment	NOUN
istl-2566	1	15	references	reference	NOUN
istl-2566	1	16	enhancing	enhance	VERB
istl-2566	1	17	the	the	DET
istl-2566	1	18	discovery	discovery	NOUN
istl-2566	1	19	of	of	ADP
istl-2566	1	20	chemistry	chemistry	NOUN
istl-2566	1	21	theses	thesis	NOUN
istl-2566	1	22	by	by	ADP
istl-2566	1	23	registering	register	VERB
istl-2566	1	24	substances	substance	NOUN
istl-2566	1	25	and	and	CCONJ
istl-2566	1	26	depositing	deposit	VERB
istl-2566	1	27	in	in	ADP
istl-2566	1	28	pubchem	pubchem	PROPN
istl-2566	1	29	vincent	vincent	PROPN
istl-2566	1	30	f.	f.	PROPN
istl-2566	1	31	scalfani	scalfani	VERB
istl-2566	1	32	science	science	NOUN
istl-2566	1	33	and	and	CCONJ
istl-2566	1	34	engineering	engineering	NOUN
istl-2566	1	35	librarian	librarian	ADJ
istl-2566	1	36	rodgers	rodger	NOUN
istl-2566	1	37	library	library	PROPN
istl-2566	1	38	for	for	ADP
istl-2566	1	39	science	science	NOUN
istl-2566	1	40	and	and	CCONJ
istl-2566	1	41	engineering	engineer	VERB
istl-2566	1	42	the	the	DET
istl-2566	1	43	university	university	PROPN
istl-2566	1	44	of	of	ADP
istl-2566	1	45	alabama	alabama	PROPN
istl-2566	1	46	tuscaloosa	tuscaloosa	PROPN
istl-2566	1	47	,	,	PUNCT
istl-2566	1	48	al	al	PROPN
istl-2566	1	49	vfscalfani@ua.edu	vfscalfani@ua.edu	PROPN
istl-2566	1	50	barbara	barbara	PROPN
istl-2566	1	51	j.	j.	PROPN
istl-2566	1	52	dahlbach	dahlbach	PROPN
istl-2566	1	53	annex	annex	PROPN
istl-2566	1	54	services	service	NOUN
istl-2566	1	55	librarian	librarian	ADJ
istl-2566	1	56	libraries	library	NOUN
istl-2566	1	57	'	'	PART
istl-2566	1	58	annex	annex	PROPN
istl-2566	1	59	the	the	DET
istl-2566	1	60	university	university	PROPN
istl-2566	1	61	of	of	ADP
istl-2566	1	62	alabama	alabama	PROPN
istl-2566	1	63	tuscaloosa	tuscaloosa	PROPN
istl-2566	1	64	,	,	PUNCT
istl-2566	1	65	al	al	PROPN
istl-2566	1	66	bdahlbac@ua.edu	bdahlbac@ua.edu	PROPN
istl-2566	1	67	jacob	jacob	PROPN
istl-2566	1	68	robertson	robertson	PROPN
istl-2566	1	69	institutional	institutional	PROPN
istl-2566	1	70	repository	repository	PROPN
istl-2566	1	71	specialist	specialist	NOUN
istl-2566	1	72	gorgas	gorgas	PROPN
istl-2566	1	73	library	library	PROPN
istl-2566	1	74	the	the	DET
istl-2566	1	75	university	university	PROPN
istl-2566	1	76	of	of	ADP
istl-2566	1	77	alabama	alabama	PROPN
istl-2566	1	78	tuscaloosa	tuscaloosa	PROPN
istl-2566	1	79	,	,	PUNCT
istl-2566	1	80	al	al	PROPN
istl-2566	1	81	jrrobertson3@ua.edu	jrrobertson3@ua.edu	PROPN
istl-2566	1	82	abstract	abstract	PROPN
istl-2566	1	83	chemical	chemical	NOUN
istl-2566	1	84	substances	substance	NOUN
istl-2566	1	85	from	from	ADP
istl-2566	1	86	theses	thesis	NOUN
istl-2566	1	87	are	be	AUX
istl-2566	1	88	not	not	PART
istl-2566	1	89	widely	widely	ADV
istl-2566	1	90	accessible	accessible	ADJ
istl-2566	1	91	as	as	ADP
istl-2566	1	92	searchable	searchable	ADJ
istl-2566	1	93	machine	machine	NOUN
istl-2566	1	94	-	-	PUNCT
istl-2566	1	95	readable	readable	ADJ
istl-2566	1	96	formats	format	NOUN
istl-2566	1	97	.	.	PUNCT
istl-2566	2	1	in	in	ADP
istl-2566	2	2	this	this	DET
istl-2566	2	3	article	article	NOUN
istl-2566	2	4	,	,	PUNCT
istl-2566	2	5	we	we	PRON
istl-2566	2	6	describe	describe	VERB
istl-2566	2	7	our	our	PRON
istl-2566	2	8	workflow	workflow	NOUN
istl-2566	2	9	for	for	ADP
istl-2566	2	10	extracting	extract	VERB
istl-2566	2	11	,	,	PUNCT
istl-2566	2	12	registering	register	VERB
istl-2566	2	13	,	,	PUNCT
istl-2566	2	14	and	and	CCONJ
istl-2566	2	15	sharing	share	VERB
istl-2566	2	16	chemical	chemical	ADJ
istl-2566	2	17	substances	substance	NOUN
istl-2566	2	18	from	from	ADP
istl-2566	2	19	the	the	DET
istl-2566	2	20	university	university	PROPN
istl-2566	2	21	of	of	ADP
istl-2566	2	22	alabama	alabama	PROPN
istl-2566	2	23	theses	theses	PROPN
istl-2566	2	24	to	to	PART
istl-2566	2	25	enhance	enhance	VERB
istl-2566	2	26	discovery	discovery	NOUN
istl-2566	2	27	.	.	PUNCT
istl-2566	3	1	in	in	ADP
istl-2566	3	2	total	total	PROPN
istl-2566	3	3	,	,	PUNCT
istl-2566	3	4	73	73	NUM
istl-2566	3	5	theses	thesis	NOUN
istl-2566	3	6	were	be	AUX
istl-2566	3	7	selected	select	VERB
istl-2566	3	8	for	for	ADP
istl-2566	3	9	the	the	DET
istl-2566	3	10	project	project	NOUN
istl-2566	3	11	,	,	PUNCT
istl-2566	3	12	resulting	result	VERB
istl-2566	3	13	in	in	ADP
istl-2566	3	14	about	about	ADV
istl-2566	3	15	3,000	3,000	NUM
istl-2566	3	16	substances	substance	NOUN
istl-2566	3	17	registered	register	VERB
istl-2566	3	18	using	use	VERB
istl-2566	3	19	the	the	DET
istl-2566	3	20	iupac	iupac	PROPN
istl-2566	3	21	international	international	PROPN
istl-2566	3	22	chemical	chemical	PROPN
istl-2566	3	23	identifier	identifier	NOUN
istl-2566	3	24	and	and	CCONJ
istl-2566	3	25	deposited	deposit	VERB
istl-2566	3	26	in	in	ADP
istl-2566	3	27	pubchem	pubchem	NOUN
istl-2566	3	28	as	as	ADP
istl-2566	3	29	either	either	DET
istl-2566	3	30	structure	structure	NOUN
istl-2566	3	31	-	-	PUNCT
istl-2566	3	32	data	data	NOUN
istl-2566	3	33	files	file	NOUN
istl-2566	3	34	or	or	CCONJ
istl-2566	3	35	simplified	simplify	VERB
istl-2566	3	36	molecular	molecular	ADJ
istl-2566	3	37	-	-	PUNCT
istl-2566	3	38	input	input	NOUN
istl-2566	3	39	line	line	NOUN
istl-2566	3	40	-	-	PUNCT
istl-2566	3	41	entry	entry	NOUN
istl-2566	3	42	system	system	NOUN
istl-2566	3	43	notations	notation	NOUN
istl-2566	3	44	.	.	PUNCT
istl-2566	4	1	in	in	ADP
istl-2566	4	2	addition	addition	NOUN
istl-2566	4	3	to	to	ADP
istl-2566	4	4	substances	substance	NOUN
istl-2566	4	5	being	be	AUX
istl-2566	4	6	deposited	deposit	VERB
istl-2566	4	7	in	in	ADP
istl-2566	4	8	pubchem	pubchem	NOUN
istl-2566	4	9	,	,	PUNCT
istl-2566	4	10	an	an	DET
istl-2566	4	11	archive	archive	NOUN
istl-2566	4	12	copy	copy	NOUN
istl-2566	4	13	was	be	AUX
istl-2566	4	14	also	also	ADV
istl-2566	4	15	deposited	deposit	VERB
istl-2566	4	16	in	in	ADP
istl-2566	4	17	the	the	DET
istl-2566	4	18	university	university	PROPN
istl-2566	4	19	of	of	ADP
istl-2566	4	20	alabama	alabama	PROPN
istl-2566	4	21	institutional	institutional	ADJ
istl-2566	4	22	repository	repository	NOUN
istl-2566	4	23	.	.	PUNCT
istl-2566	5	1	the	the	DET
istl-2566	5	2	pubchem	pubchem	PROPN
istl-2566	5	3	records	record	NOUN
istl-2566	5	4	for	for	ADP
istl-2566	5	5	the	the	DET
istl-2566	5	6	substance	substance	NOUN
istl-2566	5	7	depositions	deposition	NOUN
istl-2566	5	8	include	include	VERB
istl-2566	5	9	the	the	DET
istl-2566	5	10	full	full	ADJ
istl-2566	5	11	bibliographic	bibliographic	ADJ
istl-2566	5	12	reference	reference	NOUN
istl-2566	5	13	and	and	CCONJ
istl-2566	5	14	link	link	NOUN
istl-2566	5	15	to	to	ADP
istl-2566	5	16	the	the	DET
istl-2566	5	17	thesis	thesis	NOUN
istl-2566	5	18	full	full	ADJ
istl-2566	5	19	text	text	NOUN
istl-2566	5	20	or	or	CCONJ
istl-2566	5	21	thesis	thesis	NOUN
istl-2566	5	22	metadata	metadata	PROPN
istl-2566	5	23	when	when	SCONJ
istl-2566	5	24	the	the	DET
istl-2566	5	25	full	full	ADJ
istl-2566	5	26	text	text	NOUN
istl-2566	5	27	is	be	AUX
istl-2566	5	28	not	not	PART
istl-2566	5	29	yet	yet	ADV
istl-2566	5	30	available	available	ADJ
istl-2566	5	31	.	.	PUNCT
istl-2566	6	1	excluding	exclude	VERB
istl-2566	6	2	mixtures	mixture	NOUN
istl-2566	6	3	,	,	PUNCT
istl-2566	6	4	we	we	PRON
istl-2566	6	5	found	find	VERB
istl-2566	6	6	that	that	SCONJ
istl-2566	6	7	40	40	NUM
istl-2566	6	8	%	%	NOUN
istl-2566	6	9	of	of	ADP
istl-2566	6	10	the	the	DET
istl-2566	6	11	shared	share	VERB
istl-2566	6	12	substances	substance	NOUN
istl-2566	6	13	were	be	AUX
istl-2566	6	14	new	new	ADJ
istl-2566	6	15	to	to	ADP
istl-2566	6	16	pubchem	pubchem	NOUN
istl-2566	6	17	at	at	ADP
istl-2566	6	18	the	the	DET
istl-2566	6	19	time	time	NOUN
istl-2566	6	20	of	of	ADP
istl-2566	6	21	deposition	deposition	NOUN
istl-2566	6	22	.	.	PUNCT
istl-2566	7	1	we	we	PRON
istl-2566	7	2	conclude	conclude	VERB
istl-2566	7	3	this	this	DET
istl-2566	7	4	article	article	NOUN
istl-2566	7	5	with	with	ADP
istl-2566	7	6	a	a	DET
istl-2566	7	7	detailed	detailed	ADJ
istl-2566	7	8	discussion	discussion	NOUN
istl-2566	7	9	about	about	ADP
istl-2566	7	10	our	our	PRON
istl-2566	7	11	experiences	experience	NOUN
istl-2566	7	12	,	,	PUNCT
istl-2566	7	13	challenges	challenge	NOUN
istl-2566	7	14	,	,	PUNCT
istl-2566	7	15	and	and	CCONJ
istl-2566	7	16	recommendations	recommendation	NOUN
istl-2566	7	17	for	for	ADP
istl-2566	7	18	librarians	librarian	NOUN
istl-2566	7	19	and	and	CCONJ
istl-2566	7	20	curators	curator	NOUN
istl-2566	7	21	engaged	engage	VERB
istl-2566	7	22	in	in	ADP
istl-2566	7	23	sharing	share	VERB
istl-2566	7	24	chemical	chemical	NOUN
istl-2566	7	25	substance	substance	NOUN
istl-2566	7	26	data	datum	NOUN
istl-2566	7	27	from	from	ADP
istl-2566	7	28	theses	thesis	NOUN
istl-2566	7	29	and	and	CCONJ
istl-2566	7	30	similar	similar	ADJ
istl-2566	7	31	documents	document	NOUN
istl-2566	7	32	.	.	PUNCT
istl-2566	8	1	introduction	introduction	NOUN
istl-2566	8	2	and	and	CCONJ
istl-2566	8	3	literature	literature	NOUN
istl-2566	8	4	review	review	NOUN
istl-2566	8	5	chemical	chemical	NOUN
istl-2566	8	6	substances	substance	NOUN
istl-2566	8	7	are	be	AUX
istl-2566	8	8	core	core	NOUN
istl-2566	8	9	to	to	ADP
istl-2566	8	10	the	the	DET
istl-2566	8	11	organization	organization	NOUN
istl-2566	8	12	and	and	CCONJ
istl-2566	8	13	retrieval	retrieval	NOUN
istl-2566	8	14	of	of	ADP
istl-2566	8	15	chemical	chemical	ADJ
istl-2566	8	16	information	information	NOUN
istl-2566	8	17	.	.	PUNCT
istl-2566	9	1	modern	modern	ADJ
istl-2566	9	2	chemical	chemical	NOUN
istl-2566	9	3	databases	database	NOUN
istl-2566	9	4	contain	contain	VERB
istl-2566	9	5	millions	million	NOUN
istl-2566	9	6	of	of	ADP
istl-2566	9	7	substances	substance	NOUN
istl-2566	9	8	and	and	CCONJ
istl-2566	9	9	associated	associate	VERB
istl-2566	9	10	data	datum	NOUN
istl-2566	9	11	such	such	ADJ
istl-2566	9	12	as	as	ADP
istl-2566	9	13	literature	literature	NOUN
istl-2566	9	14	references	reference	NOUN
istl-2566	9	15	,	,	PUNCT
istl-2566	9	16	names	name	NOUN
istl-2566	9	17	,	,	PUNCT
istl-2566	9	18	identifiers	identifier	NOUN
istl-2566	9	19	,	,	PUNCT
istl-2566	9	20	and	and	CCONJ
istl-2566	9	21	property	property	NOUN
istl-2566	9	22	data	datum	NOUN
istl-2566	9	23	(	(	PUNCT
istl-2566	9	24	krallinger	krallinger	NOUN
istl-2566	9	25	et	et	PROPN
istl-2566	9	26	al	al	PROPN
istl-2566	9	27	.	.	PROPN
istl-2566	9	28	2017	2017	NUM
istl-2566	9	29	)	)	PUNCT
istl-2566	9	30	.	.	PUNCT
istl-2566	10	1	common	common	ADJ
istl-2566	10	2	to	to	ADP
istl-2566	10	3	all	all	DET
istl-2566	10	4	chemical	chemical	NOUN
istl-2566	10	5	databases	database	NOUN
istl-2566	10	6	is	be	AUX
istl-2566	10	7	the	the	DET
istl-2566	10	8	necessary	necessary	ADJ
istl-2566	10	9	step	step	NOUN
istl-2566	10	10	of	of	ADP
istl-2566	10	11	substance	substance	NOUN
istl-2566	10	12	data	datum	NOUN
istl-2566	10	13	entry	entry	NOUN
istl-2566	10	14	as	as	ADP
istl-2566	10	15	a	a	DET
istl-2566	10	16	machine	machine	NOUN
istl-2566	10	17	-	-	PUNCT
istl-2566	10	18	readable	readable	ADJ
istl-2566	10	19	format	format	NOUN
istl-2566	10	20	such	such	ADJ
istl-2566	10	21	as	as	ADP
istl-2566	10	22	a	a	DET
istl-2566	10	23	chemical	chemical	ADJ
istl-2566	10	24	line	line	NOUN
istl-2566	10	25	notation	notation	NOUN
istl-2566	10	26	or	or	CCONJ
istl-2566	10	27	connection	connection	NOUN
istl-2566	10	28	table	table	NOUN
istl-2566	10	29	(	(	PUNCT
istl-2566	10	30	weininger	weininger	NOUN
istl-2566	10	31	1988	1988	NUM
istl-2566	10	32	;	;	PUNCT
istl-2566	10	33	dalby	dalby	VERB
istl-2566	10	34	et	et	PROPN
istl-2566	10	35	al	al	PROPN
istl-2566	10	36	.	.	PROPN
istl-2566	10	37	1992	1992	NUM
istl-2566	10	38	;	;	PUNCT
istl-2566	10	39	heller	heller	NOUN
istl-2566	10	40	et	et	PROPN
istl-2566	10	41	al	al	PROPN
istl-2566	10	42	.	.	PROPN
istl-2566	10	43	2015	2015	NUM
istl-2566	10	44	)	)	PUNCT
istl-2566	10	45	.	.	PUNCT
istl-2566	11	1	after	after	ADP
istl-2566	11	2	substance	substance	NOUN
istl-2566	11	3	data	datum	NOUN
istl-2566	11	4	entry	entry	NOUN
istl-2566	11	5	,	,	PUNCT
istl-2566	11	6	substances	substance	NOUN
istl-2566	11	7	are	be	AUX
istl-2566	11	8	registered	register	VERB
istl-2566	11	9	(	(	PUNCT
istl-2566	11	10	warr	warr	PROPN
istl-2566	11	11	2011	2011	NUM
istl-2566	11	12	)	)	PUNCT
istl-2566	11	13	.	.	PUNCT
istl-2566	12	1	substance	substance	NOUN
istl-2566	12	2	registration	registration	NOUN
istl-2566	12	3	is	be	AUX
istl-2566	12	4	an	an	DET
istl-2566	12	5	algorithmic	algorithmic	ADJ
istl-2566	12	6	process	process	NOUN
istl-2566	12	7	that	that	PRON
istl-2566	12	8	uniquely	uniquely	ADV
istl-2566	12	9	identifies	identify	VERB
istl-2566	12	10	substances	substance	NOUN
istl-2566	12	11	so	so	SCONJ
istl-2566	12	12	that	that	SCONJ
istl-2566	12	13	duplicates	duplicate	NOUN
istl-2566	12	14	are	be	AUX
istl-2566	12	15	not	not	PART
istl-2566	12	16	inadvertently	inadvertently	ADV
istl-2566	12	17	entered	enter	VERB
istl-2566	12	18	into	into	ADP
istl-2566	12	19	the	the	DET
istl-2566	12	20	database	database	NOUN
istl-2566	12	21	(	(	PUNCT
istl-2566	12	22	buntrock	buntrock	NOUN
istl-2566	12	23	2001	2001	NUM
istl-2566	12	24	;	;	PUNCT
istl-2566	12	25	gobbi	gobbi	PROPN
istl-2566	12	26	&	&	CCONJ
istl-2566	12	27	lee	lee	PROPN
istl-2566	12	28	2012	2012	NUM
istl-2566	12	29	;	;	PUNCT
istl-2566	12	30	martin	martin	PROPN
istl-2566	12	31	et	et	PROPN
istl-2566	12	32	al	al	PROPN
istl-2566	12	33	.	.	PROPN
istl-2566	12	34	2012	2012	NUM
istl-2566	12	35	)	)	PUNCT
istl-2566	12	36	.	.	PUNCT
istl-2566	13	1	preventing	prevent	VERB
istl-2566	13	2	duplicates	duplicate	NOUN
istl-2566	13	3	ensures	ensure	VERB
istl-2566	13	4	that	that	SCONJ
istl-2566	13	5	associated	associate	VERB
istl-2566	13	6	known	know	VERB
istl-2566	13	7	data	data	NOUN
istl-2566	13	8	,	,	PUNCT
istl-2566	13	9	literature	literature	NOUN
istl-2566	13	10	references	reference	NOUN
istl-2566	13	11	,	,	PUNCT
istl-2566	13	12	and	and	CCONJ
istl-2566	13	13	identifiers	identifier	NOUN
istl-2566	13	14	can	can	AUX
istl-2566	13	15	all	all	ADV
istl-2566	13	16	be	be	AUX
istl-2566	13	17	linked	link	VERB
istl-2566	13	18	to	to	ADP
istl-2566	13	19	one	one	NUM
istl-2566	13	20	substance	substance	NOUN
istl-2566	13	21	record	record	NOUN
istl-2566	13	22	.	.	PUNCT
istl-2566	14	1	computerized	computerized	ADJ
istl-2566	14	2	chemical	chemical	NOUN
istl-2566	14	3	substance	substance	NOUN
istl-2566	14	4	registration	registration	NOUN
istl-2566	14	5	systems	system	NOUN
istl-2566	14	6	have	have	AUX
istl-2566	14	7	been	be	AUX
istl-2566	14	8	developed	develop	VERB
istl-2566	14	9	over	over	ADP
istl-2566	14	10	the	the	DET
istl-2566	14	11	past	past	ADJ
istl-2566	14	12	half	half	ADJ
istl-2566	14	13	century	century	NOUN
istl-2566	14	14	and	and	CCONJ
istl-2566	14	15	are	be	AUX
istl-2566	14	16	well	well	ADV
istl-2566	14	17	documented	document	VERB
istl-2566	14	18	in	in	ADP
istl-2566	14	19	the	the	DET
istl-2566	14	20	literature	literature	NOUN
istl-2566	14	21	.	.	PUNCT
istl-2566	15	1	examples	example	NOUN
istl-2566	15	2	of	of	ADP
istl-2566	15	3	substance	substance	NOUN
istl-2566	15	4	registration	registration	NOUN
istl-2566	15	5	systems	system	NOUN
istl-2566	15	6	include	include	VERB
istl-2566	15	7	the	the	DET
istl-2566	15	8	cas	cas	ADJ
istl-2566	15	9	registry	registry	NOUN
istl-2566	15	10	from	from	ADP
istl-2566	15	11	chemical	chemical	ADJ
istl-2566	15	12	abstracts	abstract	NOUN
istl-2566	15	13	service	service	NOUN
istl-2566	15	14	(	(	PUNCT
istl-2566	15	15	dittmar	dittmar	PROPN
istl-2566	15	16	et	et	PROPN
istl-2566	15	17	al	al	PROPN
istl-2566	15	18	.	.	PROPN
istl-2566	15	19	1976	1976	NUM
istl-2566	15	20	)	)	PUNCT
istl-2566	15	21	,	,	PUNCT
istl-2566	15	22	the	the	DET
istl-2566	15	23	beilstein	beilstein	ADJ
istl-2566	15	24	registry	registry	NOUN
istl-2566	15	25	file	file	NOUN
istl-2566	15	26	(	(	PUNCT
istl-2566	15	27	domokos	domokos	PROPN
istl-2566	15	28	1991	1991	NUM
istl-2566	15	29	)	)	PUNCT
istl-2566	15	30	,	,	PUNCT
istl-2566	15	31	gmelin	gmelin	NOUN
istl-2566	15	32	factual	factual	ADJ
istl-2566	15	33	database	database	NOUN
istl-2566	15	34	(	(	PUNCT
istl-2566	15	35	roth	roth	PROPN
istl-2566	15	36	et	et	PROPN
istl-2566	15	37	al	al	PROPN
istl-2566	15	38	.	.	PROPN
istl-2566	15	39	1992	1992	NUM
istl-2566	15	40	;	;	PUNCT
istl-2566	15	41	lawson	lawson	PROPN
istl-2566	15	42	et	et	PROPN
istl-2566	15	43	al	al	PROPN
istl-2566	15	44	.	.	PROPN
istl-2566	15	45	2014	2014	NUM
istl-2566	15	46	)	)	PUNCT
istl-2566	15	47	,	,	PUNCT
istl-2566	15	48	the	the	DET
istl-2566	15	49	pubchem	pubchem	PROPN
istl-2566	15	50	compound	compound	NOUN
istl-2566	15	51	standardization	standardization	NOUN
istl-2566	15	52	system	system	NOUN
istl-2566	15	53	(	(	PUNCT
istl-2566	15	54	kim	kim	PROPN
istl-2566	15	55	et	et	PROPN
istl-2566	15	56	al	al	PROPN
istl-2566	15	57	.	.	PUNCT
istl-2566	15	58	2016a	2016a	NUM
istl-2566	15	59	;	;	PUNCT
istl-2566	15	60	hähnke	hähnke	PROPN
istl-2566	15	61	et	et	NOUN
istl-2566	15	62	al	al	PROPN
istl-2566	15	63	.	.	PROPN
istl-2566	15	64	2018	2018	NUM
istl-2566	15	65	)	)	PUNCT
istl-2566	15	66	and	and	CCONJ
istl-2566	15	67	systems	system	NOUN
istl-2566	15	68	based	base	VERB
istl-2566	15	69	on	on	ADP
istl-2566	15	70	the	the	DET
istl-2566	15	71	iupac	iupac	PROPN
istl-2566	15	72	international	international	PROPN
istl-2566	15	73	chemical	chemical	PROPN
istl-2566	15	74	identifier	identifier	NOUN
istl-2566	15	75	(	(	PUNCT
istl-2566	15	76	inchi	inchi	PROPN
istl-2566	15	77	)	)	PUNCT
istl-2566	15	78	such	such	ADJ
istl-2566	15	79	as	as	ADP
istl-2566	15	80	unichem	unichem	PRON
istl-2566	15	81	and	and	CCONJ
istl-2566	15	82	chemspider	chemspider	NOUN
istl-2566	15	83	(	(	PUNCT
istl-2566	15	84	chambers	chamber	NOUN
istl-2566	15	85	et	et	PROPN
istl-2566	15	86	al	al	PROPN
istl-2566	15	87	.	.	PROPN
istl-2566	15	88	2013	2013	NUM
istl-2566	15	89	;	;	PUNCT
istl-2566	15	90	heller	heller	NOUN
istl-2566	15	91	et	et	PROPN
istl-2566	15	92	al	al	PROPN
istl-2566	15	93	.	.	PROPN
istl-2566	15	94	2015	2015	NUM
istl-2566	15	95	;	;	PUNCT
istl-2566	15	96	richardson	richardson	PROPN
istl-2566	15	97	2018	2018	NUM
istl-2566	15	98	)	)	PUNCT
istl-2566	15	99	.	.	PUNCT
istl-2566	16	1	major	major	ADJ
istl-2566	16	2	efforts	effort	NOUN
istl-2566	16	3	to	to	PART
istl-2566	16	4	extract	extract	VERB
istl-2566	16	5	and	and	CCONJ
istl-2566	16	6	register	register	VERB
istl-2566	16	7	substances	substance	NOUN
istl-2566	16	8	into	into	ADP
istl-2566	16	9	secondary	secondary	ADJ
istl-2566	16	10	chemical	chemical	NOUN
istl-2566	16	11	literature	literature	NOUN
istl-2566	16	12	databases	database	VERB
istl-2566	16	13	over	over	ADP
istl-2566	16	14	the	the	DET
istl-2566	16	15	past	past	ADJ
istl-2566	16	16	half	half	ADJ
istl-2566	16	17	century	century	NOUN
istl-2566	16	18	have	have	AUX
istl-2566	16	19	mainly	mainly	ADV
istl-2566	16	20	focused	focus	VERB
istl-2566	16	21	on	on	ADP
istl-2566	16	22	substances	substance	NOUN
istl-2566	16	23	from	from	ADP
istl-2566	16	24	journals	journal	NOUN
istl-2566	16	25	,	,	PUNCT
istl-2566	16	26	technical	technical	ADJ
istl-2566	16	27	reports	report	NOUN
istl-2566	16	28	,	,	PUNCT
istl-2566	16	29	and	and	CCONJ
istl-2566	16	30	patents	patent	NOUN
istl-2566	16	31	.	.	PUNCT
istl-2566	17	1	to	to	ADP
istl-2566	17	2	our	our	PRON
istl-2566	17	3	knowledge	knowledge	NOUN
istl-2566	17	4	,	,	PUNCT
istl-2566	17	5	reaxys	reaxys	NOUN
istl-2566	17	6	(	(	PUNCT
istl-2566	17	7	elsevier	elsevi	ADJ
istl-2566	17	8	2021	2021	NUM
istl-2566	17	9	)	)	PUNCT
istl-2566	17	10	and	and	CCONJ
istl-2566	17	11	pubchem	pubchem	PROPN
istl-2566	17	12	(	(	PUNCT
istl-2566	17	13	kim	kim	PROPN
istl-2566	17	14	et	et	PROPN
istl-2566	17	15	al	al	PROPN
istl-2566	17	16	.	.	PROPN
istl-2566	17	17	2016b	2016b	NUM
istl-2566	17	18	)	)	PUNCT
istl-2566	17	19	do	do	AUX
istl-2566	17	20	not	not	PART
istl-2566	17	21	contain	contain	VERB
istl-2566	17	22	thesis	thesis	NOUN
istl-2566	17	23	bibliographic	bibliographic	ADJ
istl-2566	17	24	data	datum	NOUN
istl-2566	17	25	nor	nor	CCONJ
istl-2566	17	26	substance	substance	NOUN
istl-2566	17	27	data	datum	NOUN
istl-2566	17	28	that	that	PRON
istl-2566	17	29	is	be	AUX
istl-2566	17	30	extracted	extract	VERB
istl-2566	17	31	and	and	CCONJ
istl-2566	17	32	shared	share	VERB
istl-2566	17	33	systematically	systematically	ADV
istl-2566	17	34	from	from	ADP
istl-2566	17	35	university	university	NOUN
istl-2566	17	36	theses	thesis	NOUN
istl-2566	17	37	.	.	PUNCT
istl-2566	18	1	both	both	DET
istl-2566	18	2	scifinder	scifinder	NOUN
istl-2566	18	3	(	(	PUNCT
istl-2566	18	4	gabrielson	gabrielson	NOUN
istl-2566	18	5	2018	2018	NUM
istl-2566	18	6	)	)	PUNCT
istl-2566	18	7	and	and	CCONJ
istl-2566	18	8	chemspider	chemspider	NOUN
istl-2566	18	9	(	(	PUNCT
istl-2566	18	10	pence	pence	PROPN
istl-2566	18	11	&	&	CCONJ
istl-2566	18	12	williams	williams	PROPN
istl-2566	18	13	2010	2010	NUM
istl-2566	18	14	)	)	PUNCT
istl-2566	18	15	contain	contain	VERB
istl-2566	18	16	data	datum	NOUN
istl-2566	18	17	from	from	ADP
istl-2566	18	18	the	the	DET
istl-2566	18	19	selected	select	VERB
istl-2566	18	20	organic	organic	ADJ
istl-2566	18	21	reactions	reaction	NOUN
istl-2566	18	22	database	database	NOUN
istl-2566	18	23	(	(	PUNCT
istl-2566	18	24	sord	sord	NOUN
istl-2566	18	25	)	)	PUNCT
istl-2566	18	26	(	(	PUNCT
istl-2566	18	27	garritano	garritano	NOUN
istl-2566	18	28	2013	2013	NUM
istl-2566	18	29	;	;	PUNCT
istl-2566	18	30	royal	royal	ADJ
istl-2566	18	31	society	society	NOUN
istl-2566	18	32	of	of	ADP
istl-2566	18	33	chemistry	chemistry	NOUN
istl-2566	18	34	2020	2020	NUM
istl-2566	18	35	)	)	PUNCT
istl-2566	18	36	.	.	PUNCT
istl-2566	19	1	the	the	DET
istl-2566	19	2	sord	sord	NOUN
istl-2566	19	3	database	database	NOUN
istl-2566	19	4	efforts	effort	NOUN
istl-2566	19	5	in	in	ADP
istl-2566	19	6	the	the	DET
istl-2566	19	7	early	early	ADJ
istl-2566	19	8	2000s	2000	NOUN
istl-2566	19	9	partnered	partner	VERB
istl-2566	19	10	with	with	ADP
istl-2566	19	11	academic	academic	ADJ
istl-2566	19	12	institutions	institution	NOUN
istl-2566	19	13	to	to	PART
istl-2566	19	14	gain	gain	VERB
istl-2566	19	15	access	access	NOUN
istl-2566	19	16	to	to	ADP
istl-2566	19	17	thesis	thesis	NOUN
istl-2566	19	18	collections	collection	NOUN
istl-2566	19	19	and	and	CCONJ
istl-2566	19	20	index	index	NOUN
istl-2566	19	21	reaction	reaction	NOUN
istl-2566	19	22	and	and	CCONJ
istl-2566	19	23	substance	substance	NOUN
istl-2566	19	24	data	datum	NOUN
istl-2566	19	25	(	(	PUNCT
istl-2566	19	26	wife	wife	NOUN
istl-2566	19	27	2010	2010	NUM
istl-2566	19	28	)	)	PUNCT
istl-2566	19	29	.	.	PUNCT
istl-2566	20	1	the	the	DET
istl-2566	20	2	latest	late	ADJ
istl-2566	20	3	information	information	NOUN
istl-2566	20	4	we	we	PRON
istl-2566	20	5	could	could	AUX
istl-2566	20	6	find	find	VERB
istl-2566	20	7	about	about	ADP
istl-2566	20	8	sord	sord	PROPN
istl-2566	20	9	data	data	PROPN
istl-2566	20	10	content	content	NOUN
istl-2566	20	11	suggests	suggest	VERB
istl-2566	20	12	that	that	SCONJ
istl-2566	20	13	substance	substance	NOUN
istl-2566	20	14	and	and	CCONJ
istl-2566	20	15	reaction	reaction	NOUN
istl-2566	20	16	data	datum	NOUN
istl-2566	20	17	were	be	AUX
istl-2566	20	18	extracted	extract	VERB
istl-2566	20	19	from	from	ADP
istl-2566	20	20	1,300	1,300	NUM
istl-2566	20	21	theses	thesis	NOUN
istl-2566	20	22	in	in	ADP
istl-2566	20	23	total	total	NOUN
istl-2566	20	24	,	,	PUNCT
istl-2566	20	25	mostly	mostly	ADV
istl-2566	20	26	from	from	ADP
istl-2566	20	27	europe	europe	PROPN
istl-2566	20	28	(	(	PUNCT
istl-2566	20	29	wife	wife	NOUN
istl-2566	20	30	2010	2010	NUM
istl-2566	20	31	)	)	PUNCT
istl-2566	20	32	.	.	PUNCT
istl-2566	21	1	within	within	ADP
istl-2566	21	2	scifinder	scifinder	PROPN
istl-2566	21	3	,	,	PUNCT
istl-2566	21	4	there	there	PRON
istl-2566	21	5	is	be	VERB
istl-2566	21	6	sord	sord	NOUN
istl-2566	21	7	reaction	reaction	PROPN
istl-2566	21	8	data	datum	NOUN
istl-2566	21	9	from	from	ADP
istl-2566	21	10	about	about	ADV
istl-2566	21	11	900	900	NUM
istl-2566	21	12	theses	thesis	NOUN
istl-2566	21	13	(	(	PUNCT
istl-2566	21	14	garritano	garritano	NOUN
istl-2566	21	15	2013	2013	NUM
istl-2566	21	16	)	)	PUNCT
istl-2566	21	17	.	.	PUNCT
istl-2566	22	1	and	and	CCONJ
istl-2566	22	2	within	within	ADP
istl-2566	22	3	chemspider	chemspider	NOUN
istl-2566	22	4	,	,	PUNCT
istl-2566	22	5	a	a	DET
istl-2566	22	6	data	data	NOUN
istl-2566	22	7	source	source	NOUN
istl-2566	22	8	search	search	NOUN
istl-2566	22	9	for	for	ADP
istl-2566	22	10	sord	sord	NOUN
istl-2566	22	11	reveals	reveal	VERB
istl-2566	22	12	57,000	57,000	NUM
istl-2566	22	13	substances	substance	NOUN
istl-2566	22	14	(	(	PUNCT
istl-2566	22	15	royal	royal	ADJ
istl-2566	22	16	society	society	NOUN
istl-2566	22	17	of	of	ADP
istl-2566	22	18	chemistry	chemistry	NOUN
istl-2566	22	19	2020	2020	NUM
istl-2566	22	20	)	)	PUNCT
istl-2566	22	21	.	.	PUNCT
istl-2566	23	1	the	the	DET
istl-2566	23	2	sord	sord	PROPN
istl-2566	23	3	thesis	thesis	NOUN
istl-2566	23	4	substance	substance	NOUN
istl-2566	23	5	data	datum	NOUN
istl-2566	23	6	extraction	extraction	NOUN
istl-2566	23	7	efforts	effort	NOUN
istl-2566	23	8	appear	appear	VERB
istl-2566	23	9	to	to	PART
istl-2566	23	10	no	no	ADV
istl-2566	23	11	longer	long	ADV
istl-2566	23	12	be	be	AUX
istl-2566	23	13	active	active	ADJ
istl-2566	23	14	,	,	PUNCT
istl-2566	23	15	as	as	SCONJ
istl-2566	23	16	we	we	PRON
istl-2566	23	17	were	be	AUX
istl-2566	23	18	unable	unable	ADJ
istl-2566	23	19	to	to	PART
istl-2566	23	20	locate	locate	VERB
istl-2566	23	21	a	a	DET
istl-2566	23	22	live	live	ADJ
istl-2566	23	23	website	website	NOUN
istl-2566	23	24	or	or	CCONJ
istl-2566	23	25	other	other	ADJ
istl-2566	23	26	current	current	ADJ
istl-2566	23	27	information	information	NOUN
istl-2566	23	28	about	about	ADP
istl-2566	23	29	sord	sord	NOUN
istl-2566	23	30	.	.	PUNCT
istl-2566	24	1	from	from	ADP
istl-2566	24	2	the	the	DET
istl-2566	24	3	sord	sord	NOUN
istl-2566	24	4	efforts	effort	NOUN
istl-2566	24	5	,	,	PUNCT
istl-2566	24	6	it	it	PRON
istl-2566	24	7	was	be	AUX
istl-2566	24	8	estimated	estimate	VERB
istl-2566	24	9	that	that	SCONJ
istl-2566	24	10	80	80	NUM
istl-2566	24	11	%	%	NOUN
istl-2566	24	12	of	of	ADP
istl-2566	24	13	content	content	NOUN
istl-2566	24	14	in	in	ADP
istl-2566	24	15	university	university	NOUN
istl-2566	24	16	chemistry	chemistry	NOUN
istl-2566	24	17	theses	theses	PROPN
istl-2566	24	18	is	be	AUX
istl-2566	24	19	never	never	ADV
istl-2566	24	20	published	publish	VERB
istl-2566	24	21	and	and	CCONJ
istl-2566	24	22	was	be	AUX
istl-2566	24	23	termed	term	VERB
istl-2566	24	24	“	"	PUNCT
istl-2566	24	25	lost	lose	VERB
istl-2566	24	26	chemistry	chemistry	NOUN
istl-2566	24	27	”	"	PUNCT
istl-2566	24	28	(	(	PUNCT
istl-2566	24	29	de	de	X
istl-2566	24	30	laet	laet	ADJ
istl-2566	24	31	et	et	PROPN
istl-2566	24	32	al	al	PROPN
istl-2566	24	33	.	.	PROPN
istl-2566	24	34	2000	2000	NUM
istl-2566	24	35	;	;	PUNCT
istl-2566	24	36	wife	wife	NOUN
istl-2566	24	37	2010	2010	NUM
istl-2566	24	38	)	)	PUNCT
istl-2566	24	39	.	.	PUNCT
istl-2566	25	1	in	in	ADP
istl-2566	25	2	addition	addition	NOUN
istl-2566	25	3	to	to	ADP
istl-2566	25	4	sord	sord	PROPN
istl-2566	25	5	content	content	PROPN
istl-2566	25	6	in	in	ADP
istl-2566	25	7	cas	cas	PROPN
istl-2566	25	8	databases	database	NOUN
istl-2566	25	9	,	,	PUNCT
istl-2566	25	10	cas	cas	PROPN
istl-2566	25	11	indexes	index	NOUN
istl-2566	25	12	thesis	thesis	NOUN
istl-2566	25	13	references	reference	NOUN
istl-2566	25	14	(	(	PUNCT
istl-2566	25	15	caplus	caplus	NOUN
istl-2566	25	16	)	)	PUNCT
istl-2566	25	17	and	and	CCONJ
istl-2566	25	18	registers	register	VERB
istl-2566	25	19	substances	substance	NOUN
istl-2566	25	20	from	from	ADP
istl-2566	25	21	theses	thesis	NOUN
istl-2566	25	22	into	into	ADP
istl-2566	25	23	the	the	DET
istl-2566	25	24	cas	cas	ADJ
istl-2566	25	25	registry	registry	NOUN
istl-2566	25	26	(	(	PUNCT
istl-2566	25	27	garritano	garritano	NOUN
istl-2566	25	28	2013	2013	NUM
istl-2566	25	29	)	)	PUNCT
istl-2566	25	30	.	.	PUNCT
istl-2566	26	1	as	as	ADP
istl-2566	26	2	of	of	ADP
istl-2566	26	3	july	july	PROPN
istl-2566	26	4	2020	2020	NUM
istl-2566	26	5	,	,	PUNCT
istl-2566	26	6	cas	cas	PROPN
istl-2566	26	7	has	have	VERB
istl-2566	26	8	about	about	ADV
istl-2566	26	9	670,000	670,000	NUM
istl-2566	26	10	thesis	thesis	NOUN
istl-2566	26	11	and	and	CCONJ
istl-2566	26	12	dissertation	dissertation	NOUN
istl-2566	26	13	records	record	NOUN
istl-2566	26	14	with	with	ADP
istl-2566	26	15	substance	substance	NOUN
istl-2566	26	16	and	and	CCONJ
istl-2566	26	17	concept	concept	NOUN
istl-2566	26	18	indexing	indexing	NOUN
istl-2566	26	19	in	in	ADP
istl-2566	26	20	caplus	caplus	NOUN
istl-2566	26	21	(	(	PUNCT
istl-2566	26	22	chemical	chemical	NOUN
istl-2566	26	23	abstracts	abstract	NOUN
istl-2566	26	24	service	service	NOUN
istl-2566	26	25	,	,	PUNCT
istl-2566	26	26	personal	personal	ADJ
istl-2566	26	27	communication	communication	NOUN
istl-2566	26	28	,	,	PUNCT
istl-2566	26	29	july	july	PROPN
istl-2566	26	30	13	13	NUM
istl-2566	26	31	,	,	PUNCT
istl-2566	26	32	2020	2020	NUM
istl-2566	26	33	)	)	PUNCT
istl-2566	26	34	.	.	PUNCT
istl-2566	27	1	in	in	ADP
istl-2566	27	2	our	our	PRON
istl-2566	27	3	experience	experience	NOUN
istl-2566	27	4	with	with	ADP
istl-2566	27	5	the	the	DET
istl-2566	27	6	chemistry	chemistry	NOUN
istl-2566	27	7	theses	thesis	NOUN
istl-2566	27	8	at	at	ADP
istl-2566	27	9	the	the	DET
istl-2566	27	10	university	university	PROPN
istl-2566	27	11	of	of	ADP
istl-2566	27	12	alabama	alabama	PROPN
istl-2566	27	13	(	(	PUNCT
istl-2566	27	14	ua	ua	PROPN
istl-2566	27	15	)	)	PUNCT
istl-2566	27	16	,	,	PUNCT
istl-2566	27	17	the	the	DET
istl-2566	27	18	cas	cas	PROPN
istl-2566	27	19	registry	registry	NOUN
istl-2566	27	20	typically	typically	ADV
istl-2566	27	21	contains	contain	VERB
istl-2566	27	22	two	two	NUM
istl-2566	27	23	or	or	CCONJ
istl-2566	27	24	less	less	ADV
istl-2566	27	25	registered	register	VERB
istl-2566	27	26	substances	substance	NOUN
istl-2566	27	27	for	for	ADP
istl-2566	27	28	each	each	DET
istl-2566	27	29	ua	ua	NOUN
istl-2566	27	30	chemistry	chemistry	NOUN
istl-2566	27	31	thesis	thesis	NOUN
istl-2566	27	32	.	.	PUNCT
istl-2566	28	1	as	as	SCONJ
istl-2566	28	2	chemistry	chemistry	NOUN
istl-2566	28	3	theses	these	VERB
istl-2566	28	4	with	with	ADP
istl-2566	28	5	a	a	DET
istl-2566	28	6	synthetic	synthetic	ADJ
istl-2566	28	7	focus	focus	NOUN
istl-2566	28	8	typically	typically	ADV
istl-2566	28	9	contain	contain	VERB
istl-2566	28	10	many	many	ADV
istl-2566	28	11	more	more	ADJ
istl-2566	28	12	than	than	ADP
istl-2566	28	13	a	a	DET
istl-2566	28	14	handful	handful	NOUN
istl-2566	28	15	of	of	ADP
istl-2566	28	16	synthesized	synthesize	VERB
istl-2566	28	17	substances	substance	NOUN
istl-2566	28	18	,	,	PUNCT
istl-2566	28	19	there	there	PRON
istl-2566	28	20	is	be	VERB
istl-2566	28	21	an	an	DET
istl-2566	28	22	opportunity	opportunity	NOUN
istl-2566	28	23	to	to	PART
istl-2566	28	24	increase	increase	VERB
istl-2566	28	25	thesis	thesis	NOUN
istl-2566	28	26	substance	substance	NOUN
istl-2566	28	27	registration	registration	NOUN
istl-2566	28	28	,	,	PUNCT
istl-2566	28	29	sharing	sharing	NOUN
istl-2566	28	30	,	,	PUNCT
istl-2566	28	31	and	and	CCONJ
istl-2566	28	32	ultimately	ultimately	ADV
istl-2566	28	33	information	information	NOUN
istl-2566	28	34	discovery	discovery	NOUN
istl-2566	28	35	.	.	PUNCT
istl-2566	29	1	there	there	PRON
istl-2566	29	2	are	be	VERB
istl-2566	29	3	few	few	ADJ
istl-2566	29	4	reports	report	NOUN
istl-2566	29	5	in	in	ADP
istl-2566	29	6	the	the	DET
istl-2566	29	7	literature	literature	NOUN
istl-2566	29	8	focused	focus	VERB
istl-2566	29	9	specifically	specifically	ADV
istl-2566	29	10	on	on	ADP
istl-2566	29	11	extracting	extract	VERB
istl-2566	29	12	substance	substance	NOUN
istl-2566	29	13	and	and	CCONJ
istl-2566	29	14	related	related	ADJ
istl-2566	29	15	data	datum	NOUN
istl-2566	29	16	from	from	ADP
istl-2566	29	17	university	university	NOUN
istl-2566	29	18	chemistry	chemistry	NOUN
istl-2566	29	19	theses	thesis	NOUN
istl-2566	29	20	.	.	PUNCT
istl-2566	30	1	in	in	ADP
istl-2566	30	2	fact	fact	NOUN
istl-2566	30	3	,	,	PUNCT
istl-2566	30	4	we	we	PRON
istl-2566	30	5	are	be	AUX
istl-2566	30	6	only	only	ADV
istl-2566	30	7	aware	aware	ADJ
istl-2566	30	8	of	of	ADP
istl-2566	30	9	two	two	NUM
istl-2566	30	10	such	such	ADJ
istl-2566	30	11	reports	report	NOUN
istl-2566	30	12	,	,	PUNCT
istl-2566	30	13	one	one	NUM
istl-2566	30	14	from	from	ADP
istl-2566	30	15	downing	down	VERB
istl-2566	30	16	et	et	PROPN
istl-2566	30	17	al	al	PROPN
istl-2566	30	18	.	.	PUNCT
istl-2566	31	1	(	(	PUNCT
istl-2566	31	2	2010	2010	NUM
istl-2566	31	3	)	)	PUNCT
istl-2566	31	4	and	and	CCONJ
istl-2566	31	5	one	one	NUM
istl-2566	31	6	from	from	ADP
istl-2566	31	7	andrews	andrew	NOUN
istl-2566	32	1	et	et	PROPN
istl-2566	33	1	al	al	PROPN
istl-2566	33	2	.	.	PUNCT
istl-2566	33	3	(	(	PUNCT
istl-2566	33	4	2016	2016	NUM
istl-2566	33	5	)	)	PUNCT
istl-2566	33	6	.	.	PUNCT
istl-2566	34	1	downing	down	VERB
istl-2566	34	2	et	et	PROPN
istl-2566	34	3	al	al	PROPN
istl-2566	34	4	.	.	PROPN
istl-2566	35	1	developed	develop	VERB
istl-2566	35	2	automated	automate	VERB
istl-2566	35	3	text	text	NOUN
istl-2566	35	4	mining	mining	NOUN
istl-2566	35	5	tools	tool	NOUN
istl-2566	35	6	to	to	PART
istl-2566	35	7	extract	extract	VERB
istl-2566	35	8	chemical	chemical	ADJ
istl-2566	35	9	information	information	NOUN
istl-2566	35	10	such	such	ADJ
istl-2566	35	11	as	as	ADP
istl-2566	35	12	names	name	NOUN
istl-2566	35	13	,	,	PUNCT
istl-2566	35	14	experimental	experimental	ADJ
istl-2566	35	15	procedures	procedure	NOUN
istl-2566	35	16	,	,	PUNCT
istl-2566	35	17	and	and	CCONJ
istl-2566	35	18	characterization	characterization	NOUN
istl-2566	35	19	data	datum	NOUN
istl-2566	35	20	directly	directly	ADV
istl-2566	35	21	from	from	ADP
istl-2566	35	22	pdf	pdf	NOUN
istl-2566	35	23	/	/	SYM
istl-2566	35	24	docx	docx	VERB
istl-2566	35	25	electronic	electronic	ADJ
istl-2566	35	26	theses	thesis	NOUN
istl-2566	35	27	.	.	PUNCT
istl-2566	36	1	about	about	ADV
istl-2566	36	2	40	40	NUM
istl-2566	36	3	theses	thesis	NOUN
istl-2566	36	4	were	be	AUX
istl-2566	36	5	used	use	VERB
istl-2566	36	6	as	as	ADP
istl-2566	36	7	a	a	DET
istl-2566	36	8	proof	proof	NOUN
istl-2566	36	9	of	of	ADP
istl-2566	36	10	concept	concept	NOUN
istl-2566	36	11	and	and	CCONJ
istl-2566	36	12	the	the	DET
istl-2566	36	13	extracted	extract	VERB
istl-2566	36	14	data	datum	NOUN
istl-2566	36	15	was	be	AUX
istl-2566	36	16	arranged	arrange	VERB
istl-2566	36	17	in	in	ADP
istl-2566	36	18	markup	markup	PROPN
istl-2566	36	19	language	language	NOUN
istl-2566	36	20	format	format	NOUN
istl-2566	36	21	to	to	PART
istl-2566	36	22	allow	allow	VERB
istl-2566	36	23	for	for	ADP
istl-2566	36	24	data	datum	NOUN
istl-2566	36	25	repository	repository	NOUN
istl-2566	36	26	storage	storage	NOUN
istl-2566	36	27	and	and	CCONJ
istl-2566	36	28	semantic	semantic	ADJ
istl-2566	36	29	searching	searching	NOUN
istl-2566	36	30	.	.	PUNCT
istl-2566	37	1	there	there	PRON
istl-2566	37	2	were	be	VERB
istl-2566	37	3	many	many	ADJ
istl-2566	37	4	challenges	challenge	NOUN
istl-2566	37	5	with	with	ADP
istl-2566	37	6	data	datum	NOUN
istl-2566	37	7	cleanup	cleanup	NOUN
istl-2566	37	8	and	and	CCONJ
istl-2566	37	9	false	false	ADJ
istl-2566	37	10	hits	hit	NOUN
istl-2566	37	11	,	,	PUNCT
istl-2566	37	12	but	but	CCONJ
istl-2566	37	13	overall	overall	ADV
istl-2566	37	14	,	,	PUNCT
istl-2566	37	15	their	their	PRON
istl-2566	37	16	approach	approach	NOUN
istl-2566	37	17	validated	validate	VERB
istl-2566	37	18	the	the	DET
istl-2566	37	19	use	use	NOUN
istl-2566	37	20	of	of	ADP
istl-2566	37	21	machine	machine	NOUN
istl-2566	37	22	extraction	extraction	NOUN
istl-2566	37	23	of	of	ADP
istl-2566	37	24	chemical	chemical	ADJ
istl-2566	37	25	data	datum	NOUN
istl-2566	37	26	from	from	ADP
istl-2566	37	27	theses	thesis	NOUN
istl-2566	37	28	with	with	ADP
istl-2566	37	29	acceptable	acceptable	ADJ
istl-2566	37	30	precision	precision	NOUN
istl-2566	37	31	in	in	ADP
istl-2566	37	32	some	some	DET
istl-2566	37	33	cases	case	NOUN
istl-2566	37	34	(	(	PUNCT
istl-2566	37	35	downing	down	VERB
istl-2566	37	36	et	et	PROPN
istl-2566	37	37	al	al	PROPN
istl-2566	37	38	.	.	PROPN
istl-2566	37	39	2010	2010	NUM
istl-2566	37	40	)	)	PUNCT
istl-2566	37	41	.	.	PUNCT
istl-2566	38	1	it	it	PRON
istl-2566	38	2	is	be	AUX
istl-2566	38	3	worth	worth	ADJ
istl-2566	38	4	noting	note	VERB
istl-2566	38	5	that	that	SCONJ
istl-2566	38	6	there	there	PRON
istl-2566	38	7	is	be	VERB
istl-2566	38	8	a	a	DET
istl-2566	38	9	large	large	ADJ
istl-2566	38	10	amount	amount	NOUN
istl-2566	38	11	of	of	ADP
istl-2566	38	12	related	related	ADJ
istl-2566	38	13	ongoing	ongoing	ADJ
istl-2566	38	14	research	research	NOUN
istl-2566	38	15	and	and	CCONJ
istl-2566	38	16	available	available	ADJ
istl-2566	38	17	tools	tool	NOUN
istl-2566	38	18	in	in	ADP
istl-2566	38	19	cheminformatics	cheminformatic	NOUN
istl-2566	38	20	focused	focus	VERB
istl-2566	38	21	on	on	ADP
istl-2566	38	22	automated	automate	VERB
istl-2566	38	23	data	datum	NOUN
istl-2566	38	24	extraction	extraction	NOUN
istl-2566	38	25	from	from	ADP
istl-2566	38	26	digital	digital	ADJ
istl-2566	38	27	documents	document	NOUN
istl-2566	38	28	,	,	PUNCT
istl-2566	38	29	including	include	VERB
istl-2566	38	30	methods	method	NOUN
istl-2566	38	31	to	to	PART
istl-2566	38	32	optically	optically	ADV
istl-2566	38	33	recognize	recognize	VERB
istl-2566	38	34	chemical	chemical	ADJ
istl-2566	38	35	substance	substance	NOUN
istl-2566	38	36	diagrams	diagram	NOUN
istl-2566	38	37	and	and	CCONJ
istl-2566	38	38	convert	convert	VERB
istl-2566	38	39	them	they	PRON
istl-2566	38	40	to	to	ADP
istl-2566	38	41	machine	machine	NOUN
istl-2566	38	42	-	-	PUNCT
istl-2566	38	43	readable	readable	ADJ
istl-2566	38	44	format	format	NOUN
istl-2566	38	45	(	(	PUNCT
istl-2566	38	46	filippov	filippov	PROPN
istl-2566	38	47	&	&	CCONJ
istl-2566	38	48	nicklaus	nicklaus	PROPN
istl-2566	38	49	2009	2009	NUM
istl-2566	38	50	;	;	PUNCT
istl-2566	38	51	valko	valko	PROPN
istl-2566	38	52	&	&	CCONJ
istl-2566	38	53	johnson	johnson	PROPN
istl-2566	38	54	2009	2009	NUM
istl-2566	38	55	;	;	PUNCT
istl-2566	38	56	swain	swain	PROPN
istl-2566	38	57	&	&	CCONJ
istl-2566	38	58	cole	cole	PROPN
istl-2566	38	59	2016	2016	NUM
istl-2566	38	60	;	;	PUNCT
istl-2566	38	61	krallinger	krallinger	NOUN
istl-2566	38	62	et	et	PROPN
istl-2566	39	1	al	al	PROPN
istl-2566	39	2	.	.	PROPN
istl-2566	39	3	2017	2017	NUM
istl-2566	39	4	;	;	PUNCT
istl-2566	39	5	nguyen	nguyen	PROPN
istl-2566	39	6	et	et	PROPN
istl-2566	39	7	al	al	PROPN
istl-2566	39	8	.	.	PROPN
istl-2566	39	9	2019	2019	NUM
istl-2566	39	10	)	)	PUNCT
istl-2566	40	1	.	.	PUNCT
istl-2566	41	1	however	however	ADV
istl-2566	41	2	,	,	PUNCT
istl-2566	41	3	the	the	DET
istl-2566	41	4	downing	downing	ADJ
istl-2566	41	5	et	et	NOUN
istl-2566	42	1	al	al	PROPN
istl-2566	42	2	.	.	PUNCT
istl-2566	43	1	(	(	PUNCT
istl-2566	43	2	2010	2010	NUM
istl-2566	43	3	)	)	PUNCT
istl-2566	43	4	article	article	NOUN
istl-2566	43	5	is	be	AUX
istl-2566	43	6	the	the	DET
istl-2566	43	7	only	only	ADJ
istl-2566	43	8	article	article	NOUN
istl-2566	43	9	we	we	PRON
istl-2566	43	10	are	be	AUX
istl-2566	43	11	aware	aware	ADJ
istl-2566	43	12	of	of	ADP
istl-2566	43	13	that	that	PRON
istl-2566	43	14	systematically	systematically	ADV
istl-2566	43	15	evaluates	evaluate	VERB
istl-2566	43	16	machine	machine	NOUN
istl-2566	43	17	extraction	extraction	NOUN
istl-2566	43	18	of	of	ADP
istl-2566	43	19	chemistry	chemistry	NOUN
istl-2566	43	20	thesis	thesis	NOUN
istl-2566	43	21	data	datum	NOUN
istl-2566	43	22	.	.	PUNCT
istl-2566	44	1	we	we	PRON
istl-2566	44	2	suspect	suspect	VERB
istl-2566	44	3	many	many	ADJ
istl-2566	44	4	of	of	ADP
istl-2566	44	5	these	these	DET
istl-2566	44	6	automated	automate	VERB
istl-2566	44	7	text	text	NOUN
istl-2566	44	8	and	and	CCONJ
istl-2566	44	9	chemical	chemical	NOUN
istl-2566	44	10	substance	substance	NOUN
istl-2566	44	11	recognition	recognition	NOUN
istl-2566	44	12	methods	method	NOUN
istl-2566	44	13	could	could	AUX
istl-2566	44	14	certainly	certainly	ADV
istl-2566	44	15	be	be	AUX
istl-2566	44	16	applied	apply	VERB
istl-2566	44	17	to	to	ADP
istl-2566	44	18	thesis	thesis	NOUN
istl-2566	44	19	documents	document	NOUN
istl-2566	44	20	,	,	PUNCT
istl-2566	44	21	but	but	CCONJ
istl-2566	44	22	the	the	DET
istl-2566	44	23	focus	focus	NOUN
istl-2566	44	24	has	have	AUX
istl-2566	44	25	been	be	AUX
istl-2566	44	26	on	on	ADP
istl-2566	44	27	other	other	ADJ
istl-2566	44	28	documents	document	NOUN
istl-2566	44	29	like	like	ADP
istl-2566	44	30	patents	patent	NOUN
istl-2566	44	31	and	and	CCONJ
istl-2566	44	32	journals	journal	NOUN
istl-2566	44	33	.	.	PUNCT
istl-2566	45	1	more	more	ADV
istl-2566	45	2	recently	recently	ADV
istl-2566	45	3	,	,	PUNCT
istl-2566	45	4	andrews	andrews	PROPN
istl-2566	45	5	et	et	PROPN
istl-2566	45	6	al	al	PROPN
istl-2566	45	7	.	.	PUNCT
istl-2566	46	1	(	(	PUNCT
istl-2566	46	2	2016	2016	NUM
istl-2566	46	3	)	)	PUNCT
istl-2566	46	4	reported	report	VERB
istl-2566	46	5	on	on	ADP
istl-2566	46	6	an	an	DET
istl-2566	46	7	initiative	initiative	NOUN
istl-2566	46	8	that	that	PRON
istl-2566	46	9	extracted	extract	VERB
istl-2566	46	10	substances	substance	NOUN
istl-2566	46	11	from	from	ADP
istl-2566	46	12	united	united	PROPN
istl-2566	46	13	kingdom	kingdom	PROPN
istl-2566	46	14	chemistry	chemistry	NOUN
istl-2566	46	15	theses	thesis	NOUN
istl-2566	46	16	and	and	CCONJ
istl-2566	46	17	deposited	deposit	VERB
istl-2566	46	18	the	the	DET
istl-2566	46	19	substances	substance	NOUN
istl-2566	46	20	publicly	publicly	ADV
istl-2566	46	21	in	in	ADP
istl-2566	46	22	chemspider	chemspider	NOUN
istl-2566	46	23	.	.	PUNCT
istl-2566	47	1	after	after	ADP
istl-2566	47	2	an	an	DET
istl-2566	47	3	initial	initial	ADJ
istl-2566	47	4	evaluation	evaluation	NOUN
istl-2566	47	5	of	of	ADP
istl-2566	47	6	substance	substance	NOUN
istl-2566	47	7	optical	optical	ADJ
istl-2566	47	8	recognition	recognition	NOUN
istl-2566	47	9	software	software	NOUN
istl-2566	47	10	,	,	PUNCT
istl-2566	47	11	andrews	andrews	PROPN
istl-2566	47	12	et	et	PROPN
istl-2566	47	13	al	al	PROPN
istl-2566	47	14	.	.	PROPN
istl-2566	47	15	selected	select	VERB
istl-2566	47	16	a	a	DET
istl-2566	47	17	manual	manual	ADJ
istl-2566	47	18	extraction	extraction	NOUN
istl-2566	47	19	workflow	workflow	NOUN
istl-2566	47	20	largely	largely	ADV
istl-2566	47	21	due	due	ADP
istl-2566	47	22	to	to	ADP
istl-2566	47	23	the	the	DET
istl-2566	47	24	initial	initial	ADJ
istl-2566	47	25	uncertainty	uncertainty	NOUN
istl-2566	47	26	of	of	ADP
istl-2566	47	27	potential	potential	ADJ
istl-2566	47	28	copyright	copyright	NOUN
istl-2566	47	29	restrictions	restriction	NOUN
istl-2566	47	30	associated	associate	VERB
istl-2566	47	31	with	with	ADP
istl-2566	47	32	automated	automate	VERB
istl-2566	47	33	extraction	extraction	NOUN
istl-2566	47	34	and	and	CCONJ
istl-2566	47	35	complexities	complexity	NOUN
istl-2566	47	36	associated	associate	VERB
istl-2566	47	37	with	with	ADP
istl-2566	47	38	validating	validate	VERB
istl-2566	47	39	the	the	DET
istl-2566	47	40	accuracy	accuracy	NOUN
istl-2566	47	41	of	of	ADP
istl-2566	47	42	machine	machine	NOUN
istl-2566	47	43	extracted	extract	VERB
istl-2566	47	44	substances	substance	NOUN
istl-2566	47	45	.	.	PUNCT
istl-2566	48	1	in	in	ADP
istl-2566	48	2	total	total	NOUN
istl-2566	48	3	,	,	PUNCT
istl-2566	48	4	about	about	ADV
istl-2566	48	5	45,000	45,000	NUM
istl-2566	48	6	substances	substance	NOUN
istl-2566	48	7	from	from	ADP
istl-2566	48	8	over	over	ADP
