id	sid	tid	token	lemma	pos
cajgh-121	1	1	whole	whole	ADJ
cajgh-121	1	2	genome	genome	NOUN
cajgh-121	1	3	sequencing	sequencing	NOUN
cajgh-121	1	4	of	of	ADP
cajgh-121	1	5	m.tuberculosis	m.tuberculosis	NOUN
cajgh-121	1	6	in	in	ADP
cajgh-121	1	7	kazakhstan	kazakhstan	PROPN
cajgh-121	1	8	:	:	PUNCT
cajgh-121	1	9	preliminary	preliminary	ADJ
cajgh-121	1	10	data	datum	NOUN
cajgh-121	1	11	new	new	ADJ
cajgh-121	1	12	articles	article	NOUN
cajgh-121	1	13	in	in	ADP
cajgh-121	1	14	this	this	DET
cajgh-121	1	15	journal	journal	NOUN
cajgh-121	1	16	are	be	AUX
cajgh-121	1	17	licensed	license	VERB
cajgh-121	1	18	under	under	ADP
cajgh-121	1	19	a	a	DET
cajgh-121	1	20	creative	creative	ADJ
cajgh-121	1	21	commons	common	NOUN
cajgh-121	1	22	attribution	attribution	NOUN
cajgh-121	1	23	3.0	3.0	NUM
cajgh-121	1	24	united	unite	VERB
cajgh-121	1	25	states	states	PROPN
cajgh-121	1	26	license	license	NOUN
cajgh-121	1	27	.	.	PUNCT
cajgh-121	2	1	this	this	DET
cajgh-121	2	2	journal	journal	NOUN
cajgh-121	2	3	is	be	AUX
cajgh-121	2	4	published	publish	VERB
cajgh-121	2	5	by	by	ADP
cajgh-121	2	6	the	the	DET
cajgh-121	2	7	university	university	NOUN
cajgh-121	2	8	library	library	NOUN
cajgh-121	2	9	system	system	NOUN
cajgh-121	2	10	of	of	ADP
cajgh-121	2	11	the	the	DET
cajgh-121	2	12	university	university	PROPN
cajgh-121	2	13	of	of	ADP
cajgh-121	2