istl-2566	48	9	700	700	NUM
istl-2566	48	10	chemistry	chemistry	NOUN
istl-2566	48	11	theses	thesis	NOUN
istl-2566	48	12	were	be	AUX
istl-2566	48	13	manually	manually	ADV
istl-2566	48	14	extracted	extract	VERB
istl-2566	48	15	,	,	PUNCT
istl-2566	48	16	redrawn	redrawn	NOUN
istl-2566	48	17	,	,	PUNCT
istl-2566	48	18	encoded	encode	VERB
istl-2566	48	19	in	in	ADP
istl-2566	48	20	machine	machine	NOUN
istl-2566	48	21	format	format	NOUN
istl-2566	48	22	and	and	CCONJ
istl-2566	48	23	deposited	deposit	VERB
istl-2566	48	24	publicly	publicly	ADV
istl-2566	48	25	in	in	ADP
istl-2566	48	26	chemspider	chemspider	NOUN
istl-2566	48	27	(	(	PUNCT
istl-2566	48	28	andrews	andrew	NOUN
istl-2566	48	29	et	et	PROPN
istl-2566	48	30	al	al	PROPN
istl-2566	48	31	.	.	PROPN
istl-2566	48	32	2016	2016	NUM
istl-2566	48	33	)	)	PUNCT
istl-2566	48	34	.	.	PUNCT
istl-2566	49	1	importantly	importantly	ADV
istl-2566	49	2	,	,	PUNCT
istl-2566	49	3	the	the	DET
istl-2566	49	4	bibliographic	bibliographic	ADJ
istl-2566	49	5	information	information	NOUN
istl-2566	49	6	was	be	AUX
istl-2566	49	7	submitted	submit	VERB
istl-2566	49	8	along	along	ADP
istl-2566	49	9	with	with	ADP
istl-2566	49	10	the	the	DET
istl-2566	49	11	substances	substance	NOUN
istl-2566	49	12	,	,	PUNCT
istl-2566	49	13	which	which	PRON
istl-2566	49	14	greatly	greatly	ADV
istl-2566	49	15	enhances	enhance	VERB
istl-2566	49	16	the	the	DET
istl-2566	49	17	discovery	discovery	NOUN
istl-2566	49	18	of	of	ADP
istl-2566	49	19	the	the	DET
istl-2566	49	20	data	datum	NOUN
istl-2566	49	21	as	as	ADV
istl-2566	49	22	well	well	ADV
istl-2566	49	23	as	as	ADP
istl-2566	49	24	providing	provide	VERB
istl-2566	49	25	a	a	DET
istl-2566	49	26	provenance	provenance	NOUN
istl-2566	49	27	record	record	NOUN
istl-2566	49	28	for	for	ADP
istl-2566	49	29	users	user	NOUN
istl-2566	49	30	.	.	PUNCT
istl-2566	50	1	about	about	ADV
istl-2566	50	2	70	70	NUM
istl-2566	50	3	%	%	NOUN
istl-2566	50	4	of	of	ADP
istl-2566	50	5	the	the	DET
istl-2566	50	6	substances	substance	NOUN
istl-2566	50	7	were	be	AUX
istl-2566	50	8	new	new	ADJ
istl-2566	50	9	to	to	PART
istl-2566	50	10	chemspider	chemspider	VERB
istl-2566	50	11	at	at	ADP
istl-2566	50	12	the	the	DET
istl-2566	50	13	time	time	NOUN
istl-2566	50	14	of	of	ADP
istl-2566	50	15	deposition	deposition	NOUN
istl-2566	50	16	,	,	PUNCT
istl-2566	50	17	which	which	PRON
istl-2566	50	18	is	be	AUX
istl-2566	50	19	close	close	ADJ
istl-2566	50	20	to	to	ADP
istl-2566	50	21	the	the	DET
istl-2566	50	22	estimate	estimate	NOUN
istl-2566	50	23	of	of	ADP
istl-2566	50	24	80	80	NUM
istl-2566	50	25	%	%	NOUN
istl-2566	50	26	“	"	PUNCT
istl-2566	50	27	lost	lose	VERB
istl-2566	50	28	chemistry	chemistry	NOUN
istl-2566	50	29	”	"	PUNCT
istl-2566	50	30	from	from	ADP
istl-2566	50	31	wife	wife	NOUN
istl-2566	50	32	(	(	PUNCT
istl-2566	50	33	2010	2010	NUM
istl-2566	50	34	)	)	PUNCT
istl-2566	50	35	and	and	CCONJ
istl-2566	50	36	de	de	PROPN
istl-2566	50	37	laet	laet	ADJ
istl-2566	50	38	et	et	PROPN
istl-2566	51	1	al	al	PROPN
istl-2566	51	2	.	.	PUNCT
istl-2566	51	3	(	(	PUNCT
istl-2566	51	4	2000	2000	NUM
istl-2566	51	5	)	)	PUNCT
istl-2566	51	6	.	.	PUNCT
istl-2566	52	1	interestingly	interestingly	ADV
istl-2566	52	2	,	,	PUNCT
istl-2566	52	3	chemistry	chemistry	NOUN
istl-2566	52	4	theses	thesis	NOUN
istl-2566	52	5	are	be	AUX
istl-2566	52	6	rarely	rarely	ADV
istl-2566	52	7	cited	cite	VERB
istl-2566	52	8	in	in	ADP
istl-2566	52	9	the	the	DET
istl-2566	52	10	chemical	chemical	NOUN
istl-2566	52	11	literature	literature	NOUN
istl-2566	52	12	.	.	PUNCT
istl-2566	53	1	for	for	ADP
istl-2566	53	2	example	example	NOUN
istl-2566	53	3	,	,	PUNCT
istl-2566	53	4	an	an	DET
istl-2566	53	5	analysis	analysis	NOUN
istl-2566	53	6	of	of	ADP
istl-2566	53	7	chemistry	chemistry	NOUN
istl-2566	53	8	theses	thesis	NOUN
istl-2566	53	9	at	at	ADP
istl-2566	53	10	mississippi	mississippi	PROPN
istl-2566	53	11	state	state	PROPN
istl-2566	53	12	university	university	PROPN
istl-2566	53	13	(	(	PUNCT
istl-2566	53	14	zhang	zhang	PROPN
istl-2566	53	15	2013	2013	NUM
istl-2566	53	16	)	)	PUNCT
istl-2566	53	17	and	and	CCONJ
istl-2566	53	18	the	the	DET
istl-2566	53	19	university	university	PROPN
istl-2566	53	20	of	of	ADP
istl-2566	53	21	texas	texas	PROPN
istl-2566	53	22	at	at	ADP
istl-2566	53	23	austin	austin	PROPN
istl-2566	53	24	(	(	PUNCT
istl-2566	53	25	flaxbart	flaxbart	PROPN
istl-2566	53	26	2018	2018	NUM
istl-2566	53	27	)	)	PUNCT
istl-2566	53	28	found	find	VERB
istl-2566	53	29	that	that	SCONJ
istl-2566	53	30	citations	citation	NOUN
istl-2566	53	31	to	to	ADP
istl-2566	53	32	theses	thesis	NOUN
istl-2566	53	33	amounted	amount	VERB
istl-2566	53	34	to	to	ADP
istl-2566	53	35	less	less	ADJ
istl-2566	53	36	than	than	ADP
istl-2566	53	37	one	one	NUM
istl-2566	53	38	percent	percent	NOUN
istl-2566	53	39	of	of	ADP
istl-2566	53	40	the	the	DET
istl-2566	53	41	total	total	ADJ
istl-2566	53	42	citations	citation	NOUN
istl-2566	53	43	.	.	PUNCT
istl-2566	54	1	similar	similar	ADJ
istl-2566	54	2	results	result	NOUN
istl-2566	54	3	were	be	AUX
istl-2566	54	4	reported	report	VERB
istl-2566	54	5	in	in	ADP
istl-2566	54	6	a	a	DET
istl-2566	54	7	recent	recent	ADJ
istl-2566	54	8	analysis	analysis	NOUN
istl-2566	54	9	of	of	ADP
istl-2566	54	10	citations	citation	NOUN
istl-2566	54	11	in	in	ADP
istl-2566	54	12	ten	ten	NUM
istl-2566	54	13	different	different	ADJ
istl-2566	54	14	american	american	ADJ
istl-2566	54	15	chemical	chemical	PROPN
istl-2566	54	16	society	society	PROPN
istl-2566	54	17	journals	journal	NOUN
istl-2566	54	18	where	where	SCONJ
istl-2566	54	19	the	the	DET
istl-2566	54	20	citations	citation	NOUN
istl-2566	54	21	for	for	ADP
istl-2566	54	22	“	"	PUNCT
istl-2566	54	23	other	other	ADJ
istl-2566	54	24	”	"	PUNCT
istl-2566	54	25	information	information	NOUN
istl-2566	54	26	types	type	NOUN
istl-2566	54	27	,	,	PUNCT
istl-2566	54	28	which	which	PRON
istl-2566	54	29	includes	include	VERB
istl-2566	54	30	theses	thesis	NOUN
istl-2566	54	31	,	,	PUNCT
istl-2566	54	32	were	be	AUX
istl-2566	54	33	found	find	VERB
istl-2566	54	34	to	to	PART
istl-2566	54	35	be	be	AUX
istl-2566	54	36	less	less	ADJ
istl-2566	54	37	than	than	ADP
istl-2566	54	38	5	5	NUM
istl-2566	54	39	%	%	NOUN
istl-2566	54	40	(	(	PUNCT
istl-2566	54	41	rose	rose	NOUN
istl-2566	54	42	-	-	PUNCT
istl-2566	54	43	wiles	wile	NOUN
istl-2566	54	44	&	&	CCONJ
istl-2566	54	45	marzabadi	marzabadi	NOUN
istl-2566	54	46	2018	2018	NUM
istl-2566	54	47	)	)	PUNCT
istl-2566	54	48	.	.	PUNCT
istl-2566	55	1	the	the	DET
istl-2566	55	2	lack	lack	NOUN
istl-2566	55	3	of	of	ADP
istl-2566	55	4	discoverability	discoverability	NOUN
istl-2566	55	5	and	and	CCONJ
istl-2566	55	6	access	access	NOUN
istl-2566	55	7	to	to	ADP
istl-2566	55	8	theses	thesis	NOUN
istl-2566	55	9	,	,	PUNCT
istl-2566	55	10	including	include	VERB
istl-2566	55	11	any	any	DET
istl-2566	55	12	substance	substance	NOUN
istl-2566	55	13	content	content	NOUN
istl-2566	55	14	,	,	PUNCT
istl-2566	55	15	could	could	AUX
istl-2566	55	16	be	be	AUX
istl-2566	55	17	one	one	NUM
istl-2566	55	18	factor	factor	NOUN
istl-2566	55	19	contributing	contribute	VERB
istl-2566	55	20	to	to	ADP
istl-2566	55	21	low	low	ADJ
istl-2566	55	22	chemistry	chemistry	NOUN
istl-2566	55	23	thesis	thesis	NOUN
istl-2566	55	24	citation	citation	NOUN
istl-2566	55	25	counts	count	NOUN
istl-2566	55	26	.	.	PUNCT
istl-2566	56	1	we	we	PRON
istl-2566	56	2	recognize	recognize	VERB
istl-2566	56	3	this	this	PRON
istl-2566	56	4	is	be	AUX
istl-2566	56	5	a	a	DET
istl-2566	56	6	minor	minor	ADJ
istl-2566	56	7	factor	factor	NOUN
istl-2566	56	8	as	as	ADP
istl-2566	56	9	peer	peer	NOUN
istl-2566	56	10	-	-	PUNCT
istl-2566	56	11	reviewed	review	VERB
istl-2566	56	12	articles	article	NOUN
istl-2566	56	13	are	be	AUX
istl-2566	56	14	the	the	DET
istl-2566	56	15	main	main	ADJ
istl-2566	56	16	information	information	NOUN
istl-2566	56	17	resource	resource	NOUN
istl-2566	56	18	used	use	VERB
istl-2566	56	19	in	in	ADP
istl-2566	56	20	chemistry	chemistry	NOUN
istl-2566	56	21	(	(	PUNCT
istl-2566	56	22	flaxbart	flaxbart	PROPN
istl-2566	56	23	2018	2018	NUM
istl-2566	56	24	)	)	PUNCT
istl-2566	56	25	.	.	PUNCT
istl-2566	57	1	regardless	regardless	ADV
istl-2566	57	2	,	,	PUNCT
istl-2566	57	3	it	it	PRON
istl-2566	57	4	is	be	AUX
istl-2566	57	5	evident	evident	ADJ
istl-2566	57	6	that	that	SCONJ
istl-2566	57	7	chemistry	chemistry	NOUN
istl-2566	57	8	theses	these	VERB
istl-2566	57	9	contain	contain	VERB
istl-2566	57	10	useful	useful	ADJ
istl-2566	57	11	data	datum	NOUN
istl-2566	57	12	such	such	ADJ
istl-2566	57	13	as	as	ADP
istl-2566	57	14	substances	substance	NOUN
istl-2566	57	15	that	that	PRON
istl-2566	57	16	are	be	AUX
istl-2566	57	17	currently	currently	ADV
istl-2566	57	18	not	not	PART
istl-2566	57	19	electronically	electronically	ADV
istl-2566	57	20	discoverable	discoverable	ADJ
istl-2566	57	21	in	in	ADP
istl-2566	57	22	chemical	chemical	ADJ
istl-2566	57	23	databases	database	NOUN
istl-2566	57	24	and	and	CCONJ
istl-2566	57	25	,	,	PUNCT
istl-2566	57	26	therefore	therefore	ADV
istl-2566	57	27	,	,	PUNCT
istl-2566	57	28	offer	offer	VERB
istl-2566	57	29	a	a	DET
istl-2566	57	30	unique	unique	ADJ
istl-2566	57	31	opportunity	opportunity	NOUN
istl-2566	57	32	for	for	ADP
istl-2566	57	33	research	research	NOUN
istl-2566	57	34	libraries	library	NOUN
istl-2566	57	35	seeking	seek	VERB
istl-2566	57	36	to	to	PART
istl-2566	57	37	improve	improve	VERB
istl-2566	57	38	discoverability	discoverability	NOUN
istl-2566	57	39	of	of	ADP
istl-2566	57	40	chemical	chemical	ADJ
istl-2566	57	41	research	research	NOUN
istl-2566	57	42	at	at	ADP
istl-2566	57	43	their	their	PRON
istl-2566	57	44	institution	institution	NOUN
istl-2566	57	45	.	.	PUNCT
istl-2566	58	1	the	the	DET
istl-2566	58	2	recent	recent	ADJ
istl-2566	58	3	efforts	effort	NOUN
istl-2566	58	4	by	by	ADP
istl-2566	58	5	andrews	andrew	NOUN
istl-2566	58	6	et	et	PROPN
istl-2566	58	7	al	al	PROPN
istl-2566	58	8	.	.	PUNCT
istl-2566	58	9	(	(	PUNCT
istl-2566	58	10	2016	2016	NUM
istl-2566	58	11	)	)	PUNCT
istl-2566	58	12	to	to	PART
istl-2566	58	13	manually	manually	ADV
istl-2566	58	14	extract	extract	VERB
istl-2566	58	15	thesis	thesis	NOUN
istl-2566	58	16	substances	substance	NOUN
istl-2566	58	17	and	and	CCONJ
istl-2566	58	18	deposit	deposit	VERB
istl-2566	58	19	them	they	PRON
istl-2566	58	20	openly	openly	ADV
istl-2566	58	21	in	in	ADP
istl-2566	58	22	chemspider	chemspider	NOUN
istl-2566	58	23	was	be	AUX
istl-2566	58	24	a	a	DET
istl-2566	58	25	workflow	workflow	NOUN
istl-2566	58	26	we	we	PRON
istl-2566	58	27	envisioned	envision	VERB
istl-2566	58	28	could	could	AUX
istl-2566	58	29	be	be	AUX
istl-2566	58	30	adapted	adapt	VERB
istl-2566	58	31	for	for	ADP
istl-2566	58	32	research	research	NOUN
istl-2566	58	33	libraries	library	NOUN
istl-2566	58	34	;	;	PUNCT
istl-2566	58	35	that	that	PRON
istl-2566	58	36	is	be	AUX
istl-2566	58	37	,	,	PUNCT
istl-2566	58	38	subject	subject	ADJ
istl-2566	58	39	chemistry	chemistry	NOUN
istl-2566	58	40	librarians	librarian	VERB
istl-2566	58	41	along	along	ADP
istl-2566	58	42	with	with	ADP
istl-2566	58	43	data	datum	NOUN
istl-2566	58	44	repository	repository	PROPN
istl-2566	58	45	librarians	librarians	PROPN
istl-2566	58	46	could	could	AUX
istl-2566	58	47	extract	extract	VERB
istl-2566	58	48	and	and	CCONJ
istl-2566	58	49	register	register	VERB
istl-2566	58	50	substances	substance	NOUN
istl-2566	58	51	from	from	ADP
istl-2566	58	52	their	their	PRON
istl-2566	58	53	local	local	ADJ
istl-2566	58	54	university	university	NOUN
istl-2566	58	55	chemistry	chemistry	NOUN
istl-2566	58	56	theses	thesis	NOUN
istl-2566	58	57	and	and	CCONJ
istl-2566	58	58	share	share	VERB
istl-2566	58	59	them	they	PRON
istl-2566	58	60	in	in	ADP
istl-2566	58	61	public	public	ADJ
istl-2566	58	62	disciplinary	disciplinary	ADJ
istl-2566	58	63	repositories	repository	NOUN
istl-2566	58	64	such	such	ADJ
istl-2566	58	65	as	as	ADP
istl-2566	58	66	chemspider	chemspider	NOUN
istl-2566	58	67	or	or	CCONJ
istl-2566	58	68	pubchem	pubchem	NOUN
istl-2566	58	69	.	.	PUNCT
istl-2566	59	1	such	such	ADJ
istl-2566	59	2	efforts	effort	NOUN
istl-2566	59	3	would	would	AUX
istl-2566	59	4	greatly	greatly	ADV
istl-2566	59	5	enhance	enhance	VERB
istl-2566	59	6	the	the	DET
istl-2566	59	7	discovery	discovery	NOUN
istl-2566	59	8	and	and	CCONJ
istl-2566	59	9	utility	utility	NOUN
istl-2566	59	10	of	of	ADP
istl-2566	59	11	the	the	DET
istl-2566	59	12	theses	thesis	NOUN
istl-2566	59	13	,	,	PUNCT
istl-2566	59	14	as	as	SCONJ
istl-2566	59	15	users	user	NOUN
istl-2566	59	16	would	would	AUX
istl-2566	59	17	have	have	VERB
istl-2566	59	18	the	the	DET
istl-2566	59	19	ability	ability	NOUN
istl-2566	59	20	to	to	PART
istl-2566	59	21	discover	discover	VERB
istl-2566	59	22	not	not	PART
istl-2566	59	23	only	only	ADV
istl-2566	59	24	the	the	DET
istl-2566	59	25	text	text	NOUN
istl-2566	59	26	of	of	ADP
istl-2566	59	27	the	the	DET
istl-2566	59	28	thesis	thesis	NOUN
istl-2566	59	29	,	,	PUNCT
istl-2566	59	30	but	but	CCONJ
istl-2566	59	31	the	the	DET
istl-2566	59	32	actual	actual	ADJ
istl-2566	59	33	substances	substance	NOUN
istl-2566	59	34	via	via	ADP
istl-2566	59	35	standard	standard	ADJ
istl-2566	59	36	chemical	chemical	NOUN
istl-2566	59	37	specific	specific	ADJ
istl-2566	59	38	searches	search	NOUN
istl-2566	59	39	such	such	ADJ
istl-2566	59	40	as	as	ADP
istl-2566	59	41	by	by	ADP
istl-2566	59	42	molecular	molecular	ADJ
istl-2566	59	43	structure	structure	NOUN
istl-2566	59	44	,	,	PUNCT
istl-2566	59	45	formula	formula	NOUN
istl-2566	59	46	,	,	PUNCT
istl-2566	59	47	or	or	CCONJ
istl-2566	59	48	identifier	identifi	ADJ
istl-2566	59	49	.	.	PUNCT
istl-2566	60	1	as	as	SCONJ
istl-2566	60	2	we	we	PRON
istl-2566	60	3	began	begin	VERB
istl-2566	60	4	our	our	PRON
istl-2566	60	5	own	own	ADJ
istl-2566	60	6	efforts	effort	NOUN
istl-2566	60	7	to	to	PART
istl-2566	60	8	extract	extract	VERB
istl-2566	60	9	and	and	CCONJ
istl-2566	60	10	register	register	VERB
istl-2566	60	11	substances	substance	NOUN
istl-2566	60	12	from	from	ADP
istl-2566	60	13	ua	ua	PROPN
istl-2566	60	14	theses	thesis	NOUN
istl-2566	60	15	,	,	PUNCT
istl-2566	60	16	we	we	PRON
istl-2566	60	17	quickly	quickly	ADV
istl-2566	60	18	realized	realize	VERB
istl-2566	60	19	the	the	DET
istl-2566	60	20	various	various	ADJ
istl-2566	60	21	complexities	complexity	NOUN
istl-2566	60	22	of	of	ADP
istl-2566	60	23	registering	register	VERB
istl-2566	60	24	substance	substance	NOUN
istl-2566	60	25	data	datum	NOUN
istl-2566	60	26	,	,	PUNCT
istl-2566	60	27	and	and	CCONJ
istl-2566	60	28	the	the	DET
istl-2566	60	29	general	general	ADJ
istl-2566	60	30	lack	lack	NOUN
istl-2566	60	31	of	of	ADP
istl-2566	60	32	available	available	ADJ
istl-2566	60	33	detailed	detailed	ADJ
istl-2566	60	34	workflows	workflow	NOUN
istl-2566	60	35	and	and	CCONJ
istl-2566	60	36	guidelines	guideline	NOUN
istl-2566	60	37	for	for	ADP
istl-2566	60	38	the	the	DET
istl-2566	60	39	research	research	NOUN
istl-2566	60	40	library	library	NOUN
istl-2566	60	41	community	community	NOUN
istl-2566	60	42	.	.	PUNCT
istl-2566	61	1	while	while	SCONJ
istl-2566	61	2	the	the	DET
istl-2566	61	3	andrews	andrew	NOUN
istl-2566	61	4	et	et	PROPN
istl-2566	61	5	al	al	PROPN
istl-2566	61	6	.	.	PUNCT
istl-2566	62	1	(	(	PUNCT
istl-2566	62	2	2016	2016	NUM
istl-2566	62	3	)	)	PUNCT
istl-2566	62	4	report	report	NOUN
istl-2566	62	5	was	be	AUX
istl-2566	62	6	helpful	helpful	ADJ
istl-2566	62	7	to	to	PART
istl-2566	62	8	think	think	VERB
istl-2566	62	9	about	about	ADP
istl-2566	62	10	the	the	DET
istl-2566	62	11	overall	overall	ADJ
istl-2566	62	12	goals	goal	NOUN
istl-2566	62	13	and	and	CCONJ
istl-2566	62	14	significance	significance	NOUN
istl-2566	62	15	of	of	ADP
istl-2566	62	16	the	the	DET
istl-2566	62	17	project	project	NOUN
istl-2566	62	18	,	,	PUNCT
istl-2566	62	19	specific	specific	ADJ
istl-2566	62	20	workflow	workflow	ADJ
istl-2566	62	21	details	detail	NOUN
istl-2566	62	22	such	such	ADJ
istl-2566	62	23	as	as	ADP
istl-2566	62	24	how	how	SCONJ
istl-2566	62	25	to	to	PART
istl-2566	62	26	redraw	redraw	VERB
istl-2566	62	27	the	the	DET
istl-2566	62	28	substances	substance	NOUN
istl-2566	62	29	so	so	SCONJ
istl-2566	62	30	that	that	SCONJ
istl-2566	62	31	machines	machine	NOUN
istl-2566	62	32	interpret	interpret	VERB
istl-2566	62	33	them	they	PRON
istl-2566	62	34	accurately	accurately	ADV
istl-2566	62	35	,	,	PUNCT
istl-2566	62	36	how	how	SCONJ
istl-2566	62	37	to	to	PART
istl-2566	62	38	organize	organize	VERB
istl-2566	62	39	the	the	DET
istl-2566	62	40	substance	substance	NOUN
istl-2566	62	41	data	datum	NOUN
istl-2566	62	42	locally	locally	ADV
istl-2566	62	43	,	,	PUNCT
istl-2566	62	44	or	or	CCONJ
istl-2566	62	45	how	how	SCONJ
istl-2566	62	46	to	to	PART
istl-2566	62	47	create	create	VERB
istl-2566	62	48	substance	substance	NOUN
istl-2566	62	49	-	-	PUNCT
istl-2566	62	50	to	to	ADP
istl-2566	62	51	-	-	PUNCT
istl-2566	62	52	document	document	NOUN
istl-2566	62	53	links	link	NOUN
istl-2566	62	54	,	,	PUNCT
istl-2566	62	55	was	be	AUX
istl-2566	62	56	not	not	PART
istl-2566	62	57	discussed	discuss	VERB
istl-2566	62	58	in	in	ADP
istl-2566	62	59	detail	detail	NOUN
istl-2566	62	60	.	.	PUNCT
istl-2566	63	1	in	in	ADP
istl-2566	63	2	this	this	DET
istl-2566	63	3	article	article	NOUN
istl-2566	63	4	,	,	PUNCT
istl-2566	63	5	we	we	PRON
istl-2566	63	6	describe	describe	VERB
istl-2566	63	7	our	our	PRON
istl-2566	63	8	workflow	workflow	NOUN
istl-2566	63	9	and	and	CCONJ
istl-2566	63	10	results	result	VERB
istl-2566	63	11	with	with	ADP
istl-2566	63	12	registering	register	VERB
istl-2566	63	13	nearly	nearly	ADV
istl-2566	63	14	3,000	3,000	NUM
istl-2566	63	15	substances	substance	NOUN
istl-2566	63	16	from	from	ADP
istl-2566	63	17	73	73	NUM
istl-2566	63	18	ua	ua	NOUN
istl-2566	63	19	theses	thesis	NOUN
istl-2566	63	20	.	.	PUNCT
istl-2566	64	1	we	we	PRON
istl-2566	64	2	manually	manually	ADV
istl-2566	64	3	extracted	extract	VERB
istl-2566	64	4	the	the	DET
istl-2566	64	5	substances	substance	NOUN
istl-2566	64	6	,	,	PUNCT
istl-2566	64	7	encoded	encode	VERB
istl-2566	64	8	them	they	PRON
istl-2566	64	9	in	in	ADP
istl-2566	64	10	machine	machine	NOUN
istl-2566	64	11	-	-	PUNCT
istl-2566	64	12	readable	readable	ADJ
istl-2566	64	13	format	format	NOUN
istl-2566	64	14	,	,	PUNCT
istl-2566	64	15	and	and	CCONJ
istl-2566	64	16	shared	share	VERB
istl-2566	64	17	the	the	DET
istl-2566	64	18	substances	substance	NOUN
istl-2566	64	19	in	in	ADP
istl-2566	64	20	pubchem	pubchem	NOUN
istl-2566	64	21	openly	openly	ADV
istl-2566	64	22	with	with	ADP
istl-2566	64	23	links	link	NOUN
istl-2566	64	24	to	to	ADP
istl-2566	64	25	the	the	DET
istl-2566	64	26	original	original	ADJ
istl-2566	64	27	thesis	thesis	NOUN
istl-2566	64	28	document	document	NOUN
istl-2566	64	29	in	in	ADP
istl-2566	64	30	our	our	PRON
istl-2566	64	31	institutional	institutional	ADJ
istl-2566	64	32	repository	repository	NOUN
istl-2566	64	33	(	(	PUNCT
istl-2566	64	34	ua	ua	PROPN
istl-2566	64	35	ir	ir	ADV
istl-2566	64	36	)	)	PUNCT
istl-2566	64	37	or	or	CCONJ
istl-2566	64	38	library	library	NOUN
istl-2566	64	39	record	record	NOUN
istl-2566	64	40	if	if	SCONJ
istl-2566	64	41	full	full	ADJ
istl-2566	64	42	text	text	NOUN
istl-2566	64	43	was	be	AUX
istl-2566	64	44	not	not	PART
istl-2566	64	45	available	available	ADJ
istl-2566	64	46	.	.	PUNCT
istl-2566	65	1	in	in	ADP
istl-2566	65	2	addition	addition	NOUN
istl-2566	65	3	to	to	ADP
istl-2566	65	4	sharing	share	VERB
istl-2566	65	5	the	the	DET
istl-2566	65	6	data	datum	NOUN
istl-2566	65	7	openly	openly	ADV
istl-2566	65	8	in	in	ADP
istl-2566	65	9	pubchem	pubchem	NOUN
istl-2566	65	10	,	,	PUNCT
istl-2566	65	11	an	an	DET
istl-2566	65	12	archival	archival	ADJ
istl-2566	65	13	copy	copy	NOUN
istl-2566	65	14	of	of	ADP
istl-2566	65	15	the	the	DET
istl-2566	65	16	substance	substance	NOUN
istl-2566	65	17	data	datum	NOUN
istl-2566	65	18	is	be	AUX
istl-2566	65	19	available	available	ADJ
istl-2566	65	20	in	in	ADP
istl-2566	65	21	the	the	DET
istl-2566	65	22	ua	ua	NOUN
istl-2566	65	23	ir	ir	PROPN
istl-2566	65	24	,	,	PUNCT
istl-2566	65	25	and	and	CCONJ
istl-2566	65	26	all	all	DET
istl-2566	65	27	data	datum	NOUN
istl-2566	65	28	,	,	PUNCT
istl-2566	65	29	programmatic	programmatic	ADJ
istl-2566	65	30	scripts	script	NOUN
istl-2566	65	31	,	,	PUNCT
istl-2566	65	32	and	and	CCONJ
istl-2566	65	33	notes	note	NOUN
istl-2566	65	34	are	be	AUX
istl-2566	65	35	openly	openly	ADV
istl-2566	65	36	available	available	ADJ
istl-2566	65	37	in	in	ADP
istl-2566	65	38	github	github	PROPN
istl-2566	65	39	(	(	PUNCT
istl-2566	65	40	supplementary	supplementary	ADJ
istl-2566	65	41	information	information	NOUN
istl-2566	65	42	)	)	PUNCT
istl-2566	65	43	.	.	PUNCT
istl-2566	66	1	we	we	PRON
istl-2566	66	2	conclude	conclude	VERB
istl-2566	66	3	this	this	DET
istl-2566	66	4	article	article	NOUN
istl-2566	66	5	with	with	ADP
istl-2566	66	6	a	a	DET
istl-2566	66	7	discussion	discussion	NOUN
istl-2566	66	8	of	of	ADP
istl-2566	66	9	the	the	DET
istl-2566	66	10	workflow	workflow	ADJ
istl-2566	66	11	challenges	challenge	NOUN
istl-2566	66	12	and	and	CCONJ
istl-2566	66	13	our	our	PRON
istl-2566	66	14	recommendations	recommendation	NOUN
istl-2566	66	15	for	for	ADP
istl-2566	66	16	librarians	librarian	NOUN
istl-2566	66	17	and	and	CCONJ
istl-2566	66	18	curators	curator	NOUN
istl-2566	66	19	related	relate	VERB
istl-2566	66	20	to	to	ADP
istl-2566	66	21	registering	register	VERB
istl-2566	66	22	and	and	CCONJ
istl-2566	66	23	sharing	share	VERB
istl-2566	66	24	substance	substance	NOUN
istl-2566	66	25	data	datum	NOUN
istl-2566	66	26	from	from	ADP
istl-2566	66	27	university	university	NOUN
istl-2566	66	28	theses	thesis	NOUN
istl-2566	66	29	.	.	PUNCT
istl-2566	67	1	methods	method	NOUN
istl-2566	67	2	the	the	DET
istl-2566	67	3	following	follow	VERB
istl-2566	67	4	methods	method	NOUN
istl-2566	67	5	section	section	NOUN
istl-2566	67	6	was	be	AUX
istl-2566	67	7	adapted	adapt	VERB
istl-2566	67	8	from	from	ADP
istl-2566	67	9	our	our	PRON
istl-2566	67	10	github	github	PROPN
istl-2566	67	11	repository	repository	PROPN
istl-2566	67	12	readme	readme	PROPN
istl-2566	67	13	file	file	NOUN
istl-2566	67	14	(	(	PUNCT
istl-2566	67	15	scalfani	scalfani	VERB
istl-2566	67	16	2020	2020	NUM
istl-2566	67	17	)	)	PUNCT
istl-2566	67	18	.	.	PUNCT
istl-2566	68	1	the	the	DET
istl-2566	68	2	github	github	PROPN
istl-2566	68	3	repository	repository	PROPN
istl-2566	68	4	contains	contain	VERB
istl-2566	68	5	all	all	DET
istl-2566	68	6	data	datum	NOUN
istl-2566	68	7	,	,	PUNCT
istl-2566	68	8	scripts	script	NOUN
istl-2566	68	9	,	,	PUNCT
istl-2566	68	10	and	and	CCONJ
istl-2566	68	11	working	work	VERB
istl-2566	68	12	notes	note	NOUN
istl-2566	68	13	from	from	ADP
istl-2566	68	14	this	this	DET
istl-2566	68	15	project	project	NOUN
istl-2566	68	16	.	.	PUNCT
istl-2566	69	1	theses	thesis	NOUN
istl-2566	69	2	selected	select	VERB
istl-2566	69	3	a	a	DET
istl-2566	69	4	total	total	NOUN
istl-2566	69	5	of	of	ADP
istl-2566	69	6	73	73	NUM
istl-2566	69	7	ua	ua	PROPN
istl-2566	69	8	chemistry	chemistry	NOUN
istl-2566	69	9	ph.d	ph.d	PROPN
istl-2566	69	10	.	.	PUNCT
istl-2566	70	1	or	or	CCONJ
istl-2566	70	2	m.s	m.s	PROPN
istl-2566	70	3	.	.	PROPN
istl-2566	70	4	theses	theses	PROPN
istl-2566	70	5	were	be	AUX
istl-2566	70	6	used	use	VERB
istl-2566	70	7	.	.	PUNCT
istl-2566	71	1	theses	theses	PROPN
istl-2566	71	2	selected	select	VERB
istl-2566	71	3	were	be	AUX
istl-2566	71	4	related	relate	VERB
istl-2566	71	5	to	to	ADP
istl-2566	71	6	organic	organic	ADJ
istl-2566	71	7	chemistry	chemistry	NOUN
istl-2566	71	8	and	and	CCONJ
istl-2566	71	9	contained	contain	VERB
istl-2566	71	10	synthetic	synthetic	ADJ
istl-2566	71	11	details	detail	NOUN
istl-2566	71	12	for	for	ADP
istl-2566	71	13	small	small	ADJ
istl-2566	71	14	molecule	molecule	NOUN
istl-2566	71	15	preparations	preparation	NOUN
istl-2566	71	16	.	.	PUNCT
istl-2566	72	1	all	all	DET
istl-2566	72	2	theses	thesis	NOUN
istl-2566	72	3	were	be	AUX
istl-2566	72	4	not	not	PART
istl-2566	72	5	embargoed	embargoed	ADJ
istl-2566	72	6	;	;	PUNCT
istl-2566	72	7	theses	thesis	NOUN
istl-2566	72	8	selected	select	VERB
istl-2566	72	9	were	be	AUX
istl-2566	72	10	fully	fully	ADV
istl-2566	72	11	available	available	ADJ
istl-2566	72	12	for	for	ADP
istl-2566	72	13	public	public	ADJ
istl-2566	72	14	use	use	NOUN
istl-2566	72	15	.	.	PUNCT
istl-2566	73	1	nearly	nearly	ADV
istl-2566	73	2	all	all	PRON
istl-2566	73	3	theses	thesis	NOUN
istl-2566	73	4	selected	select	VERB
istl-2566	73	5	were	be	AUX
istl-2566	73	6	from	from	ADP
istl-2566	73	7	1984	1984	NUM
istl-2566	73	8	through	through	ADP
istl-2566	73	9	2019	2019	NUM
istl-2566	73	10	.	.	PUNCT
istl-2566	74	1	the	the	DET
istl-2566	74	2	few	few	ADJ
istl-2566	74	3	exceptions	exception	NOUN
istl-2566	74	4	include	include	VERB
istl-2566	74	5	three	three	NUM
istl-2566	74	6	theses	thesis	NOUN
istl-2566	74	7	from	from	ADP
istl-2566	74	8	the	the	DET
istl-2566	74	9	1960s	1960	NOUN
istl-2566	74	10	and	and	CCONJ
istl-2566	74	11	one	one	NUM
istl-2566	74	12	thesis	thesis	NOUN
istl-2566	74	13	from	from	ADP
istl-2566	74	14	1929	1929	NUM
istl-2566	74	15	.	.	PUNCT
istl-2566	75	1	the	the	DET
istl-2566	75	2	thesis	thesis	NOUN
istl-2566	75	3	date	date	NOUN
istl-2566	75	4	was	be	AUX
istl-2566	75	5	not	not	PART
istl-2566	75	6	the	the	DET
istl-2566	75	7	primary	primary	ADJ
istl-2566	75	8	selection	selection	NOUN
istl-2566	75	9	criteria	criterion	NOUN
istl-2566	75	10	;	;	PUNCT
istl-2566	75	11	theses	thesis	NOUN
istl-2566	75	12	were	be	AUX
istl-2566	75	13	selected	select	VERB
istl-2566	75	14	based	base	VERB
istl-2566	75	15	on	on	ADP
istl-2566	75	16	their	their	PRON
istl-2566	75	17	organic	organic	ADJ
istl-2566	75	18	chemistry	chemistry	NOUN
istl-2566	75	19	content	content	NOUN
istl-2566	75	20	as	as	SCONJ
istl-2566	75	21	we	we	PRON
istl-2566	75	22	discovered	discover	VERB
istl-2566	75	23	them	they	PRON
istl-2566	75	24	.	.	PUNCT
istl-2566	76	1	about	about	ADV
istl-2566	76	2	30	30	NUM
istl-2566	76	3	%	%	NOUN
istl-2566	76	4	of	of	ADP
istl-2566	76	5	the	the	DET
istl-2566	76	6	theses	thesis	NOUN
istl-2566	76	7	were	be	AUX
istl-2566	76	8	available	available	ADJ
istl-2566	76	9	as	as	ADP
istl-2566	76	10	full	full	ADJ
istl-2566	76	11	-	-	PUNCT
istl-2566	76	12	text	text	NOUN
istl-2566	76	13	pdfs	pdfs	NOUN
istl-2566	76	14	.	.	PUNCT
istl-2566	77	1	the	the	DET
istl-2566	77	2	full	full	ADJ
istl-2566	77	3	-	-	PUNCT
istl-2566	77	4	text	text	NOUN
istl-2566	77	5	pdfs	pdfs	NOUN
istl-2566	77	6	were	be	AUX
istl-2566	77	7	mostly	mostly	ADV
istl-2566	77	8	theses	theses	ADJ
istl-2566	77	9	that	that	PRON
istl-2566	77	10	were	be	AUX
istl-2566	77	11	born	bear	VERB
istl-2566	77	12	-	-	PUNCT
istl-2566	77	13	digital	digital	PROPN
istl-2566	77	14	(	(	PUNCT
istl-2566	77	15	post-2009	post-2009	NOUN
istl-2566	77	16	)	)	PUNCT
istl-2566	77	17	;	;	PUNCT
istl-2566	77	18	a	a	DET
istl-2566	77	19	few	few	ADJ
istl-2566	77	20	were	be	AUX
istl-2566	77	21	retroactively	retroactively	ADV
istl-2566	77	22	digitally	digitally	ADV
istl-2566	77	23	scanned	scan	VERB
istl-2566	77	24	.	.	PUNCT
istl-2566	78	1	software	software	NOUN
istl-2566	78	2	environment	environment	NOUN
istl-2566	78	3	all	all	DET
istl-2566	78	4	software	software	NOUN
istl-2566	78	5	and	and	CCONJ
istl-2566	78	6	data	datum	NOUN
istl-2566	78	7	analysis	analysis	NOUN
istl-2566	78	8	were	be	AUX
istl-2566	78	9	run	run	VERB
istl-2566	78	10	on	on	ADP
istl-2566	78	11	linux	linux	PROPN
istl-2566	78	12	ubuntu	ubuntu	PROPN
istl-2566	78	13	18.04	18.04	NUM
istl-2566	78	14	,	,	PUNCT
istl-2566	78	15	with	with	ADP
istl-2566	78	16	the	the	DET
istl-2566	78	17	exception	exception	NOUN
istl-2566	78	18	of	of	ADP
istl-2566	78	19	bio	bio	ADJ
istl-2566	78	20	-	-	PROPN
istl-2566	78	21	rad	rad	PROPN
istl-2566	78	22	knowitall	knowitall	PROPN
istl-2566	78	23	chemwindow	chemwindow	PROPN
istl-2566	78	24	2018	2018	NUM
istl-2566	78	25	(	(	PUNCT
istl-2566	78	26	wiley	wiley	ADJ
istl-2566	78	27	science	science	NOUN
istl-2566	78	28	solutions	solution	NOUN
istl-2566	78	29	2020	2020	NUM
istl-2566	78	30	)	)	PUNCT
istl-2566	78	31	,	,	PUNCT
istl-2566	78	32	which	which	PRON
istl-2566	78	33	was	be	AUX
istl-2566	78	34	run	run	VERB
istl-2566	78	35	on	on	ADP
istl-2566	78	36	windows	window	NOUN
istl-2566	78	37	10	10	NUM
istl-2566	78	38	.	.	PUNCT
istl-2566	79	1	the	the	DET
istl-2566	79	2	open	open	ADJ
istl-2566	79	3	source	source	NOUN
istl-2566	79	4	rdkit	rdkit	ADJ
istl-2566	79	5	cheminformatics	cheminformatic	NOUN
istl-2566	79	6	software	software	NOUN
istl-2566	79	7	package	package	NOUN
istl-2566	79	8	v2019.09.2	v2019.09.2	PROPN
istl-2566	79	9	(	(	PUNCT
istl-2566	79	10	landrum	landrum	NOUN
istl-2566	79	11	2020	2020	NUM
istl-2566	79	12	)	)	PUNCT
istl-2566	79	13	was	be	AUX
istl-2566	79	14	installed	instal	VERB
istl-2566	79	15	in	in	ADP
istl-2566	79	16	an	an	DET
istl-2566	79	17	anaconda	anaconda	PROPN
istl-2566	79	18	3	3	NUM
istl-2566	79	19	linux	linux	PROPN
istl-2566	79	20	conda	conda	PROPN
istl-2566	79	21	environment	environment	NOUN
istl-2566	79	22	with	with	ADP
istl-2566	79	23	python	python	PROPN
istl-2566	79	24	3.6	3.6	NUM
istl-2566	79	25	.	.	PUNCT
istl-2566	79	26	substance	substance	NOUN
istl-2566	79	27	selection	selection	NOUN
istl-2566	79	28	in	in	ADP
istl-2566	79	29	general	general	ADJ
istl-2566	79	30	,	,	PUNCT
istl-2566	79	31	substances	substance	NOUN
istl-2566	79	32	selected	select	VERB
istl-2566	79	33	from	from	ADP
istl-2566	79	34	theses	thesis	NOUN
istl-2566	79	35	included	include	VERB
istl-2566	79	36	those	those	PRON
istl-2566	79	37	that	that	PRON
istl-2566	79	38	could	could	AUX
istl-2566	79	39	be	be	AUX
istl-2566	79	40	represented	represent	VERB
istl-2566	79	41	using	use	VERB
istl-2566	79	42	the	the	DET
istl-2566	79	43	machine	machine	NOUN
istl-2566	79	44	-	-	PUNCT
istl-2566	79	45	readable	readable	ADJ
istl-2566	79	46	simplified	simplified	ADJ
istl-2566	79	47	molecular	molecular	ADJ
istl-2566	79	48	-	-	PUNCT
istl-2566	79	49	input	input	NOUN
istl-2566	79	50	line	line	NOUN
istl-2566	79	51	-	-	PUNCT
istl-2566	79	52	entry	entry	NOUN
istl-2566	79	53	system	system	NOUN
istl-2566	79	54	(	(	PUNCT
istl-2566	79	55	smiles	smile	NOUN
istl-2566	79	56	)	)	PUNCT
istl-2566	79	57	line	line	NOUN
istl-2566	79	58	notation	notation	NOUN
istl-2566	79	59	(	(	PUNCT
istl-2566	79	60	weininger	weininger	NOUN
istl-2566	79	61	1988	1988	NUM
istl-2566	79	62	)	)	PUNCT
istl-2566	79	63	.	.	PUNCT
istl-2566	80	1	these	these	DET
istl-2566	80	2	substances	substance	NOUN
istl-2566	80	3	included	include	VERB
istl-2566	80	4	small	small	ADJ
istl-2566	80	5	molecule	molecule	NOUN
istl-2566	80	6	organic	organic	ADJ
istl-2566	80	7	chemistry	chemistry	NOUN
istl-2566	80	8	with	with	ADP
istl-2566	80	9	some	some	DET
istl-2566	80	10	limited	limited	ADJ
istl-2566	80	11	organometallic	organometallic	ADJ
istl-2566	80	12	and	and	CCONJ
istl-2566	80	13	coordination	coordination	NOUN
istl-2566	80	14	compounds	compound	NOUN
istl-2566	80	15	.	.	PUNCT
istl-2566	81	1	in	in	ADP
istl-2566	81	2	addition	addition	NOUN
istl-2566	81	3	,	,	PUNCT
istl-2566	81	4	selected	select	VERB
istl-2566	81	5	substances	substance	NOUN
istl-2566	81	6	had	have	AUX
istl-2566	81	7	associated	associate	VERB
istl-2566	81	8	synthetic	synthetic	ADJ
istl-2566	81	9	preparatory	preparatory	ADJ
istl-2566	81	10	procedures	procedure	NOUN
istl-2566	81	11	and	and	CCONJ
istl-2566	81	12	experimental	experimental	ADJ
istl-2566	81	13	characterization	characterization	NOUN
istl-2566	81	14	details	detail	NOUN
istl-2566	81	15	such	such	ADJ
istl-2566	81	16	as	as	ADP
istl-2566	81	17	nuclear	nuclear	ADJ
istl-2566	81	18	magnetic	magnetic	ADJ
istl-2566	81	19	resonance	resonance	NOUN
istl-2566	81	20	spectroscopy	spectroscopy	NOUN
istl-2566	81	21	,	,	PUNCT
istl-2566	81	22	infrared	infrared	ADJ
istl-2566	81	23	spectroscopy	spectroscopy	PROPN
istl-2566	81	24	,	,	PUNCT
istl-2566	81	25	melting	melting	NOUN
istl-2566	81	26	point	point	NOUN
istl-2566	81	27	,	,	PUNCT
istl-2566	81	28	elemental	elemental	ADJ
istl-2566	81	29	analysis	analysis	NOUN
istl-2566	81	30	,	,	PUNCT
istl-2566	81	31	or	or	CCONJ
istl-2566	81	32	mass	mass	ADJ
istl-2566	81	33	spectrometry	spectrometry	NOUN
istl-2566	81	34	data	datum	NOUN
istl-2566	81	35	.	.	PUNCT
istl-2566	82	1	in	in	ADP
istl-2566	82	2	rare	rare	ADJ
istl-2566	82	3	cases	case	NOUN
istl-2566	82	4	,	,	PUNCT
istl-2566	82	5	substances	substance	NOUN
istl-2566	82	6	selected	select	VERB
istl-2566	82	7	for	for	ADP
istl-2566	82	8	registration	registration	NOUN
istl-2566	82	9	included	include	VERB
istl-2566	82	10	only	only	ADV
istl-2566	82	11	a	a	DET
istl-2566	82	12	quantitative	quantitative	ADJ
istl-2566	82	13	analytical	analytical	ADJ
istl-2566	82	14	test	test	NOUN
istl-2566	82	15	.	.	PUNCT
istl-2566	83	1	the	the	DET
istl-2566	83	2	preparatory	preparatory	ADJ
istl-2566	83	3	procedures	procedure	NOUN
istl-2566	83	4	were	be	AUX
istl-2566	83	5	typically	typically	ADV
istl-2566	83	6	specific	specific	ADJ
istl-2566	83	7	to	to	ADP
istl-2566	83	8	the	the	DET
istl-2566	83	9	substance	substance	NOUN
istl-2566	83	10	,	,	PUNCT
istl-2566	83	11	however	however	ADV
istl-2566	83	12	in	in	ADP
istl-2566	83	13	certain	certain	ADJ
istl-2566	83	14	cases	case	NOUN
istl-2566	83	15	,	,	PUNCT
istl-2566	83	16	substances	substance	NOUN
istl-2566	83	17	were	be	AUX
istl-2566	83	18	selected	select	VERB
istl-2566	83	19	that	that	PRON
istl-2566	83	20	had	have	VERB
istl-2566	83	21	only	only	ADV
istl-2566	83	22	general	general	ADJ
istl-2566	83	23	synthetic	synthetic	ADJ
istl-2566	83	24	procedures	procedure	NOUN
istl-2566	83	25	associated	associate	VERB
istl-2566	83	26	with	with	ADP
istl-2566	83	27	them	they	PRON
istl-2566	83	28	;	;	PUNCT
istl-2566	83	29	that	that	PRON
istl-2566	83	30	is	be	AUX
istl-2566	83	31	,	,	PUNCT
istl-2566	83	32	when	when	SCONJ
istl-2566	83	33	the	the	DET
istl-2566	83	34	same	same	ADJ
istl-2566	83	35	reaction	reaction	NOUN
istl-2566	83	36	was	be	AUX
istl-2566	83	37	run	run	VERB
istl-2566	83	38	across	across	ADP
istl-2566	83	39	similar	similar	ADJ
istl-2566	83	40	substrates	substrate	NOUN
istl-2566	83	41	.	.	PUNCT
istl-2566	84	1	we	we	PRON
istl-2566	84	2	avoided	avoid	VERB
istl-2566	84	3	selecting	select	VERB
istl-2566	84	4	substances	substance	NOUN
istl-2566	84	5	where	where	SCONJ
istl-2566	84	6	the	the	DET
istl-2566	84	7	synthetic	synthetic	ADJ
istl-2566	84	8	preparatory	preparatory	ADJ
istl-2566	84	9	method	method	NOUN
istl-2566	84	10	,	,	PUNCT
istl-2566	84	11	as	as	SCONJ
istl-2566	84	12	noted	note	VERB
istl-2566	84	13	by	by	ADP
istl-2566	84	14	the	the	DET
istl-2566	84	15	author	author	NOUN
istl-2566	84	16	,	,	PUNCT
istl-2566	84	17	directly	directly	ADV
istl-2566	84	18	followed	follow	VERB
istl-2566	84	19	a	a	DET
istl-2566	84	20	prior	prior	ADV
istl-2566	84	21	reported	report	VERB
istl-2566	84	22	literature	literature	NOUN
istl-2566	84	23	preparation	preparation	NOUN
istl-2566	84	24	.	.	PUNCT
istl-2566	85	1	substance	substance	NOUN
istl-2566	85	2	drawing	draw	VERB
istl-2566	85	3	the	the	DET
istl-2566	85	4	majority	majority	NOUN
istl-2566	85	5	of	of	ADP
istl-2566	85	6	chemical	chemical	ADJ
istl-2566	85	7	substances	substance	NOUN
istl-2566	85	8	were	be	AUX
istl-2566	85	9	redrawn	redrawn	VERB
istl-2566	85	10	similarly	similarly	ADV
istl-2566	85	11	to	to	ADP
istl-2566	85	12	the	the	DET
istl-2566	85	13	depiction	depiction	NOUN
istl-2566	85	14	in	in	ADP
istl-2566	85	15	the	the	DET
istl-2566	85	16	theses	thesis	NOUN
istl-2566	85	17	using	use	VERB
istl-2566	85	18	chemaxon	chemaxon	NOUN
istl-2566	85	19	marvinsketch	marvinsketch	NOUN
istl-2566	85	20	v19.27.0	v19.27.0	PROPN
istl-2566	85	21	(	(	PUNCT
istl-2566	85	22	chemaxon	chemaxon	NOUN
istl-2566	85	23	2019a	2019a	NUM
istl-2566	85	24	)	)	PUNCT
istl-2566	85	25	.	.	PUNCT
istl-2566	86	1	stereochemistry	stereochemistry	NOUN
istl-2566	86	2	including	include	VERB
istl-2566	86	3	double	double	ADJ
istl-2566	86	4	bond	bond	NOUN
istl-2566	86	5	configuration	configuration	NOUN
istl-2566	86	6	and	and	CCONJ
istl-2566	86	7	chiral	chiral	ADJ
istl-2566	86	8	centers	center	NOUN
istl-2566	86	9	were	be	AUX
istl-2566	86	10	reproduced	reproduce	VERB
istl-2566	86	11	as	as	SCONJ
istl-2566	86	12	originally	originally	ADV
istl-2566	86	13	defined	define	VERB
istl-2566	86	14	.	.	PUNCT
istl-2566	87	1	in	in	ADP
istl-2566	87	2	cases	case	NOUN
istl-2566	87	3	where	where	SCONJ
istl-2566	87	4	the	the	DET
istl-2566	87	5	substance	substance	NOUN
istl-2566	87	6	name	name	NOUN
istl-2566	87	7	included	include	VERB
istl-2566	87	8	racemic	racemic	ADJ
istl-2566	87	9	notation	notation	NOUN
istl-2566	87	10	,	,	PUNCT
istl-2566	87	11	(	(	PUNCT
istl-2566	87	12	±	±	PROPN
istl-2566	87	13	)	)	PUNCT
istl-2566	87	14	,	,	PUNCT
istl-2566	87	15	both	both	DET
istl-2566	87	16	enantiomers	enantiomer	NOUN
istl-2566	87	17	were	be	AUX
istl-2566	87	18	drawn	draw	VERB
istl-2566	87	19	and	and	CCONJ
istl-2566	87	20	included	include	VERB
istl-2566	87	21	within	within	ADP
istl-2566	87	22	one	one	NUM
istl-2566	87	23	registry	registry	NOUN
istl-2566	87	24	identifier	identifier	ADV
istl-2566	87	25	.	.	PUNCT
istl-2566	88	1	in	in	ADP
istl-2566	88	2	rare	rare	ADJ
istl-2566	88	3	situations	situation	NOUN
istl-2566	88	4	where	where	SCONJ
istl-2566	88	5	the	the	DET
istl-2566	88	6	author	author	NOUN
istl-2566	88	7	defined	define	VERB
istl-2566	88	8	the	the	DET
istl-2566	88	9	stereochemistry	stereochemistry	NOUN
istl-2566	88	10	drawn	draw	VERB
istl-2566	88	11	as	as	ADP
istl-2566	88	12	absolute	absolute	ADJ
istl-2566	88	13	in	in	ADP
istl-2566	88	14	the	the	DET
istl-2566	88	15	2d	2d	NUM
istl-2566	88	16	depiction	depiction	NOUN
istl-2566	88	17	,	,	PUNCT
istl-2566	88	18	but	but	CCONJ
istl-2566	88	19	named	name	VERB
istl-2566	88	20	the	the	DET
istl-2566	88	21	compound	compound	NOUN
istl-2566	88	22	with	with	ADP
istl-2566	88	23	relative	relative	ADJ
istl-2566	88	24	notation	notation	NOUN
istl-2566	88	25	symbols	symbol	NOUN
istl-2566	88	26	,	,	PUNCT
istl-2566	88	27	r	r	NOUN
istl-2566	88	28	*	*	PUNCT
istl-2566	88	29	or	or	CCONJ
istl-2566	88	30	s	s	X
istl-2566	88	31	*	*	NOUN
istl-2566	88	32	,	,	PUNCT
istl-2566	88	33	the	the	DET
istl-2566	88	34	depiction	depiction	NOUN
istl-2566	88	35	was	be	AUX
istl-2566	88	36	considered	consider	VERB
istl-2566	88	37	the	the	DET
istl-2566	88	38	correct	correct	ADJ
istl-2566	88	39	absolute	absolute	ADJ
istl-2566	88	40	stereochemistry	stereochemistry	NOUN
istl-2566	88	41	.	.	PUNCT
istl-2566	89	1	when	when	SCONJ
istl-2566	89	2	substances	substance	NOUN
istl-2566	89	3	were	be	AUX
istl-2566	89	4	drawn	draw	VERB
istl-2566	89	5	by	by	ADP
istl-2566	89	6	an	an	DET
istl-2566	89	7	author	author	NOUN
istl-2566	89	8	with	with	ADP
istl-2566	89	9	stereo	stereo	ADJ
istl-2566	89	10	non	non	ADJ
istl-2566	89	11	-	-	ADJ
istl-2566	89	12	specific	specific	ADJ
istl-2566	89	13	wavy	wavy	NOUN
istl-2566	89	14	bonds	bond	NOUN
istl-2566	89	15	,	,	PUNCT
istl-2566	89	16	these	these	PRON
istl-2566	89	17	were	be	AUX
istl-2566	89	18	reproduced	reproduce	VERB
istl-2566	89	19	as	as	SCONJ
istl-2566	89	20	drawn	draw	VERB
istl-2566	89	21	with	with	ADP
istl-2566	89	22	the	the	DET
istl-2566	89	23	non	non	ADJ
istl-2566	89	24	-	-	ADJ
istl-2566	89	25	specific	specific	ADJ
istl-2566	89	26	stereocenters	stereocenter	NOUN
istl-2566	89	27	,	,	PUNCT
istl-2566	89	28	which	which	PRON
istl-2566	89	29	is	be	AUX
istl-2566	89	30	equivalent	equivalent	ADJ
istl-2566	89	31	to	to	PART
istl-2566	89	32	plain	plain	ADJ
istl-2566	89	33	bonds	bond	NOUN
istl-2566	89	34	(	(	PUNCT
istl-2566	89	35	brecher	brecher	NOUN
istl-2566	89	36	2006	2006	NUM
istl-2566	89	37	)	)	PUNCT
istl-2566	89	38	.	.	PUNCT
istl-2566	90	1	however	however	ADV
istl-2566	90	2	,	,	PUNCT
istl-2566	90	3	when	when	SCONJ
istl-2566	90	4	additional	additional	ADJ
istl-2566	90	5	information	information	NOUN
istl-2566	90	6	was	be	AUX
istl-2566	90	7	provided	provide	VERB
istl-2566	90	8	such	such	ADJ
istl-2566	90	9	that	that	SCONJ
istl-2566	90	10	the	the	DET
istl-2566	90	11	final	final	ADJ
istl-2566	90	12	product	product	NOUN
istl-2566	90	13	was	be	AUX
istl-2566	90	14	not	not	PART
istl-2566	90	15	an	an	DET
istl-2566	90	16	isolated	isolated	ADJ
istl-2566	90	17	stereoisomer	stereoisomer	NOUN
istl-2566	90	18	,	,	PUNCT
istl-2566	90	19	and	and	CCONJ
istl-2566	90	20	instead	instead	ADV
istl-2566	90	21	an	an	DET
istl-2566	90	22	identified	identify	VERB
istl-2566	90	23	mixture	mixture	NOUN
istl-2566	90	24	of	of	ADP
istl-2566	90	25	enantiomers	enantiomer	NOUN
istl-2566	90	26	or	or	CCONJ
istl-2566	90	27	diastereomers	diastereomer	NOUN
istl-2566	90	28	,	,	PUNCT
istl-2566	90	29	we	we	PRON
istl-2566	90	30	drew	draw	VERB
istl-2566	90	31	both	both	DET
istl-2566	90	32	substance	substance	NOUN
istl-2566	90	33	configurations	configuration	NOUN
istl-2566	90	34	and	and	CCONJ
istl-2566	90	35	combined	combine	VERB
istl-2566	90	36	them	they	PRON
istl-2566	90	37	into	into	ADP
istl-2566	90	38	one	one	NUM
istl-2566	90	39	registry	registry	NOUN
istl-2566	90	40	identifier	identifier	ADV
istl-2566	90	41	with	with	ADP
istl-2566	90	42	two	two	NUM
istl-2566	90	43	components	component	NOUN
istl-2566	90	44	.	.	PUNCT
istl-2566	91	1	in	in	ADP
istl-2566	91	2	cases	case	NOUN
istl-2566	91	3	where	where	SCONJ
istl-2566	91	4	the	the	DET
istl-2566	91	5	diastereomeric	diastereomeric	ADJ
istl-2566	91	6	mixture	mixture	NOUN
istl-2566	91	7	was	be	AUX
istl-2566	91	8	not	not	PART
istl-2566	91	9	easily	easily	ADV
istl-2566	91	10	identifiable	identifiable	ADJ
istl-2566	91	11	;	;	PUNCT
istl-2566	91	12	that	that	PRON
istl-2566	91	13	is	be	AUX
istl-2566	91	14	,	,	PUNCT
istl-2566	91	15	when	when	SCONJ
istl-2566	91	16	it	it	PRON
istl-2566	91	17	was	be	AUX
istl-2566	91	18	not	not	PART
istl-2566	91	19	clear	clear	ADJ
istl-2566	91	20	which	which	DET
istl-2566	91	21	stereocenter	stereocenter	NOUN
istl-2566	91	22	or	or	CCONJ
istl-2566	91	23	bond	bond	NOUN
istl-2566	91	24	to	to	PART
istl-2566	91	25	flip	flip	VERB
istl-2566	91	26	,	,	PUNCT
istl-2566	91	27	or	or	CCONJ
istl-2566	91	28	when	when	SCONJ
istl-2566	91	29	the	the	DET
istl-2566	91	30	diastereomeric	diastereomeric	ADJ
istl-2566	91	31	mixture	mixture	NOUN
istl-2566	91	32	was	be	AUX
istl-2566	91	33	greater	great	ADJ
istl-2566	91	34	than	than	ADP
istl-2566	91	35	two	two	NUM
istl-2566	91	36	substance	substance	NOUN
istl-2566	91	37	configurations	configuration	NOUN
istl-2566	91	38	,	,	PUNCT
istl-2566	91	39	we	we	PRON
istl-2566	91	40	drew	draw	VERB
istl-2566	91	41	those	those	DET
istl-2566	91	42	substances	substance	NOUN
istl-2566	91	43	as	as	ADP
istl-2566	91	44	stereo	stereo	ADJ
istl-2566	91	45	non	non	ADJ
istl-2566	91	46	-	-	ADJ
istl-2566	91	47	specific	specific	ADJ
istl-2566	91	48	single	single	ADJ
istl-2566	91	49	component	component	NOUN
istl-2566	91	50	substances	substance	NOUN
istl-2566	91	51	.	.	PUNCT
istl-2566	92	1	lastly	lastly	ADV
istl-2566	92	2	,	,	PUNCT
istl-2566	92	3	atropisomers	atropisomer	NOUN
istl-2566	92	4	were	be	AUX
istl-2566	92	5	encoded	encode	VERB
istl-2566	92	6	as	as	ADP
istl-2566	92	7	non	non	ADJ
istl-2566	92	8	-	-	ADJ
istl-2566	92	9	specific	specific	ADJ
istl-2566	92	10	bonds	bond	NOUN
istl-2566	92	11	.	.	PUNCT
istl-2566	93	1	for	for	ADP
istl-2566	93	2	substances	substance	NOUN
istl-2566	93	3	depicted	depict	VERB
istl-2566	93	4	as	as	ADP
istl-2566	93	5	projections	projection	NOUN
istl-2566	93	6	,	,	PUNCT
istl-2566	93	7	special	special	ADJ
istl-2566	93	8	care	care	NOUN
istl-2566	93	9	was	be	AUX
istl-2566	93	10	required	require	VERB
istl-2566	93	11	to	to	PART
istl-2566	93	12	preserve	preserve	VERB
istl-2566	93	13	the	the	DET
istl-2566	93	14	stereochemistry	stereochemistry	NOUN
istl-2566	93	15	(	(	PUNCT
istl-2566	93	16	brecher	brecher	PROPN
istl-2566	93	17	2008	2008	NUM
istl-2566	93	18	;	;	PUNCT
istl-2566	93	19	martin	martin	PROPN
istl-2566	93	20	et	et	PROPN
istl-2566	93	21	al	al	PROPN
istl-2566	93	22	.	.	PROPN
istl-2566	93	23	2012	2012	NUM
istl-2566	93	24	)	)	PUNCT
istl-2566	93	25	.	.	PUNCT
istl-2566	94	1	haworth	haworth	NOUN
istl-2566	94	2	projections	projection	NOUN
istl-2566	94	3	were	be	AUX
istl-2566	94	4	manually	manually	ADV
istl-2566	94	5	converted	convert	VERB
istl-2566	94	6	to	to	ADP
istl-2566	94	7	mills	mill	NOUN
istl-2566	94	8	skeletal	skeletal	ADJ
istl-2566	94	9	depictions	depiction	NOUN
istl-2566	94	10	(	(	PUNCT
istl-2566	94	11	brecher	brecher	NOUN
istl-2566	94	12	2006	2006	NUM
istl-2566	94	13	)	)	PUNCT
istl-2566	94	14	and	and	CCONJ
istl-2566	94	15	drawn	draw	VERB
istl-2566	94	16	in	in	ADP
istl-2566	94	17	chemaxon	chemaxon	NOUN
istl-2566	94	18	marvinsketch	marvinsketch	NOUN
istl-2566	94	19	.	.	PUNCT
istl-2566	95	1	when	when	SCONJ
istl-2566	95	2	substances	substance	NOUN
istl-2566	95	3	were	be	AUX
istl-2566	95	4	presented	present	VERB
istl-2566	95	5	as	as	ADP
istl-2566	95	6	chair	chair	NOUN
istl-2566	95	7	conformations	conformation	NOUN
istl-2566	95	8	or	or	CCONJ
istl-2566	95	9	fischer	fischer	NOUN
istl-2566	95	10	projections	projection	NOUN
istl-2566	95	11	,	,	PUNCT
istl-2566	95	12	bio	bio	PROPN
istl-2566	95	13	-	-	PROPN
istl-2566	95	14	rad	rad	PROPN
istl-2566	95	15	's	's	PART
istl-2566	95	16	knowitall	knowitall	PROPN
istl-2566	95	17	chemwindow	chemwindow	ADJ
istl-2566	95	18	2018	2018	NUM
istl-2566	95	19	software	software	NOUN
istl-2566	95	20	was	be	AUX
istl-2566	95	21	used	use	VERB
istl-2566	95	22	to	to	PART
istl-2566	95	23	draw	draw	VERB
istl-2566	95	24	the	the	DET
istl-2566	95	25	structures	structure	NOUN
istl-2566	95	26	and	and	CCONJ
istl-2566	95	27	determine	determine	VERB
istl-2566	95	28	the	the	DET
istl-2566	95	29	stereochemistry	stereochemistry	NOUN
istl-2566	95	30	automatically	automatically	ADV
istl-2566	95	31	(	(	PUNCT
istl-2566	95	32	abshear	abshear	VERB
istl-2566	95	33	et	et	PROPN
istl-2566	95	34	al	al	PROPN
istl-2566	95	35	.	.	PROPN
istl-2566	95	36	2018	2018	NUM
istl-2566	95	37	)	)	PUNCT
istl-2566	95	38	.	.	PUNCT
istl-2566	96	1	some	some	DET
istl-2566	96	2	substances	substance	NOUN
istl-2566	96	3	(	(	PUNCT
istl-2566	96	4	<	<	X
istl-2566	96	5	5	5	NUM
istl-2566	96	6	%	%	NOUN
istl-2566	96	7	estimated	estimate	VERB
istl-2566	96	8	)	)	PUNCT
istl-2566	96	9	required	require	VERB
istl-2566	96	10	adjustments	adjustment	NOUN
istl-2566	96	11	to	to	ADP
istl-2566	96	12	the	the	DET
istl-2566	96	13	original	original	ADJ
istl-2566	96	14	representation	representation	NOUN
istl-2566	96	15	to	to	PART
istl-2566	96	16	maintain	maintain	VERB
istl-2566	96	17	the	the	DET
istl-2566	96	18	correct	correct	ADJ
istl-2566	96	19	hydrogen	hydrogen	NOUN
istl-2566	96	20	count	count	NOUN
istl-2566	96	21	and	and	CCONJ
istl-2566	96	22	represent	represent	VERB
istl-2566	96	23	the	the	DET
istl-2566	96	24	structures	structure	NOUN
istl-2566	96	25	within	within	ADP
istl-2566	96	26	the	the	DET
istl-2566	96	27	limitations	limitation	NOUN
istl-2566	96	28	of	of	ADP
istl-2566	96	29	chemical	chemical	ADJ
istl-2566	96	30	valence	valence	NOUN
istl-2566	96	31	rules	rule	NOUN
istl-2566	96	32	and	and	CCONJ
istl-2566	96	33	cheminformatics	cheminformatic	NOUN
istl-2566	96	34	file	file	NOUN
istl-2566	96	35	formats	format	NOUN
istl-2566	96	36	.	.	PUNCT
istl-2566	97	1	these	these	DET
istl-2566	97	2	internal	internal	ADJ
istl-2566	97	3	adjustments	adjustment	NOUN
istl-2566	97	4	are	be	AUX
istl-2566	97	5	described	describe	VERB
istl-2566	97	6	in	in	ADP
istl-2566	97	7	scalfani	scalfani	ADJ
istl-2566	97	8	(	(	PUNCT
istl-2566	97	9	2020	2020	NUM
istl-2566	97	10	)	)	PUNCT
istl-2566	97	11	.	.	PUNCT
istl-2566	98	1	our	our	PRON
istl-2566	98	2	intention	intention	NOUN
istl-2566	98	3	was	be	AUX
istl-2566	98	4	to	to	PART
istl-2566	98	5	accurately	accurately	ADV
istl-2566	98	6	maintain	maintain	VERB
istl-2566	98	7	the	the	DET
istl-2566	98	8	author	author	NOUN
istl-2566	98	9	’s	’s	PART
istl-2566	98	10	original	original	ADJ
istl-2566	98	11	chemical	chemical	NOUN
istl-2566	98	12	structures	structure	NOUN
istl-2566	98	13	as	as	ADV
istl-2566	98	14	drawn	draw	VERB
istl-2566	98	15	.	.	PUNCT
istl-2566	99	1	as	as	ADP
istl-2566	99	2	such	such	ADJ
istl-2566	99	3	,	,	PUNCT
istl-2566	99	4	we	we	PRON
istl-2566	99	5	endeavored	endeavor	VERB
istl-2566	99	6	to	to	PART
istl-2566	99	7	keep	keep	VERB
istl-2566	99	8	these	these	DET
istl-2566	99	9	local	local	ADJ
istl-2566	99	10	business	business	NOUN
istl-2566	99	11	rules	rule	NOUN
istl-2566	99	12	(	(	PUNCT
istl-2566	99	13	hersey	hersey	NOUN
istl-2566	99	14	et	et	PROPN
istl-2566	99	15	al	al	PROPN
istl-2566	99	16	.	.	PROPN
istl-2566	99	17	2015	2015	NUM
istl-2566	99	18	)	)	PUNCT
istl-2566	99	19	to	to	ADP
istl-2566	99	20	a	a	DET
istl-2566	99	21	minimum	minimum	NOUN
istl-2566	99	22	,	,	PUNCT
istl-2566	99	23	and	and	CCONJ
istl-2566	99	24	instead	instead	ADV
istl-2566	99	25	rely	rely	VERB
istl-2566	99	26	on	on	ADP
istl-2566	99	27	the	the	DET
istl-2566	99	28	well	well	ADV
istl-2566	99	29	documented	document	VERB
istl-2566	99	30	and	and	CCONJ
istl-2566	99	31	established	establish	VERB
istl-2566	99	32	pubchem	pubchem	NOUN
istl-2566	99	33	compound	compound	NOUN
istl-2566	99	34	standardization	standardization	NOUN
istl-2566	99	35	process	process	NOUN
istl-2566	99	36	to	to	PART
istl-2566	99	37	standardize	standardize	VERB
istl-2566	99	38	the	the	DET
istl-2566	99	39	structures	structure	NOUN
istl-2566	99	40	(	(	PUNCT
istl-2566	99	41	hähnke	hähnke	PROPN
istl-2566	99	42	et	et	PROPN
istl-2566	99	43	al	al	PROPN
istl-2566	99	44	.	.	PROPN
istl-2566	99	45	2018	2018	NUM
istl-2566	99	46	)	)	PUNCT
istl-2566	99	47	.	.	PUNCT
istl-2566	100	1	generation	generation	NOUN
istl-2566	100	2	of	of	ADP
istl-2566	100	3	machine	machine	NOUN
istl-2566	100	4	-	-	PUNCT
istl-2566	100	5	readable	readable	ADJ
istl-2566	100	6	substance	substance	NOUN
istl-2566	100	7	file	file	NOUN
istl-2566	100	8	formats	format	NOUN
istl-2566	100	9	for	for	ADP
istl-2566	100	10	substances	substance	NOUN
istl-2566	100	11	drawn	draw	VERB
istl-2566	100	12	in	in	ADP
istl-2566	100	13	chemaxon	chemaxon	NOUN
istl-2566	100	14	marvinsketch	marvinsketch	NOUN
istl-2566	100	15	,	,	PUNCT
istl-2566	100	16	the	the	DET
istl-2566	100	17	representations	representation	NOUN
istl-2566	100	18	were	be	AUX
istl-2566	100	19	exported	export	VERB
istl-2566	100	20	as	as	ADP
istl-2566	100	21	chemaxon	chemaxon	NOUN
istl-2566	100	22	smiles	smile	NOUN
istl-2566	100	23	(	(	PUNCT
istl-2566	100	24	v19.27.0	v19.27.0	NOUN
istl-2566	100	25	,	,	PUNCT
istl-2566	100	26	daylight	daylight	NOUN
istl-2566	100	27	variant	variant	NOUN
istl-2566	100	28	)	)	PUNCT
istl-2566	100	29	.	.	PUNCT
istl-2566	101	1	chemaxon	chemaxon	PROPN
istl-2566	101	2	extended	extend	VERB
istl-2566	101	3	smiles	smile	NOUN
istl-2566	101	4	(	(	PUNCT
istl-2566	101	5	cxsmiles	cxsmile	NOUN
istl-2566	101	6	)	)	PUNCT
istl-2566	101	7	(	(	PUNCT
istl-2566	101	8	chemaxon	chemaxon	NOUN
istl-2566	101	9	2021	2021	NUM
istl-2566	101	10	)	)	PUNCT
istl-2566	101	11	were	be	AUX
istl-2566	101	12	used	use	VERB
istl-2566	101	13	for	for	ADP
istl-2566	101	14	substances	substance	NOUN
istl-2566	101	15	containing	contain	VERB
istl-2566	101	16	radicals	radical	NOUN
istl-2566	101	17	or	or	CCONJ
istl-2566	101	18	carbenes	carbene	NOUN
istl-2566	101	19	.	.	PUNCT
istl-2566	102	1	next	next	ADV
istl-2566	102	2	,	,	PUNCT
istl-2566	102	3	the	the	DET
istl-2566	102	4	smiles	smile	NOUN
istl-2566	102	5	were	be	AUX
istl-2566	102	6	compiled	compile	VERB
istl-2566	102	7	in	in	ADP
istl-2566	102	8	a	a	DET
istl-2566	102	9	spreadsheet	spreadsheet	NOUN
istl-2566	102	10	along	along	ADP
istl-2566	102	11	with	with	ADP
istl-2566	102	12	the	the	DET
istl-2566	102	13	thesis	thesis	ADJ
istl-2566	102	14	bibliographic	bibliographic	ADJ
istl-2566	102	15	information	information	NOUN
istl-2566	102	16	and	and	CCONJ
istl-2566	102	17	processed	process	VERB
istl-2566	102	18	with	with	ADP
istl-2566	102	19	rdkit	rdkit	ADJ
istl-2566	102	20	v2019.09.2	v2019.09.2	PROPN
istl-2566	102	21	using	use	VERB
istl-2566	102	22	a	a	DET
istl-2566	102	23	custom	custom	NOUN
istl-2566	102	24	python	python	NOUN
istl-2566	102	25	script	script	NOUN
istl-2566	102	26	to	to	PART
istl-2566	102	27	generate	generate	VERB
istl-2566	102	28	a	a	DET
istl-2566	102	29	structure	structure	NOUN
istl-2566	102	30	-	-	PUNCT
istl-2566	102	31	date	date	NOUN
istl-2566	102	32	file	file	NOUN
istl-2566	102	33	(	(	PUNCT
istl-2566	102	34	sdfile	sdfile	PROPN
istl-2566	102	35	)	)	PUNCT
istl-2566	102	36	(	(	PUNCT
istl-2566	102	37	dalby	dalby	ADP
istl-2566	102	38	et	et	PROPN
istl-2566	102	39	al	al	PROPN
istl-2566	102	40	.	.	PROPN
istl-2566	102	41	1992	1992	NUM
istl-2566	102	42	)	)	PUNCT
istl-2566	102	43	containing	contain	VERB
istl-2566	102	44	the	the	DET
istl-2566	102	45	molecular	molecular	ADJ
istl-2566	102	46	representation	representation	NOUN
istl-2566	102	47	connection	connection	NOUN
istl-2566	102	48	table	table	NOUN
istl-2566	102	49	,	,	PUNCT
istl-2566	102	50	a	a	DET
istl-2566	102	51	registry	registry	NOUN
istl-2566	102	52	identifier	identifier	NOUN
istl-2566	102	53	(	(	PUNCT
istl-2566	102	54	ualib-1	ualib-1	NOUN
istl-2566	102	55	and	and	CCONJ
istl-2566	102	56	increasing	increase	VERB
istl-2566	102	57	sequentially	sequentially	ADV
istl-2566	102	58	)	)	PUNCT
istl-2566	102	59	,	,	PUNCT
istl-2566	102	60	rdkit	rdkit	ADJ
istl-2566	102	61	calculated	calculate	VERB
istl-2566	102	62	kekule	kekule	NOUN
istl-2566	102	63	smiles	smile	NOUN
istl-2566	102	64	,	,	PUNCT
istl-2566	102	65	inchi	inchi	PROPN
istl-2566	102	66	(	(	PUNCT
istl-2566	102	67	v1.05	v1.05	PROPN
istl-2566	102	68	)	)	PUNCT
istl-2566	102	69	,	,	PUNCT
istl-2566	102	70	thesis	thesis	NOUN
istl-2566	102	71	bibliographic	bibliographic	ADJ
istl-2566	102	72	reference	reference	NOUN
istl-2566	102	73	,	,	PUNCT
istl-2566	102	74	and	and	CCONJ
istl-2566	102	75	link	link	VERB
istl-2566	102	76	to	to	ADP
istl-2566	102	77	the	the	DET
istl-2566	102	78	full	full	ADJ
istl-2566	102	79	-	-	PUNCT
istl-2566	102	80	text	text	NOUN
istl-2566	102	81	thesis	thesis	NOUN
istl-2566	102	82	or	or	CCONJ
istl-2566	102	83	library	library	NOUN
istl-2566	102	84	record	record	NOUN
istl-2566	102	85	.	.	PUNCT
istl-2566	103	1	any	any	DET
istl-2566	103	2	dative	dative	ADJ
istl-2566	103	3	bonds	bond	NOUN
istl-2566	103	4	were	be	AUX
istl-2566	103	5	then	then	ADV
istl-2566	103	6	added	add	VERB
istl-2566	103	7	to	to	ADP
istl-2566	103	8	the	the	DET
istl-2566	103	9	rdkit	rdkit	ADJ
istl-2566	103	10	processed	process	VERB
istl-2566	103	11	sdfile	sdfile	NOUN
istl-2566	103	12	manually	manually	ADV
istl-2566	103	13	using	use	VERB
istl-2566	103	14	the	the	DET
istl-2566	103	15	pubchem	pubchem	PROPN
istl-2566	103	16	nonstandard	nonstandard	PROPN
istl-2566	103	17	bond	bond	NOUN
istl-2566	103	18	syntax	syntax	NOUN
istl-2566	103	19	(	(	PUNCT
istl-2566	103	20	national	national	ADJ
istl-2566	103	21	center	center	NOUN
istl-2566	103	22	for	for	ADP
istl-2566	103	23	biotechnology	biotechnology	NOUN
istl-2566	103	24	information	information	NOUN
istl-2566	103	25	[	[	PUNCT
istl-2566	103	26	date	date	NOUN
istl-2566	103	27	unknown	unknown	ADJ
istl-2566	103	28	-	-	PUNCT
istl-2566	103	29	b	b	NOUN
istl-2566	103	30	]	]	PUNCT
istl-2566	103	31	)	)	PUNCT
istl-2566	103	32	.	.	PUNCT
istl-2566	104	1	for	for	ADP
istl-2566	104	2	substances	substance	NOUN
istl-2566	104	3	drawn	draw	VERB
istl-2566	104	4	in	in	ADP
istl-2566	104	5	knowitall	knowitall	PROPN
istl-2566	104	6	chemwindow	chemwindow	ADJ
istl-2566	104	7	2018	2018	NUM
istl-2566	104	8	,	,	PUNCT
istl-2566	104	9	the	the	DET
istl-2566	104	10	representations	representation	NOUN
istl-2566	104	11	were	be	AUX
istl-2566	104	12	exported	export	VERB
istl-2566	104	13	as	as	ADP
istl-2566	104	14	smiles	smile	NOUN
istl-2566	104	15	and	and	CCONJ
istl-2566	104	16	inchi	inchi	PROPN
istl-2566	104	17	(	(	PUNCT
istl-2566	104	18	v1.05	v1.05	PROPN
istl-2566	104	19	)	)	PUNCT
istl-2566	104	20	and	and	CCONJ
istl-2566	104	21	compiled	compile	VERB
istl-2566	104	22	into	into	ADP
istl-2566	104	23	a	a	DET
istl-2566	104	24	csv	csv	ADJ
istl-2566	104	25	spreadsheet	spreadsheet	NOUN
istl-2566	104	26	with	with	ADP
istl-2566	104	27	a	a	DET
istl-2566	104	28	substance	substance	NOUN
istl-2566	104	29	registry	registry	NOUN
istl-2566	104	30	identifier	identifier	ADV
istl-2566	104	31	,	,	PUNCT
istl-2566	104	32	thesis	thesis	NOUN
istl-2566	104	33	bibliographic	bibliographic	ADJ
istl-2566	104	34	reference	reference	NOUN
istl-2566	104	35	,	,	PUNCT
istl-2566	104	36	and	and	CCONJ
istl-2566	104	37	link	link	VERB
istl-2566	104	38	to	to	ADP
istl-2566	104	39	the	the	DET
istl-2566	104	40	full	full	ADJ
istl-2566	104	41	-	-	PUNCT
istl-2566	104	42	text	text	NOUN
istl-2566	104	43	thesis	thesis	NOUN
istl-2566	104	44	or	or	CCONJ
istl-2566	104	45	library	library	NOUN
istl-2566	104	46	record	record	NOUN
istl-2566	104	47	,	,	PUNCT
istl-2566	104	48	without	without	ADP
istl-2566	104	49	any	any	DET
istl-2566	104	50	further	further	ADJ
istl-2566	104	51	local	local	ADJ
istl-2566	104	52	processing	processing	NOUN
istl-2566	104	53	.	.	PUNCT
istl-2566	105	1	registration	registration	NOUN
istl-2566	105	2	and	and	CCONJ
istl-2566	105	3	consistency	consistency	NOUN
istl-2566	105	4	check	check	NOUN
istl-2566	105	5	using	use	VERB
istl-2566	105	6	the	the	DET
istl-2566	105	7	standard	standard	ADJ
istl-2566	105	8	inchi	inchi	PROPN
istl-2566	105	9	standard	standard	ADJ
istl-2566	105	10	inchikeys	inchikeys	PROPN
istl-2566	105	11	(	(	PUNCT
istl-2566	105	12	v1.05	v1.05	PROPN
istl-2566	105	13	)	)	PUNCT
istl-2566	105	14	were	be	AUX
istl-2566	105	15	calculated	calculate	VERB
istl-2566	105	16	from	from	ADP
istl-2566	105	17	chemaxon	chemaxon	PROPN
istl-2566	105	18	marvinsketch	marvinsketch	NOUN
istl-2566	105	19	exported	export	VERB
istl-2566	105	20	smiles	smile	NOUN
istl-2566	105	21	using	use	VERB
istl-2566	105	22	the	the	DET
istl-2566	105	23	chemaxon	chemaxon	PROPN
istl-2566	105	24	command	command	NOUN
istl-2566	105	25	line	line	NOUN
istl-2566	105	26	program	program	NOUN
istl-2566	105	27	,	,	PUNCT
istl-2566	105	28	molconverter	molconverter	PROPN
istl-2566	105	29	(	(	PUNCT
istl-2566	105	30	chemaxon	chemaxon	NOUN
istl-2566	105	31	2019b	2019b	NUM
istl-2566	105	32	)	)	PUNCT
istl-2566	105	33	in	in	ADP
istl-2566	105	34	a	a	DET
istl-2566	105	35	terminal	terminal	ADJ
istl-2566	105	36	window	window	NOUN
istl-2566	105	37	as	as	SCONJ
istl-2566	105	38	follows	follow	VERB
istl-2566	105	39	:	:	PUNCT
istl-2566	105	40	$	$	SYM
istl-2566	105	41	molconvert	molconvert	PROPN
istl-2566	105	42	-g	-g	PUNCT
istl-2566	105	43	"	"	PUNCT
istl-2566	105	44	inchikey	inchikey	ADJ
istl-2566	105	45	:	:	PUNCT
istl-2566	105	46	sabs	sab	NOUN
istl-2566	105	47	,	,	PUNCT
istl-2566	105	48	auxnone	auxnone	NOUN
istl-2566	105	49	"	"	PUNCT
istl-2566	105	50	in.smi	in.smi	PROPN
istl-2566	105	51	-o	-o	PUNCT
istl-2566	105	52	out.inchikey	out.inchikey	VERB
istl-2566	105	53	the	the	DET
istl-2566	105	54	inchi	inchi	PROPN
istl-2566	105	55	absolute	absolute	PROPN
istl-2566	105	56	stereochemistry	stereochemistry	PROPN
istl-2566	105	57	,	,	PUNCT
istl-2566	105	58	sabs	sab	NOUN
istl-2566	105	59	,	,	PUNCT
istl-2566	105	60	option	option	NOUN
istl-2566	105	61	was	be	AUX
istl-2566	105	62	used	use	VERB
istl-2566	105	63	to	to	PART
istl-2566	105	64	force	force	VERB
istl-2566	105	65	the	the	DET
istl-2566	105	66	calculation	calculation	NOUN
istl-2566	105	67	of	of	ADP
istl-2566	105	68	a	a	DET
istl-2566	105	69	standard	standard	ADJ
istl-2566	105	70	inchi	inchi	NOUN
istl-2566	105	71	(	(	PUNCT
istl-2566	105	72	international	international	ADJ
istl-2566	105	73	union	union	NOUN
istl-2566	105	74	of	of	ADP
istl-2566	105	75	pure	pure	ADJ
istl-2566	105	76	and	and	CCONJ
istl-2566	105	77	applied	apply	VERB
istl-2566	105	78	chemistry	chemistry	NOUN
istl-2566	105	79	2017	2017	NUM
istl-2566	105	80	)	)	PUNCT
istl-2566	105	81	.	.	PUNCT
istl-2566	106	1	next	next	ADV
istl-2566	106	2	,	,	PUNCT
istl-2566	106	3	duplicate	duplicate	ADJ
istl-2566	106	4	substances	substance	NOUN
istl-2566	106	5	were	be	AUX
istl-2566	106	6	checked	check	VERB
istl-2566	106	7	against	against	ADP
istl-2566	106	8	a	a	DET
istl-2566	106	9	main	main	ADJ
istl-2566	106	10	local	local	ADJ
istl-2566	106	11	registry	registry	NOUN
istl-2566	106	12	file	file	NOUN
istl-2566	106	13	list	list	NOUN
istl-2566	106	14	of	of	ADP
istl-2566	106	15	inchikeys	inchikey	NOUN
istl-2566	106	16	containing	contain	VERB
istl-2566	106	17	a	a	DET
istl-2566	106	18	local	local	ADJ
istl-2566	106	19	list	list	NOUN
istl-2566	106	20	of	of	ADP
istl-2566	106	21	previously	previously	ADV
istl-2566	106	22	registered	register	VERB
istl-2566	106	23	substances	substance	NOUN
istl-2566	106	24	.	.	PUNCT
istl-2566	107	1	this	this	DET
istl-2566	107	2	step	step	NOUN
istl-2566	107	3	was	be	AUX
istl-2566	107	4	completed	complete	VERB
istl-2566	107	5	in	in	ADP
istl-2566	107	6	a	a	DET
istl-2566	107	7	unix	unix	PROPN
istl-2566	107	8	terminal	terminal	NOUN
istl-2566	107	9	:	:	PUNCT
istl-2566	107	10	$	$	SYM
istl-2566	107	11	sort	sort	ADV
istl-2566	107	12	inchikeys_list.inchikey	inchikeys_list.inchikey	PUNCT
istl-2566	107	13	|	|	NOUN
istl-2566	107	14	uniq	uniq	ADJ
istl-2566	107	15	--count	--count	NOUN
istl-2566	107	16	–	–	PUNCT
istl-2566	107	17	repeated	repeat	VERB
istl-2566	107	18	the	the	DET
istl-2566	107	19	above	above	ADJ
istl-2566	107	20	command	command	NOUN
istl-2566	107	21	outputs	output	VERB
istl-2566	107	22	a	a	DET
istl-2566	107	23	list	list	NOUN
istl-2566	107	24	of	of	ADP
istl-2566	107	25	any	any	DET
istl-2566	107	26	duplicate	duplicate	ADJ
istl-2566	107	27	inchikeys	inchikey	NOUN
istl-2566	107	28	.	.	PUNCT
istl-2566	108	1	if	if	SCONJ
istl-2566	108	2	any	any	DET
istl-2566	108	3	duplicates	duplicate	NOUN
istl-2566	108	4	were	be	AUX
istl-2566	108	5	identified	identify	VERB
istl-2566	108	6	,	,	PUNCT
istl-2566	108	7	the	the	DET
istl-2566	108	8	duplicate	duplicate	ADJ
istl-2566	108	9	substances	substance	NOUN
istl-2566	108	10	were	be	AUX
istl-2566	108	11	assigned	assign	VERB
istl-2566	108	12	the	the	DET
istl-2566	108	13	original	original	ADJ
istl-2566	108	14	registry	registry	NOUN
istl-2566	108	15	identifier	identifier	NOUN
istl-2566	108	16	.	.	PUNCT
istl-2566	109	1	the	the	DET
istl-2566	109	2	same	same	ADJ
istl-2566	109	3	sort	sort	NOUN
istl-2566	109	4	/	/	SYM
istl-2566	109	5	uniq	uniq	ADJ
istl-2566	109	6	command	command	NOUN
istl-2566	109	7	was	be	AUX
istl-2566	109	8	used	use	VERB
istl-2566	109	9	to	to	PART
istl-2566	109	10	check	check	VERB
istl-2566	109	11	for	for	ADP
istl-2566	109	12	duplicate	duplicate	ADJ
istl-2566	109	13	substances	substance	NOUN
istl-2566	109	14	with	with	ADP
istl-2566	109	15	the	the	DET
istl-2566	109	16	inchikeys	inchikey	NOUN
istl-2566	109	17	generated	generate	VERB
istl-2566	109	18	from	from	ADP
istl-2566	109	19	knowitall	knowitall	PROPN
istl-2566	109	20	.	.	PUNCT
istl-2566	110	1	inchikeys	inchikey	NOUN
istl-2566	110	2	were	be	AUX
istl-2566	110	3	also	also	ADV
istl-2566	110	4	used	use	VERB
istl-2566	110	5	as	as	ADP
istl-2566	110	6	an	an	DET
istl-2566	110	7	interoperability	interoperability	NOUN
istl-2566	110	8	check	check	NOUN
istl-2566	110	9	when	when	SCONJ
istl-2566	110	10	transferring	transfer	VERB
istl-2566	110	11	data	datum	NOUN
istl-2566	110	12	between	between	ADP
istl-2566	110	13	cheminformatics	cheminformatic	NOUN
istl-2566	110	14	toolkits	toolkit	NOUN
istl-2566	110	15	locally	locally	ADV
istl-2566	110	16	;	;	PUNCT
istl-2566	110	17	that	that	PRON
istl-2566	110	18	is	is	ADV
istl-2566	110	19	,	,	PUNCT
istl-2566	110	20	the	the	DET
istl-2566	110	21	inchikeys	inchikey	NOUN
istl-2566	110	22	generated	generate	VERB
istl-2566	110	23	from	from	ADP
istl-2566	110	24	chemaxon	chemaxon	ADJ
istl-2566	110	25	molconverter	molconverter	NOUN
istl-2566	110	26	were	be	AUX
istl-2566	110	27	compared	compare	VERB
istl-2566	110	28	to	to	ADP
istl-2566	110	29	rdkit	rdkit	ADJ
istl-2566	110	30	generated	generate	VERB
istl-2566	110	31	inchikeys	inchikey	NOUN
istl-2566	110	32	for	for	ADP
istl-2566	110	33	consistency	consistency	NOUN
istl-2566	110	34	(	(	PUNCT
istl-2566	110	35	akhondi	akhondi	VERB
istl-2566	110	36	et	et	PROPN
istl-2566	110	37	al	al	PROPN
istl-2566	110	38	.	.	PROPN
istl-2566	110	39	2012	2012	NUM
istl-2566	110	40	)	)	PUNCT
istl-2566	110	41	.	.	PUNCT
istl-2566	111	1	pubchem	pubchem	PROPN
istl-2566	111	2	deposition	deposition	VERB
istl-2566	111	3	the	the	DET
istl-2566	111	4	rdkit	rdkit	ADJ
istl-2566	111	5	generated	generate	VERB
istl-2566	111	6	sdfiles	sdfile	NOUN
istl-2566	111	7	and	and	CCONJ
istl-2566	111	8	knowitall	knowitall	PROPN
istl-2566	111	9	compiled	compile	VERB
istl-2566	111	10	csv	csv	PROPN
istl-2566	111	11	spreadsheet	spreadsheet	NOUN
istl-2566	111	12	files	file	NOUN
istl-2566	111	13	were	be	AUX
istl-2566	111	14	submitted	submit	VERB
istl-2566	111	15	to	to	ADP
istl-2566	111	16	pubchem	pubchem	NOUN
istl-2566	111	17	for	for	ADP
istl-2566	111	18	processing	process	VERB
istl-2566	111	19	into	into	ADP
istl-2566	111	20	the	the	DET
istl-2566	111	21	database	database	NOUN
istl-2566	111	22	through	through	ADP
istl-2566	111	23	the	the	DET
istl-2566	111	24	pubchem	pubchem	PROPN
istl-2566	111	25	upload	upload	NOUN
istl-2566	111	26	web	web	NOUN
istl-2566	111	27	interface	interface	NOUN
istl-2566	111	28	.	.	PUNCT
istl-2566	112	1	our	our	PRON
istl-2566	112	2	local	local	ADJ
istl-2566	112	3	registry	registry	NOUN
istl-2566	112	4	file	file	NOUN
istl-2566	112	5	was	be	AUX
istl-2566	112	6	then	then	ADV
istl-2566	112	7	updated	update	VERB
istl-2566	112	8	with	with	ADP
istl-2566	112	9	the	the	DET
istl-2566	112	10	deposited	deposit	VERB
istl-2566	112	11	pubchem	pubchem	NOUN
istl-2566	112	12	substance	substance	NOUN
istl-2566	112	13	identifier	identifier	NOUN
istl-2566	112	14	(	(	PUNCT
istl-2566	112	15	sid	sid	ADJ
istl-2566	112	16	)	)	PUNCT
istl-2566	112	17	and	and	CCONJ
istl-2566	112	18	standardized	standardized	ADJ
istl-2566	112	19	compound	compound	NOUN
istl-2566	112	20	identifiers	identifier	NOUN
istl-2566	112	21	(	(	PUNCT
istl-2566	112	22	cid	cid	PROPN
istl-2566	112	23	)	)	PUNCT
istl-2566	112	24	.	.	PUNCT
istl-2566	113	1	institutional	institutional	ADJ
istl-2566	113	2	repository	repository	NOUN
istl-2566	113	3	archiving	archiving	ADV
istl-2566	113	4	after	after	ADP
istl-2566	113	5	depositing	deposit	VERB
istl-2566	113	6	the	the	DET
istl-2566	113	7	substance	substance	NOUN
istl-2566	113	8	data	datum	NOUN
istl-2566	113	9	in	in	ADP
istl-2566	113	10	pubchem	pubchem	NOUN
istl-2566	113	11	,	,	PUNCT
istl-2566	113	12	an	an	DET
istl-2566	113	13	archive	archive	NOUN
istl-2566	113	14	copy	copy	NOUN
istl-2566	113	15	of	of	ADP
istl-2566	113	16	the	the	DET
istl-2566	113	17	substance	substance	NOUN
istl-2566	113	18	data	datum	NOUN
istl-2566	113	19	in	in	ADP
istl-2566	113	20	sdfile	sdfile	ADJ
istl-2566	113	21	or	or	CCONJ
istl-2566	113	22	csv	csv	ADJ
istl-2566	113	23	format	format	NOUN
istl-2566	113	24	was	be	AUX
istl-2566	113	25	deposited	deposit	VERB
istl-2566	113	26	in	in	ADP
istl-2566	113	27	ua	ua	PROPN
istl-2566	113	28	’s	’s	NOUN
istl-2566	113	29	dspace	dspace	NOUN
istl-2566	113	30	institutional	institutional	ADJ
istl-2566	113	31	repository	repository	NOUN
istl-2566	113	32	(	(	PUNCT
istl-2566	113	33	ua	ua	PROPN
istl-2566	113	34	ir	ir	ADV
istl-2566	113	35	)	)	PUNCT
istl-2566	113	36	.	.	PUNCT
istl-2566	114	1	a	a	DET
istl-2566	114	2	new	new	ADJ
istl-2566	114	3	record	record	NOUN
istl-2566	114	4	was	be	AUX
istl-2566	114	5	created	create	VERB
istl-2566	114	6	for	for	ADP
istl-2566	114	7	each	each	DET
istl-2566	114	8	collection	collection	NOUN
istl-2566	114	9	of	of	ADP
istl-2566	114	10	thesis	thesis	NOUN
istl-2566	114	11	substance	substance	NOUN
istl-2566	114	12	data	datum	NOUN
istl-2566	114	13	.	.	PUNCT
istl-2566	115	1	each	each	DET
istl-2566	115	2	ua	ua	PROPN
istl-2566	115	3	ir	ir	PROPN
istl-2566	115	4	record	record	NOUN
istl-2566	115	5	used	use	VERB
istl-2566	115	6	the	the	DET
istl-2566	115	7	dublin	dublin	PROPN
istl-2566	115	8	core	core	PROPN
istl-2566	115	9	metadata	metadata	PROPN
istl-2566	115	10	schema	schema	PROPN
istl-2566	115	11	with	with	ADP
istl-2566	115	12	the	the	DET
istl-2566	115	13	following	follow	VERB
istl-2566	115	14	elements	element	NOUN
istl-2566	115	15	:	:	PUNCT
istl-2566	115	16	dc.contributor	dc.contributor	X
istl-2566	115	17	,	,	PUNCT
istl-2566	115	18	dc.date.issued	dc.date.issue	VERB
istl-2566	115	19	,	,	PUNCT
istl-2566	115	20	dc.description	dc.description	NOUN
istl-2566	115	21	(	(	PUNCT
istl-2566	115	22	includes	include	VERB
istl-2566	115	23	a	a	DET
istl-2566	115	24	description	description	NOUN
istl-2566	115	25	of	of	ADP
istl-2566	115	26	the	the	DET
istl-2566	115	27	substance	substance	NOUN
istl-2566	115	28	data	datum	NOUN
istl-2566	115	29	and	and	CCONJ
istl-2566	115	30	cc	cc	NOUN
istl-2566	115	31	-	-	PUNCT
istl-2566	115	32	by	by	ADP
istl-2566	115	33	4.0	4.0	NUM
istl-2566	115	34	license	license	NOUN
istl-2566	115	35	)	)	PUNCT
istl-2566	115	36	,	,	PUNCT
istl-2566	115	37	dc.publisher	dc.publisher	X
istl-2566	115	38	,	,	PUNCT
istl-2566	115	39	dc.relation.isbasedon	dc.relation.isbasedon	PUNCT
istl-2566	115	40	(	(	PUNCT
istl-2566	115	41	reference	reference	NOUN
istl-2566	115	42	to	to	ADP
istl-2566	115	43	original	original	ADJ
istl-2566	115	44	thesis	thesis	NOUN
istl-2566	115	45	)	)	PUNCT
istl-2566	115	46	,	,	PUNCT
istl-2566	115	47	dc.title	dc.title	X
istl-2566	115	48	,	,	PUNCT
istl-2566	115	49	dc.type	dc.type	NOUN
istl-2566	115	50	,	,	PUNCT
istl-2566	115	51	local.github.url	local.github.url	PROPN
istl-2566	115	52	,	,	PUNCT
istl-2566	115	53	local.sdfpubchemexternalids.url	local.sdfpubchemexternalids.url	PROPN
istl-2566	115	54	.	.	PUNCT
istl-2566	116	1	the	the	DET
istl-2566	116	2	latter	latter	ADJ
istl-2566	116	3	two	two	NUM
istl-2566	116	4	local	local	ADJ
istl-2566	116	5	metadata	metadata	ADJ
istl-2566	116	6	elements	element	NOUN
istl-2566	116	7	provide	provide	VERB
istl-2566	116	8	cross	cross	NOUN
istl-2566	116	9	links	link	NOUN
istl-2566	116	10	to	to	ADP
istl-2566	116	11	the	the	DET
istl-2566	116	12	substance	substance	NOUN
istl-2566	116	13	data	datum	NOUN
istl-2566	116	14	on	on	ADP
istl-2566	116	15	github	github	PROPN
istl-2566	116	16	and	and	CCONJ
istl-2566	116	17	pubchem	pubchem	PROPN
istl-2566	116	18	.	.	PUNCT
istl-2566	117	1	new	new	ADJ
istl-2566	117	2	substance	substance	NOUN
istl-2566	117	3	count	count	NOUN
istl-2566	117	4	data	datum	NOUN
istl-2566	117	5	collection	collection	NOUN
istl-2566	117	6	to	to	PART
istl-2566	117	7	find	find	VERB
istl-2566	117	8	the	the	DET
istl-2566	117	9	number	number	NOUN
istl-2566	117	10	of	of	ADP
istl-2566	117	11	newly	newly	ADV
istl-2566	117	12	deposited	deposit	VERB
istl-2566	117	13	substances	substance	NOUN
istl-2566	117	14	in	in	ADP
istl-2566	117	15	pubchem	pubchem	NOUN
istl-2566	117	16	,	,	PUNCT
istl-2566	117	17	the	the	DET
istl-2566	117	18	total	total	ADJ
istl-2566	117	19	number	number	NOUN
istl-2566	117	20	of	of	ADP
istl-2566	117	21	substances	substance	NOUN
istl-2566	117	22	(	(	PUNCT
istl-2566	117	23	sids	sid	NOUN
istl-2566	117	24	for	for	ADP
istl-2566	117	25	same	same	ADJ
istl-2566	117	26	,	,	PUNCT
istl-2566	117	27	mixtures	mixture	NOUN
istl-2566	117	28	,	,	PUNCT
istl-2566	117	29	and	and	CCONJ
istl-2566	117	30	all	all	PRON
istl-2566	117	31	)	)	PUNCT
istl-2566	117	32	linked	link	VERB
istl-2566	117	33	to	to	ADP
istl-2566	117	34	each	each	PRON
istl-2566	117	35	of	of	ADP
istl-2566	117	36	the	the	DET
istl-2566	117	37	ua	ua	PROPN
istl-2566	117	38	deposited	deposit	VERB
istl-2566	117	39	compound	compound	NOUN
istl-2566	117	40	standardized	standardize	VERB
istl-2566	117	41	records	record	NOUN
istl-2566	117	42	were	be	AUX
istl-2566	117	43	retrieved	retrieve	VERB
istl-2566	117	44	.	.	PUNCT
istl-2566	118	1	if	if	SCONJ
istl-2566	118	2	there	there	PRON
istl-2566	118	3	was	be	VERB
istl-2566	118	4	only	only	ADV
istl-2566	118	5	one	one	NUM
istl-2566	118	6	associated	associate	VERB
istl-2566	118	7	sid	sid	ADJ
istl-2566	118	8	,	,	PUNCT
istl-2566	118	9	the	the	DET
istl-2566	118	10	structure	structure	NOUN
istl-2566	118	11	was	be	AUX
istl-2566	118	12	considered	consider	VERB
istl-2566	118	13	new	new	ADJ
istl-2566	118	14	to	to	ADP
istl-2566	118	15	pubchem	pubchem	NOUN
istl-2566	118	16	,	,	PUNCT
istl-2566	118	17	and	and	CCONJ
istl-2566	118	18	represents	represent	VERB
istl-2566	118	19	a	a	DET
istl-2566	118	20	new	new	ADJ
istl-2566	118	21	deposition	deposition	NOUN
istl-2566	118	22	.	.	PUNCT
istl-2566	119	1	the	the	DET
istl-2566	119	2	data	data	NOUN
istl-2566	119	3	was	be	AUX
istl-2566	119	4	programmatically	programmatically	ADV
istl-2566	119	5	collected	collect	VERB
istl-2566	119	6	using	use	VERB
istl-2566	119	7	a	a	DET
istl-2566	119	8	script	script	NOUN
istl-2566	119	9	written	write	VERB
istl-2566	119	10	in	in	ADP
istl-2566	119	11	matlab	matlab	PROPN
istl-2566	119	12	r2020a	r2020a	PROPN
istl-2566	119	13	.	.	PUNCT
istl-2566	120	1	the	the	DET
istl-2566	120	2	matlab	matlab	PROPN
istl-2566	120	3	script	script	NOUN
istl-2566	120	4	uses	use	VERB
istl-2566	120	5	the	the	DET
istl-2566	120	6	pubchem	pubchem	PROPN
istl-2566	120	7	power	power	NOUN
istl-2566	120	8	user	user	NOUN
istl-2566	120	9	gateway	gateway	NOUN
istl-2566	120	10	web	web	NOUN
istl-2566	120	11	requests	request	NOUN
istl-2566	120	12	to	to	PART
istl-2566	120	13	retrieve	retrieve	VERB
istl-2566	120	14	the	the	DET
istl-2566	120	15	data	datum	NOUN
istl-2566	120	16	and	and	CCONJ
istl-2566	120	17	is	be	AUX
istl-2566	120	18	detailed	detail	VERB
istl-2566	120	19	in	in	ADP
istl-2566	120	20	a	a	DET
istl-2566	120	21	separate	separate	ADJ
istl-2566	120	22	article	article	NOUN
istl-2566	120	23	(	(	PUNCT
istl-2566	120	24	scalfani	scalfani	VERB
istl-2566	120	25	et	et	PROPN
istl-2566	120	26	al	al	PROPN
istl-2566	120	27	.	.	PROPN
istl-2566	120	28	2020	2020	NUM
istl-2566	120	29	)	)	PUNCT
istl-2566	121	1	the	the	DET
istl-2566	121	2	substance	substance	NOUN
istl-2566	121	3	count	count	NOUN
istl-2566	121	4	data	datum	NOUN
istl-2566	121	5	was	be	AUX
istl-2566	121	6	collected	collect	VERB
istl-2566	121	7	in	in	ADP
istl-2566	121	8	may	may	PROPN
istl-2566	121	9	2020	2020	NUM
istl-2566	121	10	for	for	ADP
istl-2566	121	11	each	each	PRON
istl-2566	121	12	of	of	ADP
istl-2566	121	13	the	the	DET
istl-2566	121	14	ua	ua	ADJ
istl-2566	121	15	substances	substance	NOUN
istl-2566	121	16	deposited	deposit	VERB
istl-2566	121	17	in	in	ADP
istl-2566	121	18	pubchem	pubchem	PROPN
istl-2566	121	19	.	.	PUNCT
istl-2566	122	1	results	result	VERB
istl-2566	122	2	thesis	thesis	NOUN
istl-2566	122	3	content	content	VERB
istl-2566	122	4	the	the	DET
istl-2566	122	5	variety	variety	NOUN
istl-2566	122	6	of	of	ADP
istl-2566	122	7	chemistry	chemistry	NOUN
istl-2566	122	8	encountered	encounter	VERB
istl-2566	122	9	in	in	ADP
istl-2566	122	10	the	the	DET
istl-2566	122	11	selected	select	VERB
istl-2566	122	12	73	73	NUM
istl-2566	122	13	organic	organic	ADJ
istl-2566	122	14	chemistry	chemistry	NOUN
istl-2566	122	15	theses	thesis	NOUN
istl-2566	122	16	was	be	AUX
istl-2566	122	17	diverse	diverse	ADJ
istl-2566	122	18	and	and	CCONJ
istl-2566	122	19	reported	report	VERB
istl-2566	122	20	substances	substance	NOUN
istl-2566	122	21	synthesized	synthesize	VERB
istl-2566	122	22	included	include	VERB
istl-2566	122	23	,	,	PUNCT
istl-2566	122	24	for	for	ADP
istl-2566	122	25	example	example	NOUN
istl-2566	122	26	,	,	PUNCT
istl-2566	122	27	ionic	ionic	ADJ
istl-2566	122	28	liquids	liquid	NOUN
istl-2566	122	29	,	,	PUNCT
istl-2566	122	30	natural	natural	ADJ
istl-2566	122	31	products	product	NOUN
istl-2566	122	32	,	,	PUNCT
istl-2566	122	33	carbene	carbene	NOUN
istl-2566	122	34	complexes	complex	NOUN
istl-2566	122	35	,	,	PUNCT
istl-2566	122	36	silyl	silyl	ADJ
istl-2566	122	37	compounds	compound	NOUN
istl-2566	122	38	,	,	PUNCT
istl-2566	122	39	furanones	furanone	NOUN
istl-2566	122	40	,	,	PUNCT
istl-2566	122	41	ribose	ribose	ADJ
istl-2566	122	42	derivatives	derivative	NOUN
istl-2566	122	43	,	,	PUNCT
istl-2566	122	44	and	and	CCONJ
istl-2566	122	45	boronates	boronate	NOUN
istl-2566	122	46	.	.	PUNCT
istl-2566	123	1	on	on	ADP
istl-2566	123	2	average	average	ADJ
istl-2566	123	3	each	each	DET
istl-2566	123	4	thesis	thesis	NOUN
istl-2566	123	5	contained	contain	VERB
istl-2566	123	6	39	39	NUM
istl-2566	123	7	synthesized	synthesize	VERB
istl-2566	123	8	substances	substance	NOUN
istl-2566	123	9	with	with	ADP
istl-2566	123	10	associated	associate	VERB
istl-2566	123	11	characterization	characterization	NOUN
istl-2566	123	12	data	datum	NOUN
istl-2566	123	13	.	.	PUNCT
istl-2566	124	1	by	by	ADP
istl-2566	124	2	evaluating	evaluate	VERB
istl-2566	124	3	thesis	thesis	NOUN
istl-2566	124	4	titles	title	NOUN
istl-2566	124	5	,	,	PUNCT
istl-2566	124	6	we	we	PRON
istl-2566	124	7	estimated	estimate	VERB
istl-2566	124	8	that	that	SCONJ
istl-2566	124	9	~200	~200	PRON
istl-2566	124	10	of	of	ADP
istl-2566	124	11	the	the	DET
istl-2566	124	12	theses	thesis	NOUN
istl-2566	124	13	at	at	ADP
istl-2566	124	14	ua	ua	PROPN
istl-2566	124	15	from	from	ADP
istl-2566	124	16	1924	1924	NUM
istl-2566	124	17	-	-	SYM
istl-2566	124	18	2020	2020	NUM
istl-2566	124	19	are	be	AUX
istl-2566	124	20	in	in	ADP
istl-2566	124	21	the	the	DET
istl-2566	124	22	organic	organic	ADJ
istl-2566	124	23	chemistry	chemistry	NOUN
istl-2566	124	24	subject	subject	NOUN
istl-2566	124	25	domain	domain	NOUN
istl-2566	124	26	and	and	CCONJ
istl-2566	124	27	have	have	VERB
istl-2566	124	28	a	a	DET
istl-2566	124	29	significant	significant	ADJ
istl-2566	124	30	focus	focus	NOUN
istl-2566	124	31	on	on	ADP
istl-2566	124	32	small	small	ADJ
istl-2566	124	33	molecule	molecule	NOUN
istl-2566	124	34	synthesis	synthesis	NOUN
istl-2566	124	35	,	,	PUNCT
istl-2566	124	36	and	and	CCONJ
istl-2566	124	37	as	as	ADP
istl-2566	124	38	a	a	DET
istl-2566	124	39	result	result	NOUN
istl-2566	124	40	,	,	PUNCT
istl-2566	124	41	our	our	PRON
istl-2566	124	42	selected	select	VERB
istl-2566	124	43	sample	sample	NOUN
istl-2566	124	44	represents	represent	VERB
istl-2566	124	45	about	about	ADV
istl-2566	124	46	40	40	NUM
istl-2566	124	47	%	%	NOUN
istl-2566	124	48	of	of	ADP
istl-2566	124	49	suitable	suitable	ADJ
istl-2566	124	50	theses	thesis	NOUN
istl-2566	124	51	at	at	ADP
istl-2566	124	52	ua	ua	PROPN
istl-2566	124	53	for	for	ADP
istl-2566	124	54	organic	organic	ADJ
istl-2566	124	55	chemistry	chemistry	NOUN
istl-2566	124	56	substance	substance	NOUN
istl-2566	124	57	registration	registration	NOUN
istl-2566	124	58	.	.	PUNCT
istl-2566	125	1	about	about	ADV
istl-2566	125	2	30	30	NUM
istl-2566	125	3	%	%	NOUN
istl-2566	125	4	of	of	ADP
istl-2566	125	5	the	the	DET
istl-2566	125	6	theses	thesis	NOUN
istl-2566	125	7	selected	select	VERB
istl-2566	125	8	are	be	AUX
istl-2566	125	9	available	available	ADJ
istl-2566	125	10	in	in	ADP
istl-2566	125	11	digital	digital	ADJ
istl-2566	125	12	full	full	ADJ
istl-2566	125	13	-	-	PUNCT
istl-2566	125	14	text	text	NOUN
istl-2566	125	15	format	format	NOUN
istl-2566	125	16	.	.	PUNCT
istl-2566	126	1	substance	substance	NOUN
istl-2566	126	2	drawing	drawing	NOUN
istl-2566	126	3	and	and	CCONJ
istl-2566	126	4	machine	machine	NOUN
istl-2566	126	5	-	-	PUNCT
istl-2566	126	6	readable	readable	ADJ
istl-2566	126	7	file	file	NOUN
istl-2566	126	8	creation	creation	NOUN
istl-2566	126	9	using	use	VERB
istl-2566	126	10	the	the	DET
istl-2566	126	11	workflow	workflow	NOUN
istl-2566	126	12	described	describe	VERB
istl-2566	126	13	in	in	ADP
istl-2566	126	14	the	the	DET
istl-2566	126	15	methods	method	NOUN
istl-2566	126	16	section	section	NOUN
istl-2566	127	1	,	,	PUNCT
istl-2566	127	2	a	a	DET
istl-2566	127	3	total	total	NOUN
istl-2566	127	4	of	of	ADP
istl-2566	127	5	2,885	2,885	NUM
istl-2566	127	6	unique	unique	ADJ
istl-2566	127	7	substances	substance	NOUN
istl-2566	127	8	were	be	AUX
istl-2566	127	9	manually	manually	ADV
istl-2566	127	10	redrawn	redrawn	NOUN
istl-2566	127	11	.	.	PUNCT
istl-2566	128	1	the	the	DET
istl-2566	128	2	majority	majority	NOUN
istl-2566	128	3	of	of	ADP
istl-2566	128	4	structures	structure	NOUN
istl-2566	128	5	(	(	PUNCT
istl-2566	128	6	~94	~94	VERB
istl-2566	128	7	%	%	NOUN
istl-2566	128	8	)	)	PUNCT
istl-2566	128	9	were	be	AUX
istl-2566	128	10	drawn	draw	VERB
istl-2566	128	11	in	in	ADP
istl-2566	128	12	chemaxon	chemaxon	NOUN
istl-2566	128	13	marvinsketch	marvinsketch	NOUN
istl-2566	128	14	with	with	ADP
istl-2566	128	15	the	the	DET
istl-2566	128	16	remaining	remain	VERB
istl-2566	128	17	substances	substance	NOUN
istl-2566	128	18	,	,	PUNCT
istl-2566	128	19	originally	originally	ADV
istl-2566	128	20	depicted	depict	VERB
istl-2566	128	21	as	as	ADP
istl-2566	128	22	perspective	perspective	NOUN
istl-2566	128	23	representations	representation	NOUN
istl-2566	128	24	,	,	PUNCT
istl-2566	128	25	drawn	draw	VERB
istl-2566	128	26	in	in	ADP
istl-2566	128	27	knowitall	knowitall	PROPN
istl-2566	128	28	chemwindow	chemwindow	PROPN
istl-2566	128	29	.	.	PUNCT
istl-2566	129	1	for	for	ADP
istl-2566	129	2	reference	reference	NOUN
istl-2566	129	3	,	,	PUNCT
istl-2566	129	4	if	if	SCONJ
istl-2566	129	5	no	no	DET
istl-2566	129	6	challenges	challenge	NOUN
istl-2566	129	7	were	be	AUX
istl-2566	129	8	encountered	encounter	VERB
istl-2566	129	9	,	,	PUNCT
istl-2566	129	10	we	we	PRON
istl-2566	129	11	could	could	AUX
istl-2566	129	12	typically	typically	ADV
istl-2566	129	13	draw	draw	VERB
istl-2566	129	14	60	60	NUM
istl-2566	129	15	substances	substance	NOUN
istl-2566	129	16	in	in	ADP
istl-2566	129	17	about	about	ADV
istl-2566	129	18	3	3	NUM
istl-2566	129	19	hours	hour	NOUN
istl-2566	129	20	,	,	PUNCT
istl-2566	129	21	and	and	CCONJ
istl-2566	129	22	then	then	ADV
istl-2566	129	23	complete	complete	VERB
istl-2566	129	24	the	the	DET
istl-2566	129	25	remainder	remainder	NOUN
istl-2566	129	26	of	of	ADP
istl-2566	129	27	the	the	DET
istl-2566	129	28	workflow	workflow	NOUN
istl-2566	129	29	in	in	ADP
istl-2566	129	30	minutes	minute	NOUN
istl-2566	129	31	.	.	PUNCT
istl-2566	130	1	substance	substance	NOUN
istl-2566	130	2	registration	registration	NOUN
istl-2566	130	3	and	and	CCONJ
istl-2566	130	4	interoperability	interoperability	NOUN
istl-2566	130	5	check	check	NOUN
istl-2566	130	6	with	with	ADP
istl-2566	130	7	inchi	inchi	NOUN
istl-2566	130	8	in	in	ADP
istl-2566	130	9	our	our	PRON
istl-2566	130	10	workflow	workflow	NOUN
istl-2566	130	11	,	,	PUNCT
istl-2566	130	12	we	we	PRON
istl-2566	130	13	tracked	track	VERB
istl-2566	130	14	substances	substance	NOUN
istl-2566	130	15	by	by	ADP
istl-2566	130	16	their	their	PRON
istl-2566	130	17	calculated	calculate	VERB
istl-2566	130	18	standard	standard	ADJ
istl-2566	130	19	inchikey	inchikey	NOUN
istl-2566	130	20	.	.	PUNCT
istl-2566	131	1	a	a	DET
istl-2566	131	2	compiled	compile	VERB
istl-2566	131	3	tabular	tabular	ADJ
istl-2566	131	4	list	list	NOUN
istl-2566	131	5	of	of	ADP
istl-2566	131	6	inchikeys	inchikey	NOUN
istl-2566	131	7	and	and	CCONJ
istl-2566	131	8	a	a	DET
istl-2566	131	9	unique	unique	ADJ
istl-2566	131	10	identifier	identifier	NOUN
istl-2566	131	11	(	(	PUNCT
istl-2566	131	12	e.g.	e.g.	ADV
istl-2566	131	13	,	,	PUNCT
istl-2566	131	14	ualib-1	ualib-1	SPACE
istl-2566	131	15	)	)	PUNCT
istl-2566	131	16	served	serve	VERB
istl-2566	131	17	as	as	ADP
istl-2566	131	18	our	our	PRON
istl-2566	131	19	internal	internal	ADJ
istl-2566	131	20	registry	registry	NOUN
istl-2566	131	21	list	list	NOUN
istl-2566	131	22	.	.	PUNCT
istl-2566	132	1	if	if	SCONJ
istl-2566	132	2	the	the	DET
istl-2566	132	3	calculated	calculate	VERB
istl-2566	132	4	standard	standard	ADJ
istl-2566	132	5	inchikey	inchikey	NOUN
istl-2566	132	6	for	for	ADP
istl-2566	132	7	a	a	DET
istl-2566	132	8	substance	substance	NOUN
istl-2566	132	9	was	be	AUX
istl-2566	132	10	unique	unique	ADJ
istl-2566	132	11	,	,	PUNCT
istl-2566	132	12	the	the	DET
istl-2566	132	13	substance	substance	NOUN
istl-2566	132	14	was	be	AUX
istl-2566	132	15	determined	determine	VERB
istl-2566	132	16	as	as	ADP
istl-2566	132	17	new	new	ADJ
istl-2566	132	18	and	and	CCONJ
istl-2566	132	19	added	add	VERB
istl-2566	132	20	to	to	ADP
istl-2566	132	21	our	our	PRON
istl-2566	132	22	internal	internal	ADJ
istl-2566	132	23	registry	registry	NOUN
istl-2566	132	24	list	list	NOUN
istl-2566	132	25	.	.	PUNCT
istl-2566	133	1	if	if	SCONJ
istl-2566	133	2	the	the	DET
istl-2566	133	3	substance	substance	NOUN
istl-2566	133	4	was	be	AUX
istl-2566	133	5	identified	identify	VERB
istl-2566	133	6	as	as	ADP
istl-2566	133	7	a	a	DET
istl-2566	133	8	duplicate	duplicate	ADJ
istl-2566	133	9	inchikey	inchikey	NOUN
istl-2566	133	10	within	within	ADP
istl-2566	133	11	our	our	PRON
istl-2566	133	12	substance	substance	NOUN
istl-2566	133	13	registry	registry	NOUN
istl-2566	133	14	list	list	NOUN
istl-2566	133	15	,	,	PUNCT
istl-2566	133	16	it	it	PRON
istl-2566	133	17	was	be	AUX
istl-2566	133	18	assigned	assign	VERB
istl-2566	133	19	the	the	DET
istl-2566	133	20	previously	previously	ADV
istl-2566	133	21	known	know	VERB
istl-2566	133	22	registry	registry	NOUN
istl-2566	133	23	identifier	identifier	ADV
istl-2566	133	24	.	.	PUNCT
istl-2566	134	1	in	in	ADP
istl-2566	134	2	all	all	PRON
istl-2566	134	3	of	of	ADP
istl-2566	134	4	the	the	DET
istl-2566	134	5	substances	substance	NOUN
istl-2566	134	6	we	we	PRON
istl-2566	134	7	selected	select	VERB
istl-2566	134	8	,	,	PUNCT
istl-2566	134	9	there	there	PRON
istl-2566	134	10	were	be	VERB
istl-2566	134	11	76	76	NUM
istl-2566	134	12	duplicates	duplicate	NOUN
istl-2566	134	13	identified	identify	VERB
istl-2566	134	14	(	(	PUNCT
istl-2566	134	15	2.6	2.6	NUM
istl-2566	134	16	%	%	NOUN
istl-2566	134	17	)	)	PUNCT
istl-2566	134	18	using	use	VERB
istl-2566	134	19	the	the	DET
istl-2566	134	20	standard	standard	ADJ
istl-2566	134	21	inchi	inchi	NOUN
istl-2566	134	22	.	.	PUNCT
istl-2566	135	1	for	for	ADP
istl-2566	135	2	these	these	DET
istl-2566	135	3	substances	substance	NOUN
istl-2566	135	4	,	,	PUNCT
istl-2566	135	5	the	the	DET
istl-2566	135	6	result	result	NOUN
istl-2566	135	7	is	be	AUX
istl-2566	135	8	that	that	SCONJ
istl-2566	135	9	they	they	PRON
istl-2566	135	10	have	have	VERB
istl-2566	135	11	more	more	ADJ
istl-2566	135	12	than	than	ADP
istl-2566	135	13	one	one	NUM
istl-2566	135	14	associated	associate	VERB
istl-2566	135	15	thesis	thesis	NOUN
istl-2566	135	16	reference	reference	NOUN
istl-2566	135	17	in	in	ADP
istl-2566	135	18	our	our	PRON
istl-2566	135	19	local	local	ADJ
istl-2566	135	20	registry	registry	NOUN
istl-2566	135	21	identifier	identifier	NOUN
istl-2566	135	22	list	list	NOUN
istl-2566	135	23	.	.	PUNCT
istl-2566	136	1	the	the	DET
istl-2566	136	2	standard	standard	ADJ
istl-2566	136	3	inchi	inchi	PROPN
istl-2566	136	4	was	be	AUX
istl-2566	136	5	also	also	ADV
istl-2566	136	6	used	use	VERB
istl-2566	136	7	to	to	PART
istl-2566	136	8	check	check	VERB
istl-2566	136	9	the	the	DET
istl-2566	136	10	consistency	consistency	NOUN
istl-2566	136	11	of	of	ADP
istl-2566	136	12	the	the	DET
istl-2566	136	13	chemical	chemical	NOUN
istl-2566	136	14	substance	substance	NOUN
istl-2566	136	15	data	datum	NOUN
istl-2566	136	16	exchange	exchange	NOUN
istl-2566	136	17	between	between	ADP
istl-2566	136	18	the	the	DET
istl-2566	136	19	cheminformatics	cheminformatic	NOUN
istl-2566	136	20	toolkits	toolkit	NOUN
istl-2566	136	21	.	.	PUNCT
istl-2566	137	1	smiles	smile	NOUN
istl-2566	137	2	and	and	CCONJ
istl-2566	137	3	file	file	NOUN
istl-2566	137	4	format	format	NOUN
istl-2566	137	5	reading	read	VERB
istl-2566	137	6	differences	difference	NOUN
istl-2566	137	7	between	between	ADP
istl-2566	137	8	toolkits	toolkit	NOUN
istl-2566	137	9	are	be	AUX
istl-2566	137	10	known	know	VERB
istl-2566	137	11	to	to	PART
istl-2566	137	12	exist	exist	VERB
istl-2566	137	13	(	(	PUNCT
istl-2566	137	14	o’boyle	o’boyle	PROPN
istl-2566	137	15	et	et	PROPN
istl-2566	137	16	al	al	PROPN
istl-2566	137	17	.	.	PROPN
istl-2566	137	18	2018	2018	NUM
istl-2566	137	19	)	)	PUNCT
istl-2566	137	20	,	,	PUNCT
istl-2566	137	21	and	and	CCONJ
istl-2566	137	22	since	since	SCONJ
istl-2566	137	23	we	we	PRON
istl-2566	137	24	were	be	AUX
istl-2566	137	25	transferring	transfer	VERB
istl-2566	137	26	chemaxon	chemaxon	NOUN
istl-2566	137	27	generated	generate	VERB
istl-2566	137	28	smiles	smile	NOUN
istl-2566	137	29	to	to	AUX
istl-2566	137	30	rdkit	rdkit	ADJ
istl-2566	137	31	,	,	PUNCT
istl-2566	137	32	comparing	compare	VERB
istl-2566	137	33	the	the	DET
istl-2566	137	34	individual	individual	ADJ
istl-2566	137	35	toolkit	toolkit	NOUN
istl-2566	138	1	calculated	calculate	VERB
istl-2566	138	2	standard	standard	NOUN
istl-2566	138	3	inchis	inchis	PROPN
istl-2566	138	4	was	be	AUX
istl-2566	138	5	a	a	DET
istl-2566	138	6	convenient	convenient	ADJ
istl-2566	138	7	way	way	NOUN
istl-2566	138	8	to	to	PART
istl-2566	138	9	check	check	VERB
istl-2566	138	10	for	for	ADP
istl-2566	138	11	consistency	consistency	NOUN
istl-2566	138	12	(	(	PUNCT
istl-2566	138	13	akhondi	akhondi	VERB
istl-2566	138	14	et	et	PROPN
istl-2566	138	15	al	al	PROPN
istl-2566	138	16	.	.	PROPN
istl-2566	138	17	2012	2012	NUM
istl-2566	138	18	;	;	PUNCT
istl-2566	138	19	o’boyle	o’boyle	PROPN
istl-2566	138	20	et	et	PROPN
istl-2566	138	21	al	al	PROPN
istl-2566	138	22	.	.	PROPN
istl-2566	138	23	2018	2018	NUM
istl-2566	138	24	)	)	PUNCT
istl-2566	138	25	.	.	PUNCT
istl-2566	139	1	in	in	ADP
istl-2566	139	2	total	total	NOUN
istl-2566	139	3	,	,	PUNCT
istl-2566	139	4	there	there	PRON
istl-2566	139	5	were	be	VERB
istl-2566	139	6	19	19	NUM
istl-2566	139	7	chemical	chemical	ADJ
istl-2566	139	8	substances	substance	NOUN
istl-2566	139	9	(	(	PUNCT
istl-2566	139	10	0.7	0.7	NUM
istl-2566	139	11	%	%	NOUN
istl-2566	139	12	)	)	PUNCT
istl-2566	139	13	where	where	SCONJ
istl-2566	139	14	the	the	DET
istl-2566	139	15	calculated	calculate	VERB
istl-2566	139	16	standard	standard	NOUN
istl-2566	139	17	inchis	inchis	PROPN
istl-2566	139	18	did	do	AUX
istl-2566	139	19	not	not	PART
istl-2566	139	20	match	match	VERB
istl-2566	139	21	between	between	ADP
istl-2566	139	22	the	the	DET
istl-2566	139	23	toolkits	toolkit	NOUN
istl-2566	139	24	.	.	PUNCT
istl-2566	140	1	we	we	PRON
istl-2566	140	2	hypothesize	hypothesize	VERB
istl-2566	140	3	that	that	SCONJ
istl-2566	140	4	the	the	DET
istl-2566	140	5	differences	difference	NOUN
istl-2566	140	6	are	be	AUX
istl-2566	140	7	a	a	DET
istl-2566	140	8	result	result	NOUN
istl-2566	140	9	of	of	ADP
istl-2566	140	10	a	a	DET
istl-2566	140	11	2d	2d	NOUN
istl-2566	140	12	drawing	drawing	NOUN
istl-2566	140	13	limitation	limitation	NOUN
istl-2566	140	14	(	(	PUNCT
istl-2566	140	15	clark	clark	NOUN
istl-2566	140	16	et	et	PROPN
istl-2566	140	17	al	al	PROPN
istl-2566	140	18	.	.	PROPN
istl-2566	140	19	2006	2006	NUM
istl-2566	140	20	;	;	PUNCT
istl-2566	140	21	frączek	frączek	PROPN
istl-2566	140	22	2016	2016	NUM
istl-2566	140	23	)	)	PUNCT
istl-2566	140	24	leading	lead	VERB
istl-2566	140	25	to	to	ADP
istl-2566	140	26	a	a	DET
istl-2566	140	27	different	different	ADJ
istl-2566	140	28	calculated	calculated	ADJ
istl-2566	140	29	inchi	inchi	NOUN
istl-2566	140	30	(	(	PUNCT
istl-2566	140	31	there	there	PRON
istl-2566	140	32	are	be	VERB
istl-2566	140	33	no	no	DET
istl-2566	140	34	coordinates	coordinate	NOUN
istl-2566	140	35	in	in	ADP
istl-2566	140	36	smiles	smile	NOUN
istl-2566	140	37	)	)	PUNCT
istl-2566	140	38	.	.	PUNCT
istl-2566	141	1	out	out	ADP
istl-2566	141	2	of	of	ADP
istl-2566	141	3	caution	caution	NOUN
istl-2566	141	4	,	,	PUNCT
istl-2566	141	5	we	we	PRON
istl-2566	141	6	submitted	submit	VERB
istl-2566	141	7	these	these	DET
istl-2566	141	8	19	19	NUM
istl-2566	141	9	substances	substance	NOUN
istl-2566	141	10	as	as	ADP
istl-2566	141	11	chemaxon	chemaxon	NOUN
istl-2566	141	12	molfiles	molfile	NOUN
istl-2566	141	13	,	,	PUNCT
istl-2566	141	14	which	which	PRON
istl-2566	141	15	includes	include	VERB
istl-2566	141	16	the	the	DET
istl-2566	141	17	original	original	ADJ
istl-2566	141	18	2d	2d	NOUN
istl-2566	141	19	coordinates	coordinate	NOUN
istl-2566	141	20	,	,	PUNCT
istl-2566	141	21	directly	directly	ADV
istl-2566	141	22	to	to	ADP
istl-2566	141	23	pubchem	pubchem	NOUN
istl-2566	141	24	,	,	PUNCT
istl-2566	141	25	without	without	ADP
istl-2566	141	26	any	any	DET
istl-2566	141	27	local	local	ADJ
istl-2566	141	28	transfer	transfer	NOUN
istl-2566	141	29	to	to	ADP
istl-2566	141	30	other	other	ADJ
istl-2566	141	31	toolkits	toolkit	NOUN
istl-2566	141	32	.	.	PUNCT
istl-2566	142	1	no	no	DET
istl-2566	142	2	critical	critical	ADJ
istl-2566	142	3	differences	difference	NOUN
istl-2566	142	4	were	be	AUX
istl-2566	142	5	observed	observe	VERB
istl-2566	142	6	compared	compare	VERB
istl-2566	142	7	to	to	ADP
istl-2566	142	8	the	the	DET
istl-2566	142	9	original	original	ADJ
istl-2566	142	10	chemaxon	chemaxon	NOUN
istl-2566	142	11	smiles	smile	NOUN
istl-2566	142	12	to	to	ADP
istl-2566	142	13	rdkit	rdkit	ADJ
istl-2566	142	14	molfile	molfile	NOUN
istl-2566	142	15	derived	derive	VERB
istl-2566	142	16	submission	submission	NOUN
istl-2566	142	17	after	after	ADP
istl-2566	142	18	the	the	DET
istl-2566	142	19	pubchem	pubchem	PROPN
istl-2566	142	20	standardization	standardization	NOUN
istl-2566	142	21	process	process	NOUN
istl-2566	142	22	.	.	PUNCT
istl-2566	143	1	compounds	compound	NOUN
istl-2566	143	2	were	be	AUX
istl-2566	143	3	standardized	standardize	VERB
istl-2566	143	4	in	in	ADP
istl-2566	143	5	pubchem	pubchem	NOUN
istl-2566	143	6	compound	compound	NOUN
istl-2566	143	7	in	in	ADP
istl-2566	143	8	the	the	DET
istl-2566	143	9	same	same	ADJ
istl-2566	143	10	manner	manner	NOUN
istl-2566	143	11	.	.	PUNCT
istl-2566	144	1	pubchem	pubchem	PROPN
istl-2566	144	2	deposition	deposition	VERB
istl-2566	144	3	the	the	DET
istl-2566	144	4	substance	substance	NOUN
istl-2566	144	5	data	datum	NOUN
istl-2566	144	6	was	be	AUX
istl-2566	144	7	deposited	deposit	VERB
istl-2566	144	8	in	in	ADP
istl-2566	144	9	pubchem	pubchem	NOUN
istl-2566	144	10	through	through	ADP
istl-2566	144	11	their	their	PRON
istl-2566	144	12	pubchem	pubchem	NOUN
istl-2566	144	13	upload	upload	NOUN
istl-2566	144	14	interface	interface	NOUN
istl-2566	144	15	as	as	ADP
istl-2566	144	16	either	either	CCONJ
istl-2566	144	17	a	a	DET
istl-2566	144	18	sdfile	sdfile	NOUN
istl-2566	144	19	or	or	CCONJ
istl-2566	144	20	a	a	DET
istl-2566	144	21	csv	csv	ADJ
istl-2566	144	22	text	text	NOUN
istl-2566	144	23	file	file	NOUN
istl-2566	144	24	.	.	PUNCT
istl-2566	145	1	after	after	ADP
istl-2566	145	2	submission	submission	NOUN
istl-2566	145	3	,	,	PUNCT
istl-2566	145	4	it	it	PRON
istl-2566	145	5	typically	typically	ADV
istl-2566	145	6	took	take	VERB
istl-2566	145	7	3	3	NUM
istl-2566	145	8	-	-	SYM
istl-2566	145	9	7	7	NUM
istl-2566	145	10	days	day	NOUN
istl-2566	145	11	for	for	SCONJ
istl-2566	145	12	pubchem	pubchem	NOUN
istl-2566	145	13	to	to	PART
istl-2566	145	14	process	process	VERB
istl-2566	145	15	the	the	DET
istl-2566	145	16	data	datum	NOUN
istl-2566	145	17	and	and	CCONJ
istl-2566	145	18	assign	assign	VERB
istl-2566	145	19	public	public	ADJ
istl-2566	145	20	pubchem	pubchem	NOUN
istl-2566	145	21	sids	sid	NOUN
istl-2566	145	22	from	from	ADP
istl-2566	145	23	the	the	DET
istl-2566	145	24	substance	substance	NOUN
istl-2566	145	25	database	database	NOUN
istl-2566	145	26	along	along	ADP
istl-2566	145	27	with	with	ADP
istl-2566	145	28	the	the	DET
istl-2566	145	29	linked	link	VERB
istl-2566	145	30	standardized	standardized	ADJ
istl-2566	145	31	pubchem	pubchem	NOUN
istl-2566	145	32	cids	cid	NOUN
istl-2566	145	33	from	from	ADP
istl-2566	145	34	the	the	DET
istl-2566	145	35	compound	compound	NOUN
istl-2566	145	36	database	database	NOUN
istl-2566	145	37	.	.	PUNCT
istl-2566	146	1	each	each	DET
istl-2566	146	2	sid	sid	ADJ
istl-2566	146	3	record	record	NOUN
istl-2566	146	4	in	in	ADP
istl-2566	146	5	pubchem	pubchem	NOUN
istl-2566	146	6	deposited	deposit	VERB
istl-2566	146	7	by	by	ADP
istl-2566	146	8	ua	ua	PROPN
istl-2566	146	9	libraries	library	NOUN
istl-2566	146	10	uses	use	VERB
istl-2566	146	11	the	the	DET
istl-2566	146	12	external	external	ADJ
istl-2566	146	13	i	i	NOUN
istl-2566	146	14	d	d	PROPN
istl-2566	146	15	field	field	NOUN
istl-2566	146	16	to	to	PART
istl-2566	146	17	link	link	VERB
istl-2566	146	18	to	to	ADP
istl-2566	146	19	the	the	DET
istl-2566	146	20	full	full	ADJ
istl-2566	146	21	-	-	PUNCT
istl-2566	146	22	text	text	NOUN
istl-2566	146	23	thesis	thesis	NOUN
istl-2566	146	24	in	in	ADP
istl-2566	146	25	the	the	DET
istl-2566	146	26	ua	ua	NOUN
istl-2566	146	27	ir	ir	PROPN
istl-2566	146	28	or	or	CCONJ
istl-2566	146	29	the	the	DET
istl-2566	146	30	catalog	catalog	NOUN
istl-2566	146	31	metadata	metadata	PROPN
istl-2566	146	32	record	record	NOUN
istl-2566	146	33	if	if	SCONJ
istl-2566	146	34	the	the	DET
istl-2566	146	35	full	full	ADJ
istl-2566	146	36	text	text	NOUN
istl-2566	146	37	is	be	AUX
istl-2566	146	38	not	not	PART
istl-2566	146	39	available	available	ADJ
istl-2566	146	40	yet	yet	ADV
istl-2566	146	41	(	(	PUNCT
istl-2566	146	42	figure	figure	NOUN
istl-2566	146	43	1	1	NUM
istl-2566	146	44	)	)	PUNCT
istl-2566	146	45	.	.	PUNCT
istl-2566	147	1	figure	figure	VERB
istl-2566	147	2	1	1	NUM
istl-2566	147	3	.	.	X
istl-2566	147	4	example	example	NOUN
istl-2566	147	5	of	of	ADP
istl-2566	147	6	a	a	DET
istl-2566	147	7	pubchem	pubchem	NOUN
istl-2566	147	8	sid	sid	ADJ
istl-2566	147	9	record	record	NOUN
istl-2566	147	10	with	with	ADP
istl-2566	147	11	link	link	NOUN
istl-2566	147	12	to	to	ADP
istl-2566	147	13	the	the	DET
istl-2566	147	14	ua	ua	PROPN
istl-2566	147	15	libraries	library	NOUN
istl-2566	147	16	we	we	PRON
istl-2566	147	17	also	also	ADV
istl-2566	147	18	added	add	VERB
istl-2566	147	19	the	the	DET
istl-2566	147	20	full	full	ADJ
istl-2566	147	21	bibliographic	bibliographic	ADJ
istl-2566	147	22	citation	citation	NOUN
istl-2566	147	23	of	of	ADP
istl-2566	147	24	each	each	DET
istl-2566	147	25	thesis	thesis	NOUN
istl-2566	147	26	in	in	ADP
istl-2566	147	27	the	the	DET
istl-2566	147	28	depositor	depositor	NOUN
istl-2566	147	29	comment	comment	NOUN
istl-2566	147	30	field	field	NOUN
istl-2566	147	31	.	.	PUNCT
istl-2566	148	1	we	we	PRON
istl-2566	148	2	notified	notify	VERB
istl-2566	148	3	pubchem	pubchem	PROPN
istl-2566	148	4	staff	staff	NOUN
istl-2566	148	5	that	that	PRON
istl-2566	148	6	our	our	PRON
istl-2566	148	7	depositions	deposition	NOUN
istl-2566	148	8	contained	contain	VERB
istl-2566	148	9	linked	link	VERB
istl-2566	148	10	synthetic	synthetic	ADJ
istl-2566	148	11	preparatory	preparatory	ADJ
istl-2566	148	12	procedures	procedure	NOUN
istl-2566	148	13	in	in	ADP
istl-2566	148	14	the	the	DET
istl-2566	148	15	original	original	ADJ
istl-2566	148	16	thesis	thesis	NOUN
istl-2566	148	17	reference	reference	NOUN
istl-2566	148	18	.	.	PUNCT
istl-2566	149	1	as	as	ADP
istl-2566	149	2	a	a	DET
istl-2566	149	3	result	result	NOUN
istl-2566	149	4	,	,	PUNCT
istl-2566	149	5	pubchem	pubchem	PROPN
istl-2566	149	6	created	create	VERB
istl-2566	149	7	a	a	DET
istl-2566	149	8	workflow	workflow	NOUN
istl-2566	149	9	on	on	ADP
istl-2566	149	10	their	their	PRON
istl-2566	149	11	end	end	NOUN
istl-2566	149	12	during	during	ADP
istl-2566	149	13	the	the	DET
istl-2566	149	14	standardization	standardization	NOUN
istl-2566	149	15	process	process	NOUN
istl-2566	149	16	,	,	PUNCT
istl-2566	149	17	which	which	PRON
istl-2566	149	18	created	create	VERB
istl-2566	149	19	a	a	DET
istl-2566	149	20	“	"	PUNCT
istl-2566	149	21	synthesis	synthesis	NOUN
istl-2566	149	22	reference	reference	NOUN
istl-2566	149	23	”	"	PUNCT
istl-2566	149	24	annotation	annotation	NOUN
istl-2566	149	25	from	from	ADP
istl-2566	149	26	the	the	DET
istl-2566	149	27	bibliographic	bibliographic	ADJ
istl-2566	149	28	reference	reference	NOUN
istl-2566	149	29	in	in	ADP
istl-2566	149	30	the	the	DET
istl-2566	149	31	depositor	depositor	NOUN
istl-2566	149	32	comment	comment	NOUN
istl-2566	149	33	field	field	NOUN
istl-2566	149	34	.	.	PUNCT
istl-2566	150	1	the	the	DET
istl-2566	150	2	thesis	thesis	NOUN
istl-2566	150	3	reference	reference	NOUN
istl-2566	150	4	is	be	AUX
istl-2566	150	5	then	then	ADV
istl-2566	150	6	displayed	display	VERB
istl-2566	150	7	on	on	ADP
istl-2566	150	8	the	the	DET
istl-2566	150	9	associated	associated	ADJ
istl-2566	150	10	cid	cid	NOUN
istl-2566	150	11	record	record	NOUN
istl-2566	150	12	page	page	NOUN
istl-2566	150	13	in	in	ADP
istl-2566	150	14	the	the	DET
istl-2566	150	15	“	"	PUNCT
istl-2566	150	16	synthesis	synthesis	NOUN
istl-2566	150	17	reference	reference	NOUN
istl-2566	150	18	”	"	PUNCT
istl-2566	150	19	literature	literature	NOUN
istl-2566	150	20	section	section	NOUN
istl-2566	150	21	(	(	PUNCT
istl-2566	150	22	figure	figure	NOUN
istl-2566	150	23	2	2	NUM
istl-2566	150	24	)	)	PUNCT
istl-2566	150	25	.	.	PUNCT
istl-2566	151	1	figure	figure	VERB
istl-2566	151	2	2	2	NUM
istl-2566	151	3	.	.	X
istl-2566	151	4	example	example	NOUN
istl-2566	151	5	of	of	ADP
istl-2566	151	6	pubchem	pubchem	PROPN
istl-2566	151	7	cid	cid	PROPN
istl-2566	151	8	record	record	NOUN
istl-2566	151	9	showing	show	VERB
istl-2566	151	10	the	the	DET
istl-2566	151	11	thesis	thesis	NOUN
istl-2566	151	12	reference	reference	NOUN
istl-2566	151	13	in	in	ADP
istl-2566	151	14	the	the	DET
istl-2566	151	15	literature	literature	NOUN
istl-2566	151	16	section	section	NOUN
istl-2566	151	17	evaluation	evaluation	NOUN
istl-2566	151	18	of	of	ADP
istl-2566	151	19	substances	substance	NOUN
istl-2566	151	20	deposited	deposit	VERB
istl-2566	151	21	using	use	VERB
istl-2566	151	22	pubchem	pubchem	PROPN
istl-2566	151	23	programmatic	programmatic	ADJ
istl-2566	151	24	web	web	NOUN
istl-2566	151	25	requests	request	NOUN
istl-2566	151	26	,	,	PUNCT
istl-2566	151	27	we	we	PRON
istl-2566	151	28	found	find	VERB
istl-2566	151	29	that	that	SCONJ
istl-2566	151	30	1,461	1,461	NUM
istl-2566	151	31	(	(	PUNCT
istl-2566	151	32	51	51	NUM
istl-2566	151	33	%	%	NOUN
istl-2566	151	34	)	)	PUNCT
istl-2566	151	35	of	of	ADP
istl-2566	151	36	the	the	DET
istl-2566	151	37	ua	ua	PROPN
istl-2566	151	38	thesis	thesis	NOUN
istl-2566	151	39	pubchem	pubchem	PROPN
istl-2566	151	40	standardized	standardize	VERB
istl-2566	151	41	compounds	compound	NOUN
istl-2566	151	42	had	have	VERB
istl-2566	151	43	only	only	ADV
istl-2566	151	44	one	one	NUM
istl-2566	151	45	associated	associated	ADJ
istl-2566	151	46	substance	substance	NOUN
istl-2566	151	47	identifier	identifier	NOUN
istl-2566	151	48	(	(	PUNCT
istl-2566	151	49	sid	sid	ADJ
istl-2566	151	50	)	)	PUNCT
istl-2566	151	51	,	,	PUNCT
istl-2566	151	52	and	and	CCONJ
istl-2566	151	53	were	be	AUX
istl-2566	151	54	,	,	PUNCT
istl-2566	151	55	therefore	therefore	ADV
istl-2566	151	56	,	,	PUNCT
istl-2566	151	57	new	new	ADJ
istl-2566	151	58	to	to	ADP
istl-2566	151	59	the	the	DET
istl-2566	151	60	pubchem	pubchem	PROPN
istl-2566	151	61	database	database	NOUN
istl-2566	151	62	at	at	ADP
istl-2566	151	63	the	the	DET
istl-2566	151	64	time	time	NOUN
istl-2566	151	65	of	of	ADP
istl-2566	151	66	deposition	deposition	NOUN
istl-2566	151	67	.	.	PUNCT
istl-2566	152	1	pubchem	pubchem	PROPN
istl-2566	152	2	compound	compound	PROPN
istl-2566	152	3	considers	consider	VERB
istl-2566	152	4	mixtures	mixture	NOUN
istl-2566	152	5	as	as	ADP
istl-2566	152	6	unique	unique	ADJ
istl-2566	152	7	and	and	CCONJ
istl-2566	152	8	since	since	SCONJ
istl-2566	152	9	our	our	PRON
istl-2566	152	10	depositions	deposition	NOUN
istl-2566	152	11	include	include	VERB
istl-2566	152	12	mixtures	mixture	NOUN
istl-2566	152	13	,	,	PUNCT
istl-2566	152	14	the	the	DET
istl-2566	152	15	unique	unique	ADJ
istl-2566	152	16	percentage	percentage	NOUN
istl-2566	152	17	of	of	ADP
istl-2566	152	18	51	51	NUM
istl-2566	152	19	%	%	NOUN
istl-2566	152	20	may	may	AUX
istl-2566	152	21	be	be	AUX
istl-2566	152	22	slightly	slightly	ADV
istl-2566	152	23	inflated	inflate	VERB
istl-2566	152	24	.	.	PUNCT
istl-2566	153	1	we	we	PRON
istl-2566	153	2	had	have	VERB
istl-2566	153	3	a	a	DET
istl-2566	153	4	total	total	NOUN
istl-2566	153	5	of	of	ADP
istl-2566	153	6	298	298	NUM
istl-2566	153	7	mixture	mixture	NOUN
istl-2566	153	8	submissions	submission	NOUN
istl-2566	153	9	.	.	PUNCT
istl-2566	154	1	if	if	SCONJ
istl-2566	154	2	we	we	PRON
istl-2566	154	3	assume	assume	VERB
istl-2566	154	4	that	that	SCONJ
istl-2566	154	5	all	all	PRON
istl-2566	154	6	of	of	ADP
istl-2566	154	7	the	the	DET
istl-2566	154	8	mixtures	mixture	NOUN
istl-2566	154	9	had	have	AUX
istl-2566	154	10	known	know	VERB
istl-2566	154	11	individual	individual	ADJ
istl-2566	154	12	components	component	NOUN
istl-2566	154	13	,	,	PUNCT
istl-2566	154	14	this	this	PRON
istl-2566	154	15	brings	bring	VERB
istl-2566	154	16	the	the	DET
istl-2566	154	17	new	new	ADJ
istl-2566	154	18	compound	compound	NOUN
istl-2566	154	19	percentage	percentage	NOUN
istl-2566	154	20	down	down	ADP
istl-2566	154	21	to	to	ADP
istl-2566	154	22	40	40	NUM
istl-2566	154	23	%	%	NOUN
istl-2566	154	24	.	.	PUNCT
istl-2566	155	1	discussion	discussion	NOUN
istl-2566	155	2	thesis	thesis	NOUN
istl-2566	155	3	selection	selection	NOUN
istl-2566	155	4	,	,	PUNCT
istl-2566	155	5	full	full	ADJ
istl-2566	155	6	text	text	NOUN
istl-2566	155	7	limitations	limitation	NOUN
istl-2566	155	8	,	,	PUNCT
istl-2566	155	9	and	and	CCONJ
istl-2566	155	10	copyright	copyright	NOUN
istl-2566	155	11	considerations	consideration	NOUN
istl-2566	155	12	theses	theses	PROPN
istl-2566	155	13	containing	contain	VERB
istl-2566	155	14	organic	organic	NOUN
istl-2566	155	15	,	,	PUNCT
istl-2566	155	16	and	and	CCONJ
istl-2566	155	17	some	some	DET
istl-2566	155	18	limited	limited	ADJ
istl-2566	155	19	organometallic	organometallic	NOUN
istl-2566	155	20	,	,	PUNCT
istl-2566	155	21	substances	substance	NOUN
istl-2566	155	22	are	be	AUX
istl-2566	155	23	great	great	ADJ
istl-2566	155	24	candidates	candidate	NOUN
istl-2566	155	25	for	for	ADP
istl-2566	155	26	substance	substance	NOUN
istl-2566	155	27	data	datum	NOUN
istl-2566	155	28	sharing	sharing	NOUN
istl-2566	155	29	as	as	SCONJ
istl-2566	155	30	these	these	DET
istl-2566	155	31	molecules	molecule	NOUN
istl-2566	155	32	are	be	AUX
istl-2566	155	33	most	most	ADV
istl-2566	155	34	easily	easily	ADV
istl-2566	155	35	represented	represent	VERB
istl-2566	155	36	as	as	ADP
istl-2566	155	37	machine	machine	NOUN
istl-2566	155	38	-	-	PUNCT
istl-2566	155	39	readable	readable	ADJ
istl-2566	155	40	formats	format	NOUN
istl-2566	155	41	with	with	ADP
istl-2566	155	42	available	available	ADJ
istl-2566	155	43	cheminformatics	cheminformatic	NOUN
istl-2566	155	44	software	software	NOUN
istl-2566	155	45	(	(	PUNCT
istl-2566	155	46	clark	clark	NOUN
istl-2566	155	47	2011	2011	NUM
istl-2566	155	48	;	;	PUNCT
istl-2566	155	49	warr	warr	PROPN
istl-2566	155	50	2011	2011	NUM
istl-2566	155	51	;	;	PUNCT
istl-2566	155	52	hähnke	hähnke	PROPN
istl-2566	155	53	et	et	NOUN
istl-2566	155	54	al	al	PROPN
istl-2566	155	55	.	.	PROPN
istl-2566	155	56	2018	2018	NUM
istl-2566	155	57	)	)	PUNCT
istl-2566	155	58	.	.	PUNCT
istl-2566	156	1	we	we	PRON
istl-2566	156	2	,	,	PUNCT
istl-2566	156	3	therefore	therefore	ADV
istl-2566	156	4	,	,	PUNCT
istl-2566	156	5	considered	consider	VERB
istl-2566	156	6	organic	organic	ADJ
istl-2566	156	7	chemistry	chemistry	NOUN
istl-2566	156	8	theses	these	VERB
istl-2566	156	9	to	to	PART
istl-2566	156	10	be	be	AUX
istl-2566	156	11	the	the	DET
istl-2566	156	12	priority	priority	NOUN
istl-2566	156	13	area	area	NOUN
istl-2566	156	14	for	for	ADP
istl-2566	156	15	substance	substance	NOUN
istl-2566	156	16	registration	registration	NOUN
istl-2566	156	17	and	and	CCONJ
istl-2566	156	18	substance	substance	NOUN
istl-2566	156	19	data	datum	NOUN
istl-2566	156	20	sharing	sharing	NOUN
istl-2566	156	21	.	.	PUNCT
istl-2566	157	1	the	the	DET
istl-2566	157	2	majority	majority	NOUN
istl-2566	157	3	of	of	ADP
istl-2566	157	4	the	the	DET
istl-2566	157	5	theses	thesis	NOUN
istl-2566	157	6	we	we	PRON
istl-2566	157	7	identified	identify	VERB
istl-2566	157	8	at	at	ADP
istl-2566	157	9	ua	ua	PROPN
istl-2566	157	10	from	from	ADP
istl-2566	157	11	1924	1924	NUM
istl-2566	157	12	through	through	ADP
istl-2566	157	13	2020	2020	NUM
istl-2566	157	14	as	as	ADP
istl-2566	157	15	having	have	VERB
istl-2566	157	16	an	an	DET
istl-2566	157	17	organic	organic	ADJ
istl-2566	157	18	chemistry	chemistry	NOUN
istl-2566	157	19	focus	focus	NOUN
istl-2566	157	20	(	(	PUNCT
istl-2566	157	21	~200	~200	PROPN
istl-2566	157	22	)	)	PUNCT
istl-2566	157	23	,	,	PUNCT
istl-2566	157	24	were	be	AUX
istl-2566	157	25	only	only	ADV
istl-2566	157	26	available	available	ADJ
istl-2566	157	27	in	in	ADP
istl-2566	157	28	print	print	NOUN
istl-2566	157	29	.	.	PUNCT
istl-2566	158	1	as	as	ADP
istl-2566	158	2	such	such	ADJ
istl-2566	158	3	,	,	PUNCT
istl-2566	158	4	we	we	PRON
istl-2566	158	5	considered	consider	VERB
istl-2566	158	6	and	and	CCONJ
istl-2566	158	7	experimented	experiment	VERB
istl-2566	158	8	with	with	ADP
istl-2566	158	9	retrospective	retrospective	ADJ
istl-2566	158	10	digital	digital	ADJ
istl-2566	158	11	scanning	scanning	NOUN
istl-2566	158	12	of	of	ADP
istl-2566	158	13	theses	thesis	NOUN
istl-2566	158	14	and	and	CCONJ
istl-2566	158	15	deposition	deposition	NOUN
istl-2566	158	16	of	of	ADP
istl-2566	158	17	the	the	DET
istl-2566	158	18	full	full	ADJ
istl-2566	158	19	text	text	NOUN
istl-2566	158	20	in	in	ADP
istl-2566	158	21	the	the	DET
istl-2566	158	22	ua	ua	NOUN
istl-2566	158	23	ir	ir	ADV
istl-2566	158	24	as	as	SCONJ
istl-2566	158	25	permitted	permit	VERB
istl-2566	158	26	by	by	ADP
istl-2566	158	27	copyright	copyright	NOUN
istl-2566	158	28	(	(	PUNCT
istl-2566	158	29	copyright	copyright	NOUN
istl-2566	158	30	advisory	advisory	ADJ
istl-2566	158	31	network	network	NOUN
istl-2566	158	32	2020	2020	NUM
istl-2566	158	33	)	)	PUNCT
istl-2566	158	34	.	.	PUNCT
istl-2566	159	1	however	however	ADV
istl-2566	159	2	,	,	PUNCT
istl-2566	159	3	this	this	DET
istl-2566	159	4	manual	manual	ADJ
istl-2566	159	5	scanning	scanning	NOUN
istl-2566	159	6	process	process	NOUN
istl-2566	159	7	of	of	ADP
istl-2566	159	8	theses	thesis	NOUN
istl-2566	159	9	was	be	AUX
istl-2566	159	10	too	too	ADV
istl-2566	159	11	time	time	NOUN
istl-2566	159	12	consuming	consume	VERB
istl-2566	159	13	and	and	CCONJ
istl-2566	159	14	deemed	deem	VERB
istl-2566	159	15	not	not	PART
istl-2566	159	16	essential	essential	ADJ
istl-2566	159	17	to	to	ADP
istl-2566	159	18	the	the	DET
istl-2566	159	19	goals	goal	NOUN
istl-2566	159	20	of	of	ADP
istl-2566	159	21	the	the	DET
istl-2566	159	22	substance	substance	NOUN
istl-2566	159	23	registration	registration	NOUN
istl-2566	159	24	project	project	NOUN
istl-2566	159	25	.	.	PUNCT
istl-2566	160	1	as	as	SCONJ
istl-2566	160	2	each	each	DET
istl-2566	160	3	substance	substance	NOUN
istl-2566	160	4	registered	register	VERB
istl-2566	160	5	and	and	CCONJ
istl-2566	160	6	shared	share	VERB
istl-2566	160	7	would	would	AUX
istl-2566	160	8	include	include	VERB
istl-2566	160	9	the	the	DET
istl-2566	160	10	thesis	thesis	ADJ
istl-2566	160	11	bibliographic	bibliographic	ADJ
istl-2566	160	12	information	information	NOUN
istl-2566	160	13	,	,	PUNCT
istl-2566	160	14	users	user	NOUN
istl-2566	160	15	discovering	discover	VERB
istl-2566	160	16	the	the	DET
istl-2566	160	17	substance	substance	NOUN
istl-2566	160	18	data	datum	NOUN
istl-2566	160	19	can	can	AUX
istl-2566	160	20	contact	contact	VERB
istl-2566	160	21	ua	ua	NOUN
istl-2566	160	22	libraries	library	NOUN
istl-2566	160	23	for	for	ADP
istl-2566	160	24	the	the	DET
istl-2566	160	25	full	full	ADJ
istl-2566	160	26	text	text	NOUN
istl-2566	160	27	.	.	PUNCT
istl-2566	161	1	it	it	PRON
istl-2566	161	2	is	be	AUX
istl-2566	161	3	our	our	PRON
istl-2566	161	4	personal	personal	ADJ
istl-2566	161	5	understanding	understanding	NOUN
istl-2566	161	6	as	as	ADP
istl-2566	161	7	academic	academic	ADJ
istl-2566	161	8	researchers	researcher	NOUN
istl-2566	161	9	,	,	PUNCT
istl-2566	161	10	not	not	PART
istl-2566	161	11	lawyers	lawyer	NOUN
istl-2566	161	12	,	,	PUNCT
istl-2566	161	13	that	that	SCONJ
istl-2566	161	14	according	accord	VERB
istl-2566	161	15	to	to	ADP
istl-2566	161	16	the	the	DET
istl-2566	161	17	compendium	compendium	NOUN
istl-2566	161	18	of	of	ADP
istl-2566	161	19	u.s	u.s	PROPN
istl-2566	161	20	.	.	PROPN
istl-2566	161	21	copyright	copyright	PROPN
istl-2566	161	22	office	office	NOUN
istl-2566	161	23	practices	practice	NOUN
istl-2566	161	24	(	(	PUNCT
istl-2566	161	25	2017	2017	NUM
istl-2566	161	26	)	)	PUNCT
istl-2566	161	27	,	,	PUNCT
istl-2566	161	28	chemical	chemical	ADJ
istl-2566	161	29	substances	substance	NOUN
istl-2566	161	30	are	be	AUX
istl-2566	161	31	excluded	exclude	VERB
istl-2566	161	32	from	from	ADP
istl-2566	161	33	copyright	copyright	NOUN
istl-2566	161	34	protection	protection	NOUN
istl-2566	161	35	.	.	PUNCT
istl-2566	162	1	however	however	ADV
istl-2566	162	2	,	,	PUNCT
istl-2566	162	3	it	it	PRON
istl-2566	162	4	is	be	AUX
istl-2566	162	5	not	not	PART
istl-2566	162	6	clear	clear	ADJ
istl-2566	162	7	to	to	ADP
istl-2566	162	8	us	we	PRON
istl-2566	162	9	if	if	SCONJ
istl-2566	162	10	automated	automate	VERB
istl-2566	162	11	machine	machine	NOUN
istl-2566	162	12	extraction	extraction	NOUN
istl-2566	162	13	of	of	ADP
istl-2566	162	14	chemical	chemical	ADJ
istl-2566	162	15	substances	substance	NOUN
istl-2566	162	16	would	would	AUX
istl-2566	162	17	be	be	AUX
istl-2566	162	18	considered	consider	VERB
istl-2566	162	19	copying	copy	VERB
istl-2566	162	20	the	the	DET
istl-2566	162	21	thesis	thesis	NOUN
istl-2566	162	22	content	content	NOUN
istl-2566	162	23	and	and	CCONJ
istl-2566	162	24	a	a	DET
istl-2566	162	25	violation	violation	NOUN
istl-2566	162	26	of	of	ADP
istl-2566	162	27	the	the	DET
istl-2566	162	28	author	author	NOUN
istl-2566	162	29	’s	’s	PART
istl-2566	162	30	copyright	copyright	NOUN
istl-2566	162	31	.	.	PUNCT
istl-2566	163	1	andrews	andrew	NOUN
istl-2566	163	2	et	et	PROPN
istl-2566	163	3	al	al	PROPN
istl-2566	163	4	.	.	PUNCT
istl-2566	164	1	(	(	PUNCT
istl-2566	164	2	2016	2016	NUM
istl-2566	164	3	)	)	PUNCT
istl-2566	164	4	had	have	VERB
istl-2566	164	5	similar	similar	ADJ
istl-2566	164	6	concerns	concern	NOUN
istl-2566	164	7	with	with	ADP
istl-2566	164	8	machine	machine	NOUN
istl-2566	164	9	extraction	extraction	NOUN
istl-2566	164	10	in	in	ADP
istl-2566	164	11	their	their	PRON
istl-2566	164	12	thesis	thesis	NOUN
istl-2566	164	13	data	data	NOUN
istl-2566	164	14	extraction	extraction	NOUN
istl-2566	164	15	pilot	pilot	NOUN
istl-2566	164	16	.	.	PUNCT
istl-2566	165	1	given	give	VERB
istl-2566	165	2	this	this	DET
istl-2566	165	3	uncertainty	uncertainty	NOUN
istl-2566	165	4	of	of	ADP
istl-2566	165	5	machine	machine	NOUN
istl-2566	165	6	extraction	extraction	NOUN
istl-2566	165	7	and	and	CCONJ
istl-2566	165	8	copyright	copyright	NOUN
istl-2566	165	9	law	law	NOUN
istl-2566	165	10	,	,	PUNCT
istl-2566	165	11	combined	combine	VERB
istl-2566	165	12	with	with	ADP
istl-2566	165	13	the	the	DET
istl-2566	165	14	fact	fact	NOUN
istl-2566	165	15	that	that	SCONJ
istl-2566	165	16	most	most	ADJ
istl-2566	165	17	of	of	ADP
istl-2566	165	18	our	our	PRON
istl-2566	165	19	theses	thesis	NOUN
istl-2566	165	20	were	be	AUX
istl-2566	165	21	only	only	ADV
istl-2566	165	22	available	available	ADJ
istl-2566	165	23	in	in	ADP
istl-2566	165	24	print	print	NOUN
istl-2566	165	25	,	,	PUNCT
istl-2566	165	26	we	we	PRON
istl-2566	165	27	had	have	VERB
istl-2566	165	28	to	to	PART
istl-2566	165	29	use	use	VERB
istl-2566	165	30	a	a	DET
istl-2566	165	31	manual	manual	ADJ
istl-2566	165	32	substance	substance	NOUN
istl-2566	165	33	extraction	extraction	NOUN
istl-2566	165	34	approach	approach	NOUN
istl-2566	165	35	,	,	PUNCT
istl-2566	165	36	which	which	PRON
istl-2566	165	37	created	create	VERB
istl-2566	165	38	the	the	DET
istl-2566	165	39	necessity	necessity	NOUN
istl-2566	165	40	for	for	SCONJ
istl-2566	165	41	us	we	PRON
istl-2566	165	42	to	to	PART
istl-2566	165	43	redraw	redraw	VERB
istl-2566	165	44	all	all	DET
istl-2566	165	45	substance	substance	NOUN
istl-2566	165	46	structures	structure	NOUN
istl-2566	165	47	,	,	PUNCT
istl-2566	165	48	as	as	SCONJ
istl-2566	165	49	opposed	oppose	VERB
istl-2566	165	50	to	to	ADP
istl-2566	165	51	any	any	DET
istl-2566	165	52	automated	automate	VERB
istl-2566	165	53	substance	substance	NOUN
istl-2566	165	54	machine	machine	NOUN
istl-2566	165	55	-	-	PUNCT
istl-2566	165	56	extraction	extraction	NOUN
istl-2566	165	57	techniques	technique	NOUN
istl-2566	165	58	.	.	PUNCT
istl-2566	166	1	experiences	experience	NOUN
istl-2566	166	2	and	and	CCONJ
istl-2566	166	3	challenges	challenge	NOUN
istl-2566	166	4	with	with	ADP
istl-2566	166	5	substance	substance	NOUN
istl-2566	166	6	drawing	draw	VERB
istl-2566	166	7	the	the	DET
istl-2566	166	8	majority	majority	NOUN
istl-2566	166	9	of	of	ADP
istl-2566	166	10	substances	substance	NOUN
istl-2566	166	11	we	we	PRON
istl-2566	166	12	encountered	encounter	VERB
istl-2566	166	13	could	could	AUX
istl-2566	166	14	be	be	AUX
istl-2566	166	15	redrawn	redrawn	NOUN
istl-2566	166	16	in	in	ADP
istl-2566	166	17	chemaxon	chemaxon	NOUN
istl-2566	166	18	marvinsketch	marvinsketch	NOUN
istl-2566	166	19	similarly	similarly	ADV
istl-2566	166	20	to	to	ADP
istl-2566	166	21	how	how	SCONJ
istl-2566	166	22	they	they	PRON
istl-2566	166	23	were	be	AUX
istl-2566	166	24	depicted	depict	VERB
istl-2566	166	25	in	in	ADP
istl-2566	166	26	the	the	DET
istl-2566	166	27	original	original	ADJ
istl-2566	166	28	thesis	thesis	NOUN
istl-2566	166	29	;	;	PUNCT
istl-2566	166	30	that	that	PRON
istl-2566	166	31	is	is	ADV
istl-2566	166	32	,	,	PUNCT
istl-2566	166	33	the	the	DET
istl-2566	166	34	subsequent	subsequent	ADJ
istl-2566	166	35	export	export	NOUN
istl-2566	166	36	of	of	ADP
istl-2566	166	37	the	the	DET
istl-2566	166	38	machine	machine	NOUN
istl-2566	166	39	-	-	PUNCT
istl-2566	166	40	encoded	encode	VERB
istl-2566	166	41	smiles	smile	NOUN
istl-2566	166	42	faithfully	faithfully	ADV
istl-2566	166	43	preserved	preserve	VERB
istl-2566	166	44	the	the	DET
istl-2566	166	45	input	input	NOUN
istl-2566	166	46	structure	structure	NOUN
istl-2566	166	47	atoms	atom	NOUN
istl-2566	166	48	,	,	PUNCT
istl-2566	166	49	bonds	bond	NOUN
istl-2566	166	50	,	,	PUNCT
istl-2566	166	51	connectivity	connectivity	NOUN
istl-2566	166	52	,	,	PUNCT
istl-2566	166	53	and	and	CCONJ
istl-2566	166	54	stereochemistry	stereochemistry	NOUN
istl-2566	166	55	.	.	PUNCT
istl-2566	167	1	these	these	DET
istl-2566	167	2	“	"	PUNCT
istl-2566	167	3	well	well	ADV
istl-2566	167	4	-	-	PUNCT
istl-2566	167	5	behaved	behave	VERB
istl-2566	167	6	”	"	PUNCT
istl-2566	167	7	substances	substance	NOUN
istl-2566	167	8	(	(	PUNCT
istl-2566	167	9	>	>	SYM
istl-2566	167	10	90	90	NUM
istl-2566	167	11	%	%	NOUN
istl-2566	167	12	)	)	PUNCT
istl-2566	167	13	were	be	AUX
istl-2566	167	14	substances	substance	NOUN
istl-2566	167	15	that	that	PRON
istl-2566	167	16	were	be	AUX
istl-2566	167	17	drawn	draw	VERB
istl-2566	167	18	with	with	ADP
istl-2566	167	19	organic	organic	ADJ
istl-2566	167	20	chemistry	chemistry	NOUN
istl-2566	167	21	2d	2d	NUM
istl-2566	167	22	skeletal	skeletal	ADJ
istl-2566	167	23	formulas	formula	NOUN
istl-2566	167	24	,	,	PUNCT
istl-2566	167	25	which	which	PRON
istl-2566	167	26	followed	follow	VERB
istl-2566	167	27	,	,	PUNCT
istl-2566	167	28	or	or	CCONJ
istl-2566	167	29	at	at	ADP
istl-2566	167	30	least	least	ADJ
istl-2566	167	31	loosely	loosely	ADV
istl-2566	167	32	followed	follow	VERB
istl-2566	167	33	,	,	PUNCT
istl-2566	167	34	graphical	graphical	ADJ
istl-2566	167	35	representation	representation	NOUN
istl-2566	167	36	standards	standard	NOUN
istl-2566	167	37	from	from	ADP
istl-2566	167	38	iupac	iupac	PROPN
istl-2566	167	39	(	(	PUNCT
istl-2566	167	40	brecher	brecher	NOUN
istl-2566	167	41	2006	2006	NUM
istl-2566	167	42	;	;	PUNCT
istl-2566	167	43	brecher	brecher	NOUN
istl-2566	167	44	2008	2008	NUM
istl-2566	167	45	)	)	PUNCT
istl-2566	167	46	.	.	PUNCT
istl-2566	168	1	some	some	PRON
istl-2566	168	2	of	of	ADP
istl-2566	168	3	the	the	DET
istl-2566	168	4	key	key	ADJ
istl-2566	168	5	features	feature	NOUN
istl-2566	168	6	include	include	VERB
istl-2566	168	7	using	use	VERB
istl-2566	168	8	lines	line	NOUN
istl-2566	168	9	for	for	ADP
istl-2566	168	10	bonds	bond	NOUN
istl-2566	168	11	,	,	PUNCT
istl-2566	168	12	omitting	omit	VERB
istl-2566	168	13	hydrogen	hydrogen	NOUN
istl-2566	168	14	atoms	atom	NOUN
istl-2566	168	15	,	,	PUNCT
istl-2566	168	16	atomic	atomic	ADJ
istl-2566	168	17	symbols	symbol	NOUN
istl-2566	168	18	for	for	ADP
istl-2566	168	19	heteroatoms	heteroatom	NOUN
istl-2566	168	20	,	,	PUNCT
istl-2566	168	21	plus	plus	CCONJ
istl-2566	168	22	or	or	CCONJ
istl-2566	168	23	minus	minus	CCONJ
istl-2566	168	24	symbols	symbol	NOUN
istl-2566	168	25	for	for	ADP
istl-2566	168	26	charges	charge	NOUN
istl-2566	168	27	,	,	PUNCT
istl-2566	168	28	and	and	CCONJ
istl-2566	168	29	hashed	hash	VERB
istl-2566	168	30	or	or	CCONJ
istl-2566	168	31	solid	solid	ADJ
istl-2566	168	32	wedges	wedge	NOUN
istl-2566	168	33	/	/	SYM
istl-2566	168	34	bonds	bond	NOUN
istl-2566	168	35	for	for	ADP
istl-2566	168	36	stereochemistry	stereochemistry	NOUN
istl-2566	168	37	(	(	PUNCT
istl-2566	168	38	figure	figure	NOUN
istl-2566	168	39	3	3	NUM
istl-2566	168	40	)	)	PUNCT
istl-2566	168	41	.	.	PUNCT
istl-2566	169	1	these	these	DET
istl-2566	169	2	types	type	NOUN
istl-2566	169	3	of	of	ADP
istl-2566	169	4	structures	structure	NOUN
istl-2566	169	5	are	be	AUX
istl-2566	169	6	most	most	ADV
istl-2566	169	7	easily	easily	ADV
istl-2566	169	8	interpreted	interpret	VERB
istl-2566	169	9	by	by	ADP
istl-2566	169	10	cheminformatics	cheminformatic	NOUN
istl-2566	169	11	software	software	NOUN
istl-2566	169	12	(	(	PUNCT
istl-2566	169	13	brecher	brecher	PROPN
istl-2566	169	14	2008	2008	NUM
istl-2566	169	15	;	;	PUNCT
istl-2566	169	16	martin	martin	PROPN
istl-2566	169	17	et	et	PROPN
istl-2566	169	18	al	al	PROPN
istl-2566	169	19	.	.	PROPN
istl-2566	169	20	2012	2012	NUM
istl-2566	169	21	)	)	PUNCT
istl-2566	169	22	.	.	PUNCT
istl-2566	170	1	figure	figure	VERB
istl-2566	170	2	3	3	NUM
istl-2566	170	3	.	.	X
istl-2566	170	4	examples	example	NOUN
istl-2566	170	5	of	of	ADP
istl-2566	170	6	“	"	PUNCT
istl-2566	170	7	well	well	ADV
istl-2566	170	8	-	-	PUNCT
istl-2566	170	9	behaved	behave	VERB
istl-2566	170	10	”	"	PUNCT
istl-2566	170	11	substance	substance	NOUN
istl-2566	170	12	drawings	drawing	NOUN
istl-2566	170	13	redrawn	redrawn	NOUN
istl-2566	170	14	as	as	SCONJ
istl-2566	170	15	depicted	depict	VERB
istl-2566	170	16	we	we	PRON
istl-2566	170	17	found	find	VERB
istl-2566	170	18	that	that	SCONJ
istl-2566	170	19	we	we	PRON
istl-2566	170	20	were	be	AUX
istl-2566	170	21	efficient	efficient	ADJ
istl-2566	170	22	with	with	ADP
istl-2566	170	23	drawing	draw	VERB
istl-2566	170	24	structures	structure	NOUN
istl-2566	170	25	in	in	ADP
istl-2566	170	26	chemaxon	chemaxon	NOUN
istl-2566	170	27	marvinsketch	marvinsketch	NOUN
istl-2566	170	28	;	;	PUNCT
istl-2566	170	29	however	however	ADV
istl-2566	170	30	,	,	PUNCT
istl-2566	170	31	different	different	ADJ
istl-2566	170	32	structure	structure	NOUN
istl-2566	170	33	editors	editor	NOUN
istl-2566	170	34	can	can	AUX
istl-2566	170	35	certainly	certainly	ADV
istl-2566	170	36	be	be	AUX
istl-2566	170	37	used	use	VERB
istl-2566	170	38	and	and	CCONJ
istl-2566	170	39	there	there	PRON
istl-2566	170	40	are	be	VERB
istl-2566	170	41	a	a	DET
istl-2566	170	42	variety	variety	NOUN
istl-2566	170	43	of	of	ADP
istl-2566	170	44	other	other	ADJ
istl-2566	170	45	editors	editor	NOUN
istl-2566	170	46	available	available	ADJ
istl-2566	170	47	depending	depend	VERB
istl-2566	170	48	upon	upon	SCONJ
istl-2566	170	49	preferences	preference	NOUN
istl-2566	170	50	such	such	ADJ
istl-2566	170	51	as	as	ADP
istl-2566	170	52	chemdraw	chemdraw	NOUN
istl-2566	170	53	or	or	CCONJ
istl-2566	170	54	pubchem	pubchem	NOUN
istl-2566	170	55	sketcher	sketcher	PROPN
istl-2566	170	56	(	(	PUNCT
istl-2566	170	57	ihlenfeldt	ihlenfeldt	PROPN
istl-2566	170	58	et	et	PROPN
istl-2566	170	59	al	al	PROPN
istl-2566	170	60	.	.	PROPN
istl-2566	170	61	2009	2009	NUM
istl-2566	170	62	)	)	PUNCT
istl-2566	170	63	.	.	PUNCT
istl-2566	171	1	preserving	preserve	VERB
istl-2566	171	2	stereochemistry	stereochemistry	NOUN
istl-2566	171	3	from	from	ADP
istl-2566	171	4	perspective	perspective	ADJ
istl-2566	171	5	chemical	chemical	NOUN
istl-2566	171	6	substance	substance	NOUN
istl-2566	171	7	drawings	drawing	NOUN
istl-2566	171	8	(	(	PUNCT
istl-2566	171	9	figure	figure	NOUN
istl-2566	171	10	4	4	NUM
istl-2566	171	11	)	)	PUNCT
istl-2566	171	12	and	and	CCONJ
istl-2566	171	13	handling	handle	VERB
istl-2566	171	14	stereochemical	stereochemical	ADJ
istl-2566	171	15	mixtures	mixture	NOUN
istl-2566	171	16	was	be	AUX
istl-2566	171	17	the	the	DET
istl-2566	171	18	most	most	ADV
istl-2566	171	19	challenging	challenging	ADJ
istl-2566	171	20	aspect	aspect	NOUN
istl-2566	171	21	of	of	ADP
istl-2566	171	22	redrawing	redrawe	VERB
istl-2566	171	23	chemical	chemical	ADJ
istl-2566	171	24	substances	substance	NOUN
istl-2566	171	25	.	.	PUNCT
istl-2566	172	1	perspective	perspective	NOUN
istl-2566	172	2	drawings	drawing	NOUN
istl-2566	172	3	including	include	VERB
istl-2566	172	4	haworth	haworth	NOUN
istl-2566	172	5	,	,	PUNCT
istl-2566	172	6	chair	chair	NOUN
istl-2566	172	7	,	,	PUNCT
istl-2566	172	8	and	and	CCONJ
istl-2566	172	9	fischer	fischer	NOUN
istl-2566	172	10	projections	projection	NOUN
istl-2566	172	11	are	be	AUX
istl-2566	172	12	designed	design	VERB
istl-2566	172	13	for	for	ADP
istl-2566	172	14	humans	human	NOUN
istl-2566	172	15	and	and	CCONJ
istl-2566	172	16	are	be	AUX
istl-2566	172	17	generally	generally	ADV
istl-2566	172	18	not	not	PART
istl-2566	172	19	fully	fully	ADV
istl-2566	172	20	interpreted	interpret	VERB
istl-2566	172	21	by	by	ADP
istl-2566	172	22	most	most	ADJ
istl-2566	172	23	chemical	chemical	NOUN
istl-2566	172	24	drawing	drawing	NOUN
istl-2566	172	25	software	software	NOUN
istl-2566	172	26	tools	tool	NOUN
istl-2566	172	27	,	,	PUNCT
istl-2566	172	28	with	with	ADP
istl-2566	172	29	the	the	DET
istl-2566	172	30	major	major	ADJ
istl-2566	172	31	limitation	limitation	NOUN
istl-2566	172	32	being	be	AUX
istl-2566	172	33	loss	loss	NOUN
istl-2566	172	34	of	of	ADP
istl-2566	172	35	stereochemical	stereochemical	ADJ
istl-2566	172	36	information	information	NOUN
istl-2566	172	37	(	(	PUNCT
istl-2566	172	38	brecher	brecher	NOUN
istl-2566	172	39	2008	2008	NUM
istl-2566	172	40	;	;	PUNCT
istl-2566	172	41	gobbi	gobbi	PROPN
istl-2566	172	42	&	&	CCONJ
istl-2566	172	43	lee	lee	PROPN
istl-2566	172	44	2012	2012	NUM
istl-2566	172	45	;	;	PUNCT
istl-2566	172	46	martin	martin	PROPN
istl-2566	172	47	et	et	PROPN
istl-2566	172	48	al	al	PROPN
istl-2566	172	49	.	.	PROPN
istl-2566	172	50	2012	2012	NUM
istl-2566	172	51	)	)	PUNCT
istl-2566	172	52	.	.	PUNCT
istl-2566	173	1	to	to	ADP
istl-2566	173	2	our	our	PRON
istl-2566	173	3	knowledge	knowledge	NOUN
istl-2566	173	4	,	,	PUNCT
istl-2566	173	5	the	the	DET
istl-2566	173	6	only	only	ADJ
istl-2566	173	7	consumer	consumer	NOUN
istl-2566	173	8	/	/	SYM
istl-2566	173	9	academic	academic	ADJ
istl-2566	173	10	software	software	NOUN
istl-2566	173	11	that	that	PRON
istl-2566	173	12	can	can	AUX
istl-2566	173	13	automatically	automatically	ADV
istl-2566	173	14	assign	assign	VERB
istl-2566	173	15	stereochemistry	stereochemistry	NOUN
istl-2566	173	16	in	in	ADP
istl-2566	173	17	perspective	perspective	NOUN
istl-2566	173	18	drawings	drawing	NOUN
istl-2566	173	19	is	be	AUX
istl-2566	173	20	the	the	DET
istl-2566	173	21	knowitall	knowitall	PROPN
istl-2566	173	22	chemwindow	chemwindow	ADJ
istl-2566	173	23	structure	structure	NOUN
istl-2566	173	24	editor	editor	NOUN
istl-2566	173	25	(	(	PUNCT
istl-2566	173	26	abshear	abshear	VERB
istl-2566	173	27	et	et	PROPN
istl-2566	173	28	al	al	PROPN
istl-2566	173	29	.	.	PROPN
istl-2566	173	30	2018	2018	NUM
istl-2566	173	31	)	)	PUNCT
istl-2566	173	32	.	.	PUNCT
istl-2566	174	1	given	give	VERB
istl-2566	174	2	the	the	DET
istl-2566	174	3	software	software	NOUN
istl-2566	174	4	limitations	limitation	NOUN
istl-2566	174	5	of	of	ADP
istl-2566	174	6	interpreting	interpret	VERB
istl-2566	174	7	perspective	perspective	NOUN
istl-2566	174	8	drawings	drawing	NOUN
istl-2566	174	9	,	,	PUNCT
istl-2566	174	10	we	we	PRON
istl-2566	174	11	either	either	CCONJ
istl-2566	174	12	had	have	VERB
istl-2566	174	13	to	to	PART
istl-2566	174	14	manually	manually	ADV
istl-2566	174	15	infer	infer	VERB
istl-2566	174	16	the	the	DET
istl-2566	174	17	stereochemistry	stereochemistry	NOUN
istl-2566	174	18	and	and	CCONJ
istl-2566	174	19	redraw	redraw	VERB
istl-2566	174	20	the	the	DET
istl-2566	174	21	structures	structure	NOUN
istl-2566	174	22	with	with	ADP
istl-2566	174	23	standard	standard	ADJ
istl-2566	174	24	hash	hash	NOUN
istl-2566	174	25	/	/	SYM
istl-2566	174	26	solid	solid	ADJ
istl-2566	174	27	wedges	wedge	NOUN
istl-2566	174	28	for	for	ADP
istl-2566	174	29	stereochemistry	stereochemistry	NOUN
istl-2566	174	30	or	or	CCONJ
istl-2566	174	31	use	use	VERB
istl-2566	174	32	the	the	DET
istl-2566	174	33	knowitall	knowitall	NOUN
istl-2566	174	34	chemwindow	chemwindow	ADJ
istl-2566	174	35	software	software	NOUN
istl-2566	174	36	to	to	PART
istl-2566	174	37	perceive	perceive	VERB
istl-2566	174	38	the	the	DET
istl-2566	174	39	stereochemistry	stereochemistry	NOUN
istl-2566	174	40	automatically	automatically	ADV
istl-2566	174	41	.	.	PUNCT
istl-2566	175	1	we	we	PRON
istl-2566	175	2	found	find	VERB
istl-2566	175	3	that	that	SCONJ
istl-2566	175	4	it	it	PRON
istl-2566	175	5	was	be	AUX
istl-2566	175	6	most	most	ADV
istl-2566	175	7	efficient	efficient	ADJ
istl-2566	175	8	for	for	SCONJ
istl-2566	175	9	us	we	PRON
istl-2566	175	10	to	to	PART
istl-2566	175	11	manually	manually	ADV
istl-2566	175	12	redraw	redraw	VERB
istl-2566	175	13	haworth	haworth	NOUN
istl-2566	175	14	projections	projection	NOUN
istl-2566	175	15	as	as	ADP
istl-2566	175	16	non	non	ADJ
istl-2566	175	17	-	-	ADJ
istl-2566	175	18	perspective	perspective	ADJ
istl-2566	175	19	drawings	drawing	NOUN
istl-2566	175	20	in	in	ADP
istl-2566	175	21	marvinsketch	marvinsketch	NOUN
istl-2566	175	22	.	.	PUNCT
istl-2566	176	1	however	however	ADV
istl-2566	176	2	,	,	PUNCT
istl-2566	176	3	for	for	ADP
istl-2566	176	4	the	the	DET
istl-2566	176	5	chair	chair	NOUN
istl-2566	176	6	and	and	CCONJ
istl-2566	176	7	fischer	fischer	NOUN
istl-2566	176	8	projections	projection	NOUN
istl-2566	176	9	,	,	PUNCT
istl-2566	176	10	it	it	PRON
istl-2566	176	11	was	be	AUX
istl-2566	176	12	faster	fast	ADJ
istl-2566	176	13	for	for	SCONJ
istl-2566	176	14	us	we	PRON
istl-2566	176	15	to	to	PART
istl-2566	176	16	draw	draw	VERB
istl-2566	176	17	these	these	PRON
istl-2566	176	18	in	in	ADP
istl-2566	176	19	chemwindow	chemwindow	ADJ
istl-2566	176	20	than	than	SCONJ
istl-2566	176	21	to	to	PART
istl-2566	176	22	manually	manually	ADV
istl-2566	176	23	perceive	perceive	VERB
istl-2566	176	24	the	the	DET
istl-2566	176	25	stereochemistry	stereochemistry	NOUN
istl-2566	176	26	.	.	PUNCT
istl-2566	177	1	figure	figure	NOUN
istl-2566	177	2	4	4	NUM
istl-2566	177	3	.	.	X
istl-2566	177	4	example	example	VERB
istl-2566	177	5	haworth	haworth	NOUN
istl-2566	177	6	(	(	PUNCT
istl-2566	177	7	a	a	X
istl-2566	177	8	)	)	PUNCT
istl-2566	177	9	,	,	PUNCT
istl-2566	177	10	chair	chair	NOUN
istl-2566	177	11	(	(	PUNCT
istl-2566	177	12	b	b	PROPN
istl-2566	177	13	)	)	PUNCT
istl-2566	177	14	,	,	PUNCT
istl-2566	177	15	and	and	CCONJ
istl-2566	177	16	fischer	fischer	NOUN
istl-2566	177	17	projections	projection	NOUN
istl-2566	177	18	(	(	PUNCT
istl-2566	177	19	c	c	NOUN
istl-2566	177	20	)	)	PUNCT
istl-2566	177	21	(	(	PUNCT
istl-2566	177	22	adapted	adapt	VERB
istl-2566	177	23	from	from	ADP
istl-2566	177	24	martin	martin	PROPN
istl-2566	177	25	et	et	PROPN
istl-2566	177	26	al	al	PROPN
istl-2566	177	27	.	.	PUNCT
istl-2566	178	1	(	(	PUNCT
istl-2566	178	2	2012	2012	NUM
istl-2566	178	3	)	)	PUNCT
istl-2566	178	4	)	)	PUNCT
istl-2566	179	1	ideally	ideally	ADV
istl-2566	179	2	,	,	PUNCT
istl-2566	179	3	for	for	ADP
istl-2566	179	4	stereochemical	stereochemical	ADJ
istl-2566	179	5	mixtures	mixture	NOUN
istl-2566	179	6	including	include	VERB
istl-2566	179	7	racemic	racemic	ADJ
istl-2566	179	8	,	,	PUNCT
istl-2566	179	9	enantiomers	enantiomer	NOUN
istl-2566	179	10	,	,	PUNCT
istl-2566	179	11	and	and	CCONJ
istl-2566	179	12	diastereomers	diastereomer	NOUN
istl-2566	179	13	,	,	PUNCT
istl-2566	179	14	we	we	PRON
istl-2566	179	15	would	would	AUX
istl-2566	179	16	use	use	VERB
istl-2566	179	17	a	a	DET
istl-2566	179	18	file	file	NOUN
istl-2566	179	19	format	format	NOUN
istl-2566	179	20	such	such	ADJ
istl-2566	179	21	as	as	ADP
istl-2566	179	22	molfile	molfile	NOUN
istl-2566	179	23	v3000	v3000	PROPN
istl-2566	179	24	or	or	CCONJ
istl-2566	179	25	chemaxon	chemaxon	PROPN
istl-2566	179	26	extended	extend	VERB
istl-2566	179	27	smiles	smile	NOUN
istl-2566	179	28	that	that	PRON
istl-2566	179	29	support	support	VERB
istl-2566	179	30	relative	relative	ADJ
istl-2566	179	31	configuration	configuration	NOUN
istl-2566	179	32	of	of	ADP
istl-2566	179	33	stereocenters	stereocenter	NOUN
istl-2566	179	34	(	(	PUNCT
istl-2566	179	35	gobbi	gobbi	PROPN
istl-2566	179	36	&	&	CCONJ
istl-2566	179	37	lee	lee	PROPN
istl-2566	179	38	2012	2012	NUM
istl-2566	179	39	;	;	PUNCT
istl-2566	179	40	martin	martin	PROPN
istl-2566	179	41	et	et	PROPN
istl-2566	179	42	al	al	PROPN
istl-2566	179	43	.	.	PROPN
istl-2566	179	44	2012	2012	NUM
istl-2566	179	45	;	;	PUNCT
istl-2566	179	46	chemaxon	chemaxon	NOUN
istl-2566	179	47	2021	2021	NUM
istl-2566	179	48	)	)	PUNCT
istl-2566	179	49	.	.	PUNCT
istl-2566	180	1	however	however	ADV
istl-2566	180	2	,	,	PUNCT
istl-2566	180	3	pubchem	pubchem	PROPN
istl-2566	180	4	does	do	AUX
istl-2566	180	5	not	not	PART
istl-2566	180	6	support	support	VERB
istl-2566	180	7	relative	relative	ADJ
istl-2566	180	8	stereochemistry	stereochemistry	NOUN
istl-2566	180	9	or	or	CCONJ
istl-2566	180	10	defined	define	VERB
istl-2566	180	11	mixtures	mixture	NOUN
istl-2566	180	12	of	of	ADP
istl-2566	180	13	stereoisomers	stereoisomer	NOUN
istl-2566	180	14	as	as	ADP
istl-2566	180	15	a	a	DET
istl-2566	180	16	single	single	ADJ
istl-2566	180	17	structure	structure	NOUN
istl-2566	180	18	.	.	PUNCT
istl-2566	181	1	support	support	NOUN
istl-2566	181	2	for	for	ADP
istl-2566	181	3	enhanced	enhance	VERB
istl-2566	181	4	stereochemistry	stereochemistry	NOUN
istl-2566	181	5	is	be	AUX
istl-2566	181	6	technically	technically	ADV
istl-2566	181	7	possible	possible	ADJ
istl-2566	181	8	and	and	CCONJ
istl-2566	181	9	defined	define	VERB
istl-2566	181	10	within	within	ADP
istl-2566	181	11	the	the	DET
istl-2566	181	12	pubchem	pubchem	PROPN
istl-2566	181	13	stereochemistry	stereochemistry	NOUN
istl-2566	181	14	specification	specification	NOUN
istl-2566	181	15	,	,	PUNCT
istl-2566	181	16	but	but	CCONJ
istl-2566	181	17	this	this	DET
istl-2566	181	18	feature	feature	NOUN
istl-2566	181	19	is	be	AUX
istl-2566	181	20	not	not	PART
istl-2566	181	21	currently	currently	ADV
istl-2566	181	22	supported	support	VERB
istl-2566	181	23	(	(	PUNCT
istl-2566	181	24	national	national	ADJ
istl-2566	181	25	center	center	NOUN
istl-2566	181	26	for	for	ADP
istl-2566	181	27	biotechnology	biotechnology	NOUN
istl-2566	181	28	information	information	NOUN
istl-2566	182	1	[	[	PUNCT
istl-2566	182	2	date	date	NOUN
istl-2566	182	3	unknown	unknown	ADJ
istl-2566	182	4	-	-	PUNCT
istl-2566	182	5	a	a	NOUN
istl-2566	182	6	]	]	PUNCT
istl-2566	182	7	)	)	PUNCT
istl-2566	182	8	.	.	PUNCT
istl-2566	183	1	further	far	ADV
istl-2566	183	2	,	,	PUNCT
istl-2566	183	3	we	we	PRON
istl-2566	183	4	selected	select	VERB
istl-2566	183	5	the	the	DET
istl-2566	183	6	standard	standard	ADJ
istl-2566	183	7	inchi	inchi	NOUN
istl-2566	183	8	as	as	ADP
istl-2566	183	9	our	our	PRON
istl-2566	183	10	local	local	ADJ
istl-2566	183	11	substance	substance	NOUN
istl-2566	183	12	uniqueness	uniqueness	NOUN
istl-2566	183	13	check	check	NOUN
istl-2566	183	14	,	,	PUNCT
istl-2566	183	15	and	and	CCONJ
istl-2566	183	16	this	this	DET
istl-2566	183	17	process	process	NOUN
istl-2566	183	18	considers	consider	VERB
istl-2566	183	19	the	the	DET
istl-2566	183	20	substances	substance	NOUN
istl-2566	183	21	as	as	ADP
istl-2566	183	22	only	only	ADV
istl-2566	183	23	absolute	absolute	ADJ
istl-2566	183	24	stereochemistry	stereochemistry	NOUN
istl-2566	183	25	.	.	PUNCT
istl-2566	184	1	as	as	ADP
istl-2566	184	2	a	a	DET
istl-2566	184	3	result	result	NOUN
istl-2566	184	4	of	of	ADP
istl-2566	184	5	these	these	DET
istl-2566	184	6	limitations	limitation	NOUN
istl-2566	184	7	,	,	PUNCT
istl-2566	184	8	using	use	VERB
istl-2566	184	9	file	file	NOUN
istl-2566	184	10	formats	format	NOUN
istl-2566	184	11	that	that	PRON
istl-2566	184	12	support	support	VERB
istl-2566	184	13	enhanced	enhance	VERB
istl-2566	184	14	stereochemistry	stereochemistry	NOUN
istl-2566	184	15	was	be	AUX
istl-2566	184	16	not	not	PART
istl-2566	184	17	an	an	DET
istl-2566	184	18	option	option	NOUN
istl-2566	184	19	for	for	ADP
istl-2566	184	20	us	we	PRON
istl-2566	184	21	and	and	CCONJ
istl-2566	184	22	we	we	PRON
istl-2566	184	23	instead	instead	ADV
istl-2566	184	24	represented	represent	VERB
istl-2566	184	25	stereochemical	stereochemical	ADJ
istl-2566	184	26	mixtures	mixture	NOUN
istl-2566	184	27	including	include	VERB
istl-2566	184	28	racemates	racemate	NOUN
istl-2566	184	29	,	,	PUNCT
istl-2566	184	30	enantiomers	enantiomer	NOUN
istl-2566	184	31	with	with	ADP
istl-2566	184	32	any	any	DET
istl-2566	184	33	ratio	ratio	NOUN
istl-2566	184	34	,	,	PUNCT
istl-2566	184	35	and	and	CCONJ
istl-2566	184	36	diastereomers	diastereomer	NOUN
istl-2566	184	37	within	within	ADP
istl-2566	184	38	one	one	NUM
istl-2566	184	39	registry	registry	NOUN
istl-2566	184	40	identifier	identifier	ADV
istl-2566	184	41	as	as	ADP
istl-2566	184	42	separate	separate	ADJ
istl-2566	184	43	disconnected	disconnected	ADJ
istl-2566	184	44	substances	substance	NOUN
istl-2566	184	45	.	.	PUNCT
istl-2566	185	1	such	such	ADJ
istl-2566	185	2	representation	representation	NOUN
istl-2566	185	3	limitations	limitation	NOUN
istl-2566	185	4	within	within	ADP
istl-2566	185	5	chemical	chemical	NOUN
istl-2566	185	6	databases	database	NOUN
istl-2566	185	7	are	be	AUX
istl-2566	185	8	discussed	discuss	VERB
istl-2566	185	9	by	by	ADP
istl-2566	185	10	hersey	hersey	PROPN
istl-2566	185	11	et	et	PROPN
istl-2566	185	12	al	al	PROPN
istl-2566	185	13	.	.	PUNCT
istl-2566	185	14	(	(	PUNCT
istl-2566	185	15	2015	2015	NUM
istl-2566	185	16	)	)	PUNCT
istl-2566	185	17	,	,	PUNCT
istl-2566	185	18	and	and	CCONJ
istl-2566	185	19	there	there	PRON
istl-2566	185	20	is	be	VERB
istl-2566	185	21	,	,	PUNCT
istl-2566	185	22	unfortunately	unfortunately	ADV
istl-2566	185	23	,	,	PUNCT
istl-2566	185	24	not	not	PART
istl-2566	185	25	currently	currently	ADV
istl-2566	185	26	an	an	DET
istl-2566	185	27	accepted	accept	VERB
istl-2566	185	28	standard	standard	NOUN
istl-2566	185	29	across	across	ADP
istl-2566	185	30	public	public	ADJ
istl-2566	185	31	databases	database	NOUN
istl-2566	185	32	for	for	ADP
istl-2566	185	33	how	how	SCONJ
istl-2566	185	34	to	to	PART
istl-2566	185	35	represent	represent	VERB
istl-2566	185	36	stereochemical	stereochemical	ADJ
istl-2566	185	37	mixtures	mixture	NOUN
istl-2566	185	38	;	;	PUNCT
istl-2566	185	39	some	some	DET
istl-2566	185	40	sources	source	NOUN
istl-2566	185	41	choose	choose	VERB
istl-2566	185	42	to	to	PART
istl-2566	185	43	draw	draw	VERB
istl-2566	185	44	racemic	racemic	ADJ
istl-2566	185	45	mixtures	mixture	NOUN
istl-2566	185	46	as	as	ADP
istl-2566	185	47	one	one	NUM
istl-2566	185	48	substance	substance	NOUN
istl-2566	185	49	with	with	ADP
istl-2566	185	50	no	no	DET
istl-2566	185	51	stereochemistry	stereochemistry	NOUN
istl-2566	185	52	,	,	PUNCT
istl-2566	185	53	while	while	SCONJ
istl-2566	185	54	others	other	NOUN
istl-2566	185	55	draw	draw	VERB
istl-2566	185	56	multiple	multiple	ADJ
istl-2566	185	57	enantiomers	enantiomer	NOUN
istl-2566	185	58	or	or	CCONJ
istl-2566	185	59	diastereomers	diastereomer	NOUN
istl-2566	185	60	in	in	ADP
istl-2566	185	61	one	one	NUM
istl-2566	185	62	record	record	NOUN
istl-2566	185	63	(	(	PUNCT
istl-2566	185	64	food	food	NOUN
istl-2566	185	65	and	and	CCONJ
istl-2566	185	66	drug	drug	NOUN
istl-2566	185	67	administration	administration	NOUN
istl-2566	185	68	2007	2007	NUM
istl-2566	185	69	;	;	PUNCT
istl-2566	185	70	hersey	hersey	VERB
istl-2566	185	71	et	et	PROPN
istl-2566	185	72	al	al	PROPN
istl-2566	185	73	.	.	PROPN
istl-2566	185	74	2015	2015	NUM
istl-2566	185	75	)	)	PUNCT
istl-2566	185	76	.	.	PUNCT
istl-2566	186	1	lastly	lastly	ADV
istl-2566	186	2	,	,	PUNCT
istl-2566	186	3	drawing	draw	VERB
istl-2566	186	4	multiple	multiple	ADJ
istl-2566	186	5	substances	substance	NOUN
istl-2566	186	6	in	in	ADP
istl-2566	186	7	a	a	DET
istl-2566	186	8	record	record	NOUN
istl-2566	186	9	creates	create	VERB
istl-2566	186	10	a	a	DET
istl-2566	186	11	way	way	NOUN
istl-2566	186	12	to	to	PART
istl-2566	186	13	describe	describe	VERB
istl-2566	186	14	molecules	molecule	NOUN
istl-2566	186	15	by	by	ADP
istl-2566	186	16	the	the	DET
istl-2566	186	17	and	and	CCONJ
istl-2566	186	18	operator	operator	NOUN
istl-2566	186	19	,	,	PUNCT
istl-2566	186	20	for	for	ADP
istl-2566	186	21	example	example	NOUN
istl-2566	186	22	:	:	PUNCT
istl-2566	186	23	(	(	PUNCT
istl-2566	186	24	2s)-2	2s)-2	NUM
istl-2566	186	25	-	-	PUNCT
istl-2566	186	26	bromobutane	bromobutane	NOUN
istl-2566	186	27	and	and	CCONJ
istl-2566	186	28	(	(	PUNCT
istl-2566	186	29	2r)-2	2r)-2	NUM
istl-2566	186	30	-	-	PUNCT
istl-2566	186	31	bromobutane	bromobutane	NOUN
istl-2566	186	32	.	.	PUNCT
istl-2566	187	1	it	it	PRON
istl-2566	187	2	is	be	AUX
istl-2566	187	3	unclear	unclear	ADJ
istl-2566	187	4	how	how	SCONJ
istl-2566	187	5	to	to	PART
istl-2566	187	6	best	well	ADV
istl-2566	187	7	represent	represent	VERB
istl-2566	187	8	a	a	DET
istl-2566	187	9	substance	substance	NOUN
istl-2566	187	10	with	with	ADP
istl-2566	187	11	a	a	DET
istl-2566	187	12	defined	define	VERB
istl-2566	187	13	“	"	PUNCT
istl-2566	187	14	or	or	CCONJ
istl-2566	187	15	”	"	PUNCT
istl-2566	187	16	scenario	scenario	NOUN
istl-2566	187	17	within	within	ADP
istl-2566	187	18	one	one	NUM
istl-2566	187	19	registry	registry	NOUN
istl-2566	187	20	identifier	identifier	ADV
istl-2566	187	21	in	in	ADP
istl-2566	187	22	public	public	ADJ
istl-2566	187	23	databases	database	NOUN
istl-2566	187	24	,	,	PUNCT
istl-2566	187	25	without	without	ADP
istl-2566	187	26	using	use	VERB
istl-2566	187	27	extended	extended	ADJ
istl-2566	187	28	stereochemistry	stereochemistry	NOUN
istl-2566	187	29	file	file	NOUN
istl-2566	187	30	formats	format	NOUN
istl-2566	187	31	,	,	PUNCT
istl-2566	187	32	such	such	ADJ
istl-2566	187	33	as	as	ADP
istl-2566	187	34	in	in	ADP
istl-2566	187	35	the	the	DET
istl-2566	187	36	case	case	NOUN
istl-2566	187	37	of	of	ADP
istl-2566	187	38	(	(	PUNCT
istl-2566	187	39	2s)-2	2s)-2	NUM
istl-2566	187	40	-	-	PUNCT
istl-2566	187	41	bromobutane	bromobutane	NOUN
istl-2566	187	42	or	or	CCONJ
istl-2566	187	43	(	(	PUNCT
istl-2566	187	44	2r)-2	2r)-2	NUM
istl-2566	187	45	-	-	PUNCT
istl-2566	187	46	bromobutane	bromobutane	NOUN
istl-2566	187	47	.	.	PUNCT
istl-2566	188	1	machine	machine	NOUN
istl-2566	188	2	-	-	PUNCT
istl-2566	188	3	readable	readable	ADJ
istl-2566	188	4	file	file	NOUN
istl-2566	188	5	creation	creation	NOUN
istl-2566	188	6	experiences	experience	NOUN
istl-2566	188	7	and	and	CCONJ
istl-2566	188	8	recommendations	recommendation	NOUN
istl-2566	188	9	as	as	SCONJ
istl-2566	188	10	noted	note	VERB
istl-2566	188	11	above	above	ADV
istl-2566	188	12	,	,	PUNCT
istl-2566	188	13	most	most	ADJ
istl-2566	188	14	of	of	ADP
istl-2566	188	15	the	the	DET
istl-2566	188	16	substance	substance	NOUN
istl-2566	188	17	representations	representation	NOUN
istl-2566	188	18	were	be	AUX
istl-2566	188	19	processed	process	VERB
istl-2566	188	20	using	use	VERB
istl-2566	188	21	the	the	DET
istl-2566	188	22	rdkit	rdkit	NOUN
istl-2566	188	23	to	to	PART
istl-2566	188	24	create	create	VERB
istl-2566	188	25	sdfiles	sdfile	NOUN
istl-2566	188	26	.	.	PUNCT
istl-2566	189	1	we	we	PRON
istl-2566	189	2	selected	select	VERB
istl-2566	189	3	rdkit	rdkit	ADJ
istl-2566	189	4	because	because	SCONJ
istl-2566	189	5	of	of	ADP
istl-2566	189	6	its	its	PRON
istl-2566	189	7	strong	strong	ADJ
istl-2566	189	8	integration	integration	NOUN
istl-2566	189	9	with	with	ADP
istl-2566	189	10	the	the	DET
istl-2566	189	11	python	python	NOUN
istl-2566	189	12	programming	programming	NOUN
istl-2566	189	13	language	language	NOUN
istl-2566	189	14	and	and	CCONJ
istl-2566	189	15	our	our	PRON
istl-2566	189	16	familiarity	familiarity	NOUN
istl-2566	189	17	with	with	ADP
istl-2566	189	18	it	it	PRON
istl-2566	189	19	.	.	PUNCT
istl-2566	190	1	rdkit	rdkit	PROPN
istl-2566	190	2	is	be	AUX
istl-2566	190	3	a	a	DET
istl-2566	190	4	cheminformatics	cheminformatic	NOUN
istl-2566	190	5	toolkit	toolkit	NOUN
istl-2566	190	6	and	and	CCONJ
istl-2566	190	7	does	do	AUX
istl-2566	190	8	not	not	PART
istl-2566	190	9	contain	contain	VERB
istl-2566	190	10	a	a	DET
istl-2566	190	11	graphical	graphical	ADJ
istl-2566	190	12	structure	structure	NOUN
istl-2566	190	13	editor	editor	NOUN
istl-2566	190	14	.	.	PUNCT
istl-2566	191	1	as	as	ADP
istl-2566	191	2	such	such	ADJ
istl-2566	191	3	,	,	PUNCT
istl-2566	191	4	this	this	DET
istl-2566	191	5	required	require	VERB
istl-2566	191	6	drawing	draw	VERB
istl-2566	191	7	the	the	DET
istl-2566	191	8	structures	structure	NOUN
istl-2566	191	9	in	in	ADP
istl-2566	191	10	a	a	DET
istl-2566	191	11	separate	separate	ADJ
istl-2566	191	12	program	program	NOUN
istl-2566	191	13	,	,	PUNCT
istl-2566	191	14	in	in	ADP
istl-2566	191	15	our	our	PRON
istl-2566	191	16	case	case	NOUN
istl-2566	191	17	chemaxon	chemaxon	NOUN
istl-2566	191	18	marvinsketch	marvinsketch	NOUN
istl-2566	191	19	,	,	PUNCT
istl-2566	191	20	and	and	CCONJ
istl-2566	191	21	then	then	ADV
istl-2566	191	22	transferring	transfer	VERB
istl-2566	191	23	the	the	DET
istl-2566	191	24	molecular	molecular	ADJ
istl-2566	191	25	representation	representation	NOUN
istl-2566	191	26	data	datum	NOUN
istl-2566	191	27	to	to	PART
istl-2566	191	28	rdkit	rdkit	VERB
istl-2566	191	29	.	.	PUNCT
istl-2566	192	1	in	in	ADP
istl-2566	192	2	hindsight	hindsight	NOUN
istl-2566	192	3	,	,	PUNCT
istl-2566	192	4	processing	process	VERB
istl-2566	192	5	the	the	DET
istl-2566	192	6	chemical	chemical	NOUN
istl-2566	192	7	substance	substance	NOUN
istl-2566	192	8	smiles	smile	VERB
istl-2566	192	9	data	datum	NOUN
istl-2566	192	10	in	in	ADP
istl-2566	192	11	a	a	DET
istl-2566	192	12	separate	separate	ADJ
istl-2566	192	13	cheminformatics	cheminformatic	NOUN
istl-2566	192	14	toolkit	toolkit	NOUN
istl-2566	192	15	to	to	PART
istl-2566	192	16	create	create	VERB
istl-2566	192	17	an	an	DET
istl-2566	192	18	sdfile	sdfile	NOUN
istl-2566	192	19	was	be	AUX
istl-2566	192	20	unnecessary	unnecessary	ADJ
istl-2566	192	21	for	for	ADP
istl-2566	192	22	data	datum	NOUN
istl-2566	192	23	sharing	sharing	NOUN
istl-2566	192	24	in	in	ADP
istl-2566	192	25	pubchem	pubchem	NOUN
istl-2566	192	26	and	and	CCONJ
istl-2566	192	27	necessitated	necessitate	VERB
istl-2566	192	28	the	the	DET
istl-2566	192	29	incorporation	incorporation	NOUN
istl-2566	192	30	of	of	ADP
istl-2566	192	31	a	a	DET
istl-2566	192	32	local	local	ADJ
istl-2566	192	33	data	data	NOUN
istl-2566	192	34	interoperability	interoperability	NOUN
istl-2566	192	35	check	check	NOUN
istl-2566	192	36	using	use	VERB
istl-2566	192	37	inchi	inchi	NOUN
istl-2566	192	38	.	.	PUNCT
istl-2566	193	1	a	a	DET
istl-2566	193	2	more	more	ADV
istl-2566	193	3	efficient	efficient	ADJ
istl-2566	193	4	approach	approach	NOUN
istl-2566	193	5	is	be	AUX
istl-2566	193	6	to	to	PART
istl-2566	193	7	compile	compile	VERB
istl-2566	193	8	the	the	DET
istl-2566	193	9	molecular	molecular	ADJ
istl-2566	193	10	representation	representation	NOUN
istl-2566	193	11	data	datum	NOUN
istl-2566	193	12	as	as	ADP
istl-2566	193	13	smiles	smile	NOUN
istl-2566	193	14	along	along	ADP
istl-2566	193	15	with	with	ADP
istl-2566	193	16	the	the	DET
istl-2566	193	17	thesis	thesis	ADJ
istl-2566	193	18	bibliographic	bibliographic	ADJ
istl-2566	193	19	information	information	NOUN
istl-2566	193	20	in	in	ADP
istl-2566	193	21	a	a	DET
istl-2566	193	22	spreadsheet	spreadsheet	NOUN
istl-2566	193	23	application	application	NOUN
istl-2566	193	24	and	and	CCONJ
istl-2566	193	25	then	then	ADV
istl-2566	193	26	submit	submit	VERB
istl-2566	193	27	this	this	DET
istl-2566	193	28	file	file	NOUN
istl-2566	193	29	directly	directly	ADV
istl-2566	193	30	to	to	ADP
istl-2566	193	31	pubchem	pubchem	NOUN
istl-2566	193	32	,	,	PUNCT
istl-2566	193	33	as	as	SCONJ
istl-2566	193	34	we	we	PRON
istl-2566	193	35	did	do	VERB
istl-2566	193	36	in	in	ADP
istl-2566	193	37	the	the	DET
istl-2566	193	38	case	case	NOUN
istl-2566	193	39	of	of	ADP
istl-2566	193	40	substances	substance	NOUN
istl-2566	193	41	drawn	draw	VERB
istl-2566	193	42	with	with	ADP
istl-2566	193	43	knowitall	knowitall	PROPN
istl-2566	193	44	chemwindow	chemwindow	PROPN
istl-2566	193	45	;	;	PUNCT
istl-2566	193	46	that	that	PRON
istl-2566	193	47	is	is	ADV
istl-2566	193	48	,	,	PUNCT
istl-2566	193	49	the	the	DET
istl-2566	193	50	same	same	ADJ
istl-2566	193	51	spreadsheet	spreadsheet	NOUN
istl-2566	193	52	workflow	workflow	NOUN
istl-2566	193	53	could	could	AUX
istl-2566	193	54	have	have	AUX
istl-2566	193	55	been	be	AUX
istl-2566	193	56	used	use	VERB
istl-2566	193	57	for	for	ADP
istl-2566	193	58	substances	substance	NOUN
istl-2566	193	59	drawn	draw	VERB
istl-2566	193	60	in	in	ADP
istl-2566	193	61	chemaxon	chemaxon	NOUN
istl-2566	193	62	marvinsketch	marvinsketch	NOUN
istl-2566	193	63	.	.	PUNCT
istl-2566	194	1	the	the	DET
istl-2566	194	2	major	major	ADJ
istl-2566	194	3	limitation	limitation	NOUN
istl-2566	194	4	with	with	ADP
istl-2566	194	5	submitting	submit	VERB
istl-2566	194	6	a	a	DET
istl-2566	194	7	spreadsheet	spreadsheet	NOUN
istl-2566	194	8	of	of	ADP
istl-2566	194	9	smiles	smile	NOUN
istl-2566	194	10	chemical	chemical	PROPN
istl-2566	194	11	representations	representation	NOUN
istl-2566	194	12	to	to	ADP
istl-2566	194	13	pubchem	pubchem	PROPN
istl-2566	194	14	is	be	AUX
istl-2566	194	15	that	that	SCONJ
istl-2566	194	16	,	,	PUNCT
istl-2566	194	17	to	to	ADP
istl-2566	194	18	our	our	PRON
istl-2566	194	19	knowledge	knowledge	NOUN
istl-2566	194	20	,	,	PUNCT
istl-2566	194	21	it	it	PRON
istl-2566	194	22	is	be	AUX
istl-2566	194	23	not	not	PART
istl-2566	194	24	possible	possible	ADJ
istl-2566	194	25	to	to	PART
istl-2566	194	26	specify	specify	VERB
istl-2566	194	27	pubchem	pubchem	PROPN
istl-2566	194	28	nonstandard	nonstandard	ADJ
istl-2566	194	29	bonds	bond	NOUN
istl-2566	194	30	such	such	ADJ
istl-2566	194	31	as	as	ADP
istl-2566	194	32	dative	dative	ADJ
istl-2566	194	33	bonds	bond	NOUN
istl-2566	194	34	defined	define	VERB
istl-2566	194	35	in	in	ADP
istl-2566	194	36	pubchem	pubchem	NOUN
istl-2566	194	37	substance	substance	NOUN
istl-2566	194	38	tags	tag	NOUN
istl-2566	194	39	(	(	PUNCT
istl-2566	194	40	national	national	ADJ
istl-2566	194	41	center	center	NOUN
istl-2566	194	42	for	for	ADP
istl-2566	194	43	biotechnology	biotechnology	NOUN
istl-2566	194	44	information	information	NOUN
istl-2566	195	1	[	[	PUNCT
istl-2566	195	2	date	date	NOUN
istl-2566	195	3	unknown	unknown	ADJ
istl-2566	195	4	-	-	PUNCT
istl-2566	195	5	b	b	NOUN
istl-2566	195	6	]	]	PUNCT
istl-2566	195	7	)	)	PUNCT
istl-2566	195	8	within	within	ADP
istl-2566	195	9	the	the	DET
istl-2566	195	10	spreadsheet	spreadsheet	NOUN
istl-2566	195	11	or	or	CCONJ
istl-2566	195	12	represent	represent	VERB
istl-2566	195	13	features	feature	NOUN
istl-2566	195	14	such	such	ADJ
istl-2566	195	15	as	as	ADP
istl-2566	195	16	radicals	radical	NOUN
istl-2566	195	17	,	,	PUNCT
istl-2566	195	18	as	as	SCONJ
istl-2566	195	19	these	these	PRON
istl-2566	195	20	smiles	smile	NOUN
istl-2566	195	21	extensions	extension	NOUN
istl-2566	195	22	are	be	AUX
istl-2566	195	23	not	not	PART
istl-2566	195	24	recognized	recognize	VERB
istl-2566	195	25	by	by	ADP
istl-2566	195	26	pubchem	pubchem	NOUN
istl-2566	195	27	.	.	PUNCT
istl-2566	196	1	in	in	ADP
istl-2566	196	2	these	these	DET
istl-2566	196	3	specific	specific	ADJ
istl-2566	196	4	cases	case	NOUN
istl-2566	196	5	,	,	PUNCT
istl-2566	196	6	a	a	DET
istl-2566	196	7	molfile	molfile	NOUN
istl-2566	196	8	/	/	SYM
istl-2566	196	9	sdfile	sdfile	NOUN
istl-2566	196	10	representation	representation	NOUN
istl-2566	196	11	format	format	NOUN
istl-2566	196	12	would	would	AUX
istl-2566	196	13	need	need	VERB
istl-2566	196	14	to	to	PART
istl-2566	196	15	be	be	AUX
istl-2566	196	16	used	use	VERB
istl-2566	196	17	for	for	ADP
istl-2566	196	18	pubchem	pubchem	NOUN
istl-2566	196	19	submissions	submission	NOUN
istl-2566	196	20	.	.	PUNCT
istl-2566	197	1	such	such	DET
istl-2566	197	2	a	a	DET
istl-2566	197	3	task	task	NOUN
istl-2566	197	4	can	can	AUX
istl-2566	197	5	still	still	ADV
istl-2566	197	6	be	be	AUX
istl-2566	197	7	completed	complete	VERB
istl-2566	197	8	within	within	ADP
istl-2566	197	9	a	a	DET
istl-2566	197	10	single	single	ADJ
istl-2566	197	11	toolkit	toolkit	NOUN
istl-2566	197	12	,	,	PUNCT
istl-2566	197	13	as	as	SCONJ
istl-2566	197	14	both	both	CCONJ
istl-2566	197	15	marvinsketch	marvinsketch	NOUN
istl-2566	197	16	and	and	CCONJ
istl-2566	197	17	knowitall	knowitall	NOUN
istl-2566	197	18	can	can	AUX
istl-2566	197	19	export	export	VERB
istl-2566	197	20	molfile	molfile	NOUN
istl-2566	197	21	/	/	SYM
istl-2566	197	22	sdfile	sdfile	NOUN
istl-2566	197	23	formats	format	NOUN
istl-2566	197	24	.	.	PUNCT
istl-2566	198	1	finally	finally	ADV
istl-2566	198	2	,	,	PUNCT
istl-2566	198	3	it	it	PRON
istl-2566	198	4	should	should	AUX
istl-2566	198	5	be	be	AUX
istl-2566	198	6	noted	note	VERB
istl-2566	198	7	that	that	SCONJ
istl-2566	198	8	there	there	PRON
istl-2566	198	9	are	be	VERB
istl-2566	198	10	other	other	ADJ
istl-2566	198	11	differences	difference	NOUN
istl-2566	198	12	and	and	CCONJ
istl-2566	198	13	limitations	limitation	NOUN
istl-2566	198	14	with	with	ADP
istl-2566	198	15	molfile	molfile	NOUN
istl-2566	198	16	/	/	SYM
istl-2566	198	17	sdfile	sdfile	NOUN
istl-2566	198	18	encoded	encode	VERB
istl-2566	198	19	molecular	molecular	ADJ
istl-2566	198	20	representations	representation	NOUN
istl-2566	198	21	compared	compare	VERB
istl-2566	198	22	to	to	ADP
istl-2566	198	23	smiles	smile	NOUN
istl-2566	198	24	and	and	CCONJ
istl-2566	198	25	this	this	PRON
istl-2566	198	26	may	may	AUX
istl-2566	198	27	be	be	AUX
istl-2566	198	28	a	a	DET
istl-2566	198	29	consideration	consideration	NOUN
istl-2566	198	30	when	when	SCONJ
istl-2566	198	31	submitting	submit	VERB
istl-2566	198	32	data	datum	NOUN
istl-2566	198	33	to	to	ADP
istl-2566	198	34	pubchem	pubchem	NOUN
istl-2566	198	35	(	(	PUNCT
istl-2566	198	36	daylight	daylight	NOUN
istl-2566	198	37	chemical	chemical	ADJ
istl-2566	198	38	information	information	NOUN
istl-2566	198	39	systems	system	NOUN
istl-2566	198	40	2011	2011	NUM
istl-2566	198	41	;	;	PUNCT
istl-2566	198	42	dassault	dassault	NOUN
istl-2566	198	43	systemes	systeme	NOUN
istl-2566	198	44	2017	2017	NUM
istl-2566	198	45	)	)	PUNCT
istl-2566	198	46	.	.	PUNCT
istl-2566	199	1	however	however	ADV
istl-2566	199	2	,	,	PUNCT
istl-2566	199	3	as	as	SCONJ
istl-2566	199	4	smiles	smile	NOUN
istl-2566	199	5	contain	contain	VERB
istl-2566	199	6	the	the	DET
istl-2566	199	7	entire	entire	ADJ
istl-2566	199	8	representation	representation	NOUN
istl-2566	199	9	on	on	ADP
istl-2566	199	10	one	one	NUM
istl-2566	199	11	line	line	NOUN
istl-2566	199	12	,	,	PUNCT
istl-2566	199	13	we	we	PRON
istl-2566	199	14	found	find	VERB
istl-2566	199	15	smiles	smile	VERB
istl-2566	199	16	much	much	ADV
istl-2566	199	17	more	more	ADV
istl-2566	199	18	convenient	convenient	ADJ
istl-2566	199	19	to	to	PART
istl-2566	199	20	work	work	VERB
istl-2566	199	21	with	with	ADP
istl-2566	199	22	compared	compare	VERB
istl-2566	199	23	to	to	ADP
istl-2566	199	24	molfile	molfile	NOUN
istl-2566	199	25	/	/	SYM
istl-2566	199	26	sdfiles	sdfile	NOUN
istl-2566	199	27	.	.	PUNCT
istl-2566	200	1	inchi	inchi	PROPN
istl-2566	200	2	algorithm	algorithm	PROPN
istl-2566	200	3	for	for	ADP
istl-2566	200	4	substance	substance	NOUN
istl-2566	200	5	registration	registration	NOUN
istl-2566	200	6	the	the	DET
istl-2566	200	7	use	use	NOUN
istl-2566	200	8	of	of	ADP
istl-2566	200	9	inchi	inchi	PROPN
istl-2566	200	10	was	be	AUX
istl-2566	200	11	critical	critical	ADJ
istl-2566	200	12	to	to	ADP
istl-2566	200	13	our	our	PRON
istl-2566	200	14	substance	substance	NOUN
istl-2566	200	15	registration	registration	NOUN
istl-2566	200	16	process	process	NOUN
istl-2566	200	17	,	,	PUNCT
istl-2566	200	18	as	as	ADV
istl-2566	200	19	well	well	ADV
istl-2566	200	20	as	as	ADP
istl-2566	200	21	being	be	AUX
istl-2566	200	22	useful	useful	ADJ
istl-2566	200	23	as	as	ADP
istl-2566	200	24	a	a	DET
istl-2566	200	25	consistency	consistency	NOUN
istl-2566	200	26	check	check	NOUN
istl-2566	200	27	within	within	ADP
istl-2566	200	28	our	our	PRON
istl-2566	200	29	overall	overall	ADJ
istl-2566	200	30	workflow	workflow	NOUN
istl-2566	200	31	.	.	PUNCT
istl-2566	201	1	inchi	inchi	PROPN
istl-2566	201	2	is	be	AUX
istl-2566	201	3	an	an	DET
istl-2566	201	4	open	open	ADJ
istl-2566	201	5	non	non	ADJ
istl-2566	201	6	-	-	ADJ
istl-2566	201	7	proprietary	proprietary	ADJ
istl-2566	201	8	chemical	chemical	NOUN
istl-2566	201	9	identifier	identifier	NOUN
istl-2566	201	10	,	,	PUNCT
istl-2566	201	11	which	which	PRON
istl-2566	201	12	is	be	AUX
istl-2566	201	13	well	well	ADV
istl-2566	201	14	supported	support	VERB
istl-2566	201	15	across	across	ADP
istl-2566	201	16	cheminformatics	cheminformatic	NOUN
istl-2566	201	17	software	software	NOUN
istl-2566	201	18	.	.	PUNCT
istl-2566	202	1	the	the	DET
istl-2566	202	2	inchi	inchi	PROPN
istl-2566	202	3	algorithm	algorithm	PROPN
istl-2566	202	4	is	be	AUX
istl-2566	202	5	currently	currently	ADV
istl-2566	202	6	used	use	VERB
istl-2566	202	7	to	to	PART
istl-2566	202	8	check	check	VERB
istl-2566	202	9	for	for	ADP
istl-2566	202	10	structure	structure	NOUN
istl-2566	202	11	uniqueness	uniqueness	NOUN
istl-2566	202	12	in	in	ADP
istl-2566	202	13	several	several	ADJ
istl-2566	202	14	public	public	ADJ
istl-2566	202	15	chemical	chemical	NOUN
istl-2566	202	16	databases	database	NOUN
istl-2566	202	17	and	and	CCONJ
istl-2566	202	18	cross	cross	ADJ
istl-2566	202	19	-	-	ADJ
istl-2566	202	20	referencing	referencing	ADJ
istl-2566	202	21	services	service	NOUN
istl-2566	202	22	such	such	ADJ
istl-2566	202	23	as	as	ADP
istl-2566	202	24	chembl	chembl	NOUN
istl-2566	202	25	(	(	PUNCT
istl-2566	202	26	mendez	mendez	PROPN
istl-2566	202	27	et	et	PROPN
istl-2566	202	28	al	al	PROPN
istl-2566	202	29	.	.	PROPN
istl-2566	202	30	2018	2018	NUM
istl-2566	202	31	;	;	PUNCT
istl-2566	202	32	hersey	hersey	PROPN
istl-2566	202	33	[	[	PROPN
istl-2566	202	34	date	date	NOUN
istl-2566	202	35	unknown	unknown	ADJ
istl-2566	202	36	]	]	PUNCT
istl-2566	202	37	)	)	PUNCT
istl-2566	202	38	,	,	PUNCT
istl-2566	202	39	chebi	chebi	NOUN
istl-2566	202	40	(	(	PUNCT
istl-2566	202	41	chambers	chamber	NOUN
istl-2566	202	42	et	et	PROPN
istl-2566	202	43	al	al	PROPN
istl-2566	202	44	.	.	PROPN
istl-2566	202	45	2013	2013	NUM
istl-2566	202	46	;	;	PUNCT
istl-2566	202	47	hastings	hasting	VERB
istl-2566	202	48	et	et	PROPN
istl-2566	202	49	al	al	PROPN
istl-2566	202	50	.	.	PROPN
istl-2566	202	51	2016	2016	NUM
istl-2566	202	52	)	)	PUNCT
istl-2566	202	53	,	,	PUNCT
istl-2566	202	54	chemspider	chemspider	NOUN
istl-2566	202	55	(	(	PUNCT
istl-2566	202	56	richardson	richardson	PROPN
istl-2566	202	57	2018	2018	NUM
istl-2566	202	58	)	)	PUNCT
istl-2566	202	59	,	,	PUNCT
istl-2566	202	60	and	and	CCONJ
istl-2566	202	61	unichem	unichem	PROPN
istl-2566	202	62	(	(	PUNCT
istl-2566	202	63	chambers	chamber	NOUN
istl-2566	202	64	et	et	PROPN
istl-2566	202	65	al	al	PROPN
istl-2566	202	66	.	.	PROPN
istl-2566	202	67	2013	2013	NUM
istl-2566	202	68	)	)	PUNCT
istl-2566	202	69	.	.	PUNCT
istl-2566	203	1	combined	combine	VERB
istl-2566	203	2	with	with	ADP
istl-2566	203	3	the	the	DET
istl-2566	203	4	ability	ability	NOUN
istl-2566	203	5	to	to	PART
istl-2566	203	6	compare	compare	VERB
istl-2566	203	7	inchis	inchis	NOUN
istl-2566	203	8	across	across	ADP
istl-2566	203	9	cheminformatics	cheminformatic	NOUN
istl-2566	203	10	toolkits	toolkit	NOUN
istl-2566	203	11	and	and	CCONJ
istl-2566	203	12	the	the	DET
istl-2566	203	13	established	establish	VERB
istl-2566	203	14	record	record	NOUN
istl-2566	203	15	of	of	ADP
istl-2566	203	16	using	use	VERB
istl-2566	203	17	inchi	inchi	NOUN
istl-2566	203	18	as	as	ADP
istl-2566	203	19	a	a	DET
istl-2566	203	20	uniqueness	uniqueness	ADJ
istl-2566	203	21	check	check	NOUN
istl-2566	203	22	,	,	PUNCT
istl-2566	203	23	inchi	inchi	PROPN
istl-2566	203	24	proved	prove	VERB
istl-2566	203	25	to	to	PART
istl-2566	203	26	be	be	AUX
istl-2566	203	27	a	a	DET
istl-2566	203	28	great	great	ADJ
istl-2566	203	29	choice	choice	NOUN
istl-2566	203	30	for	for	ADP
istl-2566	203	31	our	our	PRON
istl-2566	203	32	structure	structure	NOUN
istl-2566	203	33	uniqueness	uniqueness	NOUN
istl-2566	203	34	check	check	NOUN
istl-2566	203	35	.	.	PUNCT
istl-2566	204	1	there	there	PRON
istl-2566	204	2	are	be	VERB
istl-2566	204	3	different	different	ADJ
istl-2566	204	4	levels	level	NOUN
istl-2566	204	5	of	of	ADP
istl-2566	204	6	uniqueness	uniqueness	NOUN
istl-2566	204	7	that	that	SCONJ
istl-2566	204	8	inchi	inchi	PROPN
istl-2566	204	9	can	can	AUX
istl-2566	204	10	describe	describe	VERB
istl-2566	204	11	,	,	PUNCT
istl-2566	204	12	depending	depend	VERB
istl-2566	204	13	on	on	ADP
istl-2566	204	14	if	if	SCONJ
istl-2566	204	15	a	a	DET
istl-2566	204	16	standard	standard	ADJ
istl-2566	204	17	or	or	CCONJ
istl-2566	204	18	non	non	ADJ
istl-2566	204	19	-	-	ADJ
istl-2566	204	20	standard	standard	ADJ
istl-2566	204	21	inchi	inchi	NOUN
istl-2566	204	22	is	be	AUX
istl-2566	204	23	calculated	calculate	VERB
istl-2566	204	24	.	.	PUNCT
istl-2566	205	1	standard	standard	ADJ
istl-2566	205	2	inchis	inchis	PROPN
istl-2566	205	3	,	,	PUNCT
istl-2566	205	4	for	for	ADP
istl-2566	205	5	example	example	NOUN
istl-2566	205	6	,	,	PUNCT
istl-2566	205	7	are	be	AUX
istl-2566	205	8	tautomer	tautomer	ADJ
istl-2566	205	9	independent	independent	ADJ
istl-2566	205	10	,	,	PUNCT
istl-2566	205	11	represent	represent	VERB
istl-2566	205	12	organometallics	organometallic	NOUN
istl-2566	205	13	with	with	ADP
istl-2566	205	14	disconnected	disconnected	ADJ
istl-2566	205	15	metals	metal	NOUN
istl-2566	205	16	,	,	PUNCT
istl-2566	205	17	and	and	CCONJ
istl-2566	205	18	only	only	ADV
istl-2566	205	19	support	support	VERB
istl-2566	205	20	absolute	absolute	ADJ
istl-2566	205	21	stereochemistry	stereochemistry	NOUN
istl-2566	205	22	.	.	PUNCT
istl-2566	206	1	these	these	DET
istl-2566	206	2	limitations	limitation	NOUN
istl-2566	206	3	can	can	AUX
istl-2566	206	4	be	be	AUX
istl-2566	206	5	overcome	overcome	VERB
istl-2566	206	6	by	by	ADP
istl-2566	206	7	calculating	calculate	VERB
istl-2566	206	8	a	a	DET
istl-2566	206	9	non	non	ADJ
istl-2566	206	10	-	-	ADJ
istl-2566	206	11	standard	standard	ADJ
istl-2566	206	12	inchi	inchi	NOUN
istl-2566	206	13	,	,	PUNCT
istl-2566	206	14	which	which	PRON
istl-2566	206	15	allows	allow	VERB
istl-2566	206	16	for	for	ADP
istl-2566	206	17	specific	specific	ADJ
istl-2566	206	18	options	option	NOUN
istl-2566	206	19	related	relate	VERB
istl-2566	206	20	to	to	ADP
istl-2566	206	21	tautomers	tautomer	NOUN
istl-2566	206	22	,	,	PUNCT
istl-2566	206	23	metal	metal	NOUN
istl-2566	206	24	representation	representation	NOUN
istl-2566	206	25	,	,	PUNCT
istl-2566	206	26	stereochemistry	stereochemistry	NOUN
istl-2566	206	27	and	and	CCONJ
istl-2566	206	28	more	more	ADJ
istl-2566	206	29	(	(	PUNCT
istl-2566	206	30	heller	heller	NOUN
istl-2566	206	31	et	et	PROPN
istl-2566	206	32	al	al	PROPN
istl-2566	206	33	.	.	PROPN
istl-2566	206	34	2015	2015	NUM
istl-2566	206	35	)	)	PUNCT
istl-2566	206	36	.	.	PUNCT
istl-2566	207	1	both	both	CCONJ
istl-2566	207	2	the	the	DET
istl-2566	207	3	standard	standard	ADJ
istl-2566	207	4	inchi	inchi	PROPN
istl-2566	207	5	and	and	CCONJ
istl-2566	207	6	non	non	ADJ
istl-2566	207	7	-	-	ADJ
istl-2566	207	8	standard	standard	ADJ
istl-2566	207	9	inchi	inchi	NOUN
istl-2566	207	10	are	be	AUX
istl-2566	207	11	suitable	suitable	ADJ
istl-2566	207	12	choices	choice	NOUN
istl-2566	207	13	for	for	ADP
istl-2566	207	14	checking	check	VERB
istl-2566	207	15	the	the	DET
istl-2566	207	16	uniqueness	uniqueness	NOUN
istl-2566	207	17	of	of	ADP
istl-2566	207	18	chemical	chemical	ADJ
istl-2566	207	19	substances	substance	NOUN
istl-2566	207	20	.	.	PUNCT
istl-2566	208	1	chembl	chembl	NOUN
istl-2566	208	2	and	and	CCONJ
istl-2566	208	3	unichem	unichem	PRON
istl-2566	208	4	use	use	VERB
istl-2566	208	5	the	the	DET
istl-2566	208	6	standard	standard	ADJ
istl-2566	208	7	inchi	inchi	NOUN
istl-2566	208	8	,	,	PUNCT
istl-2566	208	9	(	(	PUNCT
istl-2566	208	10	chambers	chamber	NOUN
istl-2566	208	11	et	et	PROPN
istl-2566	208	12	al	al	PROPN
istl-2566	208	13	.	.	PROPN
istl-2566	208	14	2013	2013	NUM
istl-2566	208	15	;	;	PUNCT
istl-2566	208	16	hersey	hersey	PROPN
istl-2566	209	1	[	[	PROPN
istl-2566	209	2	date	date	NOUN
istl-2566	209	3	unknown	unknown	ADJ
istl-2566	209	4	]	]	PUNCT
istl-2566	209	5	)	)	PUNCT
istl-2566	209	6	while	while	SCONJ
istl-2566	209	7	chemspider	chemspider	NOUN
istl-2566	209	8	(	(	PUNCT
istl-2566	209	9	royal	royal	ADJ
istl-2566	209	10	society	society	NOUN
istl-2566	209	11	of	of	ADP
istl-2566	209	12	chemistry	chemistry	NOUN
istl-2566	209	13	,	,	PUNCT
istl-2566	209	14	personal	personal	ADJ
istl-2566	209	15	communication	communication	NOUN
istl-2566	209	16	,	,	PUNCT
istl-2566	209	17	july	july	PROPN
istl-2566	209	18	24	24	NUM
istl-2566	209	19	,	,	PUNCT
istl-2566	209	20	2020	2020	NUM
istl-2566	209	21	)	)	PUNCT
istl-2566	209	22	and	and	CCONJ
istl-2566	209	23	chebi	chebi	NOUN
istl-2566	209	24	use	use	VERB
istl-2566	209	25	a	a	DET
istl-2566	209	26	non	non	ADJ
istl-2566	209	27	-	-	ADJ
istl-2566	209	28	standard	standard	ADJ
istl-2566	209	29	inchi	inchi	NOUN
istl-2566	209	30	(	(	PUNCT
istl-2566	209	31	chambers	chamber	NOUN
istl-2566	209	32	et	et	PROPN
istl-2566	209	33	al	al	PROPN
istl-2566	209	34	.	.	PROPN
istl-2566	209	35	2013	2013	NUM
istl-2566	209	36	;	;	PUNCT
istl-2566	209	37	hastings	hasting	VERB
istl-2566	209	38	et	et	PROPN
istl-2566	209	39	al	al	PROPN
istl-2566	209	40	.	.	PROPN
istl-2566	209	41	2016	2016	NUM
istl-2566	209	42	)	)	PUNCT
istl-2566	209	43	.	.	PUNCT
istl-2566	210	1	chambers	chamber	NOUN
istl-2566	210	2	et	et	PROPN
istl-2566	210	3	al	al	PROPN
istl-2566	210	4	.	.	PUNCT
istl-2566	211	1	(	(	PUNCT
istl-2566	211	2	2013	2013	NUM
istl-2566	211	3	)	)	PUNCT
istl-2566	211	4	argue	argue	VERB
istl-2566	211	5	that	that	SCONJ
istl-2566	211	6	the	the	DET
istl-2566	211	7	community	community	NOUN
istl-2566	211	8	considers	consider	VERB
istl-2566	211	9	the	the	DET
istl-2566	211	10	standard	standard	ADJ
istl-2566	211	11	inchi	inchi	NOUN
istl-2566	211	12	to	to	PART
istl-2566	211	13	be	be	AUX
istl-2566	211	14	an	an	DET
istl-2566	211	15	acceptable	acceptable	ADJ
istl-2566	211	16	measure	measure	NOUN
istl-2566	211	17	of	of	ADP
istl-2566	211	18	substance	substance	NOUN
istl-2566	211	19	uniqueness	uniqueness	VERB
istl-2566	211	20	relevant	relevant	ADJ
istl-2566	211	21	to	to	ADP
istl-2566	211	22	chemical	chemical	NOUN
istl-2566	211	23	biology	biology	NOUN
istl-2566	211	24	and	and	CCONJ
istl-2566	211	25	drug	drug	NOUN
istl-2566	211	26	discovery	discovery	NOUN
istl-2566	211	27	.	.	PUNCT
istl-2566	212	1	ultimately	ultimately	ADV
istl-2566	212	2	,	,	PUNCT
istl-2566	212	3	we	we	PRON
istl-2566	212	4	selected	select	VERB
istl-2566	212	5	the	the	DET
istl-2566	212	6	standard	standard	ADJ
istl-2566	212	7	inchi	inchi	NOUN
istl-2566	212	8	because	because	SCONJ
istl-2566	212	9	of	of	ADP
istl-2566	212	10	the	the	DET
istl-2566	212	11	primary	primary	ADJ
istl-2566	212	12	consideration	consideration	NOUN
istl-2566	212	13	of	of	ADP
istl-2566	212	14	data	data	NOUN
istl-2566	212	15	reuse	reuse	NOUN
istl-2566	212	16	;	;	PUNCT
istl-2566	212	17	that	that	PRON
istl-2566	212	18	is	be	AUX
istl-2566	212	19	,	,	PUNCT
istl-2566	212	20	since	since	SCONJ
istl-2566	212	21	all	all	PRON
istl-2566	212	22	of	of	ADP
istl-2566	212	23	our	our	PRON
istl-2566	212	24	data	datum	NOUN
istl-2566	212	25	,	,	PUNCT
istl-2566	212	26	including	include	VERB
istl-2566	212	27	intermediate	intermediate	ADJ
istl-2566	212	28	working	work	VERB
istl-2566	212	29	files	file	NOUN
istl-2566	212	30	and	and	CCONJ
istl-2566	212	31	registry	registry	NOUN
istl-2566	212	32	lists	list	NOUN
istl-2566	212	33	are	be	AUX
istl-2566	212	34	public	public	ADJ
istl-2566	212	35	,	,	PUNCT
istl-2566	212	36	we	we	PRON
istl-2566	212	37	felt	feel	VERB
istl-2566	212	38	it	it	PRON
istl-2566	212	39	was	be	AUX
istl-2566	212	40	best	good	ADJ
istl-2566	212	41	to	to	PART
istl-2566	212	42	share	share	VERB
istl-2566	212	43	standard	standard	ADJ
istl-2566	212	44	inchis	inchis	NOUN
istl-2566	212	45	for	for	ADP
istl-2566	212	46	data	data	NOUN
istl-2566	212	47	exchange	exchange	NOUN
istl-2566	212	48	considerations	consideration	NOUN
istl-2566	212	49	.	.	PUNCT
istl-2566	213	1	pubchem	pubchem	PROPN
istl-2566	213	2	data	datum	NOUN
istl-2566	213	3	sharing	sharing	PROPN
istl-2566	213	4	,	,	PUNCT
istl-2566	213	5	provenance	provenance	NOUN
istl-2566	213	6	,	,	PUNCT
istl-2566	213	7	and	and	CCONJ
istl-2566	213	8	access	access	NOUN
istl-2566	213	9	at	at	ADP
istl-2566	213	10	the	the	DET
istl-2566	213	11	time	time	NOUN
istl-2566	213	12	that	that	PRON
istl-2566	213	13	we	we	PRON
istl-2566	213	14	submitted	submit	VERB
istl-2566	213	15	the	the	DET
istl-2566	213	16	ua	ua	ADJ
istl-2566	213	17	thesis	thesis	NOUN
istl-2566	213	18	substances	substance	NOUN
istl-2566	213	19	,	,	PUNCT
istl-2566	213	20	pubchem	pubchem	PROPN
istl-2566	213	21	had	have	VERB
istl-2566	213	22	103	103	NUM
istl-2566	213	23	million	million	NUM
istl-2566	213	24	unique	unique	ADJ
istl-2566	213	25	compounds	compound	NOUN
istl-2566	213	26	.	.	PUNCT
istl-2566	214	1	as	as	ADP
istl-2566	214	2	such	such	ADJ
istl-2566	214	3	,	,	PUNCT
istl-2566	214	4	the	the	DET
istl-2566	214	5	fact	fact	NOUN
istl-2566	214	6	that	that	SCONJ
istl-2566	214	7	40	40	NUM
istl-2566	214	8	%	%	NOUN
istl-2566	214	9	or	or	CCONJ
istl-2566	214	10	more	more	ADJ
istl-2566	214	11	of	of	ADP
istl-2566	214	12	our	our	PRON
istl-2566	214	13	contributions	contribution	NOUN
istl-2566	214	14	were	be	AUX
istl-2566	214	15	new	new	ADJ
istl-2566	214	16	to	to	ADP
istl-2566	214	17	the	the	DET
istl-2566	214	18	database	database	NOUN
istl-2566	214	19	and	and	CCONJ
istl-2566	214	20	unique	unique	ADJ
istl-2566	214	21	from	from	ADP
istl-2566	214	22	the	the	DET
istl-2566	214	23	already	already	ADV
istl-2566	214	24	present	present	ADJ
istl-2566	214	25	103	103	NUM
istl-2566	214	26	million	million	NUM
istl-2566	214	27	compounds	compound	NOUN
istl-2566	214	28	is	be	AUX
istl-2566	214	29	highly	highly	ADV
istl-2566	214	30	significant	significant	ADJ
istl-2566	214	31	,	,	PUNCT
istl-2566	214	32	and	and	CCONJ
istl-2566	214	33	we	we	PRON
istl-2566	214	34	believe	believe	VERB
istl-2566	214	35	supports	support	VERB
istl-2566	214	36	the	the	DET
istl-2566	214	37	claim	claim	NOUN
istl-2566	214	38	that	that	SCONJ
istl-2566	214	39	contributing	contribute	VERB
istl-2566	214	40	substances	substance	NOUN
istl-2566	214	41	from	from	ADP
istl-2566	214	42	university	university	NOUN
istl-2566	214	43	theses	theses	PROPN
istl-2566	214	44	is	be	AUX
istl-2566	214	45	valuable	valuable	ADJ
istl-2566	214	46	to	to	ADP
istl-2566	214	47	the	the	DET
istl-2566	214	48	community	community	NOUN
istl-2566	214	49	.	.	PUNCT
istl-2566	215	1	for	for	ADP
istl-2566	215	2	duplicate	duplicate	ADJ
istl-2566	215	3	substances	substance	NOUN
istl-2566	215	4	submitted	submit	VERB
istl-2566	215	5	,	,	PUNCT
istl-2566	215	6	there	there	PRON
istl-2566	215	7	is	be	VERB
istl-2566	215	8	still	still	ADV
istl-2566	215	9	value	value	NOUN
istl-2566	215	10	as	as	SCONJ
istl-2566	215	11	the	the	DET
istl-2566	215	12	data	data	NOUN
istl-2566	215	13	is	be	AUX
istl-2566	215	14	merged	merge	VERB
istl-2566	215	15	with	with	ADP
istl-2566	215	16	other	other	ADJ
istl-2566	215	17	records	record	NOUN
istl-2566	215	18	in	in	ADP
istl-2566	215	19	pubchem	pubchem	NOUN
istl-2566	215	20	and	and	CCONJ
istl-2566	215	21	adds	add	VERB
istl-2566	215	22	a	a	DET
istl-2566	215	23	new	new	ADJ
istl-2566	215	24	bibliographic	bibliographic	ADJ
istl-2566	215	25	reference	reference	NOUN
istl-2566	215	26	to	to	ADP
istl-2566	215	27	the	the	DET
istl-2566	215	28	record	record	NOUN
istl-2566	215	29	.	.	PUNCT
istl-2566	216	1	there	there	PRON
istl-2566	216	2	are	be	VERB
istl-2566	216	3	many	many	ADJ
istl-2566	216	4	steps	step	NOUN
istl-2566	216	5	involved	involve	VERB
istl-2566	216	6	in	in	ADP
istl-2566	216	7	sharing	share	VERB
istl-2566	216	8	chemical	chemical	NOUN
istl-2566	216	9	substance	substance	NOUN
istl-2566	216	10	data	datum	NOUN
istl-2566	216	11	from	from	ADP
istl-2566	216	12	theses	thesis	NOUN
istl-2566	216	13	and	and	CCONJ
istl-2566	216	14	with	with	ADP
istl-2566	216	15	that	that	PRON
istl-2566	216	16	comes	come	VERB
istl-2566	216	17	many	many	ADJ
istl-2566	216	18	opportunities	opportunity	NOUN
istl-2566	216	19	for	for	ADP
istl-2566	216	20	data	data	NOUN
istl-2566	216	21	loss	loss	NOUN
istl-2566	216	22	or	or	CCONJ
istl-2566	216	23	corruption	corruption	NOUN
istl-2566	216	24	.	.	PUNCT
istl-2566	217	1	no	no	ADV
istl-2566	217	2	matter	matter	ADV
istl-2566	217	3	how	how	SCONJ
istl-2566	217	4	careful	careful	ADJ
istl-2566	217	5	data	data	NOUN
istl-2566	217	6	depositors	depositor	NOUN
istl-2566	217	7	are	be	AUX
istl-2566	217	8	locally	locally	ADV
istl-2566	217	9	,	,	PUNCT
istl-2566	217	10	there	there	PRON
istl-2566	217	11	is	be	VERB
istl-2566	217	12	still	still	ADV
istl-2566	217	13	a	a	DET
istl-2566	217	14	possibility	possibility	NOUN
istl-2566	217	15	that	that	SCONJ
istl-2566	217	16	any	any	PRON
istl-2566	217	17	of	of	ADP
istl-2566	217	18	the	the	DET
istl-2566	217	19	substances	substance	NOUN
istl-2566	217	20	shared	share	VERB
istl-2566	217	21	in	in	ADP
istl-2566	217	22	pubchem	pubchem	NOUN
istl-2566	217	23	could	could	AUX
istl-2566	217	24	be	be	AUX
istl-2566	217	25	interpreted	interpret	VERB
istl-2566	217	26	differently	differently	ADV
istl-2566	217	27	after	after	ADP
istl-2566	217	28	being	be	AUX
istl-2566	217	29	processed	process	VERB
istl-2566	217	30	with	with	ADP
istl-2566	217	31	their	their	PRON
istl-2566	217	32	selected	select	VERB
istl-2566	217	33	cheminformatics	cheminformatic	NOUN
istl-2566	217	34	software	software	NOUN
istl-2566	217	35	and	and	CCONJ
istl-2566	217	36	standardization	standardization	NOUN
istl-2566	217	37	workflow	workflow	NOUN
istl-2566	217	38	(	(	PUNCT
istl-2566	217	39	hähnke	hähnke	PROPN
istl-2566	217	40	et	et	PROPN
istl-2566	217	41	al	al	PROPN
istl-2566	217	42	.	.	PROPN
istl-2566	217	43	2018	2018	NUM
istl-2566	217	44	)	)	PUNCT
istl-2566	217	45	.	.	PUNCT
istl-2566	218	1	to	to	PART
istl-2566	218	2	evaluate	evaluate	VERB
istl-2566	218	3	how	how	SCONJ
istl-2566	218	4	our	our	PRON
istl-2566	218	5	substance	substance	NOUN
istl-2566	218	6	representations	representation	NOUN
istl-2566	218	7	changed	change	VERB
istl-2566	218	8	after	after	ADP
istl-2566	218	9	pubchem	pubchem	NOUN
istl-2566	218	10	deposition	deposition	NOUN
istl-2566	218	11	,	,	PUNCT
istl-2566	218	12	we	we	PRON
istl-2566	218	13	compared	compare	VERB
istl-2566	218	14	our	our	PRON
istl-2566	218	15	locally	locally	ADV
istl-2566	218	16	computed	compute	VERB
istl-2566	218	17	standard	standard	ADJ
istl-2566	218	18	inchis	inchis	NOUN
istl-2566	218	19	for	for	ADP
istl-2566	218	20	all	all	DET
istl-2566	218	21	substances	substance	NOUN
istl-2566	218	22	that	that	PRON
istl-2566	218	23	passed	pass	VERB
istl-2566	218	24	pubchem	pubchem	NOUN
istl-2566	218	25	standardization	standardization	NOUN
istl-2566	218	26	to	to	ADP
istl-2566	218	27	the	the	DET
istl-2566	218	28	pubchem	pubchem	PROPN
istl-2566	218	29	compound	compound	NOUN
istl-2566	218	30	standard	standard	NOUN
istl-2566	218	31	inchis	inchis	NOUN
istl-2566	218	32	and	and	CCONJ
istl-2566	218	33	found	find	VERB
istl-2566	218	34	that	that	SCONJ
istl-2566	218	35	150	150	NUM
istl-2566	218	36	(	(	PUNCT
istl-2566	218	37	5.2	5.2	NUM
istl-2566	218	38	%	%	NOUN
istl-2566	218	39	)	)	PUNCT
istl-2566	218	40	of	of	ADP
istl-2566	218	41	the	the	DET
istl-2566	218	42	substances	substance	NOUN
istl-2566	218	43	did	do	AUX
istl-2566	218	44	not	not	PART
istl-2566	218	45	have	have	VERB
istl-2566	218	46	identical	identical	ADJ
istl-2566	218	47	inchis	inchis	NOUN
istl-2566	218	48	after	after	ADP
istl-2566	218	49	pubchem	pubchem	NOUN
istl-2566	218	50	processing	processing	NOUN
istl-2566	218	51	,	,	PUNCT
istl-2566	218	52	suggesting	suggest	VERB
istl-2566	218	53	a	a	DET
istl-2566	218	54	possible	possible	ADJ
istl-2566	218	55	change	change	NOUN
istl-2566	218	56	in	in	ADP
istl-2566	218	57	structure	structure	NOUN
istl-2566	218	58	representation	representation	NOUN
istl-2566	218	59	.	.	PUNCT
istl-2566	219	1	chemical	chemical	NOUN
istl-2566	219	2	substance	substance	NOUN
istl-2566	219	3	interpretation	interpretation	NOUN
istl-2566	219	4	differences	difference	NOUN
istl-2566	219	5	such	such	ADJ
istl-2566	219	6	as	as	ADP
istl-2566	219	7	a	a	DET
istl-2566	219	8	stereochemistry	stereochemistry	NOUN
istl-2566	219	9	loss	loss	NOUN
istl-2566	219	10	or	or	CCONJ
istl-2566	219	11	hydrogen	hydrogen	NOUN
istl-2566	219	12	count	count	NOUN
istl-2566	219	13	disagreement	disagreement	NOUN
istl-2566	219	14	highlights	highlight	VERB
istl-2566	219	15	the	the	DET
istl-2566	219	16	importance	importance	NOUN
istl-2566	219	17	of	of	ADP
istl-2566	219	18	maintaining	maintain	VERB
istl-2566	219	19	provenance	provenance	NOUN
istl-2566	219	20	to	to	ADP
istl-2566	219	21	the	the	DET
istl-2566	219	22	original	original	ADJ
istl-2566	219	23	data	datum	NOUN
istl-2566	219	24	and	and	CCONJ
istl-2566	219	25	link	link	NOUN
istl-2566	219	26	to	to	ADP
istl-2566	219	27	bibliographic	bibliographic	ADJ
istl-2566	219	28	record	record	NOUN
istl-2566	219	29	.	.	PUNCT
istl-2566	220	1	while	while	SCONJ
istl-2566	220	2	we	we	PRON
istl-2566	220	3	can	can	AUX
istl-2566	220	4	endeavor	endeavor	VERB
istl-2566	220	5	to	to	PART
istl-2566	220	6	limit	limit	VERB
istl-2566	220	7	errors	error	NOUN
istl-2566	220	8	(	(	PUNCT
istl-2566	220	9	~95	~95	ADJ
istl-2566	220	10	%	%	NOUN
istl-2566	220	11	precision	precision	NOUN
istl-2566	220	12	based	base	VERB
istl-2566	220	13	on	on	ADP
istl-2566	220	14	standard	standard	ADJ
istl-2566	220	15	inchi	inchi	NOUN
istl-2566	220	16	comparison	comparison	NOUN
istl-2566	220	17	)	)	PUNCT
istl-2566	220	18	,	,	PUNCT
istl-2566	220	19	ultimately	ultimately	ADV
istl-2566	220	20	the	the	DET
istl-2566	220	21	end	end	NOUN
istl-2566	220	22	user	user	NOUN
istl-2566	220	23	should	should	AUX
istl-2566	220	24	always	always	ADV
istl-2566	220	25	validate	validate	VERB
istl-2566	220	26	the	the	DET
istl-2566	220	27	data	datum	NOUN
istl-2566	220	28	with	with	ADP
istl-2566	220	29	the	the	DET
istl-2566	220	30	original	original	ADJ
istl-2566	220	31	source	source	NOUN
istl-2566	220	32	.	.	PUNCT
istl-2566	221	1	one	one	NUM
istl-2566	221	2	of	of	ADP
istl-2566	221	3	the	the	DET
istl-2566	221	4	biggest	big	ADJ
istl-2566	221	5	advantages	advantage	NOUN
istl-2566	221	6	of	of	ADP
istl-2566	221	7	depositing	deposit	VERB
istl-2566	221	8	data	datum	NOUN
istl-2566	221	9	in	in	ADP
istl-2566	221	10	pubchem	pubchem	PROPN
istl-2566	221	11	is	be	AUX
istl-2566	221	12	that	that	SCONJ
istl-2566	221	13	users	user	NOUN
istl-2566	221	14	can	can	AUX
istl-2566	221	15	now	now	ADV
istl-2566	221	16	search	search	VERB
istl-2566	221	17	for	for	ADP
istl-2566	221	18	ua	ua	PROPN
istl-2566	221	19	thesis	thesis	NOUN
istl-2566	221	20	substance	substance	NOUN
istl-2566	221	21	data	datum	NOUN
istl-2566	221	22	with	with	ADP
istl-2566	221	23	chemical	chemical	ADJ
istl-2566	221	24	specific	specific	ADJ
istl-2566	221	25	search	search	NOUN
istl-2566	221	26	query	query	NOUN
istl-2566	221	27	options	option	NOUN
istl-2566	221	28	,	,	PUNCT
istl-2566	221	29	such	such	ADJ
istl-2566	221	30	as	as	ADP
istl-2566	221	31	by	by	ADP
istl-2566	221	32	chemical	chemical	NOUN
istl-2566	221	33	structure	structure	NOUN
istl-2566	221	34	,	,	PUNCT
istl-2566	221	35	substructure	substructure	NOUN
istl-2566	221	36	,	,	PUNCT
istl-2566	221	37	molecular	molecular	ADJ
istl-2566	221	38	formula	formula	NOUN
istl-2566	221	39	,	,	PUNCT
istl-2566	221	40	and	and	CCONJ
istl-2566	221	41	identifier	identifier	ADV
istl-2566	221	42	.	.	PUNCT
istl-2566	222	1	notably	notably	ADV
istl-2566	222	2	,	,	PUNCT
istl-2566	222	3	there	there	PRON
istl-2566	222	4	is	be	VERB
istl-2566	222	5	limited	limited	ADJ
istl-2566	222	6	information	information	NOUN
istl-2566	222	7	available	available	ADJ
istl-2566	222	8	about	about	ADP
istl-2566	222	9	chemists	chemist	NOUN
istl-2566	222	10	’	’	PART
istl-2566	222	11	use	use	NOUN
istl-2566	222	12	of	of	ADP
istl-2566	222	13	pubchem	pubchem	NOUN
istl-2566	222	14	as	as	ADP
istl-2566	222	15	citations	citation	NOUN
istl-2566	222	16	to	to	ADP
istl-2566	222	17	databases	database	NOUN
istl-2566	222	18	in	in	ADP
istl-2566	222	19	the	the	DET
istl-2566	222	20	literature	literature	NOUN
istl-2566	222	21	are	be	AUX
istl-2566	222	22	rare	rare	ADJ
istl-2566	222	23	(	(	PUNCT
istl-2566	222	24	tomaszewski	tomaszewski	ADJ
istl-2566	222	25	2019	2019	NUM
istl-2566	222	26	)	)	PUNCT
istl-2566	222	27	.	.	PUNCT
istl-2566	223	1	in	in	ADP
istl-2566	223	2	a	a	DET
istl-2566	223	3	recent	recent	ADJ
istl-2566	223	4	information	information	NOUN
istl-2566	223	5	seeking	seek	VERB
istl-2566	223	6	behavior	behavior	NOUN
istl-2566	223	7	study	study	NOUN
istl-2566	223	8	of	of	ADP
istl-2566	223	9	chemists	chemist	NOUN
istl-2566	223	10	,	,	PUNCT
istl-2566	223	11	however	however	ADV
istl-2566	223	12	,	,	PUNCT
istl-2566	223	13	it	it	PRON
istl-2566	223	14	was	be	AUX
istl-2566	223	15	found	find	VERB
istl-2566	223	16	that	that	SCONJ
istl-2566	223	17	about	about	ADV
istl-2566	223	18	17	17	NUM
istl-2566	223	19	%	%	NOUN
istl-2566	223	20	of	of	ADP
istl-2566	223	21	the	the	DET
istl-2566	223	22	chemists	chemist	NOUN
istl-2566	223	23	surveyed	survey	VERB
istl-2566	223	24	use	use	VERB
istl-2566	223	25	pubmed	pubmed	PROPN
istl-2566	223	26	(	(	PUNCT
istl-2566	223	27	gordon	gordon	PROPN
istl-2566	223	28	et	et	PROPN
istl-2566	223	29	al	al	PROPN
istl-2566	223	30	.	.	PROPN
istl-2566	223	31	2018	2018	NUM
istl-2566	223	32	)	)	PUNCT
istl-2566	223	33	,	,	PUNCT
istl-2566	223	34	which	which	PRON
istl-2566	223	35	is	be	AUX
istl-2566	223	36	closely	closely	ADV
istl-2566	223	37	integrated	integrate	VERB
istl-2566	223	38	with	with	ADP
istl-2566	223	39	pubchem	pubchem	PROPN
istl-2566	223	40	.	.	PUNCT
istl-2566	224	1	moreover	moreover	ADV
istl-2566	224	2	,	,	PUNCT
istl-2566	224	3	throughout	throughout	ADP
istl-2566	224	4	2020	2020	NUM
istl-2566	224	5	,	,	PUNCT
istl-2566	224	6	pubchem	pubchem	PROPN
istl-2566	224	7	had	have	VERB
istl-2566	224	8	between	between	ADP
istl-2566	224	9	two	two	NUM
istl-2566	224	10	and	and	CCONJ
istl-2566	224	11	four	four	NUM
istl-2566	224	12	million	million	NUM
istl-2566	224	13	unique	unique	ADJ
istl-2566	224	14	users	user	NOUN
istl-2566	224	15	per	per	ADP
istl-2566	224	16	month	month	NOUN
istl-2566	224	17	(	(	PUNCT
istl-2566	224	18	kim	kim	PROPN
istl-2566	224	19	et	et	PROPN
istl-2566	224	20	al	al	PROPN
istl-2566	224	21	.	.	PROPN
istl-2566	224	22	2021	2021	NUM
istl-2566	224	23	)	)	PUNCT
istl-2566	224	24	.	.	PUNCT
istl-2566	225	1	full	full	ADJ
istl-2566	225	2	access	access	NOUN
istl-2566	225	3	to	to	ADP
istl-2566	225	4	the	the	DET
istl-2566	225	5	ua	ua	PROPN
istl-2566	225	6	thesis	thesis	NOUN
istl-2566	225	7	substance	substance	NOUN
istl-2566	225	8	data	datum	NOUN
istl-2566	225	9	is	be	AUX
istl-2566	225	10	available	available	ADJ
istl-2566	225	11	through	through	ADP
istl-2566	225	12	pubchem	pubchem	NOUN
istl-2566	225	13	via	via	ADP
istl-2566	225	14	the	the	DET
istl-2566	225	15	web	web	NOUN
istl-2566	225	16	interface	interface	NOUN
istl-2566	225	17	or	or	CCONJ
istl-2566	225	18	any	any	PRON
istl-2566	225	19	of	of	ADP
istl-2566	225	20	their	their	PRON
istl-2566	225	21	programmatic	programmatic	ADJ
istl-2566	225	22	interfaces	interface	NOUN
istl-2566	225	23	such	such	ADJ
istl-2566	225	24	as	as	ADP
istl-2566	225	25	pug	pug	NOUN
istl-2566	225	26	-	-	PUNCT
istl-2566	225	27	rest	rest	NOUN
istl-2566	225	28	(	(	PUNCT
istl-2566	225	29	kim	kim	PROPN
istl-2566	225	30	et	et	PROPN
istl-2566	225	31	al	al	PROPN
istl-2566	225	32	.	.	PROPN
istl-2566	225	33	2015	2015	NUM
istl-2566	225	34	)	)	PUNCT
istl-2566	225	35	,	,	PUNCT
istl-2566	225	36	pug	pug	NOUN
istl-2566	225	37	-	-	PUNCT
istl-2566	225	38	view	view	NOUN
istl-2566	225	39	(	(	PUNCT
istl-2566	225	40	kim	kim	X
istl-2566	225	41	et	et	PROPN
istl-2566	225	42	al	al	PROPN
istl-2566	225	43	.	.	PROPN
istl-2566	225	44	2019	2019	NUM
istl-2566	225	45	)	)	PUNCT
istl-2566	225	46	or	or	CCONJ
istl-2566	225	47	e	e	NOUN
istl-2566	225	48	-	-	NOUN
istl-2566	225	49	utilities	utility	NOUN
istl-2566	225	50	(	(	PUNCT
istl-2566	225	51	national	national	ADJ
istl-2566	225	52	center	center	NOUN
istl-2566	225	53	for	for	ADP
istl-2566	225	54	biotechnology	biotechnology	NOUN
istl-2566	225	55	information	information	NOUN
istl-2566	225	56	2021	2021	NUM
istl-2566	225	57	)	)	PUNCT
istl-2566	225	58	.	.	PUNCT
istl-2566	226	1	we	we	PRON
istl-2566	226	2	recommend	recommend	VERB
istl-2566	226	3	accessing	access	VERB
istl-2566	226	4	ua	ua	PROPN
istl-2566	226	5	thesis	thesis	NOUN
istl-2566	226	6	substance	substance	NOUN
istl-2566	226	7	data	datum	NOUN
istl-2566	226	8	through	through	ADP
istl-2566	226	9	pubchem	pubchem	NOUN
istl-2566	226	10	,	,	PUNCT
istl-2566	226	11	since	since	SCONJ
istl-2566	226	12	pubchem	pubchem	NOUN
istl-2566	226	13	standardizes	standardize	VERB
istl-2566	226	14	the	the	DET
istl-2566	226	15	data	datum	NOUN
istl-2566	226	16	and	and	CCONJ
istl-2566	226	17	combines	combine	VERB
istl-2566	226	18	the	the	DET
istl-2566	226	19	data	datum	NOUN
istl-2566	226	20	with	with	ADP
istl-2566	226	21	related	related	ADJ
istl-2566	226	22	information	information	NOUN
istl-2566	226	23	.	.	PUNCT
istl-2566	227	1	however	however	ADV
istl-2566	227	2	,	,	PUNCT
istl-2566	227	3	to	to	PART
istl-2566	227	4	maintain	maintain	VERB
istl-2566	227	5	the	the	DET
istl-2566	227	6	provenance	provenance	NOUN
istl-2566	227	7	of	of	ADP
istl-2566	227	8	the	the	DET
istl-2566	227	9	substance	substance	NOUN
istl-2566	227	10	data	datum	NOUN
istl-2566	227	11	,	,	PUNCT
istl-2566	227	12	and	and	CCONJ
istl-2566	227	13	allow	allow	VERB
istl-2566	227	14	users	user	NOUN
istl-2566	227	15	to	to	PART
istl-2566	227	16	validate	validate	VERB
istl-2566	227	17	the	the	DET
istl-2566	227	18	data	datum	NOUN
istl-2566	227	19	,	,	PUNCT
istl-2566	227	20	there	there	PRON
istl-2566	227	21	is	be	VERB
istl-2566	227	22	a	a	DET
istl-2566	227	23	link	link	NOUN
istl-2566	227	24	from	from	ADP
istl-2566	227	25	the	the	DET
istl-2566	227	26	source	source	NOUN
istl-2566	227	27	field	field	NOUN
istl-2566	227	28	in	in	ADP
istl-2566	227	29	our	our	PRON
istl-2566	227	30	pubchem	pubchem	NOUN
istl-2566	227	31	deposited	deposit	VERB
istl-2566	227	32	data	datum	NOUN
istl-2566	227	33	directly	directly	ADV
istl-2566	227	34	to	to	ADP
istl-2566	227	35	our	our	PRON
istl-2566	227	36	ualib_chemstructures	ualib_chemstructure	NOUN
istl-2566	227	37	github	github	PROPN
istl-2566	227	38	repository	repository	NOUN
istl-2566	227	39	which	which	PRON
istl-2566	227	40	contains	contain	VERB
istl-2566	227	41	notes	note	NOUN
istl-2566	227	42	about	about	ADP
istl-2566	227	43	reuse	reuse	NOUN
istl-2566	227	44	(	(	PUNCT
istl-2566	227	45	cc	cc	X
istl-2566	227	46	-	-	NOUN
istl-2566	227	47	by	by	ADP
istl-2566	227	48	4.0	4.0	NUM
istl-2566	227	49	)	)	PUNCT
istl-2566	227	50	,	,	PUNCT
istl-2566	227	51	the	the	DET
istl-2566	227	52	original	original	ADJ
istl-2566	227	53	substance	substance	NOUN
istl-2566	227	54	data	datum	NOUN
istl-2566	227	55	files	file	NOUN
istl-2566	227	56	,	,	PUNCT
istl-2566	227	57	and	and	CCONJ
istl-2566	227	58	thesis	thesis	NOUN
istl-2566	227	59	bibliographic	bibliographic	ADJ
istl-2566	227	60	reference	reference	NOUN
istl-2566	227	61	.	.	PUNCT
istl-2566	228	1	another	another	DET
istl-2566	228	2	advantage	advantage	NOUN
istl-2566	228	3	of	of	ADP
istl-2566	228	4	depositing	deposit	VERB
istl-2566	228	5	substance	substance	NOUN
istl-2566	228	6	data	datum	NOUN
istl-2566	228	7	in	in	ADP
istl-2566	228	8	pubchem	pubchem	NOUN
istl-2566	228	9	is	be	AUX
istl-2566	228	10	the	the	DET
istl-2566	228	11	ability	ability	NOUN
istl-2566	228	12	to	to	PART
istl-2566	228	13	update	update	VERB
istl-2566	228	14	records	record	NOUN
istl-2566	228	15	.	.	PUNCT
istl-2566	229	1	if	if	SCONJ
istl-2566	229	2	the	the	DET
istl-2566	229	3	updated	update	VERB
istl-2566	229	4	data	datum	NOUN
istl-2566	229	5	is	be	AUX
istl-2566	229	6	submitted	submit	VERB
istl-2566	229	7	with	with	ADP
istl-2566	229	8	the	the	DET
istl-2566	229	9	original	original	ADJ
istl-2566	229	10	registry	registry	NOUN
istl-2566	229	11	identifier	identifier	NOUN
istl-2566	229	12	,	,	PUNCT
istl-2566	229	13	pubchem	pubchem	PROPN
istl-2566	229	14	will	will	AUX
istl-2566	229	15	maintain	maintain	VERB
istl-2566	229	16	substance	substance	NOUN
istl-2566	229	17	record	record	NOUN
istl-2566	229	18	versioning	versioning	NOUN
istl-2566	229	19	and	and	CCONJ
istl-2566	229	20	reprocess	reprocess	VERB
istl-2566	229	21	the	the	DET
istl-2566	229	22	data	datum	NOUN
istl-2566	229	23	into	into	ADP
istl-2566	229	24	pubchem	pubchem	PROPN
istl-2566	229	25	compound	compound	PROPN
istl-2566	229	26	.	.	PUNCT
istl-2566	230	1	this	this	PRON
istl-2566	230	2	is	be	AUX
istl-2566	230	3	important	important	ADJ
istl-2566	230	4	,	,	PUNCT
istl-2566	230	5	and	and	CCONJ
istl-2566	230	6	allows	allow	VERB
istl-2566	230	7	us	we	PRON
istl-2566	230	8	to	to	PART
istl-2566	230	9	update	update	VERB
istl-2566	230	10	our	our	PRON
istl-2566	230	11	substance	substance	NOUN
istl-2566	230	12	records	record	NOUN
istl-2566	230	13	,	,	PUNCT
istl-2566	230	14	for	for	ADP
istl-2566	230	15	example	example	NOUN
istl-2566	230	16	,	,	PUNCT
istl-2566	230	17	as	as	SCONJ
istl-2566	230	18	we	we	PRON
istl-2566	230	19	become	become	VERB
istl-2566	230	20	aware	aware	ADJ
istl-2566	230	21	of	of	ADP
istl-2566	230	22	errors	error	NOUN
istl-2566	230	23	or	or	CCONJ
istl-2566	230	24	need	need	VERB
istl-2566	230	25	to	to	PART
istl-2566	230	26	update	update	VERB
istl-2566	230	27	a	a	DET
istl-2566	230	28	bibliographic	bibliographic	ADJ
istl-2566	230	29	reference	reference	NOUN
istl-2566	230	30	link	link	NOUN
istl-2566	230	31	.	.	PUNCT
istl-2566	231	1	moreover	moreover	ADV
istl-2566	231	2	,	,	PUNCT
istl-2566	231	3	we	we	PRON
istl-2566	231	4	expect	expect	VERB
istl-2566	231	5	to	to	PART
istl-2566	231	6	submit	submit	VERB
istl-2566	231	7	updates	update	NOUN
istl-2566	231	8	as	as	SCONJ
istl-2566	231	9	cheminformatics	cheminformatic	NOUN
istl-2566	231	10	file	file	NOUN
istl-2566	231	11	formats	format	NOUN
istl-2566	231	12	improve	improve	VERB
istl-2566	231	13	and	and	CCONJ
istl-2566	231	14	as	as	ADP
istl-2566	231	15	our	our	PRON
istl-2566	231	16	workflows	workflow	NOUN
istl-2566	231	17	and	and	CCONJ
istl-2566	231	18	understanding	understanding	NOUN
istl-2566	231	19	of	of	ADP
istl-2566	231	20	how	how	SCONJ
istl-2566	231	21	to	to	PART
istl-2566	231	22	handle	handle	VERB
istl-2566	231	23	chemical	chemical	ADJ
istl-2566	231	24	representation	representation	NOUN
istl-2566	231	25	increases	increase	NOUN
istl-2566	231	26	.	.	PUNCT
istl-2566	232	1	cost	cost	VERB
istl-2566	232	2	versus	versus	ADP
istl-2566	232	3	benefit	benefit	NOUN
istl-2566	232	4	considerations	consideration	NOUN
istl-2566	232	5	a	a	DET
istl-2566	232	6	reasonable	reasonable	ADJ
istl-2566	232	7	question	question	NOUN
istl-2566	232	8	to	to	PART
istl-2566	232	9	consider	consider	VERB
istl-2566	232	10	is	be	AUX
istl-2566	232	11	what	what	PRON
istl-2566	232	12	is	be	AUX
istl-2566	232	13	the	the	DET
istl-2566	232	14	cost	cost	NOUN
istl-2566	232	15	versus	versus	ADP
istl-2566	232	16	benefit	benefit	NOUN
istl-2566	232	17	of	of	ADP
istl-2566	232	18	spending	spend	VERB
istl-2566	232	19	the	the	DET
istl-2566	232	20	time	time	NOUN
istl-2566	232	21	to	to	PART
istl-2566	232	22	extract	extract	VERB
istl-2566	232	23	,	,	PUNCT
istl-2566	232	24	register	register	VERB
istl-2566	232	25	,	,	PUNCT
istl-2566	232	26	and	and	CCONJ
istl-2566	232	27	share	share	NOUN
istl-2566	232	28	substances	substance	NOUN
istl-2566	232	29	retrospectively	retrospectively	ADV
istl-2566	232	30	from	from	ADP
istl-2566	232	31	theses	thesis	NOUN
istl-2566	232	32	?	?	PUNCT
istl-2566	233	1	it	it	PRON
istl-2566	233	2	is	be	AUX
istl-2566	233	3	a	a	DET
istl-2566	233	4	hard	hard	ADJ
istl-2566	233	5	question	question	NOUN
istl-2566	233	6	to	to	PART
istl-2566	233	7	answer	answer	VERB
istl-2566	233	8	,	,	PUNCT
istl-2566	233	9	but	but	CCONJ
istl-2566	233	10	we	we	PRON
istl-2566	233	11	do	do	AUX
istl-2566	233	12	have	have	VERB
istl-2566	233	13	a	a	DET
istl-2566	233	14	couple	couple	NOUN
istl-2566	233	15	of	of	ADP
istl-2566	233	16	supporting	support	VERB
istl-2566	233	17	quantitative	quantitative	ADJ
istl-2566	233	18	data	datum	NOUN
istl-2566	233	19	points	point	NOUN
istl-2566	233	20	.	.	PUNCT
istl-2566	234	1	for	for	ADP
istl-2566	234	2	example	example	NOUN
istl-2566	234	3	,	,	PUNCT
istl-2566	234	4	we	we	PRON
istl-2566	234	5	found	find	VERB
istl-2566	234	6	that	that	SCONJ
istl-2566	234	7	at	at	ADV
istl-2566	234	8	least	least	ADV
istl-2566	234	9	40	40	NUM
istl-2566	234	10	%	%	NOUN
istl-2566	234	11	of	of	ADP
istl-2566	234	12	the	the	DET
istl-2566	234	13	substances	substance	NOUN
istl-2566	234	14	we	we	PRON
istl-2566	234	15	shared	share	VERB
istl-2566	234	16	were	be	AUX
istl-2566	234	17	new	new	ADJ
istl-2566	234	18	to	to	ADP
istl-2566	234	19	pubchem	pubchem	NOUN
istl-2566	234	20	.	.	PUNCT
istl-2566	235	1	the	the	DET
istl-2566	235	2	40	40	NUM
istl-2566	235	3	%	%	NOUN
istl-2566	235	4	we	we	PRON
istl-2566	235	5	found	find	VERB
istl-2566	235	6	is	be	AUX
istl-2566	235	7	less	less	ADJ
istl-2566	235	8	than	than	ADP
istl-2566	235	9	the	the	DET
istl-2566	235	10	70	70	NUM
istl-2566	235	11	%	%	NOUN
istl-2566	235	12	reported	report	VERB
istl-2566	235	13	by	by	ADP
istl-2566	235	14	andrews	andrew	NOUN
istl-2566	235	15	et	et	PROPN
istl-2566	236	1	al	al	PROPN
istl-2566	236	2	.	.	PUNCT
istl-2566	236	3	(	(	PUNCT
istl-2566	236	4	2016	2016	NUM
istl-2566	236	5	)	)	PUNCT
istl-2566	236	6	for	for	ADP
istl-2566	236	7	new	new	ADJ
istl-2566	236	8	substances	substance	NOUN
istl-2566	236	9	deposited	deposit	VERB
istl-2566	236	10	to	to	PART
istl-2566	236	11	chemspider	chemspider	VERB
istl-2566	236	12	from	from	ADP
istl-2566	236	13	uk	uk	PROPN
istl-2566	236	14	theses	theses	PROPN
istl-2566	236	15	;	;	PUNCT
istl-2566	236	16	however	however	ADV
istl-2566	236	17	,	,	PUNCT
istl-2566	236	18	it	it	PRON
istl-2566	236	19	is	be	AUX
istl-2566	236	20	still	still	ADV
istl-2566	236	21	a	a	DET
istl-2566	236	22	large	large	ADJ
istl-2566	236	23	percentage	percentage	NOUN
istl-2566	236	24	of	of	ADP
istl-2566	236	25	new	new	ADJ
istl-2566	236	26	substances	substance	NOUN
istl-2566	236	27	deposited	deposit	VERB
istl-2566	236	28	.	.	PUNCT
istl-2566	237	1	there	there	PRON
istl-2566	237	2	is	be	VERB
istl-2566	237	3	also	also	ADV
istl-2566	237	4	a	a	DET
istl-2566	237	5	potential	potential	NOUN
istl-2566	237	6	to	to	PART
istl-2566	237	7	quantify	quantify	VERB
istl-2566	237	8	any	any	DET
istl-2566	237	9	increased	increase	VERB
istl-2566	237	10	web	web	NOUN
istl-2566	237	11	traffic	traffic	NOUN
istl-2566	237	12	views	view	NOUN
istl-2566	237	13	of	of	ADP
istl-2566	237	14	ua	ua	NOUN
istl-2566	237	15	theses	these	VERB
istl-2566	237	16	with	with	ADP
istl-2566	237	17	substances	substance	NOUN
istl-2566	237	18	shared	share	VERB
istl-2566	237	19	versus	versus	ADP
istl-2566	237	20	theses	thesis	NOUN
istl-2566	237	21	that	that	PRON
istl-2566	237	22	do	do	AUX
istl-2566	237	23	not	not	PART
istl-2566	237	24	have	have	VERB
istl-2566	237	25	their	their	PRON
istl-2566	237	26	substances	substance	NOUN
istl-2566	237	27	shared	share	VERB
istl-2566	237	28	in	in	ADP
istl-2566	237	29	machine	machine	NOUN
istl-2566	237	30	-	-	PUNCT
istl-2566	237	31	readable	readable	ADJ
istl-2566	237	32	format	format	NOUN
istl-2566	237	33	.	.	PUNCT
istl-2566	238	1	we	we	PRON
istl-2566	238	2	hope	hope	VERB
istl-2566	238	3	to	to	PART
istl-2566	238	4	have	have	VERB
istl-2566	238	5	some	some	DET
istl-2566	238	6	meaningful	meaningful	ADJ
istl-2566	238	7	usage	usage	NOUN
istl-2566	238	8	data	datum	NOUN
istl-2566	238	9	to	to	PART
istl-2566	238	10	analyze	analyze	VERB
istl-2566	238	11	after	after	ADP
istl-2566	238	12	a	a	DET
istl-2566	238	13	few	few	ADJ
istl-2566	238	14	years	year	NOUN
istl-2566	238	15	,	,	PUNCT
istl-2566	238	16	which	which	PRON
istl-2566	238	17	should	should	AUX
istl-2566	238	18	provide	provide	VERB
istl-2566	238	19	a	a	DET
istl-2566	238	20	reasonable	reasonable	ADJ
istl-2566	238	21	time	time	NOUN
istl-2566	238	22	frame	frame	NOUN
istl-2566	238	23	for	for	ADP
istl-2566	238	24	discovery	discovery	NOUN
istl-2566	238	25	of	of	ADP
istl-2566	238	26	the	the	DET
istl-2566	238	27	new	new	ADJ
istl-2566	238	28	data	datum	NOUN
istl-2566	238	29	in	in	ADP
istl-2566	238	30	pubchem	pubchem	NOUN
istl-2566	238	31	.	.	PUNCT
istl-2566	239	1	more	more	ADV
istl-2566	239	2	broadly	broadly	ADV
istl-2566	239	3	,	,	PUNCT
istl-2566	239	4	theses	theses	PROPN
istl-2566	239	5	represent	represent	VERB
istl-2566	239	6	the	the	DET
istl-2566	239	7	history	history	NOUN
istl-2566	239	8	of	of	ADP
istl-2566	239	9	the	the	DET
istl-2566	239	10	research	research	NOUN
istl-2566	239	11	at	at	ADP
istl-2566	239	12	an	an	DET
istl-2566	239	13	institution	institution	NOUN
istl-2566	239	14	(	(	PUNCT
istl-2566	239	15	scalfani	scalfani	VERB
istl-2566	239	16	2017	2017	NUM
istl-2566	239	17	)	)	PUNCT
istl-2566	239	18	,	,	PUNCT
istl-2566	239	19	and	and	CCONJ
istl-2566	239	20	we	we	PRON
istl-2566	239	21	feel	feel	VERB
istl-2566	239	22	strongly	strongly	ADV
istl-2566	239	23	that	that	SCONJ
istl-2566	239	24	one	one	NUM
istl-2566	239	25	of	of	ADP
istl-2566	239	26	the	the	DET
istl-2566	239	27	most	most	ADV
istl-2566	239	28	important	important	ADJ
istl-2566	239	29	tasks	task	NOUN
istl-2566	239	30	a	a	DET
istl-2566	239	31	librarian	librarian	NOUN
istl-2566	239	32	should	should	AUX
istl-2566	239	33	engage	engage	VERB
istl-2566	239	34	in	in	ADP
istl-2566	239	35	is	be	AUX
istl-2566	239	36	to	to	PART
istl-2566	239	37	help	help	VERB
istl-2566	239	38	promote	promote	VERB
istl-2566	239	39	,	,	PUNCT
istl-2566	239	40	share	share	NOUN
istl-2566	239	41	,	,	PUNCT
istl-2566	239	42	and	and	CCONJ
istl-2566	239	43	preserve	preserve	VERB
istl-2566	239	44	their	their	PRON
istl-2566	239	45	institutions	institution	NOUN
istl-2566	239	46	’	’	PART
istl-2566	239	47	research	research	NOUN
istl-2566	239	48	for	for	SCONJ
istl-2566	239	49	others	other	NOUN
istl-2566	239	50	to	to	PART
istl-2566	239	51	discover	discover	VERB
istl-2566	239	52	and	and	CCONJ
istl-2566	239	53	build	build	VERB
istl-2566	239	54	upon	upon	SCONJ
istl-2566	239	55	.	.	PUNCT
istl-2566	240	1	we	we	PRON
istl-2566	240	2	acknowledge	acknowledge	VERB
istl-2566	240	3	that	that	SCONJ
istl-2566	240	4	a	a	DET
istl-2566	240	5	significant	significant	ADJ
istl-2566	240	6	time	time	NOUN
istl-2566	240	7	investment	investment	NOUN
istl-2566	240	8	will	will	AUX
istl-2566	240	9	be	be	AUX
istl-2566	240	10	necessary	necessary	ADJ
istl-2566	240	11	for	for	ADP
istl-2566	240	12	the	the	DET
istl-2566	240	13	workflow	workflow	NOUN
istl-2566	240	14	setup	setup	NOUN
istl-2566	240	15	and	and	CCONJ
istl-2566	240	16	becoming	become	VERB
istl-2566	240	17	familiar	familiar	ADJ
istl-2566	240	18	with	with	ADP
istl-2566	240	19	chemical	chemical	ADJ
istl-2566	240	20	structures	structure	NOUN
istl-2566	240	21	,	,	PUNCT
istl-2566	240	22	software	software	NOUN
istl-2566	240	23	,	,	PUNCT
istl-2566	240	24	and	and	CCONJ
istl-2566	240	25	machine	machine	NOUN
istl-2566	240	26	-	-	PUNCT
istl-2566	240	27	readable	readable	ADJ
istl-2566	240	28	chemical	chemical	NOUN
istl-2566	240	29	file	file	NOUN
istl-2566	240	30	formats	format	NOUN
istl-2566	240	31	.	.	PUNCT
istl-2566	241	1	however	however	ADV
istl-2566	241	2	,	,	PUNCT
istl-2566	241	3	after	after	SCONJ
istl-2566	241	4	a	a	DET
istl-2566	241	5	workflow	workflow	NOUN
istl-2566	241	6	is	be	AUX
istl-2566	241	7	set	set	VERB
istl-2566	241	8	up	up	ADP
istl-2566	241	9	similarly	similarly	ADV
istl-2566	241	10	to	to	ADP
istl-2566	241	11	that	that	PRON
istl-2566	241	12	described	describe	VERB
istl-2566	241	13	in	in	ADP
istl-2566	241	14	this	this	DET
istl-2566	241	15	article	article	NOUN
istl-2566	241	16	,	,	PUNCT
istl-2566	241	17	the	the	DET
istl-2566	241	18	actual	actual	ADJ
istl-2566	241	19	process	process	NOUN
istl-2566	241	20	of	of	ADP
istl-2566	241	21	redrawing	redrawe	VERB
istl-2566	241	22	structures	structure	NOUN
istl-2566	241	23	and	and	CCONJ
istl-2566	241	24	sharing	share	VERB
istl-2566	241	25	them	they	PRON
istl-2566	241	26	is	be	AUX
istl-2566	241	27	reasonable	reasonable	ADJ
istl-2566	241	28	and	and	CCONJ
istl-2566	241	29	practical	practical	ADJ
istl-2566	241	30	to	to	PART
istl-2566	241	31	incorporate	incorporate	VERB
istl-2566	241	32	within	within	ADP
istl-2566	241	33	regular	regular	ADJ
istl-2566	241	34	liaison	liaison	NOUN
istl-2566	241	35	workloads	workload	NOUN
istl-2566	241	36	.	.	PUNCT
istl-2566	242	1	with	with	ADP
istl-2566	242	2	a	a	DET
istl-2566	242	3	bit	bit	NOUN
istl-2566	242	4	of	of	ADP
istl-2566	242	5	practice	practice	NOUN
istl-2566	242	6	,	,	PUNCT
istl-2566	242	7	we	we	PRON
istl-2566	242	8	were	be	AUX
istl-2566	242	9	able	able	ADJ
istl-2566	242	10	to	to	PART
istl-2566	242	11	complete	complete	VERB
istl-2566	242	12	an	an	DET
istl-2566	242	13	entire	entire	ADJ
istl-2566	242	14	thesis	thesis	NOUN
istl-2566	242	15	with	with	ADP
istl-2566	242	16	60	60	NUM
istl-2566	242	17	substances	substance	NOUN
istl-2566	242	18	in	in	ADP
istl-2566	242	19	about	about	ADV
istl-2566	242	20	3	3	NUM
istl-2566	242	21	hours	hour	NOUN
istl-2566	242	22	.	.	PUNCT
istl-2566	243	1	conclusion	conclusion	NOUN
istl-2566	243	2	we	we	PRON
istl-2566	243	3	successfully	successfully	ADV
istl-2566	243	4	implemented	implement	VERB
istl-2566	243	5	a	a	DET
istl-2566	243	6	workflow	workflow	NOUN
istl-2566	243	7	to	to	PART
istl-2566	243	8	manually	manually	ADV
istl-2566	243	9	redraw	redraw	VERB
istl-2566	243	10	chemical	chemical	ADJ
istl-2566	243	11	substances	substance	NOUN
istl-2566	243	12	from	from	ADP
istl-2566	243	13	ua	ua	PROPN
istl-2566	243	14	theses	thesis	NOUN
istl-2566	243	15	and	and	CCONJ
istl-2566	243	16	share	share	VERB
istl-2566	243	17	them	they	PRON
istl-2566	243	18	in	in	ADP
istl-2566	243	19	machine	machine	NOUN
istl-2566	243	20	-	-	PUNCT
istl-2566	243	21	readable	readable	ADJ
istl-2566	243	22	format	format	NOUN
istl-2566	243	23	in	in	ADP
istl-2566	243	24	pubchem	pubchem	NOUN
istl-2566	243	25	.	.	PUNCT
istl-2566	244	1	the	the	DET
istl-2566	244	2	main	main	ADJ
istl-2566	244	3	workflow	workflow	NOUN
istl-2566	244	4	used	use	VERB
istl-2566	244	5	a	a	DET
istl-2566	244	6	combination	combination	NOUN
istl-2566	244	7	of	of	ADP
istl-2566	244	8	chemaxon	chemaxon	NOUN
istl-2566	244	9	marvinsketch	marvinsketch	NOUN
istl-2566	244	10	and	and	CCONJ
istl-2566	244	11	rdkit	rdkit	ADJ
istl-2566	244	12	to	to	PART
istl-2566	244	13	create	create	VERB
istl-2566	244	14	a	a	DET
istl-2566	244	15	machine	machine	NOUN
istl-2566	244	16	-	-	PUNCT
istl-2566	244	17	readable	readable	ADJ
istl-2566	244	18	sdfile	sdfile	NOUN
istl-2566	244	19	containing	contain	VERB
istl-2566	244	20	the	the	DET
istl-2566	244	21	substance	substance	NOUN
istl-2566	244	22	connection	connection	NOUN
istl-2566	244	23	tables	table	NOUN
istl-2566	244	24	,	,	PUNCT
istl-2566	244	25	smiles	smile	NOUN
istl-2566	244	26	,	,	PUNCT
istl-2566	244	27	inchi	inchi	PROPN
istl-2566	244	28	and	and	CCONJ
istl-2566	244	29	bibliographic	bibliographic	ADJ
istl-2566	244	30	reference	reference	NOUN
istl-2566	244	31	.	.	PUNCT
istl-2566	245	1	the	the	DET
istl-2566	245	2	greatest	great	ADJ
istl-2566	245	3	challenge	challenge	NOUN
istl-2566	245	4	was	be	AUX
istl-2566	245	5	the	the	DET
istl-2566	245	6	manual	manual	ADJ
istl-2566	245	7	redrawing	redrawing	NOUN
istl-2566	245	8	of	of	ADP
istl-2566	245	9	the	the	DET
istl-2566	245	10	chemical	chemical	ADJ
istl-2566	245	11	substances	substance	NOUN
istl-2566	245	12	,	,	PUNCT
istl-2566	245	13	particularly	particularly	ADV
istl-2566	245	14	when	when	SCONJ
istl-2566	245	15	encountering	encounter	VERB
istl-2566	245	16	perspective	perspective	NOUN
istl-2566	245	17	drawings	drawing	NOUN
istl-2566	245	18	and	and	CCONJ
istl-2566	245	19	stereochemical	stereochemical	ADJ
istl-2566	245	20	mixtures	mixture	NOUN
istl-2566	245	21	.	.	PUNCT
istl-2566	246	1	in	in	ADP
istl-2566	246	2	total	total	PROPN
istl-2566	246	3	,	,	PUNCT
istl-2566	246	4	about	about	ADV
istl-2566	246	5	3,000	3,000	NUM
istl-2566	246	6	chemical	chemical	NOUN
istl-2566	246	7	substances	substance	NOUN
istl-2566	246	8	from	from	ADP
istl-2566	246	9	73	73	NUM
istl-2566	246	10	ua	ua	PROPN
istl-2566	246	11	theses	thesis	NOUN
istl-2566	246	12	were	be	AUX
istl-2566	246	13	shared	share	VERB
istl-2566	246	14	.	.	PUNCT
istl-2566	247	1	at	at	ADV
istl-2566	247	2	least	least	ADV
istl-2566	247	3	40	40	NUM
istl-2566	247	4	%	%	NOUN
istl-2566	247	5	of	of	ADP
istl-2566	247	6	the	the	DET
istl-2566	247	7	substances	substance	NOUN
istl-2566	247	8	were	be	AUX
istl-2566	247	9	new	new	ADJ
istl-2566	247	10	to	to	ADP
istl-2566	247	11	pubchem	pubchem	NOUN
istl-2566	247	12	at	at	ADP
istl-2566	247	13	the	the	DET
istl-2566	247	14	time	time	NOUN
istl-2566	247	15	of	of	ADP
istl-2566	247	16	deposition	deposition	NOUN
istl-2566	247	17	.	.	PUNCT
istl-2566	248	1	substance	substance	NOUN
istl-2566	248	2	depositions	deposition	NOUN
istl-2566	248	3	in	in	ADP
istl-2566	248	4	pubchem	pubchem	NOUN
istl-2566	248	5	include	include	VERB
istl-2566	248	6	the	the	DET
istl-2566	248	7	full	full	ADJ
istl-2566	248	8	thesis	thesis	NOUN
istl-2566	248	9	bibliographic	bibliographic	ADJ
istl-2566	248	10	information	information	NOUN
istl-2566	248	11	and	and	CCONJ
istl-2566	248	12	link	link	VERB
istl-2566	248	13	to	to	ADP
istl-2566	248	14	the	the	DET
istl-2566	248	15	thesis	thesis	NOUN
istl-2566	248	16	full	full	ADJ
istl-2566	248	17	-	-	PUNCT
istl-2566	248	18	text	text	NOUN
istl-2566	248	19	pdf	pdf	NOUN
istl-2566	248	20	or	or	CCONJ
istl-2566	248	21	metadata	metadata	PROPN
istl-2566	248	22	record	record	NOUN
istl-2566	248	23	if	if	SCONJ
istl-2566	248	24	the	the	DET
istl-2566	248	25	digital	digital	ADJ
istl-2566	248	26	full	full	ADJ
istl-2566	248	27	text	text	NOUN
istl-2566	248	28	is	be	AUX
istl-2566	248	29	not	not	PART
istl-2566	248	30	yet	yet	ADV
istl-2566	248	31	available	available	ADJ
istl-2566	248	32	.	.	PUNCT
istl-2566	249	1	users	user	NOUN
istl-2566	249	2	can	can	AUX
istl-2566	249	3	now	now	ADV
istl-2566	249	4	discover	discover	VERB
istl-2566	249	5	ua	ua	PROPN
istl-2566	249	6	theses	thesis	NOUN
istl-2566	249	7	in	in	ADP
istl-2566	249	8	pubchem	pubchem	NOUN
istl-2566	249	9	using	use	VERB
istl-2566	249	10	specific	specific	ADJ
istl-2566	249	11	chemical	chemical	NOUN
istl-2566	249	12	literature	literature	NOUN
istl-2566	249	13	search	search	NOUN
istl-2566	249	14	strategies	strategy	NOUN
istl-2566	249	15	like	like	ADP
istl-2566	249	16	molecular	molecular	ADJ
istl-2566	249	17	formula	formula	NOUN
istl-2566	249	18	,	,	PUNCT
istl-2566	249	19	structure	structure	NOUN
istl-2566	249	20	,	,	PUNCT
istl-2566	249	21	and	and	CCONJ
istl-2566	249	22	identifier	identifier	NOUN
istl-2566	249	23	searches	search	NOUN
istl-2566	249	24	.	.	PUNCT
istl-2566	250	1	for	for	ADP
istl-2566	250	2	librarians	librarian	NOUN
istl-2566	250	3	and	and	CCONJ
istl-2566	250	4	curators	curator	NOUN
istl-2566	250	5	seeking	seek	VERB
istl-2566	250	6	to	to	PART
istl-2566	250	7	share	share	VERB
istl-2566	250	8	chemical	chemical	ADJ
istl-2566	250	9	substance	substance	NOUN
istl-2566	250	10	data	datum	NOUN
istl-2566	250	11	from	from	ADP
istl-2566	250	12	theses	thesis	NOUN
istl-2566	250	13	,	,	PUNCT
istl-2566	250	14	it	it	PRON
istl-2566	250	15	is	be	AUX
istl-2566	250	16	necessary	necessary	ADJ
istl-2566	250	17	to	to	PART
istl-2566	250	18	first	first	ADV
istl-2566	250	19	become	become	VERB
istl-2566	250	20	familiar	familiar	ADJ
istl-2566	250	21	with	with	ADP
istl-2566	250	22	chemical	chemical	ADJ
istl-2566	250	23	file	file	NOUN
istl-2566	250	24	formats	format	NOUN
istl-2566	250	25	and	and	CCONJ
istl-2566	250	26	their	their	PRON
istl-2566	250	27	limitations	limitation	NOUN
istl-2566	250	28	.	.	PUNCT
istl-2566	251	1	it	it	PRON
istl-2566	251	2	will	will	AUX
istl-2566	251	3	take	take	VERB
istl-2566	251	4	time	time	NOUN
istl-2566	251	5	to	to	PART
istl-2566	251	6	register	register	VERB
istl-2566	251	7	and	and	CCONJ
istl-2566	251	8	share	share	VERB
istl-2566	251	9	a	a	DET
istl-2566	251	10	significant	significant	ADJ
istl-2566	251	11	amount	amount	NOUN
istl-2566	251	12	of	of	ADP
istl-2566	251	13	retrospective	retrospective	ADJ
istl-2566	251	14	thesis	thesis	NOUN
istl-2566	251	15	substance	substance	NOUN
istl-2566	251	16	data	datum	NOUN
istl-2566	251	17	from	from	ADP
istl-2566	251	18	research	research	NOUN
istl-2566	251	19	libraries	library	NOUN
istl-2566	251	20	;	;	PUNCT
istl-2566	251	21	however	however	ADV
istl-2566	251	22	,	,	PUNCT
istl-2566	251	23	we	we	PRON
istl-2566	251	24	are	be	AUX
istl-2566	251	25	hopeful	hopeful	ADJ
istl-2566	251	26	that	that	SCONJ
istl-2566	251	27	this	this	DET
istl-2566	251	28	article	article	NOUN
istl-2566	251	29	will	will	AUX
istl-2566	251	30	help	help	VERB
istl-2566	251	31	stimulate	stimulate	VERB
istl-2566	251	32	interest	interest	NOUN
istl-2566	251	33	among	among	ADP
istl-2566	251	34	chemistry	chemistry	NOUN
istl-2566	251	35	librarians	librarian	NOUN
istl-2566	251	36	and	and	CCONJ
istl-2566	251	37	support	support	VERB
istl-2566	251	38	the	the	DET
istl-2566	251	39	idea	idea	NOUN
istl-2566	251	40	that	that	SCONJ
istl-2566	251	41	enhancing	enhance	VERB
istl-2566	251	42	the	the	DET
istl-2566	251	43	discovery	discovery	NOUN
istl-2566	251	44	of	of	ADP
istl-2566	251	45	theses	thesis	NOUN
istl-2566	251	46	is	be	AUX
istl-2566	251	47	of	of	ADP
istl-2566	251	48	value	value	NOUN
istl-2566	251	49	to	to	ADP
istl-2566	251	50	the	the	DET
istl-2566	251	51	community	community	NOUN
istl-2566	251	52	and	and	CCONJ
istl-2566	251	53	profession	profession	NOUN
istl-2566	251	54	.	.	PUNCT
istl-2566	252	1	supporting	support	VERB
istl-2566	252	2	information	information	NOUN
istl-2566	252	3	github	github	PROPN
istl-2566	252	4	repository	repository	NOUN
istl-2566	252	5	:	:	PUNCT
istl-2566	252	6	https://github.com/ualibweb/ualib_chemstructures	https://github.com/ualibweb/ualib_chemstructure	NOUN
istl-2566	252	7	–	–	PUNCT
istl-2566	252	8	includes	include	VERB
istl-2566	252	9	all	all	DET
istl-2566	252	10	working	work	VERB
istl-2566	252	11	substance	substance	NOUN
istl-2566	252	12	data	datum	NOUN
istl-2566	252	13	files	file	NOUN
istl-2566	252	14	,	,	PUNCT
istl-2566	252	15	programmatic	programmatic	ADJ
istl-2566	252	16	scripts	script	NOUN
istl-2566	252	17	,	,	PUNCT
istl-2566	252	18	and	and	CCONJ
istl-2566	252	19	notes	note	NOUN
istl-2566	252	20	.	.	PUNCT
istl-2566	253	1	pubchem	pubchem	PROPN
istl-2566	253	2	data	datum	NOUN
istl-2566	253	3	:	:	PUNCT
istl-2566	253	4	https://pubchem.ncbi.nlm.nih.gov/source/15645	https://pubchem.ncbi.nlm.nih.gov/source/15645	PROPN
istl-2566	253	5	–	–	PUNCT
istl-2566	253	6	includes	include	VERB
istl-2566	253	7	substance	substance	NOUN
istl-2566	253	8	data	datum	NOUN
istl-2566	253	9	submitted	submit	VERB
istl-2566	253	10	to	to	ADP
istl-2566	253	11	pubchem	pubchem	NOUN
istl-2566	253	12	(	(	PUNCT
istl-2566	253	13	sids	sid	NOUN
istl-2566	253	14	)	)	PUNCT
istl-2566	253	15	and	and	CCONJ
istl-2566	253	16	standardized	standardize	VERB
istl-2566	253	17	pubchem	pubchem	NOUN
istl-2566	253	18	data	datum	NOUN
istl-2566	253	19	(	(	PUNCT
istl-2566	253	20	cids	cid	NOUN
istl-2566	253	21	)	)	PUNCT
istl-2566	253	22	.	.	PUNCT
istl-2566	254	1	institutional	institutional	ADJ
istl-2566	254	2	repository	repository	ADJ
istl-2566	254	3	archived	archive	VERB
istl-2566	254	4	data	datum	NOUN
istl-2566	254	5	:	:	PUNCT
istl-2566	254	6	https://ir.ua.edu/	https://ir.ua.edu/	PROPN
istl-2566	254	7	includes	include	VERB
istl-2566	254	8	a	a	DET
istl-2566	254	9	copy	copy	NOUN
istl-2566	254	10	of	of	ADP
istl-2566	254	11	the	the	DET
istl-2566	254	12	original	original	ADJ
istl-2566	254	13	machine	machine	NOUN
istl-2566	254	14	-	-	PUNCT
istl-2566	254	15	readable	readable	ADJ
istl-2566	254	16	files	file	NOUN
istl-2566	254	17	submitted	submit	VERB
istl-2566	254	18	to	to	ADP
istl-2566	254	19	pubchem	pubchem	NOUN
istl-2566	254	20	.	.	PUNCT
istl-2566	255	1	acknowledgments	acknowledgment	NOUN
istl-2566	255	2	vfs	vfs	PROPN
istl-2566	255	3	thanks	thank	NOUN
istl-2566	255	4	jeweles	jeweles	PROPN
istl-2566	255	5	moton	moton	PROPN
istl-2566	255	6	,	,	PUNCT
istl-2566	255	7	rachel	rachel	PROPN
istl-2566	255	8	humphrey	humphrey	PROPN
istl-2566	255	9	,	,	PUNCT
istl-2566	255	10	donald	donald	PROPN
istl-2566	255	11	williams	williams	PROPN
istl-2566	255	12	,	,	PUNCT
istl-2566	255	13	and	and	CCONJ
istl-2566	255	14	mary	mary	PROPN
istl-2566	255	15	alexander	alexander	PROPN
istl-2566	255	16	for	for	ADP
istl-2566	255	17	help	help	NOUN
istl-2566	255	18	with	with	ADP
istl-2566	255	19	early	early	ADJ
istl-2566	255	20	data	data	NOUN
istl-2566	255	21	collection	collection	NOUN
istl-2566	255	22	and	and	CCONJ
istl-2566	255	23	workflows	workflow	NOUN
istl-2566	255	24	.	.	PUNCT
istl-2566	256	1	we	we	PRON
istl-2566	256	2	thank	thank	VERB
istl-2566	256	3	chemaxon	chemaxon	PROPN
istl-2566	256	4	for	for	ADP
istl-2566	256	5	the	the	DET
istl-2566	256	6	marvinsketch	marvinsketch	NOUN
istl-2566	256	7	academic	academic	ADJ
istl-2566	256	8	research	research	NOUN
istl-2566	256	9	license	license	NOUN
istl-2566	256	10	,	,	PUNCT
istl-2566	256	11	bio	bio	PROPN
istl-2566	256	12	-	-	PROPN
istl-2566	256	13	rad	rad	PROPN
istl-2566	256	14	for	for	ADP
istl-2566	256	15	the	the	DET
istl-2566	256	16	knowitall	knowitall	NOUN
istl-2566	256	17	academic	academic	ADJ
istl-2566	256	18	license	license	NOUN
istl-2566	256	19	(	(	PUNCT
istl-2566	256	20	now	now	ADV
istl-2566	256	21	wiley	wiley	ADJ
istl-2566	256	22	science	science	NOUN
istl-2566	256	23	solutions	solution	NOUN
istl-2566	256	24	)	)	PUNCT
istl-2566	256	25	,	,	PUNCT
istl-2566	256	26	and	and	CCONJ
istl-2566	256	27	all	all	DET
istl-2566	256	28	contributors	contributor	NOUN
istl-2566	256	29	to	to	PART
istl-2566	256	30	rdkit	rdkit	VERB
istl-2566	256	31	.	.	PUNCT
istl-2566	257	1	vfs	vfs	PROPN
istl-2566	257	2	acknowledges	acknowledge	VERB
istl-2566	257	3	the	the	DET
istl-2566	257	4	university	university	PROPN
istl-2566	257	5	of	of	ADP
istl-2566	257	6	alabama	alabama	PROPN
istl-2566	257	7	libraries	library	NOUN
istl-2566	257	8	for	for	ADP
istl-2566	257	9	granting	grant	VERB
istl-2566	257	10	research	research	NOUN
istl-2566	257	11	leave	leave	NOUN
istl-2566	257	12	for	for	ADP
istl-2566	257	13	this	this	DET
istl-2566	257	14	work	work	NOUN
istl-2566	257	15	.	.	PUNCT
istl-2566	258	1	finally	finally	ADV
istl-2566	258	2	,	,	PUNCT
istl-2566	258	3	we	we	PRON
istl-2566	258	4	thank	thank	VERB
istl-2566	258	5	nih	nih	PROPN
istl-2566	258	6	/	/	SYM
istl-2566	258	7	nlm	nlm	PROPN
istl-2566	258	8	/	/	SYM
istl-2566	258	9	ncbi	ncbi	PROPN
istl-2566	258	10	pubchem	pubchem	PROPN
istl-2566	258	11	staff	staff	NOUN
istl-2566	258	12	for	for	ADP
istl-2566	258	13	their	their	PRON
istl-2566	258	14	helpful	helpful	ADJ
istl-2566	258	15	responses	response	NOUN
istl-2566	258	16	related	relate	VERB
istl-2566	258	17	to	to	ADP
istl-2566	258	18	chemical	chemical	NOUN
istl-2566	258	19	file	file	NOUN
istl-2566	258	20	formats	format	NOUN
istl-2566	258	21	and	and	CCONJ
istl-2566	258	22	data	data	NOUN
istl-2566	258	23	submission	submission	NOUN
istl-2566	258	24	questions	question	NOUN
istl-2566	258	25	.	.	PUNCT
istl-2566	259	1	references	reference	NOUN
istl-2566	259	2	abshear	abshear	PROPN
istl-2566	259	3	,	,	PUNCT
istl-2566	259	4	t.	t.	PROPN
istl-2566	259	5	,	,	PUNCT
istl-2566	259	6	banik	banik	PROPN
istl-2566	259	7	,	,	PUNCT
istl-2566	259	8	g.	g.	PROPN
istl-2566	259	9	,	,	PUNCT
istl-2566	259	10	dalvi	dalvi	PROPN
istl-2566	259	11	,	,	PUNCT
istl-2566	259	12	s.	s.	PROPN
istl-2566	259	13	,	,	PUNCT
istl-2566	259	14	d’souza	d’souza	PROPN
istl-2566	259	15	,	,	PUNCT
istl-2566	259	16	m.	m.	NOUN
istl-2566	259	17	,	,	PUNCT
istl-2566	259	18	kunitsky	kunitsky	PROPN
istl-2566	259	19	,	,	PUNCT
istl-2566	259	20	k.	k.	PROPN
istl-2566	259	21	&	&	CCONJ
istl-2566	259	22	nedwed	nedwe	VERB
istl-2566	259	23	,	,	PUNCT
istl-2566	259	24	k.	k.	NOUN
istl-2566	259	25	2018	2018	NUM
istl-2566	259	26	.	.	PUNCT
istl-2566	260	1	validation	validation	NOUN
istl-2566	260	2	of	of	ADP
istl-2566	260	3	the	the	DET
istl-2566	260	4	knowitall	knowitall	NOUN
istl-2566	260	5	stereochemistry	stereochemistry	NOUN
istl-2566	260	6	toolkit	toolkit	NOUN
istl-2566	260	7	:	:	PUNCT
istl-2566	260	8	tech	tech	NOUN
istl-2566	260	9	note	note	NOUN
istl-2566	260	10	210434	210434	NUM
istl-2566	260	11	.	.	PUNCT
istl-2566	261	1	philadelphia	philadelphia	PROPN
istl-2566	261	2	(	(	PUNCT
istl-2566	261	3	pa	pa	PROPN
istl-2566	261	4	):	):	PUNCT
istl-2566	261	5	bio	bio	PROPN
istl-2566	261	6	-	-	PUNCT
istl-2566	261	7	rad	rad	ADJ
istl-2566	261	8	laboratories	laboratory	NOUN
istl-2566	261	9	.	.	PUNCT
istl-2566	262	1	akhondi	akhondi	PROPN
istl-2566	262	2	,	,	PUNCT
istl-2566	262	3	s.a	s.a	PROPN
istl-2566	262	4	.	.	PROPN
istl-2566	262	5	,	,	PUNCT
istl-2566	262	6	kors	kors	PROPN
istl-2566	262	7	,	,	PUNCT
istl-2566	262	8	j.a	j.a	PROPN
istl-2566	262	9	.	.	PROPN
istl-2566	262	10	&	&	CCONJ
istl-2566	262	11	muresan	muresan	PROPN
istl-2566	262	12	,	,	PUNCT
istl-2566	262	13	s.	s.	PROPN
istl-2566	262	14	2012	2012	NUM
istl-2566	262	15	.	.	PUNCT
istl-2566	263	1	consistency	consistency	NOUN
istl-2566	263	2	of	of	ADP
istl-2566	263	3	systematic	systematic	ADJ
istl-2566	263	4	chemical	chemical	NOUN
istl-2566	263	5	identifiers	identifier	NOUN
istl-2566	263	6	within	within	ADP
istl-2566	263	7	and	and	CCONJ
istl-2566	263	8	between	between	ADP
istl-2566	263	9	small	small	ADJ
istl-2566	263	10	-	-	PUNCT
istl-2566	263	11	molecule	molecule	NOUN
istl-2566	263	12	databases	database	NOUN
istl-2566	263	13	.	.	PUNCT
istl-2566	264	1	journal	journal	PROPN
istl-2566	264	2	of	of	ADP
istl-2566	264	3	cheminformatics	cheminformatics	PROPN
istl-2566	264	4	4:35	4:35	NUM
istl-2566	264	5	.	.	PUNCT
istl-2566	265	1	doi:10.1186/1758	doi:10.1186/1758	NOUN
istl-2566	265	2	-	-	PUNCT
istl-2566	265	3	2946	2946	NUM
istl-2566	265	4	-	-	PUNCT
istl-2566	265	5	4	4	NUM
istl-2566	265	6	-	-	SYM
istl-2566	265	7	35	35	NUM
istl-2566	265	8	.	.	PUNCT
istl-2566	265	9	andrews	andrews	PROPN
istl-2566	265	10	,	,	PUNCT
istl-2566	265	11	d.m	d.m	PROPN
istl-2566	265	12	.	.	PROPN
istl-2566	265	13	,	,	PUNCT
istl-2566	265	14	broad	broad	PROPN
istl-2566	265	15	,	,	PUNCT
istl-2566	265	16	l.m	l.m	PROPN
istl-2566	265	17	.	.	PROPN
istl-2566	265	18	,	,	PUNCT
istl-2566	265	19	edwards	edwards	PROPN
istl-2566	265	20	,	,	PUNCT
istl-2566	265	21	p.j	p.j	PROPN
istl-2566	265	22	.	.	PROPN
istl-2566	265	23	,	,	PUNCT
istl-2566	265	24	fox	fox	PROPN
istl-2566	265	25	,	,	PUNCT
istl-2566	265	26	d.n.a	d.n.a	PROPN
istl-2566	265	27	.	.	PROPN
istl-2566	265	28	,	,	PUNCT
istl-2566	265	29	gallagher	gallagher	PROPN
istl-2566	265	30	,	,	PUNCT
istl-2566	265	31	t.	t.	PROPN
istl-2566	265	32	,	,	PUNCT
istl-2566	265	33	garland	garland	PROPN
istl-2566	265	34	,	,	PUNCT
istl-2566	265	35	s.l	s.l	PROPN
istl-2566	265	36	.	.	PROPN
istl-2566	265	37	,	,	PUNCT
istl-2566	265	38	kidd	kidd	PROPN
istl-2566	265	39	,	,	PUNCT
istl-2566	265	40	r.	r.	PROPN
istl-2566	265	41	&	&	CCONJ
istl-2566	265	42	sweeney	sweeney	PROPN
istl-2566	265	43	,	,	PUNCT
istl-2566	265	44	j.b	j.b	PROPN
istl-2566	265	45	.	.	PROPN
istl-2566	265	46	2016	2016	NUM
istl-2566	265	47	.	.	PUNCT
istl-2566	266	1	the	the	DET
istl-2566	266	2	creation	creation	NOUN
istl-2566	266	3	and	and	CCONJ
istl-2566	266	4	characterisation	characterisation	NOUN
istl-2566	266	5	of	of	ADP
istl-2566	266	6	a	a	DET
istl-2566	266	7	national	national	ADJ
istl-2566	266	8	compound	compound	NOUN
istl-2566	266	9	collection	collection	NOUN
istl-2566	266	10	:	:	PUNCT
istl-2566	266	11	the	the	DET
istl-2566	266	12	royal	royal	ADJ
istl-2566	266	13	society	society	NOUN
istl-2566	266	14	of	of	ADP
istl-2566	266	15	chemistry	chemistry	NOUN
istl-2566	266	16	pilot	pilot	NOUN
istl-2566	266	17	.	.	PUNCT
istl-2566	267	1	chemical	chemical	PROPN
istl-2566	267	2	science	science	PROPN
istl-2566	267	3	7(6):3869–3878	7(6):3869–3878	PROPN
istl-2566	267	4	.	.	PUNCT
istl-2566	268	1	doi:10.1039	doi:10.1039	PROPN
istl-2566	268	2	/	/	SYM
istl-2566	268	3	c6sc00264a	c6sc00264a	PROPN
istl-2566	268	4	.	.	PUNCT
istl-2566	268	5	brecher	brecher	PROPN
istl-2566	268	6	,	,	PUNCT
istl-2566	268	7	j.	j.	PROPN
istl-2566	268	8	2006	2006	NUM
istl-2566	268	9	.	.	PUNCT
istl-2566	269	1	graphical	graphical	ADJ
istl-2566	269	2	representation	representation	NOUN
istl-2566	269	3	of	of	ADP
istl-2566	269	4	stereochemical	stereochemical	ADJ
istl-2566	269	5	configuration	configuration	NOUN
istl-2566	269	6	(	(	PUNCT
istl-2566	269	7	iupac	iupac	ADJ
istl-2566	269	8	recommendations	recommendation	NOUN
istl-2566	269	9	2006	2006	NUM
istl-2566	269	10	)	)	PUNCT
istl-2566	269	11	.	.	PUNCT
istl-2566	270	1	pure	pure	ADJ
istl-2566	270	2	and	and	CCONJ
istl-2566	270	3	applied	apply	VERB
istl-2566	270	4	chemistry	chemistry	NOUN
istl-2566	270	5	78(10):1897–1970	78(10):1897–1970	PROPN
istl-2566	270	6	.	.	PUNCT
istl-2566	270	7	doi:10.1351	doi:10.1351	PROPN
istl-2566	270	8	/	/	SYM
istl-2566	270	9	pac200678101897	pac200678101897	PROPN
istl-2566	270	10	.	.	PUNCT
istl-2566	271	1	brecher	brecher	PROPN
istl-2566	271	2	,	,	PUNCT
istl-2566	271	3	j.	j.	PROPN
istl-2566	271	4	2008	2008	NUM
istl-2566	271	5	.	.	PUNCT
istl-2566	272	1	graphical	graphical	ADJ
istl-2566	272	2	representation	representation	NOUN
istl-2566	272	3	standards	standard	NOUN
istl-2566	272	4	for	for	ADP
istl-2566	272	5	chemical	chemical	NOUN
istl-2566	272	6	structure	structure	NOUN
istl-2566	272	7	diagrams	diagram	NOUN
istl-2566	272	8	.	.	PUNCT
istl-2566	273	1	pure	pure	ADJ
istl-2566	273	2	and	and	CCONJ
istl-2566	273	3	applied	apply	VERB
istl-2566	273	4	chemistry	chemistry	NOUN
istl-2566	273	5	80(2):277–410	80(2):277–410	PROPN
istl-2566	273	6	.	.	PUNCT
istl-2566	274	1	doi:10.1351	doi:10.1351	NOUN
istl-2566	274	2	/	/	SYM
istl-2566	274	3	pac200880020277	pac200880020277	NOUN
istl-2566	274	4	.	.	PUNCT
istl-2566	275	1	buntrock	buntrock	NOUN
istl-2566	275	2	,	,	PUNCT
istl-2566	275	3	r.e	r.e	PROPN
istl-2566	275	4	.	.	PROPN
istl-2566	275	5	2001	2001	NUM
istl-2566	275	6	.	.	PUNCT
istl-2566	276	1	chemical	chemical	NOUN
istl-2566	276	2	registries	registry	NOUN
istl-2566	276	3	in	in	ADP
istl-2566	276	4	the	the	DET
istl-2566	276	5	fourth	fourth	ADJ
istl-2566	276	6	decade	decade	NOUN
istl-2566	276	7	of	of	ADP
istl-2566	276	8	service	service	NOUN
istl-2566	276	9	.	.	PUNCT
istl-2566	277	1	journal	journal	PROPN
istl-2566	277	2	of	of	ADP
istl-2566	277	3	chemical	chemical	ADJ
istl-2566	277	4	information	information	NOUN
istl-2566	277	5	and	and	CCONJ
istl-2566	277	6	computer	computer	NOUN
istl-2566	277	7	sciences	science	NOUN
istl-2566	277	8	41(2):259–263	41(2):259–263	PROPN
istl-2566	277	9	.	.	PUNCT
istl-2566	278	1	doi:10.1021	doi:10.1021	ADJ
istl-2566	278	2	/	/	SYM
istl-2566	278	3	ci000109q	ci000109q	NOUN
istl-2566	278	4	.	.	PUNCT
istl-2566	279	1	chambers	chamber	NOUN
istl-2566	279	2	,	,	PUNCT
istl-2566	279	3	j.	j.	PROPN
istl-2566	279	4	,	,	PUNCT
istl-2566	279	5	davies	davy	NOUN
istl-2566	279	6	,	,	PUNCT
istl-2566	279	7	m.	m.	NOUN
istl-2566	279	8	,	,	PUNCT
istl-2566	279	9	gaulton	gaulton	PROPN
istl-2566	279	10	,	,	PUNCT
istl-2566	279	11	a.	a.	PROPN
istl-2566	279	12	,	,	PUNCT
istl-2566	279	13	hersey	hersey	PROPN
istl-2566	279	14	,	,	PUNCT
istl-2566	279	15	a.	a.	PROPN
istl-2566	279	16	,	,	PUNCT
istl-2566	279	17	velankar	velankar	PROPN
istl-2566	279	18	,	,	PUNCT
istl-2566	279	19	s.	s.	PROPN
istl-2566	279	20	,	,	PUNCT
istl-2566	279	21	petryszak	petryszak	PROPN
istl-2566	279	22	,	,	PUNCT
istl-2566	279	23	r.	r.	PROPN
istl-2566	279	24	,	,	PUNCT
istl-2566	279	25	hastings	hastings	PROPN
istl-2566	279	26	,	,	PUNCT
istl-2566	279	27	j.	j.	PROPN
istl-2566	279	28	,	,	PUNCT
istl-2566	279	29	bellis	bellis	PROPN
istl-2566	279	30	,	,	PUNCT
istl-2566	279	31	l.	l.	PROPN
istl-2566	279	32	,	,	PUNCT
istl-2566	279	33	mcglinchey	mcglinchey	PROPN
istl-2566	279	34	,	,	PUNCT
istl-2566	279	35	s.	s.	PROPN
istl-2566	279	36	&	&	CCONJ
istl-2566	279	37	overington	overington	PROPN
istl-2566	279	38	,	,	PUNCT
istl-2566	279	39	j.p	j.p	PROPN
istl-2566	279	40	.	.	PROPN
istl-2566	279	41	2013	2013	NUM
istl-2566	279	42	.	.	PUNCT
istl-2566	280	1	unichem	unichem	PROPN
istl-2566	280	2	:	:	PUNCT
istl-2566	280	3	a	a	DET
istl-2566	280	4	unified	unify	VERB
istl-2566	280	5	chemical	chemical	NOUN
istl-2566	280	6	structure	structure	NOUN
istl-2566	280	7	cross	cros	VERB
istl-2566	280	8	-	-	NOUN
istl-2566	280	9	referencing	referencing	ADJ
istl-2566	280	10	and	and	CCONJ
istl-2566	280	11	identifier	identifier	NOUN
istl-2566	280	12	tracking	tracking	NOUN
istl-2566	280	13	system	system	NOUN
istl-2566	280	14	.	.	PUNCT
istl-2566	280	15	journal	journal	PROPN
istl-2566	280	16	of	of	ADP
istl-2566	280	17	cheminformatics	cheminformatic	NOUN
istl-2566	280	18	5:3	5:3	NUM
istl-2566	280	19	.	.	PUNCT
istl-2566	281	1	doi:10.1186/1758	doi:10.1186/1758	NOUN
istl-2566	281	2	-	-	PUNCT
istl-2566	281	3	2946	2946	NUM
istl-2566	281	4	-	-	PUNCT
istl-2566	281	5	5	5	NUM
istl-2566	281	6	-	-	SYM
istl-2566	281	7	3	3	NUM
istl-2566	281	8	.	.	NUM
istl-2566	281	9	chemaxon	chemaxon	PROPN
istl-2566	281	10	.	.	PUNCT
istl-2566	282	1	2019a	2019a	NUM
istl-2566	282	2	.	.	PUNCT
istl-2566	283	1	marvinsketch	marvinsketch	NOUN
istl-2566	283	2	v19.27.0	v19.27.0	PROPN
istl-2566	284	1	[	[	X
istl-2566	284	2	internet	internet	NOUN
istl-2566	284	3	]	]	PUNCT
istl-2566	284	4	.	.	PUNCT
istl-2566	285	1	[	[	X
istl-2566	285	2	cited	cite	VERB
istl-2566	285	3	2021	2021	NUM
istl-2566	285	4	jan	jan	PROPN
istl-2566	285	5	13	13	NUM
istl-2566	285	6	]	]	PUNCT
istl-2566	285	7	.	.	PUNCT
istl-2566	286	1	available	available	ADJ
istl-2566	286	2	from	from	ADP
istl-2566	286	3	https://chemaxon.com	https://chemaxon.com	X
istl-2566	286	4	.	.	PUNCT
istl-2566	287	1	chemaxon	chemaxon	PROPN
istl-2566	287	2	.	.	PUNCT
istl-2566	288	1	2019b	2019b	NUM
istl-2566	288	2	.	.	PUNCT
istl-2566	289	1	molconverter	molconverter	NOUN
istl-2566	289	2	v19.27.0	v19.27.0	PROPN
istl-2566	290	1	[	[	X
istl-2566	290	2	internet	internet	NOUN
istl-2566	290	3	]	]	PUNCT
istl-2566	290	4	.	.	PUNCT
istl-2566	291	1	[	[	X
istl-2566	291	2	cited	cite	VERB
istl-2566	291	3	2021	2021	NUM
istl-2566	291	4	jan	jan	PROPN
istl-2566	291	5	13	13	NUM
istl-2566	291	6	]	]	PUNCT
istl-2566	291	7	.	.	PUNCT
istl-2566	292	1	available	available	ADJ
istl-2566	292	2	from	from	ADP
istl-2566	292	3	https://chemaxon.com	https://chemaxon.com	X
istl-2566	292	4	.	.	PUNCT
istl-2566	293	1	chemaxon	chemaxon	PROPN
istl-2566	293	2	.	.	PUNCT
istl-2566	294	1	2021	2021	NUM
istl-2566	294	2	.	.	PUNCT
istl-2566	295	1	extended	extended	ADJ
istl-2566	295	2	smiles	smile	NOUN
istl-2566	295	3	and	and	CCONJ
istl-2566	295	4	smarts	smart	NOUN
istl-2566	295	5	cxsmiles	cxsmile	NOUN
istl-2566	295	6	and	and	CCONJ
istl-2566	295	7	cxsmarts	cxsmart	NOUN
istl-2566	296	1	[	[	X
istl-2566	296	2	internet	internet	NOUN
istl-2566	296	3	]	]	PUNCT
istl-2566	296	4	.	.	PUNCT
istl-2566	297	1	[	[	X
istl-2566	297	2	cited	cite	VERB
istl-2566	297	3	2021	2021	NUM
istl-2566	297	4	apr	apr	VERB
istl-2566	297	5	15	15	NUM
istl-2566	297	6	]	]	PUNCT
istl-2566	297	7	.	.	PUNCT
istl-2566	298	1	available	available	ADJ
istl-2566	298	2	from	from	ADP
istl-2566	298	3	https://docs.chemaxon.com/display/docs/chemaxon-extended-smiles-and-smarts-cxsmiles-and-cxsmarts.md	https://docs.chemaxon.com/display/docs/chemaxon-extended-smiles-and-smarts-cxsmiles-and-cxsmarts.md	PROPN
istl-2566	298	4	.	.	PUNCT
istl-2566	299	1	clark	clark	PROPN
istl-2566	299	2	,	,	PUNCT
istl-2566	299	3	a.m.	a.m.	PROPN
istl-2566	299	4	2011	2011	NUM
istl-2566	299	5	.	.	PUNCT
istl-2566	300	1	accurate	accurate	ADJ
istl-2566	300	2	specification	specification	NOUN
istl-2566	300	3	of	of	ADP
istl-2566	300	4	molecular	molecular	ADJ
istl-2566	300	5	structures	structure	NOUN
istl-2566	300	6	:	:	PUNCT
istl-2566	300	7	the	the	DET
istl-2566	300	8	case	case	NOUN
istl-2566	300	9	for	for	ADP
istl-2566	300	10	zero	zero	NUM
istl-2566	300	11	-	-	PUNCT
istl-2566	300	12	order	order	NOUN
istl-2566	300	13	bonds	bond	NOUN
istl-2566	300	14	and	and	CCONJ
istl-2566	300	15	explicit	explicit	ADJ
istl-2566	300	16	hydrogen	hydrogen	NOUN
istl-2566	300	17	counting	counting	NOUN
istl-2566	300	18	.	.	PUNCT
istl-2566	301	1	journal	journal	PROPN
istl-2566	301	2	of	of	ADP
istl-2566	301	3	chemical	chemical	ADJ
istl-2566	301	4	information	information	NOUN
istl-2566	301	5	and	and	CCONJ
istl-2566	301	6	modeling	model	VERB
istl-2566	301	7	51(12):3149–3157	51(12):3149–3157	PROPN
istl-2566	301	8	.	.	PUNCT
istl-2566	302	1	doi:10.1021	doi:10.1021	ADJ
istl-2566	302	2	/	/	SYM
istl-2566	302	3	ci200488k	ci200488k	NOUN
istl-2566	302	4	.	.	PUNCT
istl-2566	303	1	clark	clark	PROPN
istl-2566	303	2	,	,	PUNCT
istl-2566	303	3	a.m.	a.m.	PROPN
istl-2566	303	4	,	,	PUNCT
istl-2566	303	5	labute	labute	NOUN
istl-2566	303	6	,	,	PUNCT
istl-2566	303	7	p.	p.	PROPN
istl-2566	303	8	&	&	CCONJ
istl-2566	303	9	santavy	santavy	PROPN
istl-2566	303	10	,	,	PUNCT
istl-2566	303	11	m.	m.	NOUN
istl-2566	303	12	2006	2006	NUM
istl-2566	303	13	.	.	PUNCT
istl-2566	304	1	2d	2d	NUM
istl-2566	304	2	structure	structure	NOUN
istl-2566	304	3	depiction	depiction	NOUN
istl-2566	304	4	.	.	PUNCT
istl-2566	305	1	journal	journal	PROPN
istl-2566	305	2	of	of	ADP
istl-2566	305	3	chemical	chemical	ADJ
istl-2566	305	4	information	information	NOUN
istl-2566	305	5	and	and	CCONJ
istl-2566	305	6	modeling	model	VERB
istl-2566	305	7	46(3):1107–1123	46(3):1107–1123	NUM
istl-2566	305	8	.	.	PUNCT
istl-2566	306	1	doi:10.1021	doi:10.1021	ADJ
istl-2566	306	2	/	/	SYM
istl-2566	306	3	ci050550	ci050550	NOUN
istl-2566	306	4	m.	m.	NOUN
istl-2566	306	5	copyright	copyright	NOUN
istl-2566	306	6	advisory	advisory	ADJ
istl-2566	306	7	network	network	NOUN
istl-2566	306	8	.	.	PUNCT
istl-2566	307	1	2020	2020	NUM
istl-2566	307	2	.	.	PUNCT
istl-2566	308	1	public	public	ADJ
istl-2566	308	2	domain	domain	NOUN
istl-2566	308	3	slider	slider	NOUN
istl-2566	308	4	[	[	X
istl-2566	308	5	internet	internet	NOUN
istl-2566	308	6	]	]	PUNCT
istl-2566	308	7	.	.	PUNCT
istl-2566	309	1	available	available	ADJ
istl-2566	309	2	from	from	ADP
istl-2566	309	3	https://librarycopyright.net/.	https://librarycopyright.net/.	PROPN
istl-2566	309	4	dalby	dalby	PROPN
istl-2566	309	5	,	,	PUNCT
istl-2566	309	6	a.	a.	PROPN
istl-2566	309	7	,	,	PUNCT
istl-2566	309	8	nourse	nourse	PROPN
istl-2566	309	9	,	,	PUNCT
istl-2566	309	10	j.g	j.g	PROPN
istl-2566	309	11	,	,	PUNCT
istl-2566	309	12	hounshell	hounshell	PROPN
istl-2566	309	13	,	,	PUNCT
istl-2566	309	14	w.d	w.d	PROPN
istl-2566	309	15	.	.	PROPN
istl-2566	309	16	,	,	PUNCT
istl-2566	309	17	gushurst	gushurst	PROPN
istl-2566	309	18	,	,	PUNCT
istl-2566	309	19	a.k.i	a.k.i	PROPN
istl-2566	309	20	.	.	PROPN
istl-2566	309	21	,	,	PUNCT
istl-2566	309	22	grier	grier	PROPN
istl-2566	309	23	,	,	PUNCT
istl-2566	309	24	d.l	d.l	PROPN
istl-2566	309	25	.	.	PROPN
istl-2566	309	26	,	,	PUNCT
istl-2566	309	27	leland	leland	PROPN
istl-2566	309	28	,	,	PUNCT
istl-2566	309	29	b.a	b.a	PROPN
istl-2566	309	30	.	.	PROPN
istl-2566	309	31	&	&	CCONJ
istl-2566	309	32	laufer	laufer	PROPN
istl-2566	309	33	,	,	PUNCT
istl-2566	309	34	j.	j.	PROPN
istl-2566	309	35	1992	1992	NUM
istl-2566	309	36	.	.	PUNCT
istl-2566	310	1	description	description	NOUN
istl-2566	310	2	of	of	ADP
istl-2566	310	3	several	several	ADJ
istl-2566	310	4	chemical	chemical	NOUN
istl-2566	310	5	structure	structure	NOUN
istl-2566	310	6	file	file	NOUN
istl-2566	310	7	formats	format	NOUN
istl-2566	310	8	used	use	VERB
istl-2566	310	9	by	by	ADP
istl-2566	310	10	computer	computer	NOUN
istl-2566	310	11	programs	program	NOUN
istl-2566	310	12	developed	develop	VERB
istl-2566	310	13	at	at	ADP
istl-2566	310	14	molecular	molecular	ADJ
istl-2566	310	15	design	design	NOUN
istl-2566	310	16	limited	limited	ADJ
istl-2566	310	17	.	.	PUNCT
istl-2566	311	1	journal	journal	PROPN
istl-2566	311	2	of	of	ADP
istl-2566	311	3	chemical	chemical	ADJ
istl-2566	311	4	information	information	NOUN
istl-2566	311	5	and	and	CCONJ
istl-2566	311	6	modeling	model	VERB
istl-2566	311	7	32(3):244–255	32(3):244–255	PROPN
istl-2566	311	8	.	.	PUNCT
istl-2566	312	1	doi	doi	PROPN
istl-2566	312	2	:	:	PUNCT
istl-2566	312	3	doi:10.1021	doi:10.1021	PROPN
istl-2566	312	4	/	/	SYM
istl-2566	312	5	ci00007a012	ci00007a012	PROPN
istl-2566	312	6	.	.	PUNCT
istl-2566	312	7	dassault	dassault	PROPN
istl-2566	312	8	systemes	systeme	NOUN
istl-2566	312	9	.	.	PUNCT
istl-2566	313	1	2017	2017	NUM
istl-2566	313	2	.	.	PUNCT
istl-2566	314	1	biovia	biovia	PROPN
istl-2566	314	2	ctfile	ctfile	PROPN
istl-2566	314	3	formats	format	NOUN
istl-2566	314	4	:	:	PUNCT
istl-2566	314	5	biovia	biovia	NOUN
istl-2566	314	6	databases	database	VERB
istl-2566	314	7	[	[	X
istl-2566	314	8	internet	internet	NOUN
istl-2566	314	9	]	]	PUNCT
istl-2566	314	10	.	.	PUNCT
istl-2566	315	1	available	available	ADJ
istl-2566	315	2	from	from	ADP
istl-2566	315	3	http://help.accelrysonline.com/ulm/onelab/1.0/content/ulm_pdfs/direct/reference/ctfileformats2016.pdf	http://help.accelrysonline.com/ulm/onelab/1.0/content/ulm_pdfs/direct/reference/ctfileformats2016.pdf	NOUN
istl-2566	315	4	..	..	PUNCT
istl-2566	315	5	daylight	daylight	NOUN
istl-2566	315	6	chemical	chemical	NOUN
istl-2566	315	7	information	information	NOUN
istl-2566	315	8	systems	system	NOUN
istl-2566	315	9	.	.	PUNCT
istl-2566	316	1	2011	2011	NUM
istl-2566	316	2	.	.	PUNCT
istl-2566	317	1	daylight	daylight	NOUN
istl-2566	317	2	theory	theory	NOUN
istl-2566	317	3	manual	manual	NOUN
istl-2566	317	4	v4.9	v4.9	PROPN
istl-2566	318	1	[	[	X
istl-2566	318	2	internet	internet	NOUN
istl-2566	318	3	]	]	PUNCT
istl-2566	318	4	.	.	PUNCT
istl-2566	319	1	[	[	X
istl-2566	319	2	accessed	access	VERB
istl-2566	319	3	august	august	PROPN
istl-2566	319	4	2020	2020	NUM
istl-2566	319	5	]	]	PUNCT
istl-2566	319	6	.	.	PUNCT
istl-2566	320	1	available	available	ADJ
istl-2566	320	2	from	from	ADP
istl-2566	320	3	https://www.daylight.com/dayhtml/doc/theory/.	https://www.daylight.com/dayhtml/doc/theory/.	NOUN
istl-2566	320	4	de	de	PROPN
istl-2566	320	5	laet	laet	PROPN
istl-2566	320	6	,	,	PUNCT
istl-2566	320	7	a.	a.	PROPN
istl-2566	320	8	,	,	PUNCT
istl-2566	320	9	hehenkamp	hehenkamp	PROPN
istl-2566	320	10	,	,	PUNCT
istl-2566	320	11	j.j.j	j.j.j	PROPN
istl-2566	320	12	.	.	PROPN
istl-2566	320	13	&	&	CCONJ
istl-2566	320	14	wife	wife	PROPN
istl-2566	320	15	,	,	PUNCT
istl-2566	320	16	r.l	r.l	PROPN
istl-2566	320	17	.	.	PROPN
istl-2566	320	18	2000	2000	NUM
istl-2566	320	19	.	.	PUNCT
istl-2566	321	1	finding	find	VERB
istl-2566	321	2	drug	drug	NOUN
istl-2566	321	3	candidates	candidate	NOUN
istl-2566	321	4	in	in	ADP
istl-2566	321	5	virtual	virtual	ADJ
istl-2566	321	6	and	and	CCONJ
istl-2566	321	7	lost	lost	ADJ
istl-2566	321	8	/	/	SYM
istl-2566	321	9	emerging	emerge	VERB
istl-2566	321	10	chemistry	chemistry	NOUN
istl-2566	321	11	.	.	PUNCT
istl-2566	322	1	journal	journal	PROPN
istl-2566	322	2	of	of	ADP
istl-2566	322	3	heterocyclic	heterocyclic	ADJ
istl-2566	322	4	chemistry	chemistry	NOUN
istl-2566	322	5	37(3):669–674	37(3):669–674	NOUN
istl-2566	322	6	.	.	PUNCT
istl-2566	323	1	doi:10.1002	doi:10.1002	NOUN
istl-2566	323	2	/	/	SYM
istl-2566	323	3	jhet.5570370324	jhet.5570370324	PROPN
istl-2566	323	4	.	.	PUNCT
istl-2566	324	1	dittmar	dittmar	PROPN
istl-2566	324	2	,	,	PUNCT
istl-2566	324	3	p.g	p.g	PROPN
istl-2566	324	4	.	.	PROPN
istl-2566	324	5	,	,	PUNCT
istl-2566	324	6	stobaugh	stobaugh	NOUN
istl-2566	324	7	,	,	PUNCT
istl-2566	324	8	r.e	r.e	PROPN
istl-2566	324	9	.	.	PROPN
istl-2566	324	10	&	&	CCONJ
istl-2566	324	11	watson	watson	PROPN
istl-2566	324	12	,	,	PUNCT
istl-2566	324	13	c.e	c.e	PROPN
istl-2566	324	14	.	.	PROPN
istl-2566	324	15	1976	1976	NUM
istl-2566	324	16	.	.	PUNCT
istl-2566	325	1	the	the	DET
istl-2566	325	2	chemical	chemical	NOUN
istl-2566	325	3	abstracts	abstract	VERB
istl-2566	325	4	service	service	NOUN
istl-2566	325	5	chemical	chemical	NOUN
istl-2566	325	6	registry	registry	NOUN
istl-2566	325	7	system	system	NOUN
istl-2566	325	8	.	.	PUNCT
istl-2566	326	1	i.	i.	PROPN
istl-2566	326	2	general	general	PROPN
istl-2566	326	3	design	design	PROPN
istl-2566	326	4	.	.	PUNCT
istl-2566	327	1	journal	journal	PROPN
istl-2566	327	2	of	of	ADP
istl-2566	327	3	chemical	chemical	ADJ
istl-2566	327	4	information	information	NOUN
istl-2566	327	5	and	and	CCONJ
istl-2566	327	6	computer	computer	NOUN
istl-2566	327	7	sciences	science	NOUN
istl-2566	327	8	16(2):111–121	16(2):111–121	PROPN
istl-2566	327	9	.	.	PUNCT
istl-2566	328	1	doi:10.1021	doi:10.1021	PROPN
istl-2566	328	2	/	/	SYM
istl-2566	328	3	ci60006a016	ci60006a016	PROPN
istl-2566	328	4	.	.	PUNCT
istl-2566	329	1	domokos	domokos	PROPN
istl-2566	329	2	,	,	PUNCT
istl-2566	329	3	l.	l.	PROPN
istl-2566	329	4	1991	1991	NUM
istl-2566	329	5	.	.	PUNCT
istl-2566	330	1	the	the	DET
istl-2566	330	2	beilstein	beilstein	ADJ
istl-2566	330	3	structure	structure	NOUN
istl-2566	330	4	registry	registry	NOUN
istl-2566	330	5	system	system	NOUN
istl-2566	330	6	.	.	PUNCT
istl-2566	331	1	1	1	X
istl-2566	331	2	.	.	X
istl-2566	331	3	general	general	ADJ
istl-2566	331	4	design	design	NOUN
istl-2566	331	5	.	.	PUNCT
istl-2566	332	1	journal	journal	PROPN
istl-2566	332	2	of	of	ADP
istl-2566	332	3	chemical	chemical	ADJ
istl-2566	332	4	information	information	NOUN
istl-2566	332	5	and	and	CCONJ
istl-2566	332	6	modeling	model	VERB
istl-2566	332	7	31(2):320–326	31(2):320–326	PROPN
istl-2566	332	8	.	.	PUNCT
istl-2566	333	1	doi:10.1021	doi:10.1021	ADJ
istl-2566	333	2	/	/	SYM
istl-2566	333	3	ci00002a019	ci00002a019	PROPN
istl-2566	333	4	.	.	PUNCT
istl-2566	334	1	downing	downing	ADJ
istl-2566	334	2	,	,	PUNCT
istl-2566	334	3	j.	j.	PROPN
istl-2566	334	4	,	,	PUNCT
istl-2566	334	5	harvey	harvey	PROPN
istl-2566	334	6	,	,	PUNCT
istl-2566	334	7	m.j	m.j	PROPN
istl-2566	334	8	.	.	PROPN
istl-2566	334	9	,	,	PUNCT
istl-2566	334	10	morgan	morgan	PROPN
istl-2566	334	11	,	,	PUNCT
istl-2566	334	12	p.b	p.b	PROPN
istl-2566	334	13	.	.	PROPN
istl-2566	334	14	,	,	PUNCT
istl-2566	334	15	murray	murray	NOUN
istl-2566	334	16	-	-	PUNCT
istl-2566	334	17	rust	rust	NOUN
istl-2566	334	18	,	,	PUNCT
istl-2566	334	19	p.	p.	PROPN
istl-2566	334	20	,	,	PUNCT
istl-2566	334	21	rzepa	rzepa	PROPN
istl-2566	334	22	,	,	PUNCT
istl-2566	334	23	h.s	h.s	PROPN
istl-2566	334	24	.	.	PROPN
istl-2566	334	25	,	,	PUNCT
istl-2566	334	26	stewart	stewart	PROPN
istl-2566	334	27	,	,	PUNCT
istl-2566	334	28	d.c	d.c	PROPN
istl-2566	334	29	.	.	PROPN
istl-2566	334	30	,	,	PUNCT
istl-2566	334	31	tonge	tonge	PROPN
istl-2566	334	32	,	,	PUNCT
istl-2566	334	33	a.p	a.p	PROPN
istl-2566	334	34	.	.	PROPN
istl-2566	334	35	&	&	CCONJ
istl-2566	334	36	townsend	townsend	VERB
istl-2566	334	37	,	,	PUNCT
istl-2566	334	38	j.a	j.a	PROPN
istl-2566	334	39	.	.	PROPN
istl-2566	334	40	2010	2010	NUM
istl-2566	334	41	.	.	PUNCT
istl-2566	335	1	spectra	spectra	PROPN
istl-2566	335	2	-	-	PROPN
istl-2566	335	3	t	t	PROPN
istl-2566	335	4	:	:	PUNCT
istl-2566	335	5	machine	machine	NOUN
istl-2566	335	6	-	-	PUNCT
istl-2566	335	7	based	base	VERB
istl-2566	335	8	data	data	NOUN
istl-2566	335	9	extraction	extraction	NOUN
istl-2566	335	10	and	and	CCONJ
istl-2566	335	11	semantic	semantic	ADJ
istl-2566	335	12	searching	searching	NOUN
istl-2566	335	13	of	of	ADP
istl-2566	335	14	chemistry	chemistry	NOUN
istl-2566	335	15	e	e	NOUN
istl-2566	335	16	-	-	NOUN
istl-2566	335	17	theses	thesis	NOUN
istl-2566	335	18	.	.	PUNCT
istl-2566	335	19	journal	journal	PROPN
istl-2566	335	20	of	of	ADP
istl-2566	335	21	chemical	chemical	ADJ
istl-2566	335	22	information	information	NOUN
istl-2566	335	23	and	and	CCONJ
istl-2566	335	24	modeling	model	VERB
istl-2566	335	25	50(2):251–261	50(2):251–261	PROPN
istl-2566	335	26	.	.	PUNCT
istl-2566	336	1	doi:10.1021	doi:10.1021	ADJ
istl-2566	336	2	/	/	SYM
istl-2566	336	3	ci9003688	ci9003688	NOUN
istl-2566	336	4	.	.	PUNCT
istl-2566	337	1	elsevier	elsevi	ADJ
istl-2566	337	2	.	.	PUNCT
istl-2566	338	1	2021	2021	NUM
istl-2566	338	2	.	.	PUNCT
istl-2566	339	1	reaxys	reaxys	PROPN
istl-2566	339	2	content	content	NOUN
istl-2566	339	3	.	.	PUNCT
istl-2566	340	1	[	[	X
istl-2566	340	2	internet	internet	NOUN
istl-2566	340	3	]	]	PUNCT
istl-2566	340	4	.	.	PUNCT
istl-2566	341	1	[	[	X
istl-2566	341	2	cited	cite	VERB
istl-2566	341	3	2021	2021	NUM
istl-2566	341	4	jan	jan	PROPN
istl-2566	341	5	13	13	NUM
istl-2566	341	6	]	]	PUNCT
istl-2566	341	7	.	.	PUNCT
istl-2566	342	1	available	available	ADJ
istl-2566	342	2	from	from	ADP
istl-2566	342	3	https://www.elsevier.com/solutions/reaxys/features-and-capabilities/content	https://www.elsevier.com/solutions/reaxys/features-and-capabilities/content	NOUN
istl-2566	342	4	.	.	PUNCT
istl-2566	343	1	filippov	filippov	PROPN
istl-2566	343	2	,	,	PUNCT
istl-2566	343	3	i.v	i.v	PROPN
istl-2566	343	4	.	.	PROPN
istl-2566	343	5	&	&	CCONJ
istl-2566	343	6	nicklaus	nicklaus	PROPN
istl-2566	343	7	,	,	PUNCT
istl-2566	343	8	m.c	m.c	PROPN
istl-2566	343	9	.	.	PROPN
istl-2566	343	10	2009	2009	NUM
istl-2566	343	11	.	.	PUNCT
istl-2566	344	1	optical	optical	ADJ
istl-2566	344	2	structure	structure	NOUN
istl-2566	344	3	recognition	recognition	NOUN
istl-2566	344	4	software	software	NOUN
istl-2566	344	5	to	to	PART
istl-2566	344	6	recover	recover	VERB
istl-2566	344	7	chemical	chemical	ADJ
istl-2566	344	8	information	information	NOUN
istl-2566	344	9	:	:	PUNCT
istl-2566	344	10	osra	osra	NOUN
istl-2566	344	11	,	,	PUNCT
istl-2566	344	12	an	an	DET
istl-2566	344	13	open	open	ADJ
istl-2566	344	14	source	source	NOUN
istl-2566	344	15	solution	solution	NOUN
istl-2566	344	16	.	.	PUNCT
istl-2566	345	1	journal	journal	PROPN
istl-2566	345	2	of	of	ADP
istl-2566	345	3	chemical	chemical	ADJ
istl-2566	345	4	information	information	NOUN
istl-2566	345	5	and	and	CCONJ
istl-2566	345	6	modeling	model	VERB
istl-2566	345	7	49(3):740–743	49(3):740–743	PROPN
istl-2566	345	8	.	.	PUNCT
istl-2566	346	1	doi:10.1021	doi:10.1021	PROPN
istl-2566	346	2	/	/	SYM
istl-2566	346	3	ci800067r	ci800067r	PROPN
istl-2566	346	4	.	.	PUNCT
istl-2566	347	1	flaxbart	flaxbart	PROPN
istl-2566	347	2	,	,	PUNCT
istl-2566	347	3	d.	d.	PROPN
istl-2566	347	4	2018	2018	NUM
istl-2566	347	5	.	.	PUNCT
istl-2566	348	1	analysis	analysis	NOUN
istl-2566	348	2	of	of	ADP
istl-2566	348	3	citations	citation	NOUN
istl-2566	348	4	to	to	ADP
istl-2566	348	5	books	book	NOUN
istl-2566	348	6	in	in	ADP
istl-2566	348	7	chemistry	chemistry	NOUN
istl-2566	348	8	phd	phd	NOUN
istl-2566	348	9	dissertations	dissertation	NOUN
istl-2566	348	10	in	in	ADP
istl-2566	348	11	an	an	DET
istl-2566	348	12	era	era	NOUN
istl-2566	348	13	of	of	ADP
istl-2566	348	14	transition	transition	NOUN
istl-2566	348	15	.	.	PUNCT
istl-2566	349	1	issues	issue	NOUN
istl-2566	349	2	in	in	ADP
istl-2566	349	3	science	science	NOUN
istl-2566	349	4	and	and	CCONJ
istl-2566	349	5	technology	technology	NOUN
istl-2566	349	6	librarianship	librarianship	NOUN
istl-2566	349	7	.	.	PUNCT
istl-2566	350	1	88	88	NUM
istl-2566	350	2	.	.	PUNCT
istl-2566	351	1	doi:10.5062	doi:10.5062	PRON
istl-2566	351	2	/	/	SYM
istl-2566	351	3	f4dv1h4	f4dv1h4	NUM
istl-2566	351	4	t.	t.	PROPN
istl-2566	351	5	food	food	PROPN
istl-2566	351	6	and	and	CCONJ
istl-2566	351	7	drug	drug	PROPN
istl-2566	351	8	administration	administration	NOUN
istl-2566	351	9	.	.	PUNCT
istl-2566	352	1	2007	2007	NUM
istl-2566	352	2	substance	substance	NOUN
istl-2566	352	3	registration	registration	NOUN
istl-2566	352	4	system	system	NOUN
istl-2566	352	5	standard	standard	ADJ
istl-2566	352	6	operating	operating	NOUN
istl-2566	352	7	procedure	procedure	NOUN
istl-2566	352	8	[	[	PUNCT
istl-2566	352	9	internet	internet	NOUN
istl-2566	352	10	]	]	PUNCT
istl-2566	352	11	.	.	PUNCT
istl-2566	353	1	available	available	ADJ
istl-2566	353	2	from	from	ADP
istl-2566	353	3	https://www.fda.gov/media/75274/download	https://www.fda.gov/media/75274/download	PROPN
istl-2566	353	4	.	.	PUNCT
istl-2566	354	1	frączek	frączek	PROPN
istl-2566	354	2	,	,	PUNCT
istl-2566	354	3	t.	t.	PROPN
istl-2566	354	4	2016	2016	NUM
istl-2566	354	5	.	.	PUNCT
istl-2566	355	1	simulation	simulation	NOUN
istl-2566	355	2	-	-	PUNCT
istl-2566	355	3	based	base	VERB
istl-2566	355	4	algorithm	algorithm	NOUN
istl-2566	355	5	for	for	ADP
istl-2566	355	6	two	two	NUM
istl-2566	355	7	-	-	PUNCT
istl-2566	355	8	dimensional	dimensional	ADJ
istl-2566	355	9	chemical	chemical	NOUN
istl-2566	355	10	structure	structure	NOUN
istl-2566	355	11	diagram	diagram	NOUN
istl-2566	355	12	generation	generation	NOUN
istl-2566	355	13	of	of	ADP
istl-2566	355	14	complex	complex	ADJ
istl-2566	355	15	molecules	molecule	NOUN
istl-2566	355	16	and	and	CCONJ
istl-2566	355	17	ligand	ligand	NOUN
istl-2566	355	18	–	–	PUNCT
istl-2566	355	19	protein	protein	NOUN
istl-2566	355	20	interactions	interaction	NOUN
istl-2566	355	21	.	.	PUNCT
istl-2566	356	1	journal	journal	PROPN
istl-2566	356	2	of	of	ADP
istl-2566	356	3	chemical	chemical	ADJ
istl-2566	356	4	information	information	NOUN
istl-2566	356	5	and	and	CCONJ
istl-2566	356	6	modeling	model	VERB
istl-2566	356	7	56(12):2320–2335	56(12):2320–2335	NUM
istl-2566	356	8	.	.	PUNCT
istl-2566	357	1	doi:10.1021	doi:10.1021	PROPN
istl-2566	357	2	/	/	SYM
istl-2566	357	3	acs.jcim.6b00391	acs.jcim.6b00391	PROPN
istl-2566	357	4	.	.	PUNCT
istl-2566	358	1	gabrielson	gabrielson	PROPN
istl-2566	358	2	,	,	PUNCT
istl-2566	358	3	s.w	s.w	PROPN
istl-2566	358	4	.	.	PROPN
istl-2566	358	5	2018	2018	NUM
istl-2566	358	6	.	.	PUNCT
istl-2566	359	1	scifinder	scifinder	PROPN
istl-2566	359	2	.	.	PUNCT
istl-2566	359	3	journal	journal	PROPN
istl-2566	359	4	of	of	ADP
istl-2566	359	5	the	the	DET
istl-2566	359	6	medical	medical	PROPN
istl-2566	359	7	library	library	PROPN
istl-2566	359	8	association	association	PROPN
istl-2566	359	9	106(4):588–590	106(4):588–590	NUM
istl-2566	359	10	.	.	PUNCT
istl-2566	360	1	doi:10.5195	doi:10.5195	PROPN
istl-2566	360	2	/	/	SYM
istl-2566	360	3	jmla.2018.515	jmla.2018.515	PROPN
istl-2566	360	4	.	.	PUNCT
istl-2566	361	1	garritano	garritano	NOUN
istl-2566	361	2	,	,	PUNCT
istl-2566	361	3	j.r	j.r	PROPN
istl-2566	361	4	.	.	PROPN
istl-2566	361	5	2013	2013	NUM
istl-2566	361	6	.	.	PUNCT
istl-2566	362	1	evolution	evolution	NOUN
istl-2566	362	2	of	of	ADP
istl-2566	362	3	scifinder	scifinder	PROPN
istl-2566	362	4	,	,	PUNCT
istl-2566	362	5	2011–2013	2011–2013	NUM
istl-2566	362	6	:	:	PUNCT
istl-2566	362	7	new	new	ADJ
istl-2566	362	8	features	feature	NOUN
istl-2566	362	9	,	,	PUNCT
istl-2566	362	10	new	new	ADJ
istl-2566	362	11	content	content	NOUN
istl-2566	362	12	.	.	PUNCT
istl-2566	363	1	science	science	NOUN
istl-2566	363	2	&	&	CCONJ
istl-2566	363	3	technology	technology	NOUN
istl-2566	363	4	libraries	librarie	VERB
istl-2566	363	5	32(4):346–371	32(4):346–371	PROPN
istl-2566	363	6	.	.	PUNCT
istl-2566	364	1	doi:10.1080/0194262x.2013.833068	doi:10.1080/0194262x.2013.833068	VERB
istl-2566	364	2	.	.	PUNCT
istl-2566	365	1	gobbi	gobbi	PROPN
istl-2566	365	2	,	,	PUNCT
istl-2566	365	3	a.	a.	PROPN
istl-2566	365	4	&	&	CCONJ
istl-2566	365	5	lee	lee	PROPN
istl-2566	365	6	,	,	PUNCT
istl-2566	365	7	m	m	PROPN
istl-2566	365	8	-	-	NOUN
istl-2566	365	9	l.	l.	NOUN
istl-2566	365	10	2012	2012	NUM
istl-2566	365	11	.	.	PUNCT
istl-2566	366	1	handling	handle	VERB
istl-2566	366	2	of	of	ADP
istl-2566	366	3	tautomerism	tautomerism	NOUN
istl-2566	366	4	and	and	CCONJ
istl-2566	366	5	stereochemistry	stereochemistry	NOUN
istl-2566	366	6	in	in	ADP
istl-2566	366	7	compound	compound	NOUN
istl-2566	366	8	registration	registration	NOUN
istl-2566	366	9	.	.	PUNCT
istl-2566	367	1	journal	journal	PROPN
istl-2566	367	2	of	of	ADP
istl-2566	367	3	chemical	chemical	ADJ
istl-2566	367	4	information	information	NOUN
istl-2566	367	5	and	and	CCONJ
istl-2566	367	6	modeling	model	VERB
istl-2566	367	7	52(2):285–292	52(2):285–292	PROPN
istl-2566	367	8	.	.	PUNCT
istl-2566	368	1	doi:10.1021	doi:10.1021	ADJ
istl-2566	368	2	/	/	SYM
istl-2566	368	3	ci200330x	ci200330x	PROPN
istl-2566	368	4	.	.	PUNCT
istl-2566	369	1	gordon	gordon	PROPN
istl-2566	369	2	,	,	PUNCT
istl-2566	369	3	i.d	i.d	PROPN
istl-2566	369	4	.	.	PROPN
istl-2566	369	5	,	,	PUNCT
istl-2566	369	6	meindl	meindl	PROPN
istl-2566	369	7	,	,	PUNCT
istl-2566	369	8	p.	p.	PROPN
istl-2566	369	9	,	,	PUNCT
istl-2566	369	10	white	white	ADJ
istl-2566	369	11	,	,	PUNCT
istl-2566	369	12	m.	m.	PROPN
istl-2566	369	13	&	&	CCONJ
istl-2566	369	14	szigeti	szigeti	PROPN
istl-2566	369	15	,	,	PUNCT
istl-2566	369	16	k.	k.	NOUN
istl-2566	369	17	2018	2018	NUM
istl-2566	369	18	.	.	PUNCT
istl-2566	370	1	information	information	NOUN
istl-2566	370	2	seeking	seek	VERB
istl-2566	370	3	behaviors	behavior	NOUN
istl-2566	370	4	,	,	PUNCT
istl-2566	370	5	attitudes	attitude	NOUN
istl-2566	370	6	,	,	PUNCT
istl-2566	370	7	and	and	CCONJ
istl-2566	370	8	choices	choice	NOUN
istl-2566	370	9	of	of	ADP
istl-2566	370	10	academic	academic	ADJ
istl-2566	370	11	chemists	chemist	NOUN
istl-2566	370	12	.	.	PUNCT
istl-2566	371	1	science	science	NOUN
istl-2566	371	2	&	&	CCONJ
istl-2566	371	3	technology	technology	PROPN
istl-2566	371	4	libraries	librarie	VERB
istl-2566	371	5	37(2):130–151	37(2):130–151	PROPN
istl-2566	371	6	.	.	PUNCT
istl-2566	372	1	doi:10.1080/0194262x.2018.1445063	doi:10.1080/0194262x.2018.1445063	SPACE
istl-2566	372	2	.	.	PUNCT
istl-2566	373	1	hähnke	hähnke	PROPN
istl-2566	373	2	,	,	PUNCT
istl-2566	373	3	v.d	v.d	PROPN
istl-2566	373	4	.	.	PROPN
istl-2566	373	5	,	,	PUNCT
istl-2566	373	6	kim	kim	PROPN
istl-2566	373	7	,	,	PUNCT
istl-2566	373	8	s.	s.	PROPN
istl-2566	373	9	&	&	CCONJ
istl-2566	373	10	bolton	bolton	PROPN
istl-2566	373	11	,	,	PUNCT
istl-2566	373	12	e.e	e.e	PROPN
istl-2566	373	13	.	.	PROPN
istl-2566	373	14	2018	2018	NUM
istl-2566	373	15	.	.	PUNCT
istl-2566	374	1	pubchem	pubchem	PROPN
istl-2566	374	2	chemical	chemical	PROPN
istl-2566	374	3	structure	structure	NOUN
istl-2566	374	4	standardization	standardization	NOUN
istl-2566	374	5	.	.	PUNCT
istl-2566	375	1	journal	journal	PROPN
istl-2566	375	2	of	of	ADP
istl-2566	375	3	cheminformatics	cheminformatics	PROPN
istl-2566	375	4	10:36	10:36	NUM
istl-2566	375	5	.	.	PUNCT
istl-2566	376	1	doi:10.1186	doi:10.1186	PROPN
istl-2566	376	2	/	/	SYM
istl-2566	376	3	s13321	s13321	PROPN
istl-2566	376	4	-	-	PUNCT
istl-2566	376	5	018	018	NUM
istl-2566	376	6	-	-	PUNCT
istl-2566	376	7	0293	0293	NUM
istl-2566	376	8	-	-	SYM
istl-2566	376	9	8	8	NUM
istl-2566	376	10	.	.	X
istl-2566	376	11	hastings	hastings	PROPN
istl-2566	376	12	,	,	PUNCT
istl-2566	376	13	j.	j.	PROPN
istl-2566	376	14	,	,	PUNCT
istl-2566	376	15	owen	owen	PROPN
istl-2566	376	16	,	,	PUNCT
istl-2566	376	17	g.	g.	PROPN
istl-2566	376	18	,	,	PUNCT
istl-2566	376	19	dekker	dekker	PROPN
istl-2566	376	20	,	,	PUNCT
istl-2566	376	21	a.	a.	PROPN
istl-2566	376	22	,	,	PUNCT
istl-2566	376	23	ennis	ennis	PROPN
istl-2566	376	24	,	,	PUNCT
istl-2566	376	25	m.	m.	NOUN
istl-2566	376	26	,	,	PUNCT
istl-2566	376	27	kale	kale	PROPN
istl-2566	376	28	,	,	PUNCT
istl-2566	376	29	n.	n.	PROPN
istl-2566	376	30	,	,	PUNCT
istl-2566	376	31	muthukrishnan	muthukrishnan	PROPN
istl-2566	376	32	,	,	PUNCT
istl-2566	376	33	v.	v.	PROPN
istl-2566	376	34	,	,	PUNCT
istl-2566	376	35	turner	turner	PROPN
istl-2566	376	36	,	,	PUNCT
istl-2566	376	37	s.	s.	PROPN
istl-2566	376	38	,	,	PUNCT
istl-2566	376	39	swainston	swainston	PROPN
istl-2566	376	40	,	,	PUNCT
istl-2566	376	41	n.	n.	PROPN
istl-2566	376	42	,	,	PUNCT
istl-2566	376	43	mendes	mende	NOUN
istl-2566	376	44	,	,	PUNCT
istl-2566	376	45	p.	p.	PROPN
istl-2566	376	46	&	&	CCONJ
istl-2566	376	47	steinbeck	steinbeck	PROPN
istl-2566	376	48	,	,	PUNCT
istl-2566	376	49	c.	c.	PROPN
istl-2566	376	50	2016	2016	NUM
istl-2566	376	51	.	.	PUNCT
istl-2566	377	1	chebi	chebi	NOUN
istl-2566	377	2	in	in	ADP
istl-2566	377	3	2016	2016	NUM
istl-2566	377	4	:	:	PUNCT
istl-2566	377	5	improved	improve	VERB
istl-2566	377	6	services	service	NOUN
istl-2566	377	7	and	and	CCONJ
istl-2566	377	8	an	an	DET
istl-2566	377	9	expanding	expand	VERB
istl-2566	377	10	collection	collection	NOUN
istl-2566	377	11	of	of	ADP
istl-2566	377	12	metabolites	metabolite	NOUN
istl-2566	377	13	.	.	PUNCT
istl-2566	378	1	nucleic	nucleic	ADJ
istl-2566	378	2	acids	acid	NOUN
istl-2566	378	3	research	research	NOUN
istl-2566	378	4	44(d1):d1214	44(d1):d1214	PROPN
istl-2566	378	5	–	–	PUNCT
istl-2566	378	6	d1219	d1219	PROPN
istl-2566	378	7	.	.	PUNCT
istl-2566	378	8	doi:10.1093	doi:10.1093	NOUN
istl-2566	378	9	/	/	SYM
istl-2566	378	10	nar	nar	NOUN
istl-2566	378	11	/	/	SYM
istl-2566	378	12	gkv1031	gkv1031	PROPN
istl-2566	378	13	.	.	PUNCT
istl-2566	379	1	heller	heller	PROPN
istl-2566	379	2	,	,	PUNCT
istl-2566	379	3	s.r	s.r	PROPN
istl-2566	379	4	.	.	PROPN
istl-2566	379	5	,	,	PUNCT
istl-2566	379	6	mcnaught	mcnaught	NOUN
istl-2566	379	7	,	,	PUNCT
istl-2566	379	8	a.	a.	NOUN
istl-2566	379	9	,	,	PUNCT
istl-2566	379	10	pletnev	pletnev	PROPN
istl-2566	379	11	,	,	PUNCT
istl-2566	379	12	i.	i.	PROPN
istl-2566	379	13	,	,	PUNCT
istl-2566	379	14	stein	stein	PROPN
istl-2566	379	15	,	,	PUNCT
istl-2566	379	16	s.	s.	PROPN
istl-2566	379	17	&	&	CCONJ
istl-2566	379	18	tchekhovskoi	tchekhovskoi	NOUN
istl-2566	379	19	,	,	PUNCT
istl-2566	379	20	d.	d.	PROPN
istl-2566	379	21	2015	2015	NUM
istl-2566	379	22	.	.	PUNCT
istl-2566	380	1	inchi	inchi	PROPN
istl-2566	380	2	,	,	PUNCT
istl-2566	380	3	the	the	DET
istl-2566	380	4	iupac	iupac	PROPN
istl-2566	380	5	international	international	PROPN
istl-2566	380	6	chemical	chemical	PROPN
istl-2566	380	7	identifier	identifier	NOUN
istl-2566	380	8	.	.	PUNCT
istl-2566	381	1	journal	journal	PROPN
istl-2566	381	2	of	of	ADP
istl-2566	381	3	cheminformatics	cheminformatics	PROPN
istl-2566	381	4	7:23	7:23	NUM
istl-2566	381	5	.	.	PUNCT
istl-2566	382	1	doi:10.1186	doi:10.1186	PROPN
istl-2566	382	2	/	/	SYM
istl-2566	382	3	s13321	s13321	PROPN
istl-2566	382	4	-	-	PUNCT
istl-2566	382	5	015	015	NUM
istl-2566	382	6	-	-	PUNCT
istl-2566	382	7	0068	0068	NUM
istl-2566	382	8	-	-	SYM
istl-2566	382	9	4	4	NUM
istl-2566	382	10	.	.	PROPN
istl-2566	382	11	hersey	hersey	PROPN
istl-2566	382	12	,	,	PUNCT
istl-2566	382	13	a.	a.	PROPN
istl-2566	383	1	[	[	X
istl-2566	383	2	date	date	NOUN
istl-2566	383	3	unknown	unknown	ADJ
istl-2566	383	4	]	]	PUNCT
istl-2566	383	5	.	.	PUNCT
istl-2566	384	1	chembl	chembl	NOUN
istl-2566	384	2	database	database	PROPN
istl-2566	384	3	:	:	PUNCT
istl-2566	384	4	meeting	meet	VERB
istl-2566	384	5	chemical	chemical	NOUN
istl-2566	384	6	and	and	CCONJ
istl-2566	384	7	biological	biological	ADJ
istl-2566	384	8	information	information	NOUN
istl-2566	384	9	needs	need	NOUN
istl-2566	384	10	of	of	ADP
istl-2566	384	11	scientists	scientist	NOUN
istl-2566	384	12	of	of	ADP
istl-2566	384	13	the	the	DET
istl-2566	384	14	future	future	ADJ
istl-2566	385	1	[	[	X
istl-2566	385	2	internet	internet	NOUN
istl-2566	385	3	]	]	PUNCT
istl-2566	385	4	.	.	PUNCT
istl-2566	386	1	available	available	ADJ
istl-2566	386	2	from	from	ADP
istl-2566	386	3	https://www.rsc.org/images/chembl-anne-hersey_tcm18-213324.pdf	https://www.rsc.org/images/chembl-anne-hersey_tcm18-213324.pdf	PROPN
istl-2566	386	4	.	.	PUNCT
istl-2566	386	5	hersey	hersey	PROPN
istl-2566	386	6	,	,	PUNCT
istl-2566	386	7	a.	a.	PROPN
istl-2566	386	8	,	,	PUNCT
istl-2566	386	9	chambers	chambers	PROPN
istl-2566	386	10	,	,	PUNCT
istl-2566	386	11	j.	j.	PROPN
istl-2566	386	12	,	,	PUNCT
istl-2566	386	13	bellis	bellis	PROPN
istl-2566	386	14	,	,	PUNCT
istl-2566	386	15	l.	l.	PROPN
istl-2566	386	16	,	,	PUNCT
istl-2566	386	17	bento	bento	PROPN
istl-2566	386	18	,	,	PUNCT
istl-2566	386	19	a.p	a.p	PROPN
istl-2566	386	20	.	.	PROPN
istl-2566	386	21	,	,	PUNCT
istl-2566	386	22	gaulton	gaulton	PROPN
istl-2566	386	23	,	,	PUNCT
istl-2566	386	24	a.	a.	PROPN
istl-2566	386	25	&	&	CCONJ
istl-2566	386	26	overington	overington	PROPN
istl-2566	386	27	,	,	PUNCT
istl-2566	386	28	j.p	j.p	PROPN
istl-2566	386	29	.	.	PROPN
istl-2566	386	30	2015	2015	NUM
istl-2566	386	31	.	.	PUNCT
istl-2566	387	1	chemical	chemical	NOUN
istl-2566	387	2	databases	database	NOUN
istl-2566	387	3	:	:	PUNCT
istl-2566	387	4	curation	curation	NOUN
istl-2566	387	5	or	or	CCONJ
istl-2566	387	6	integration	integration	NOUN
istl-2566	387	7	by	by	ADP
istl-2566	387	8	user	user	NOUN
istl-2566	387	9	-	-	PUNCT
istl-2566	387	10	defined	define	VERB
istl-2566	387	11	equivalence	equivalence	NOUN
istl-2566	387	12	?	?	PUNCT
istl-2566	388	1	drug	drug	NOUN
istl-2566	388	2	discovery	discovery	NOUN
istl-2566	388	3	today	today	NOUN
istl-2566	388	4	technology	technology	NOUN
istl-2566	388	5	14:17–24	14:17–24	PROPN
istl-2566	388	6	.	.	PUNCT
istl-2566	389	1	doi:10.1016	doi:10.1016	PROPN
istl-2566	389	2	/	/	SYM
istl-2566	389	3	j.ddtec.2015.01.005	j.ddtec.2015.01.005	PROPN
istl-2566	389	4	.	.	PROPN
istl-2566	389	5	ihlenfeldt	ihlenfeldt	PROPN
istl-2566	389	6	,	,	PUNCT
istl-2566	389	7	w.d	w.d	PROPN
istl-2566	389	8	.	.	PROPN
istl-2566	389	9	,	,	PUNCT
istl-2566	389	10	bolton	bolton	PROPN
istl-2566	389	11	,	,	PUNCT
istl-2566	389	12	e.e	e.e	PROPN
istl-2566	389	13	.	.	PROPN
istl-2566	389	14	&	&	CCONJ
istl-2566	389	15	bryant	bryant	PROPN
istl-2566	389	16	,	,	PUNCT
istl-2566	389	17	s.h	s.h	PROPN
istl-2566	389	18	.	.	PROPN
istl-2566	389	19	2009	2009	NUM
istl-2566	389	20	.	.	PUNCT
istl-2566	390	1	the	the	DET
istl-2566	390	2	pubchem	pubchem	PROPN
istl-2566	390	3	chemical	chemical	PROPN
istl-2566	390	4	structure	structure	PROPN
istl-2566	390	5	sketcher	sketcher	PROPN
istl-2566	390	6	.	.	PUNCT
istl-2566	390	7	journal	journal	PROPN
istl-2566	390	8	of	of	ADP
istl-2566	390	9	cheminformatics	cheminformatic	NOUN
istl-2566	390	10	1:20	1:20	NUM
istl-2566	390	11	.	.	PUNCT
istl-2566	391	1	doi:10.1186/1758–2946	doi:10.1186/1758–2946	NOUN
istl-2566	391	2	-	-	PUNCT
istl-2566	391	3	1	1	NUM
istl-2566	391	4	-	-	SYM
istl-2566	391	5	20	20	NUM
istl-2566	391	6	.	.	PUNCT
istl-2566	391	7	international	international	PROPN
istl-2566	391	8	union	union	PROPN
istl-2566	391	9	of	of	ADP
istl-2566	391	10	pure	pure	ADJ
istl-2566	391	11	and	and	CCONJ
istl-2566	391	12	applied	apply	VERB
istl-2566	391	13	chemistry	chemistry	NOUN
istl-2566	391	14	.	.	PUNCT
istl-2566	392	1	2017	2017	NUM
istl-2566	392	2	.	.	PUNCT
istl-2566	393	1	international	international	ADJ
istl-2566	393	2	chemical	chemical	PROPN
istl-2566	393	3	identifier	identifier	NOUN
istl-2566	393	4	(	(	PUNCT
istl-2566	393	5	inchi	inchi	PROPN
istl-2566	393	6	)	)	PUNCT
istl-2566	393	7	version	version	NOUN
istl-2566	393	8	1	1	NUM
istl-2566	393	9	,	,	PUNCT
istl-2566	393	10	software	software	NOUN
istl-2566	393	11	version	version	NOUN
istl-2566	393	12	1.05	1.05	NUM
istl-2566	393	13	api	api	NOUN
istl-2566	393	14	reference	reference	NOUN
istl-2566	393	15	[	[	X
istl-2566	393	16	internet	internet	NOUN
istl-2566	393	17	]	]	PUNCT
istl-2566	393	18	.	.	PUNCT
istl-2566	394	1	available	available	ADJ
istl-2566	394	2	from	from	ADP
istl-2566	394	3	https://www.inchi-trust.org/downloads/.	https://www.inchi-trust.org/downloads/.	PROPN
istl-2566	394	4	kim	kim	PROPN
istl-2566	394	5	,	,	PUNCT
istl-2566	394	6	s.	s.	PROPN
istl-2566	394	7	,	,	PUNCT
istl-2566	394	8	chen	chen	PROPN
istl-2566	394	9	,	,	PUNCT
istl-2566	394	10	j.	j.	PROPN
istl-2566	394	11	,	,	PUNCT
istl-2566	394	12	cheng	cheng	PROPN
istl-2566	394	13	,	,	PUNCT
istl-2566	394	14	t.	t.	PROPN
istl-2566	394	15	,	,	PUNCT
istl-2566	394	16	gindulyte	gindulyte	PROPN
istl-2566	394	17	,	,	PUNCT
istl-2566	394	18	a.	a.	PROPN
istl-2566	394	19	,	,	PUNCT
istl-2566	394	20	he	he	PROPN
istl-2566	394	21	,	,	PUNCT
istl-2566	394	22	j.	j.	PROPN
istl-2566	394	23	,	,	PUNCT
istl-2566	394	24	he	he	PRON
istl-2566	394	25	,	,	PUNCT
istl-2566	394	26	s.	s.	PROPN
istl-2566	394	27	,	,	PUNCT
istl-2566	394	28	li	li	PROPN
istl-2566	394	29	,	,	PUNCT
istl-2566	394	30	q.	q.	PROPN
istl-2566	394	31	,	,	PUNCT
istl-2566	394	32	shoemaker	shoemaker	NOUN
istl-2566	394	33	,	,	PUNCT
istl-2566	394	34	b.a	b.a	PROPN
istl-2566	394	35	.	.	PROPN
istl-2566	394	36	,	,	PUNCT
istl-2566	394	37	thiessen	thiessen	PROPN
istl-2566	394	38	,	,	PUNCT
istl-2566	394	39	p.a	p.a	PROPN
istl-2566	394	40	.	.	PROPN
istl-2566	394	41	,	,	PUNCT
istl-2566	394	42	yu	yu	PROPN
istl-2566	394	43	,	,	PUNCT
istl-2566	394	44	b.	b.	PROPN
istl-2566	394	45	,	,	PUNCT
istl-2566	394	46	et	et	PROPN
istl-2566	394	47	al	al	PROPN
istl-2566	394	48	.	.	PROPN
istl-2566	394	49	2021	2021	NUM
istl-2566	394	50	.	.	PUNCT
istl-2566	395	1	pubchem	pubchem	NOUN
istl-2566	395	2	in	in	ADP
istl-2566	395	3	2021	2021	NUM
istl-2566	395	4	:	:	PUNCT
istl-2566	395	5	new	new	ADJ
istl-2566	395	6	data	datum	NOUN
istl-2566	395	7	content	content	NOUN
istl-2566	395	8	and	and	CCONJ
istl-2566	395	9	improved	improved	ADJ
istl-2566	395	10	web	web	NOUN
istl-2566	395	11	interfaces	interface	NOUN
istl-2566	395	12	.	.	PUNCT
istl-2566	396	1	nucleic	nucleic	ADJ
istl-2566	396	2	acids	acid	NOUN
istl-2566	396	3	research	research	PROPN
istl-2566	396	4	49(d1):d1388	49(d1):d1388	PROPN
istl-2566	396	5	–	–	PUNCT
istl-2566	396	6	d1395	d1395	PROPN
istl-2566	396	7	.	.	NUM
istl-2566	396	8	doi:10.1093	doi:10.1093	NOUN
istl-2566	396	9	/	/	SYM
istl-2566	396	10	nar	nar	NOUN
istl-2566	396	11	/	/	SYM
istl-2566	396	12	gkaa971	gkaa971	PROPN
istl-2566	396	13	.	.	PUNCT
istl-2566	397	1	kim	kim	PROPN
istl-2566	397	2	,	,	PUNCT
istl-2566	397	3	s.	s.	PROPN
istl-2566	397	4	,	,	PUNCT
istl-2566	397	5	thiessen	thiessen	PROPN
istl-2566	397	6	,	,	PUNCT
istl-2566	397	7	p.a	p.a	PROPN
istl-2566	397	8	.	.	PROPN
istl-2566	397	9	,	,	PUNCT
istl-2566	397	10	bolton	bolton	PROPN
istl-2566	397	11	,	,	PUNCT
istl-2566	397	12	e.e	e.e	PROPN
istl-2566	397	13	.	.	PROPN
istl-2566	397	14	&	&	CCONJ
istl-2566	397	15	bryant	bryant	PROPN
istl-2566	397	16	,	,	PUNCT
istl-2566	397	17	s.h	s.h	PROPN
istl-2566	397	18	.	.	PROPN
istl-2566	397	19	2015	2015	NUM
istl-2566	397	20	.	.	PUNCT
istl-2566	398	1	pug	pug	NOUN
istl-2566	398	2	-	-	PUNCT
istl-2566	398	3	soap	soap	NOUN
istl-2566	398	4	and	and	CCONJ
istl-2566	398	5	pug	pug	NOUN
istl-2566	398	6	-	-	PUNCT
istl-2566	398	7	rest	rest	NOUN
istl-2566	398	8	:	:	PUNCT
istl-2566	398	9	web	web	NOUN
istl-2566	398	10	services	service	NOUN
istl-2566	398	11	for	for	ADP
istl-2566	398	12	programmatic	programmatic	ADJ
istl-2566	398	13	access	access	NOUN
istl-2566	398	14	to	to	ADP
istl-2566	398	15	chemical	chemical	ADJ
istl-2566	398	16	information	information	NOUN
istl-2566	398	17	in	in	ADP
istl-2566	398	18	pubchem	pubchem	PROPN
istl-2566	398	19	.	.	PUNCT
istl-2566	399	1	nucleic	nucleic	ADJ
istl-2566	399	2	acids	acid	NOUN
istl-2566	399	3	research	research	NOUN
istl-2566	399	4	43(w1):w605	43(w1):w605	NUM
istl-2566	399	5	–	–	PUNCT
istl-2566	399	6	w611	w611	PROPN
istl-2566	399	7	.	.	PUNCT
istl-2566	400	1	doi:10.1093	doi:10.1093	NOUN
istl-2566	400	2	/	/	SYM
istl-2566	400	3	nar	nar	PROPN
istl-2566	400	4	/	/	SYM
istl-2566	400	5	gkv396	gkv396	PROPN
istl-2566	400	6	.	.	PUNCT
istl-2566	401	1	kim	kim	PROPN
istl-2566	401	2	,	,	PUNCT
istl-2566	401	3	s.	s.	PROPN
istl-2566	401	4	,	,	PUNCT
istl-2566	401	5	thiessen	thiessen	PROPN
istl-2566	401	6	,	,	PUNCT
istl-2566	401	7	p.a	p.a	PROPN
istl-2566	401	8	.	.	PROPN
istl-2566	401	9	,	,	PUNCT
istl-2566	401	10	bolton	bolton	PROPN
istl-2566	401	11	,	,	PUNCT
istl-2566	401	12	e.e	e.e	PROPN
istl-2566	401	13	.	.	PROPN
istl-2566	401	14	,	,	PUNCT
istl-2566	401	15	chen	chen	PROPN
istl-2566	401	16	,	,	PUNCT
istl-2566	401	17	j.	j.	PROPN
istl-2566	401	18	,	,	PUNCT
istl-2566	401	19	fu	fu	PROPN
istl-2566	401	20	,	,	PUNCT
istl-2566	401	21	g.	g.	PROPN
istl-2566	401	22	,	,	PUNCT
istl-2566	401	23	gindulyte	gindulyte	PROPN
istl-2566	401	24	,	,	PUNCT
istl-2566	401	25	a.	a.	PROPN
istl-2566	401	26	,	,	PUNCT
istl-2566	401	27	han	han	PROPN
istl-2566	401	28	,	,	PUNCT
istl-2566	401	29	l.	l.	PROPN
istl-2566	401	30	,	,	PUNCT
istl-2566	401	31	he	he	PRON
istl-2566	401	32	,	,	PUNCT
istl-2566	401	33	j.	j.	PROPN
istl-2566	401	34	,	,	PUNCT
istl-2566	401	35	he	he	PRON
istl-2566	401	36	,	,	PUNCT
istl-2566	401	37	s.	s.	PROPN
istl-2566	401	38	,	,	PUNCT
istl-2566	401	39	shoemaker	shoemaker	NOUN
istl-2566	401	40	,	,	PUNCT
istl-2566	401	41	b.a	b.a	PROPN
istl-2566	401	42	.	.	PROPN
istl-2566	401	43	,	,	PUNCT
istl-2566	401	44	et	et	PROPN
istl-2566	401	45	al	al	PROPN
istl-2566	401	46	.	.	PUNCT
istl-2566	401	47	2016a	2016a	NOUN
istl-2566	401	48	.	.	PUNCT
istl-2566	402	1	pubchem	pubchem	PROPN
istl-2566	402	2	substance	substance	NOUN
istl-2566	402	3	and	and	CCONJ
istl-2566	402	4	compound	compound	NOUN
istl-2566	402	5	databases	database	NOUN
istl-2566	402	6	.	.	PUNCT
istl-2566	403	1	nucleic	nucleic	ADJ
istl-2566	403	2	acids	acid	NOUN
istl-2566	403	3	research	research	PROPN
istl-2566	403	4	44(d1):d1202	44(d1):d1202	PROPN
istl-2566	403	5	–	–	PUNCT
istl-2566	403	6	d1213	d1213	PROPN
istl-2566	403	7	.	.	NUM
istl-2566	403	8	doi:10.1093	doi:10.1093	NOUN
istl-2566	403	9	/	/	SYM
istl-2566	403	10	nar	nar	NOUN
istl-2566	403	11	/	/	SYM
istl-2566	403	12	gkv951	gkv951	PROPN
istl-2566	403	13	.	.	PUNCT
istl-2566	404	1	kim	kim	PROPN
istl-2566	404	2	,	,	PUNCT
istl-2566	404	3	s.	s.	PROPN
istl-2566	404	4	,	,	PUNCT
istl-2566	404	5	thiessen	thiessen	PROPN
istl-2566	404	6	,	,	PUNCT
istl-2566	404	7	p.a	p.a	PROPN
istl-2566	404	8	.	.	PROPN
istl-2566	404	9	,	,	PUNCT
istl-2566	404	10	bolton	bolton	PROPN
istl-2566	404	11	,	,	PUNCT
istl-2566	404	12	e.e	e.e	PROPN
istl-2566	404	13	.	.	PROPN
istl-2566	404	14	,	,	PUNCT
istl-2566	404	15	chen	chen	PROPN
istl-2566	404	16	,	,	PUNCT
istl-2566	404	17	j.	j.	PROPN
istl-2566	404	18	,	,	PUNCT
istl-2566	404	19	fu	fu	PROPN
istl-2566	404	20	,	,	PUNCT
istl-2566	404	21	g.	g.	PROPN
istl-2566	404	22	,	,	PUNCT
istl-2566	404	23	gindulyte	gindulyte	PROPN
istl-2566	404	24	,	,	PUNCT
istl-2566	404	25	a.	a.	PROPN
istl-2566	404	26	,	,	PUNCT
istl-2566	404	27	han	han	PROPN
istl-2566	404	28	,	,	PUNCT
istl-2566	404	29	l.	l.	PROPN
istl-2566	404	30	,	,	PUNCT
istl-2566	404	31	he	he	PRON
istl-2566	404	32	,	,	PUNCT
istl-2566	404	33	j.	j.	PROPN
istl-2566	404	34	,	,	PUNCT
istl-2566	404	35	he	he	PRON
istl-2566	404	36	,	,	PUNCT
istl-2566	404	37	s.	s.	PROPN
istl-2566	404	38	,	,	PUNCT
istl-2566	404	39	shoemaker	shoemaker	NOUN
istl-2566	404	40	,	,	PUNCT
istl-2566	404	41	b.a	b.a	PROPN
istl-2566	404	42	.	.	PROPN
istl-2566	404	43	,	,	PUNCT
istl-2566	404	44	et	et	PROPN
istl-2566	404	45	al	al	PROPN
istl-2566	404	46	.	.	PUNCT
istl-2566	404	47	2016b	2016b	NUM
istl-2566	404	48	.	.	PUNCT
istl-2566	405	1	literature	literature	NOUN
istl-2566	405	2	information	information	NOUN
istl-2566	405	3	in	in	ADP
istl-2566	405	4	pubchem	pubchem	NOUN
istl-2566	405	5	:	:	PUNCT
istl-2566	405	6	associations	association	NOUN
istl-2566	405	7	between	between	ADP
istl-2566	405	8	pubchem	pubchem	NOUN
istl-2566	405	9	records	record	NOUN
istl-2566	405	10	and	and	CCONJ
istl-2566	405	11	scientific	scientific	ADJ
istl-2566	405	12	articles	article	NOUN
istl-2566	405	13	.	.	PUNCT
istl-2566	406	1	journal	journal	PROPN
istl-2566	406	2	of	of	ADP
istl-2566	406	3	cheminformatics	cheminformatics	PROPN
istl-2566	406	4	8:32	8:32	PROPN
istl-2566	406	5	.	.	PUNCT
istl-2566	407	1	doi:10.1186	doi:10.1186	PROPN
istl-2566	407	2	/	/	SYM
istl-2566	407	3	s13321	s13321	PROPN
istl-2566	407	4	-	-	PUNCT
istl-2566	407	5	016	016	NUM
istl-2566	407	6	-	-	PUNCT
istl-2566	407	7	0142	0142	NUM
istl-2566	407	8	-	-	SYM
istl-2566	407	9	6	6	NUM
istl-2566	407	10	.	.	PUNCT
istl-2566	407	11	kim	kim	PROPN
istl-2566	407	12	,	,	PUNCT
istl-2566	407	13	s.	s.	PROPN
istl-2566	407	14	,	,	PUNCT
istl-2566	407	15	thiessen	thiessen	PROPN
istl-2566	407	16	,	,	PUNCT
istl-2566	407	17	p.a	p.a	PROPN
istl-2566	407	18	.	.	PROPN
istl-2566	407	19	,	,	PUNCT
istl-2566	407	20	cheng	cheng	PROPN
istl-2566	407	21	,	,	PUNCT
istl-2566	407	22	t.	t.	PROPN
istl-2566	407	23	,	,	PUNCT
istl-2566	407	24	zhang	zhang	PROPN
istl-2566	407	25	,	,	PUNCT
istl-2566	407	26	j.	j.	PROPN
istl-2566	407	27	,	,	PUNCT
istl-2566	407	28	gindulyte	gindulyte	PROPN
istl-2566	407	29	,	,	PUNCT
istl-2566	407	30	a.	a.	PROPN
istl-2566	407	31	&	&	CCONJ
istl-2566	407	32	bolton	bolton	PROPN
istl-2566	407	33	,	,	PUNCT
istl-2566	407	34	e.e	e.e	PROPN
istl-2566	407	35	.	.	PROPN
istl-2566	407	36	2019	2019	NUM
istl-2566	407	37	.	.	PUNCT
istl-2566	408	1	pug	pug	NOUN
istl-2566	408	2	-	-	PUNCT
istl-2566	408	3	view	view	NOUN
istl-2566	408	4	:	:	PUNCT
istl-2566	408	5	programmatic	programmatic	ADJ
istl-2566	408	6	access	access	NOUN
istl-2566	408	7	to	to	ADP
istl-2566	408	8	chemical	chemical	NOUN
istl-2566	408	9	annotations	annotation	NOUN
istl-2566	408	10	integrated	integrate	VERB
istl-2566	408	11	in	in	ADP
istl-2566	408	12	pubchem	pubchem	PROPN
istl-2566	408	13	.	.	PUNCT
istl-2566	409	1	journal	journal	PROPN
istl-2566	409	2	of	of	ADP
istl-2566	409	3	cheminformatics	cheminformatic	NOUN
istl-2566	409	4	11:56	11:56	NUM
istl-2566	409	5	.	.	PUNCT
istl-2566	410	1	doi:10.1186	doi:10.1186	PROPN
istl-2566	410	2	/	/	SYM
istl-2566	410	3	s13321	s13321	PROPN
istl-2566	410	4	-	-	PUNCT
istl-2566	410	5	019	019	NUM
istl-2566	410	6	-	-	PUNCT
istl-2566	410	7	0375	0375	NUM
istl-2566	410	8	-	-	PUNCT
istl-2566	410	9	2	2	NUM
istl-2566	410	10	.	.	X
istl-2566	410	11	krallinger	krallinger	NOUN
istl-2566	410	12	,	,	PUNCT
istl-2566	410	13	m.	m.	NOUN
istl-2566	410	14	,	,	PUNCT
istl-2566	410	15	rabal	rabal	NOUN
istl-2566	410	16	,	,	PUNCT
istl-2566	410	17	o.	o.	PROPN
istl-2566	410	18	,	,	PUNCT
istl-2566	410	19	lourenço	lourenço	PROPN
istl-2566	410	20	,	,	PUNCT
istl-2566	410	21	a.	a.	PROPN
istl-2566	410	22	,	,	PUNCT
istl-2566	410	23	oyarzabal	oyarzabal	PROPN
istl-2566	410	24	,	,	PUNCT
istl-2566	410	25	j.	j.	PROPN
istl-2566	410	26	&	&	CCONJ
istl-2566	410	27	valencia	valencia	PROPN
istl-2566	410	28	,	,	PUNCT
istl-2566	410	29	a.	a.	PROPN
istl-2566	410	30	2017	2017	NUM
istl-2566	410	31	.	.	PUNCT
istl-2566	411	1	information	information	NOUN
istl-2566	411	2	retrieval	retrieval	NOUN
istl-2566	411	3	and	and	CCONJ
istl-2566	411	4	text	text	NOUN
istl-2566	411	5	mining	mining	NOUN
istl-2566	411	6	technologies	technology	NOUN
istl-2566	411	7	for	for	ADP
istl-2566	411	8	chemistry	chemistry	NOUN
istl-2566	411	9	.	.	PUNCT
istl-2566	412	1	chemical	chemical	PROPN
istl-2566	412	2	reviews	reviews	PROPN
istl-2566	412	3	117(12):7673–7761	117(12):7673–7761	PROPN
istl-2566	412	4	.	.	PUNCT
istl-2566	413	1	doi:10.1021	doi:10.1021	PROPN
istl-2566	413	2	/	/	SYM
istl-2566	413	3	acs.chemrev.6b00851	acs.chemrev.6b00851	PROPN
istl-2566	413	4	.	.	PUNCT
istl-2566	414	1	landrum	landrum	NOUN
istl-2566	414	2	,	,	PUNCT
istl-2566	414	3	g.a	g.a	PROPN
istl-2566	414	4	.	.	PROPN
istl-2566	414	5	2020	2020	NUM
istl-2566	414	6	.	.	PUNCT
istl-2566	415	1	rdkit	rdkit	PROPN
istl-2566	415	2	:	:	PUNCT
istl-2566	415	3	open	open	ADJ
istl-2566	415	4	-	-	PUNCT
istl-2566	415	5	source	source	NOUN
istl-2566	415	6	cheminformatics	cheminformatic	NOUN
istl-2566	415	7	software	software	NOUN
istl-2566	415	8	[	[	X
istl-2566	415	9	internet	internet	NOUN
istl-2566	415	10	]	]	PUNCT
istl-2566	415	11	.	.	PUNCT
istl-2566	416	1	available	available	ADJ
istl-2566	416	2	from	from	ADP
istl-2566	416	3	https://www.rdkit.org/.	https://www.rdkit.org/.	PROPN
istl-2566	416	4	lawson	lawson	PROPN
istl-2566	416	5	,	,	PUNCT
istl-2566	416	6	a.j	a.j	PROPN
istl-2566	416	7	.	.	PROPN
istl-2566	416	8	,	,	PUNCT
istl-2566	416	9	swienty	swienty	PROPN
istl-2566	416	10	-	-	PUNCT
istl-2566	416	11	busch	busch	PROPN
istl-2566	416	12	,	,	PUNCT
istl-2566	416	13	j.	j.	PROPN
istl-2566	416	14	,	,	PUNCT
istl-2566	416	15	géoui	géoui	PROPN
istl-2566	416	16	,	,	PUNCT
istl-2566	416	17	t.	t.	PROPN
istl-2566	416	18	&	&	CCONJ
istl-2566	416	19	evans	evans	PROPN
istl-2566	416	20	,	,	PUNCT
istl-2566	416	21	d.	d.	PROPN
istl-2566	416	22	2014	2014	NUM
istl-2566	416	23	.	.	PUNCT
istl-2566	417	1	the	the	DET
istl-2566	417	2	making	making	NOUN
istl-2566	417	3	of	of	ADP
istl-2566	417	4	reaxys	reaxys	NOUN
istl-2566	417	5	—	—	PUNCT
istl-2566	417	6	towards	towards	ADP
istl-2566	417	7	unobstructed	unobstructed	ADJ
istl-2566	417	8	access	access	NOUN
istl-2566	417	9	to	to	ADP
istl-2566	417	10	relevant	relevant	ADJ
istl-2566	417	11	chemistry	chemistry	NOUN
istl-2566	417	12	information	information	NOUN
istl-2566	417	13	.	.	PUNCT
istl-2566	418	1	in	in	ADP
istl-2566	418	2	:	:	PUNCT
istl-2566	418	3	mcewen	mcewen	PROPN
istl-2566	418	4	,	,	PUNCT
istl-2566	418	5	l.r	l.r	PROPN
istl-2566	418	6	.	.	PROPN
istl-2566	418	7	&	&	CCONJ
istl-2566	418	8	buntrock	buntrock	PROPN
istl-2566	418	9	,	,	PUNCT
istl-2566	418	10	r.e	r.e	PROPN
istl-2566	418	11	.	.	PROPN
istl-2566	418	12	,	,	PUNCT
istl-2566	418	13	editors	editor	NOUN
istl-2566	418	14	.	.	PUNCT
istl-2566	419	1	the	the	DET
istl-2566	419	2	future	future	NOUN
istl-2566	419	3	of	of	ADP
istl-2566	419	4	the	the	DET
istl-2566	419	5	history	history	NOUN
istl-2566	419	6	of	of	ADP
istl-2566	419	7	chemical	chemical	ADJ
istl-2566	419	8	information	information	NOUN
istl-2566	419	9	.	.	PUNCT
istl-2566	420	1	washington	washington	PROPN
istl-2566	420	2	(	(	PUNCT
istl-2566	420	3	dc	dc	PROPN
istl-2566	420	4	):	):	PUNCT
istl-2566	420	5	american	american	PROPN
istl-2566	420	6	chemical	chemical	PROPN
istl-2566	420	7	society	society	NOUN
istl-2566	420	8	.	.	PUNCT
istl-2566	421	1	p.	p.	NOUN
istl-2566	421	2	127–148	127–148	NUM
istl-2566	421	3	.	.	PUNCT
istl-2566	422	1	martin	martin	PROPN
istl-2566	422	2	,	,	PUNCT
istl-2566	422	3	e.	e.	PROPN
istl-2566	422	4	,	,	PUNCT
istl-2566	422	5	monge	monge	PROPN
istl-2566	422	6	,	,	PUNCT
istl-2566	422	7	a.	a.	PROPN
istl-2566	422	8	,	,	PUNCT
istl-2566	422	9	duret	duret	PROPN
istl-2566	422	10	,	,	PUNCT
istl-2566	422	11	j	j	PROPN
istl-2566	422	12	-	-	PUNCT
istl-2566	422	13	a.	a.	NOUN
istl-2566	422	14	,	,	PUNCT
istl-2566	422	15	gualandi	gualandi	PROPN
istl-2566	422	16	,	,	PUNCT
istl-2566	422	17	f.	f.	PROPN
istl-2566	422	18	,	,	PUNCT
istl-2566	422	19	peitsch	peitsch	PROPN
istl-2566	422	20	,	,	PUNCT
istl-2566	422	21	m.c	m.c	PROPN
istl-2566	422	22	.	.	PROPN
istl-2566	422	23	&	&	CCONJ
istl-2566	422	24	pospisil	pospisil	PROPN
istl-2566	422	25	,	,	PUNCT
istl-2566	422	26	p.	p.	NOUN
istl-2566	422	27	2012	2012	NUM
istl-2566	422	28	.	.	PUNCT
istl-2566	423	1	building	build	VERB
istl-2566	423	2	an	an	DET
istl-2566	423	3	r&d	r&d	NOUN
istl-2566	423	4	chemical	chemical	NOUN
istl-2566	423	5	registration	registration	NOUN
istl-2566	423	6	system	system	NOUN
istl-2566	423	7	.	.	PUNCT
istl-2566	424	1	journal	journal	PROPN
istl-2566	424	2	of	of	ADP
istl-2566	424	3	cheminformatics	cheminformatic	NOUN
istl-2566	424	4	4:11	4:11	NUM
istl-2566	424	5	.	.	PUNCT
istl-2566	425	1	doi:10.1186/1758	doi:10.1186/1758	NOUN
istl-2566	425	2	-	-	PUNCT
istl-2566	425	3	2946	2946	NUM
istl-2566	425	4	-	-	PUNCT
istl-2566	425	5	4	4	NUM
istl-2566	425	6	-	-	SYM
istl-2566	425	7	11	11	NUM
istl-2566	425	8	.	.	PUNCT
istl-2566	425	9	mendez	mendez	PROPN
istl-2566	425	10	,	,	PUNCT
istl-2566	425	11	d.	d.	PROPN
istl-2566	425	12	,	,	PUNCT
istl-2566	425	13	gaulton	gaulton	PROPN
istl-2566	425	14	,	,	PUNCT
istl-2566	425	15	a.	a.	PROPN
istl-2566	425	16	,	,	PUNCT
istl-2566	425	17	bento	bento	PROPN
istl-2566	425	18	,	,	PUNCT
istl-2566	425	19	a.p	a.p	PROPN
istl-2566	425	20	.	.	PROPN
istl-2566	425	21	,	,	PUNCT
istl-2566	425	22	chambers	chambers	PROPN
istl-2566	425	23	,	,	PUNCT
istl-2566	425	24	j.	j.	PROPN
istl-2566	425	25	,	,	PUNCT
istl-2566	425	26	de	de	PROPN
istl-2566	425	27	veij	veij	PROPN
istl-2566	425	28	,	,	PUNCT
istl-2566	425	29	m.	m.	NOUN
istl-2566	425	30	,	,	PUNCT
istl-2566	425	31	félix	félix	NOUN
istl-2566	425	32	,	,	PUNCT
istl-2566	425	33	e.	e.	PROPN
istl-2566	425	34	,	,	PUNCT
istl-2566	425	35	magariños	magariños	PROPN
istl-2566	425	36	,	,	PUNCT
istl-2566	425	37	m.p	m.p	PROPN
istl-2566	425	38	.	.	PROPN
istl-2566	425	39	,	,	PUNCT
istl-2566	425	40	mosquera	mosquera	PROPN
istl-2566	425	41	,	,	PUNCT
istl-2566	425	42	j.f	j.f	PROPN
istl-2566	425	43	.	.	PROPN
istl-2566	425	44	,	,	PUNCT
istl-2566	425	45	mutowo	mutowo	PROPN
istl-2566	425	46	,	,	PUNCT
istl-2566	425	47	p.	p.	PROPN
istl-2566	425	48	,	,	PUNCT
istl-2566	425	49	nowotka	nowotka	PROPN
istl-2566	425	50	,	,	PUNCT
istl-2566	425	51	m.	m.	NOUN
istl-2566	425	52	,	,	PUNCT
istl-2566	425	53	et	et	PROPN
istl-2566	425	54	al	al	PROPN
istl-2566	425	55	.	.	PROPN
istl-2566	425	56	2018	2018	NUM
istl-2566	425	57	.	.	PUNCT
istl-2566	426	1	chembl	chembl	NOUN
istl-2566	426	2	:	:	PUNCT
istl-2566	426	3	towards	towards	ADP
istl-2566	426	4	direct	direct	ADJ
istl-2566	426	5	deposition	deposition	NOUN
istl-2566	426	6	of	of	ADP
istl-2566	426	7	bioassay	bioassay	VERB
istl-2566	426	8	data	data	PROPN
istl-2566	426	9	.	.	PUNCT
istl-2566	427	1	nucleic	nucleic	ADJ
istl-2566	427	2	acids	acid	NOUN
istl-2566	427	3	research	research	PROPN
istl-2566	427	4	47(d1):d930	47(d1):d930	NUM
istl-2566	427	5	–	–	PUNCT
istl-2566	427	6	d940	d940	PROPN
istl-2566	427	7	.	.	PUNCT
istl-2566	427	8	doi:10.1093	doi:10.1093	NOUN
istl-2566	427	9	/	/	SYM
istl-2566	427	10	nar	nar	PROPN
istl-2566	427	11	/	/	SYM
istl-2566	427	12	gky1075	gky1075	PROPN
istl-2566	427	13	.	.	PUNCT
istl-2566	428	1	national	national	ADJ
istl-2566	428	2	center	center	NOUN
istl-2566	428	3	for	for	ADP
istl-2566	428	4	biotechnology	biotechnology	NOUN
istl-2566	428	5	information	information	NOUN
istl-2566	428	6	.	.	PUNCT
istl-2566	429	1	2021	2021	NUM
istl-2566	429	2	.	.	PUNCT
istl-2566	430	1	entrez	entrez	PROPN
istl-2566	430	2	programming	programming	NOUN
istl-2566	430	3	utilities	utility	NOUN
istl-2566	430	4	help	help	VERB
istl-2566	430	5	[	[	X
istl-2566	430	6	internet	internet	NOUN
istl-2566	430	7	]	]	PUNCT
istl-2566	430	8	.	.	PUNCT
istl-2566	431	1	available	available	ADJ
istl-2566	431	2	from	from	ADP
istl-2566	431	3	https://www.ncbi.nlm.nih.gov/books/nbk25501/.	https://www.ncbi.nlm.nih.gov/books/nbk25501/.	PROPN
istl-2566	431	4	national	national	PROPN
istl-2566	431	5	center	center	NOUN
istl-2566	431	6	for	for	ADP
istl-2566	431	7	biotechnology	biotechnology	NOUN
istl-2566	431	8	information	information	NOUN
istl-2566	431	9	.	.	PUNCT
istl-2566	432	1	[	[	X
istl-2566	432	2	date	date	NOUN
istl-2566	432	3	unknown	unknown	NOUN
istl-2566	432	4	-	-	PUNCT
istl-2566	432	5	a	a	NOUN
istl-2566	432	6	]	]	PUNCT
istl-2566	432	7	.	.	PUNCT
istl-2566	433	1	pubchem	pubchem	NOUN
istl-2566	433	2	specification	specification	NOUN
istl-2566	433	3	:	:	PUNCT
istl-2566	433	4	pc	pc	NOUN
istl-2566	433	5	-	-	NOUN
istl-2566	433	6	stereogroup	stereogroup	NOUN
istl-2566	434	1	[	[	X
istl-2566	434	2	internet	internet	NOUN
istl-2566	434	3	]	]	PUNCT
istl-2566	434	4	.	.	PUNCT
istl-2566	435	1	[	[	X
istl-2566	435	2	accessed	access	VERB
istl-2566	435	3	2020	2020	NUM
istl-2566	435	4	jul	jul	NOUN
istl-2566	435	5	2	2	NUM
istl-2566	435	6	]	]	PUNCT
istl-2566	435	7	.	.	PUNCT
istl-2566	436	1	available	available	ADJ
istl-2566	436	2	from	from	ADP
istl-2566	436	3	https://www.ncbi.nlm.nih.gov/ieb/toolbox/cpp_doc/asn_spec/pc-stereogroup.html	https://www.ncbi.nlm.nih.gov/ieb/toolbox/cpp_doc/asn_spec/pc-stereogroup.html	PROPN
istl-2566	436	4	.	.	PUNCT
istl-2566	437	1	national	national	ADJ
istl-2566	437	2	center	center	NOUN
istl-2566	437	3	for	for	ADP
istl-2566	437	4	biotechnology	biotechnology	NOUN
istl-2566	437	5	information	information	NOUN
istl-2566	437	6	.	.	PUNCT
istl-2566	438	1	[	[	X
istl-2566	438	2	date	date	NOUN
istl-2566	438	3	unknown	unknown	NOUN
istl-2566	438	4	-	-	PUNCT
istl-2566	438	5	b	b	NOUN
istl-2566	438	6	]	]	PUNCT
istl-2566	438	7	.	.	PUNCT
istl-2566	439	1	pubchem	pubchem	PROPN
istl-2566	439	2	substance	substance	NOUN
istl-2566	439	3	tags	tag	NOUN
istl-2566	439	4	[	[	X
istl-2566	439	5	internet	internet	NOUN
istl-2566	439	6	]	]	PUNCT
istl-2566	439	7	.	.	PUNCT
istl-2566	440	1	[	[	X
istl-2566	440	2	accessed	access	VERB
istl-2566	440	3	2020	2020	NUM
istl-2566	440	4	may	may	AUX
istl-2566	440	5	18	18	NUM
istl-2566	440	6	]	]	PUNCT
istl-2566	440	7	.	.	PUNCT
istl-2566	441	1	available	available	ADJ
istl-2566	441	2	from	from	ADP
istl-2566	441	3	https://pubchem.ncbi.nlm.nih.gov/upload/html/tags_substance.html	https://pubchem.ncbi.nlm.nih.gov/upload/html/tags_substance.html	PROPN
istl-2566	441	4	.	.	PUNCT
istl-2566	442	1	nguyen	nguyen	PROPN
istl-2566	442	2	,	,	PUNCT
istl-2566	442	3	a.	a.	PROPN
istl-2566	442	4	,	,	PUNCT
istl-2566	442	5	huang	huang	PROPN
istl-2566	442	6	,	,	PUNCT
istl-2566	442	7	y	y	PROPN
istl-2566	442	8	-	-	PUNCT
istl-2566	442	9	c.	c.	PROPN
istl-2566	442	10	,	,	PUNCT
istl-2566	442	11	tremouilhac	tremouilhac	PROPN
istl-2566	442	12	,	,	PUNCT
istl-2566	442	13	p.	p.	PROPN
istl-2566	442	14	,	,	PUNCT
istl-2566	442	15	jung	jung	PROPN
istl-2566	442	16	,	,	PUNCT
istl-2566	442	17	n.	n.	PROPN
istl-2566	442	18	&	&	CCONJ
istl-2566	442	19	bräse	bräse	PROPN
istl-2566	442	20	,	,	PUNCT
istl-2566	442	21	s.	s.	PROPN
istl-2566	442	22	2019	2019	NUM
istl-2566	442	23	.	.	PUNCT
istl-2566	443	1	chemscanner	chemscanner	NOUN
istl-2566	443	2	:	:	PUNCT
istl-2566	443	3	extraction	extraction	NOUN
istl-2566	443	4	and	and	CCONJ
istl-2566	443	5	re	re	NOUN
istl-2566	443	6	-	-	NOUN
istl-2566	443	7	use(ability	use(ability	NOUN
istl-2566	443	8	)	)	PUNCT
istl-2566	443	9	of	of	ADP
istl-2566	443	10	chemical	chemical	ADJ
istl-2566	443	11	information	information	NOUN
istl-2566	443	12	from	from	ADP
istl-2566	443	13	common	common	ADJ
istl-2566	443	14	scientific	scientific	ADJ
istl-2566	443	15	documents	document	NOUN
istl-2566	443	16	containing	contain	VERB
istl-2566	443	17	chemdraw	chemdraw	NOUN
istl-2566	443	18	files	file	NOUN
istl-2566	443	19	.	.	PUNCT
istl-2566	444	1	journal	journal	PROPN
istl-2566	444	2	of	of	ADP
istl-2566	444	3	cheminformatics	cheminformatics	PROPN
istl-2566	444	4	11:77	11:77	NUM
istl-2566	444	5	.	.	PUNCT
istl-2566	445	1	doi:10.1186	doi:10.1186	PROPN
istl-2566	445	2	/	/	SYM
istl-2566	445	3	s13321	s13321	PROPN
istl-2566	445	4	-	-	PUNCT
istl-2566	445	5	019	019	NUM
istl-2566	445	6	-	-	PUNCT
istl-2566	445	7	0400	0400	NUM
istl-2566	445	8	-	-	PUNCT
istl-2566	445	9	5	5	NUM
istl-2566	445	10	.	.	PUNCT
istl-2566	445	11	o’boyle	o’boyle	NOUN
istl-2566	445	12	,	,	PUNCT
istl-2566	445	13	n.m	n.m	PROPN
istl-2566	445	14	.	.	PROPN
istl-2566	445	15	,	,	PUNCT
istl-2566	445	16	mayfield	mayfield	PROPN
istl-2566	445	17	,	,	PUNCT
istl-2566	445	18	j.w	j.w	PROPN
istl-2566	445	19	.	.	PROPN
istl-2566	445	20	&	&	CCONJ
istl-2566	445	21	sayle	sayle	PROPN
istl-2566	445	22	,	,	PUNCT
istl-2566	445	23	r.a	r.a	PROPN
istl-2566	445	24	.	.	PROPN
istl-2566	445	25	2018	2018	NUM
istl-2566	445	26	.	.	PUNCT
istl-2566	446	1	can	can	AUX
istl-2566	446	2	we	we	PRON
istl-2566	446	3	agree	agree	VERB
istl-2566	446	4	on	on	ADP
istl-2566	446	5	the	the	DET
istl-2566	446	6	structure	structure	NOUN
istl-2566	446	7	represented	represent	VERB
istl-2566	446	8	by	by	ADP
istl-2566	446	9	a	a	DET
istl-2566	446	10	smiles	smile	NOUN
istl-2566	446	11	string	string	NOUN
istl-2566	446	12	?	?	PUNCT
istl-2566	447	1	a	a	DET
istl-2566	447	2	benchmark	benchmark	ADJ
istl-2566	447	3	dataset	dataset	NOUN
istl-2566	447	4	[	[	X
istl-2566	447	5	internet	internet	NOUN
istl-2566	447	6	]	]	PUNCT
istl-2566	447	7	.	.	PUNCT
istl-2566	448	1	available	available	ADJ
istl-2566	448	2	from	from	ADP
istl-2566	448	3	https://www.nextmovesoftware.com/products/smilesbenchmark_iccs_may2018.pdf	https://www.nextmovesoftware.com/products/smilesbenchmark_iccs_may2018.pdf	PROPN
istl-2566	448	4	.	.	PUNCT
istl-2566	448	5	pence	pence	PROPN
istl-2566	448	6	,	,	PUNCT
istl-2566	448	7	h.e	h.e	PROPN
istl-2566	448	8	.	.	PROPN
istl-2566	448	9	&	&	CCONJ
istl-2566	448	10	williams	williams	PROPN
istl-2566	448	11	,	,	PUNCT
istl-2566	448	12	a.	a.	PROPN
istl-2566	448	13	2010	2010	NUM
istl-2566	448	14	.	.	PUNCT
istl-2566	449	1	chemspider	chemspider	VERB
istl-2566	449	2	:	:	PUNCT
istl-2566	449	3	an	an	DET
istl-2566	449	4	online	online	ADJ
istl-2566	449	5	chemical	chemical	NOUN
istl-2566	449	6	information	information	NOUN
istl-2566	449	7	resource	resource	NOUN
istl-2566	449	8	.	.	PUNCT
istl-2566	450	1	journal	journal	PROPN
istl-2566	450	2	of	of	ADP
istl-2566	450	3	chemical	chemical	NOUN
istl-2566	450	4	education	education	NOUN
istl-2566	450	5	87(11):1123–1124	87(11):1123–1124	PROPN
istl-2566	450	6	.	.	PUNCT
istl-2566	451	1	doi:10.1021	doi:10.1021	ADJ
istl-2566	451	2	/	/	SYM
istl-2566	451	3	ed100697w	ed100697w	NUM
istl-2566	451	4	.	.	PUNCT
istl-2566	452	1	richardson	richardson	PROPN
istl-2566	452	2	,	,	PUNCT
istl-2566	452	3	s.	s.	PROPN
istl-2566	452	4	2018	2018	NUM
istl-2566	452	5	.	.	PUNCT
istl-2566	453	1	chemspider	chemspider	VERB
istl-2566	453	2	pre	pre	ADJ
istl-2566	453	3	-	-	ADJ
istl-2566	453	4	deposition	deposition	ADJ
istl-2566	453	5	filters	filter	NOUN
istl-2566	453	6	[	[	X
istl-2566	453	7	internet	internet	NOUN
istl-2566	453	8	]	]	PUNCT
istl-2566	453	9	.	.	PUNCT
istl-2566	454	1	available	available	ADJ
istl-2566	454	2	from	from	ADP
istl-2566	454	3	https://blogs.rsc.org/chemspider/2018/09/18/chemspider-pre-deposition-filters/.	https://blogs.rsc.org/chemspider/2018/09/18/chemspider-pre-deposition-filters/.	PROPN
istl-2566	454	4	rose	rose	NOUN
istl-2566	454	5	-	-	PUNCT
istl-2566	454	6	wiles	wile	NOUN
istl-2566	454	7	,	,	PUNCT
istl-2566	454	8	l.m	l.m	PROPN
istl-2566	454	9	.	.	PROPN
istl-2566	454	10	&	&	CCONJ
istl-2566	454	11	marzabadi	marzabadi	PROPN
istl-2566	454	12	,	,	PUNCT
istl-2566	454	13	c.	c.	PROPN
istl-2566	454	14	2018	2018	NUM
istl-2566	454	15	.	.	PUNCT
istl-2566	455	1	what	what	PRON
istl-2566	455	2	do	do	AUX
istl-2566	455	3	chemists	chemist	NOUN
istl-2566	455	4	cite	cite	VERB
istl-2566	455	5	?	?	PUNCT
istl-2566	456	1	a	a	DET
istl-2566	456	2	5	5	NUM
istl-2566	456	3	-	-	PUNCT
istl-2566	456	4	year	year	NOUN
istl-2566	456	5	analysis	analysis	NOUN
istl-2566	456	6	of	of	ADP
istl-2566	456	7	references	reference	NOUN
istl-2566	456	8	cited	cite	VERB
istl-2566	456	9	in	in	ADP
istl-2566	456	10	american	american	PROPN
istl-2566	456	11	chemical	chemical	PROPN
istl-2566	456	12	society	society	PROPN
istl-2566	456	13	journal	journal	PROPN
istl-2566	456	14	articles	article	NOUN
istl-2566	456	15	.	.	PUNCT
istl-2566	457	1	science	science	NOUN
istl-2566	457	2	&	&	CCONJ
istl-2566	457	3	technology	technology	PROPN
istl-2566	457	4	libraries	librarie	VERB
istl-2566	457	5	37(3):246–273	37(3):246–273	PROPN
istl-2566	457	6	.	.	PUNCT
istl-2566	458	1	doi:10.1080/0194262x.2018.1481488	doi:10.1080/0194262x.2018.1481488	PROPN
istl-2566	458	2	.	.	PUNCT
istl-2566	459	1	roth	roth	PROPN
istl-2566	459	2	,	,	PUNCT
istl-2566	459	3	b.	b.	PROPN
istl-2566	459	4	,	,	PUNCT
istl-2566	459	5	böhmer	böhmer	PROPN
istl-2566	459	6	,	,	PUNCT
istl-2566	459	7	h	h	NOUN
istl-2566	459	8	-	-	PUNCT
istl-2566	459	9	u.	u.	PROPN
istl-2566	459	10	&	&	CCONJ
istl-2566	459	11	deplanque	deplanque	PROPN
istl-2566	459	12	,	,	PUNCT
istl-2566	459	13	r.	r.	PROPN
istl-2566	459	14	1992	1992	NUM
istl-2566	459	15	.	.	PUNCT
istl-2566	460	1	registration	registration	NOUN
istl-2566	460	2	of	of	ADP
istl-2566	460	3	substances	substance	NOUN
istl-2566	460	4	in	in	ADP
istl-2566	460	5	the	the	DET
istl-2566	460	6	gmelin	gmelin	NOUN
istl-2566	460	7	factual	factual	ADJ
istl-2566	460	8	database	database	PROPN
istl-2566	460	9	.	.	PUNCT
istl-2566	461	1	analytica	analytica	PROPN
istl-2566	461	2	chimica	chimica	PROPN
istl-2566	461	3	acta	acta	PROPN
istl-2566	461	4	265(2):301–304	265(2):301–304	NUM
istl-2566	461	5	.	.	PUNCT
istl-2566	462	1	doi:10.1016/0003	doi:10.1016/0003	PROPN
istl-2566	462	2	-	-	PUNCT
istl-2566	462	3	2670(92)85036	2670(92)85036	NUM
istl-2566	462	4	-	-	SYM
istl-2566	462	5	6	6	NUM
istl-2566	462	6	.	.	PUNCT
istl-2566	462	7	royal	royal	ADJ
istl-2566	462	8	society	society	NOUN
istl-2566	462	9	of	of	ADP
istl-2566	462	10	chemistry	chemistry	NOUN
istl-2566	462	11	.	.	PUNCT
istl-2566	463	1	2020	2020	NUM
istl-2566	463	2	.	.	PUNCT
istl-2566	464	1	chemspider	chemspider	VERB
istl-2566	464	2	data	datum	NOUN
istl-2566	464	3	source	source	NOUN
istl-2566	464	4	search	search	NOUN
istl-2566	464	5	:	:	PUNCT
istl-2566	464	6	sord	sord	NOUN
istl-2566	464	7	[	[	X
istl-2566	464	8	internet	internet	NOUN
istl-2566	464	9	]	]	PUNCT
istl-2566	464	10	.	.	PUNCT
istl-2566	465	1	[	[	X
istl-2566	465	2	cited	cite	VERB
istl-2566	465	3	2020	2020	NUM
istl-2566	465	4	may	may	AUX
istl-2566	465	5	12	12	NUM
istl-2566	465	6	]	]	PUNCT
istl-2566	465	7	.	.	PUNCT
istl-2566	466	1	available	available	ADJ
istl-2566	466	2	from	from	ADP
istl-2566	466	3	https://www.chemspider.com/search.aspx?dsn=sord	https://www.chemspider.com/search.aspx?dsn=sord	PROPN
istl-2566	466	4	.	.	PUNCT
istl-2566	467	1	scalfani	scalfani	PROPN
istl-2566	467	2	,	,	PUNCT
istl-2566	467	3	v.f	v.f	PROPN
istl-2566	467	4	.	.	PROPN
istl-2566	467	5	2017	2017	NUM
istl-2566	467	6	.	.	PUNCT
istl-2566	468	1	text	text	NOUN
istl-2566	468	2	analysis	analysis	NOUN
istl-2566	468	3	of	of	ADP
istl-2566	468	4	chemistry	chemistry	NOUN
istl-2566	468	5	thesis	thesis	NOUN
istl-2566	468	6	and	and	CCONJ
istl-2566	468	7	dissertation	dissertation	NOUN
istl-2566	468	8	titles	title	NOUN
istl-2566	468	9	.	.	PUNCT
istl-2566	469	1	issues	issue	NOUN
istl-2566	469	2	in	in	ADP
istl-2566	469	3	science	science	NOUN
istl-2566	469	4	and	and	CCONJ
istl-2566	469	5	technology	technology	NOUN
istl-2566	469	6	librarianship	librarianship	NOUN
istl-2566	469	7	86	86	NUM
istl-2566	469	8	.	.	PUNCT
istl-2566	470	1	doi:10.5062	doi:10.5062	PROPN
istl-2566	470	2	/	/	SYM
istl-2566	470	3	f4td9vbx	f4td9vbx	NUM
istl-2566	470	4	.	.	PUNCT
istl-2566	471	1	scalfani	scalfani	PROPN
istl-2566	471	2	,	,	PUNCT
istl-2566	471	3	v.f	v.f	PROPN
istl-2566	471	4	.	.	PROPN
istl-2566	471	5	2020	2020	NUM
istl-2566	471	6	.	.	PUNCT
istl-2566	472	1	ualib_chemstructures	ualib_chemstructure	VERB
istl-2566	472	2	github	github	PROPN
istl-2566	472	3	repository	repository	PROPN
istl-2566	473	1	[	[	X
istl-2566	473	2	internet	internet	NOUN
istl-2566	473	3	]	]	PUNCT
istl-2566	473	4	.	.	PUNCT
istl-2566	474	1	available	available	ADJ
istl-2566	474	2	from	from	ADP
istl-2566	474	3	https://github.com/ualibweb/ualib_chemstructures/blob/master/readme.md	https://github.com/ualibweb/ualib_chemstructures/blob/master/readme.md	PROPN
istl-2566	474	4	.	.	PUNCT
istl-2566	475	1	scalfani	scalfani	PROPN
istl-2566	475	2	,	,	PUNCT
istl-2566	475	3	v.f	v.f	PROPN
istl-2566	475	4	.	.	PROPN
istl-2566	475	5	,	,	PUNCT
istl-2566	475	6	ralph	ralph	PROPN
istl-2566	475	7	,	,	PUNCT
istl-2566	475	8	s.c	s.c	PROPN
istl-2566	475	9	.	.	PROPN
istl-2566	475	10	,	,	PUNCT
istl-2566	475	11	alshaikh	alshaikh	PROPN
istl-2566	475	12	,	,	PUNCT
istl-2566	475	13	a.a	a.a	PROPN
istl-2566	475	14	.	.	PROPN
istl-2566	475	15	&	&	CCONJ
istl-2566	475	16	bara	bara	PROPN
istl-2566	475	17	,	,	PUNCT
istl-2566	475	18	j.e	j.e	PROPN
istl-2566	475	19	.	.	PROPN
istl-2566	475	20	2020	2020	NUM
istl-2566	475	21	.	.	PUNCT
istl-2566	476	1	class	class	NOUN
istl-2566	476	2	and	and	CCONJ
istl-2566	476	3	home	home	NOUN
istl-2566	476	4	problems	problem	NOUN
istl-2566	476	5	:	:	PUNCT
istl-2566	476	6	programmatic	programmatic	ADJ
istl-2566	476	7	compilation	compilation	NOUN
istl-2566	476	8	of	of	ADP
istl-2566	476	9	chemical	chemical	ADJ
istl-2566	476	10	data	datum	NOUN
istl-2566	476	11	and	and	CCONJ
istl-2566	476	12	literature	literature	NOUN
istl-2566	476	13	from	from	ADP
istl-2566	476	14	pubchem	pubchem	NOUN
istl-2566	476	15	using	use	VERB
istl-2566	476	16	matlab	matlab	PROPN
istl-2566	476	17	.	.	PUNCT
istl-2566	477	1	chemical	chemical	PROPN
istl-2566	477	2	engineering	engineering	NOUN
istl-2566	477	3	education	education	NOUN
istl-2566	477	4	54(4):230	54(4):230	PROPN
istl-2566	477	5	-	-	NUM
istl-2566	477	6	241	241	NUM
istl-2566	477	7	.	.	PUNCT
istl-2566	478	1	doi:10.18260/2	doi:10.18260/2	PROPN
istl-2566	478	2	-	-	PUNCT
istl-2566	478	3	1	1	NUM
istl-2566	478	4	-	-	SYM
istl-2566	478	5	370.660	370.660	NUM
istl-2566	478	6	-	-	SYM
istl-2566	478	7	115508	115508	NUM
istl-2566	478	8	.	.	PUNCT
istl-2566	479	1	swain	swain	PROPN
istl-2566	479	2	,	,	PUNCT
istl-2566	479	3	m.c	m.c	PROPN
istl-2566	479	4	.	.	PROPN
istl-2566	479	5	&	&	CCONJ
istl-2566	479	6	cole	cole	PROPN
istl-2566	479	7	,	,	PUNCT
istl-2566	479	8	j.m	j.m	PROPN
istl-2566	479	9	.	.	PROPN
istl-2566	479	10	2016	2016	NUM
istl-2566	479	11	.	.	PUNCT
istl-2566	480	1	chemdataextractor	chemdataextractor	NOUN
istl-2566	480	2	:	:	PUNCT
istl-2566	480	3	a	a	DET
istl-2566	480	4	toolkit	toolkit	NOUN
istl-2566	480	5	for	for	ADP
istl-2566	480	6	automated	automate	VERB
istl-2566	480	7	extraction	extraction	NOUN
istl-2566	480	8	of	of	ADP
istl-2566	480	9	chemical	chemical	ADJ
istl-2566	480	10	information	information	NOUN
istl-2566	480	11	from	from	ADP
istl-2566	480	12	the	the	DET
istl-2566	480	13	scientific	scientific	ADJ
istl-2566	480	14	literature	literature	NOUN
istl-2566	480	15	.	.	PUNCT
istl-2566	481	1	journal	journal	PROPN
istl-2566	481	2	of	of	ADP
istl-2566	481	3	chemical	chemical	ADJ
istl-2566	481	4	information	information	NOUN
istl-2566	481	5	and	and	CCONJ
istl-2566	481	6	modeling	model	VERB
istl-2566	481	7	56(10):1894–1904	56(10):1894–1904	PROPN
istl-2566	481	8	.	.	PUNCT
istl-2566	482	1	doi:10.1021	doi:10.1021	PROPN
istl-2566	482	2	/	/	SYM
istl-2566	482	3	acs.jcim.6b00207	acs.jcim.6b00207	NOUN
istl-2566	482	4	.	.	PUNCT
istl-2566	483	1	tomaszewski	tomaszewski	ADJ
istl-2566	483	2	,	,	PUNCT
istl-2566	483	3	r.	r.	PROPN
istl-2566	483	4	2019	2019	NUM
istl-2566	483	5	.	.	PUNCT
istl-2566	484	1	citations	citation	NOUN
istl-2566	484	2	to	to	ADP
istl-2566	484	3	chemical	chemical	NOUN
istl-2566	484	4	databases	database	NOUN
istl-2566	484	5	in	in	ADP
istl-2566	484	6	scholarly	scholarly	ADJ
istl-2566	484	7	articles	article	NOUN
istl-2566	484	8	:	:	PUNCT
istl-2566	484	9	to	to	PART
istl-2566	484	10	cite	cite	VERB
istl-2566	484	11	or	or	CCONJ
istl-2566	484	12	not	not	PART
istl-2566	484	13	to	to	PART
istl-2566	484	14	cite	cite	VERB
istl-2566	484	15	?	?	PUNCT
istl-2566	484	16	journal	journal	PROPN
istl-2566	484	17	of	of	ADP
istl-2566	484	18	documentation	documentation	NOUN
istl-2566	484	19	75(6):1317–1332	75(6):1317–1332	NUM
istl-2566	484	20	.	.	PUNCT
istl-2566	485	1	doi:10.1108	doi:10.1108	PROPN
istl-2566	485	2	/	/	SYM
istl-2566	485	3	jd-12	jd-12	NOUN
istl-2566	485	4	-	-	PUNCT
istl-2566	485	5	2018	2018	NUM
istl-2566	485	6	-	-	SYM
istl-2566	485	7	0214	0214	NUM
istl-2566	485	8	.	.	PUNCT
istl-2566	486	1	u.s	u.s	PROPN
istl-2566	486	2	.	.	PROPN
istl-2566	486	3	copyright	copyright	PROPN
istl-2566	486	4	office	office	PROPN
istl-2566	486	5	.	.	PUNCT
istl-2566	487	1	2017	2017	NUM
istl-2566	487	2	.	.	PUNCT
istl-2566	488	1	compendium	compendium	NOUN
istl-2566	488	2	of	of	ADP
istl-2566	488	3	u.s	u.s	PROPN
istl-2566	488	4	.	.	PROPN
istl-2566	488	5	copyright	copyright	PROPN
istl-2566	488	6	office	office	NOUN
istl-2566	488	7	practices	practice	NOUN
istl-2566	488	8	[	[	X
istl-2566	488	9	internet	internet	NOUN
istl-2566	488	10	]	]	PUNCT
istl-2566	488	11	.	.	PUNCT
istl-2566	489	1	3rd	3rd	ADJ
istl-2566	489	2	ed	ed	PROPN
istl-2566	489	3	.	.	PROPN
istl-2566	489	4	available	available	ADJ
istl-2566	489	5	from	from	ADP
istl-2566	489	6	https://www.copyright.gov/comp3/.	https://www.copyright.gov/comp3/.	PROPN
istl-2566	489	7	valko	valko	PROPN
istl-2566	489	8	,	,	PUNCT
istl-2566	489	9	a.t	a.t	PROPN
istl-2566	489	10	.	.	PROPN
istl-2566	489	11	&	&	CCONJ
istl-2566	489	12	johnson	johnson	PROPN
istl-2566	489	13	,	,	PUNCT
istl-2566	489	14	a.p	a.p	PROPN
istl-2566	489	15	.	.	PROPN
istl-2566	489	16	2009	2009	NUM
istl-2566	489	17	.	.	PUNCT
istl-2566	490	1	clide	clide	NOUN
istl-2566	490	2	pro	pro	ADV
istl-2566	490	3	:	:	PUNCT
istl-2566	490	4	the	the	DET
istl-2566	490	5	latest	late	ADJ
istl-2566	490	6	generation	generation	NOUN
istl-2566	490	7	of	of	ADP
istl-2566	490	8	clide	clide	NOUN
istl-2566	490	9	,	,	PUNCT
istl-2566	490	10	a	a	DET
istl-2566	490	11	tool	tool	NOUN
istl-2566	490	12	for	for	ADP
istl-2566	490	13	optical	optical	ADJ
istl-2566	490	14	chemical	chemical	NOUN
istl-2566	490	15	structure	structure	NOUN
istl-2566	490	16	recognition	recognition	NOUN
istl-2566	490	17	.	.	PUNCT
istl-2566	491	1	journal	journal	PROPN
istl-2566	491	2	of	of	ADP
istl-2566	491	3	chemical	chemical	ADJ
istl-2566	491	4	information	information	NOUN
istl-2566	491	5	and	and	CCONJ
istl-2566	491	6	modeling	model	VERB
istl-2566	491	7	49(4):780–787	49(4):780–787	PROPN
istl-2566	491	8	.	.	PUNCT
istl-2566	492	1	doi:10.1021	doi:10.1021	PROPN
istl-2566	492	2	/	/	SYM
istl-2566	492	3	ci800449	ci800449	PROPN
istl-2566	492	4	t.	t.	PROPN
istl-2566	492	5	warr	warr	PROPN
istl-2566	492	6	,	,	PUNCT
istl-2566	492	7	w.a	w.a	PROPN
istl-2566	492	8	.	.	PROPN
istl-2566	492	9	2011	2011	NUM
istl-2566	492	10	.	.	PUNCT
istl-2566	493	1	representation	representation	NOUN
istl-2566	493	2	of	of	ADP
istl-2566	493	3	chemical	chemical	ADJ
istl-2566	493	4	structures	structure	NOUN
istl-2566	493	5	.	.	PUNCT
istl-2566	494	1	wires	wire	NOUN
istl-2566	494	2	computational	computational	ADJ
istl-2566	494	3	molecular	molecular	PROPN
istl-2566	494	4	science	science	PROPN
istl-2566	494	5	1(4):557–579	1(4):557–579	PROPN
istl-2566	494	6	.	.	PUNCT
istl-2566	495	1	doi:10.1002	doi:10.1002	NOUN
istl-2566	495	2	/	/	SYM
istl-2566	495	3	wcms.36	wcms.36	NOUN
istl-2566	495	4	.	.	PUNCT
istl-2566	496	1	weininger	weininger	NOUN
istl-2566	496	2	,	,	PUNCT
istl-2566	496	3	d.	d.	PROPN
istl-2566	496	4	1988	1988	NUM
istl-2566	496	5	.	.	PUNCT
istl-2566	497	1	smiles	smile	NOUN
istl-2566	497	2	,	,	PUNCT
istl-2566	497	3	a	a	DET
istl-2566	497	4	chemical	chemical	NOUN
istl-2566	497	5	language	language	NOUN
istl-2566	497	6	and	and	CCONJ
istl-2566	497	7	information	information	NOUN
istl-2566	497	8	system	system	NOUN
istl-2566	497	9	1	1	NUM
istl-2566	497	10	.	.	PUNCT
istl-2566	497	11	introduction	introduction	NOUN
istl-2566	497	12	to	to	ADP
istl-2566	497	13	methodology	methodology	NOUN
istl-2566	497	14	and	and	CCONJ
istl-2566	497	15	encoding	encoding	NOUN
istl-2566	497	16	rules	rule	NOUN
istl-2566	497	17	.	.	PUNCT
istl-2566	498	1	journal	journal	PROPN
istl-2566	498	2	of	of	ADP
istl-2566	498	3	chemical	chemical	ADJ
istl-2566	498	4	information	information	NOUN
istl-2566	498	5	and	and	CCONJ
istl-2566	498	6	computer	computer	NOUN
istl-2566	498	7	sciences	science	NOUN
istl-2566	498	8	28(1):31–36	28(1):31–36	NUM
istl-2566	498	9	.	.	PUNCT
istl-2566	499	1	doi:10.1021	doi:10.1021	ADJ
istl-2566	499	2	/	/	SYM
istl-2566	499	3	ci00057a005	ci00057a005	PROPN
istl-2566	499	4	.	.	PUNCT
istl-2566	500	1	wife	wife	NOUN
istl-2566	500	2	,	,	PUNCT
istl-2566	500	3	d.	d.	PROPN
istl-2566	500	4	2010	2010	NUM
istl-2566	500	5	.	.	PUNCT
istl-2566	501	1	selected	select	VERB
istl-2566	501	2	organic	organic	ADJ
istl-2566	501	3	reactions	reaction	NOUN
istl-2566	501	4	database	database	NOUN
istl-2566	502	1	[	[	X
istl-2566	502	2	internet	internet	NOUN
istl-2566	502	3	]	]	PUNCT
istl-2566	502	4	.	.	PUNCT
istl-2566	503	1	available	available	ADJ
istl-2566	503	2	from	from	ADP
istl-2566	503	3	https://www.acdlabs.com/download/publ/2010/eum10_wife.pdf	https://www.acdlabs.com/download/publ/2010/eum10_wife.pdf	PROPN
istl-2566	503	4	.	.	PUNCT
istl-2566	504	1	wiley	wiley	PROPN
istl-2566	504	2	science	science	NOUN
istl-2566	504	3	solutions	solution	NOUN
istl-2566	504	4	.	.	PUNCT
istl-2566	505	1	2020	2020	NUM
istl-2566	505	2	.	.	PUNCT
istl-2566	506	1	chemwindow	chemwindow	PROPN
istl-2566	506	2	chemical	chemical	NOUN
istl-2566	506	3	structure	structure	NOUN
istl-2566	506	4	drawing	drawing	NOUN
istl-2566	506	5	software	software	NOUN
istl-2566	507	1	[	[	X
istl-2566	507	2	internet	internet	NOUN
istl-2566	507	3	]	]	PUNCT
istl-2566	507	4	.	.	PUNCT
istl-2566	508	1	available	available	ADJ
istl-2566	508	2	from	from	ADP
istl-2566	508	3	https://sciencesolutions.wiley.com/chemwindow-chemical-structure-drawing-software/.	https://sciencesolutions.wiley.com/chemwindow-chemical-structure-drawing-software/.	PROPN
istl-2566	508	4	zhang	zhang	PROPN
istl-2566	508	5	,	,	PUNCT
istl-2566	508	6	l.	l.	PROPN
istl-2566	508	7	2013	2013	NUM
istl-2566	508	8	.	.	PUNCT
istl-2566	509	1	a	a	DET
istl-2566	509	2	comparison	comparison	NOUN
istl-2566	509	3	of	of	ADP
istl-2566	509	4	the	the	DET
istl-2566	509	5	citation	citation	NOUN
istl-2566	509	6	patterns	pattern	NOUN
istl-2566	509	7	of	of	ADP
istl-2566	509	8	doctoral	doctoral	ADJ
istl-2566	509	9	students	student	NOUN
istl-2566	509	10	in	in	ADP
istl-2566	509	11	chemistry	chemistry	NOUN
istl-2566	509	12	versus	versus	ADP
istl-2566	509	13	chemical	chemical	NOUN
istl-2566	509	14	engineering	engineering	NOUN
istl-2566	509	15	at	at	ADP
istl-2566	509	16	mississippi	mississippi	PROPN
istl-2566	509	17	state	state	PROPN
istl-2566	509	18	university	university	PROPN
istl-2566	509	19	,	,	PUNCT
istl-2566	509	20	2002–2011	2002–2011	NUM
istl-2566	509	21	.	.	PUNCT
istl-2566	509	22	science	science	NOUN
istl-2566	509	23	&	&	CCONJ
istl-2566	509	24	technology	technology	PROPN
istl-2566	509	25	libraries	librarie	VERB
istl-2566	509	26	32(3):299–313	32(3):299–313	PROPN
istl-2566	509	27	.	.	PUNCT
istl-2566	510	1	doi:10.1080/0194262x.2013.791169	doi:10.1080/0194262x.2013.791169	PROPN
istl-2566	510	2	.	.	PUNCT
istl-2566	511	1	this	this	DET
istl-2566	511	2	work	work	NOUN
istl-2566	511	3	is	be	AUX
istl-2566	511	4	licensed	license	VERB
istl-2566	511	5	under	under	ADP
istl-2566	511	6	a	a	DET
istl-2566	511	7	creative	creative	ADJ
istl-2566	511	8	commons	common	NOUN
istl-2566	511	9	attribution	attribution	NOUN
istl-2566	511	10	4.0	4.0	NUM
istl-2566	511	11	international	international	ADJ
istl-2566	511	12	license	license	NOUN
istl-2566	511	13	.	.	PUNCT
istl-2566	512	1	issues	issue	NOUN
istl-2566	512	2	in	in	ADP
istl-2566	512	3	science	science	NOUN
istl-2566	512	4	and	and	CCONJ
istl-2566	512	5	technology	technology	NOUN
istl-2566	512	6	librarianship	librarianship	NOUN
istl-2566	512	7	no	no	NOUN
istl-2566	512	8	.	.	PROPN
istl-2566	512	9	97	97	NUM
istl-2566	512	10	,	,	PUNCT
istl-2566	512	11	winter	winter	NOUN
istl-2566	512	12	2021	2021	NUM
istl-2566	512	13	.	.	PUNCT
istl-2566	513	1	doi	doi	PROPN
istl-2566	513	2	:	:	PUNCT
istl-2566	513	3	10.29173	10.29173	NUM
istl-2566	513	4	/	/	SYM
istl-2566	513	5	istl2566	istl2566	PROPN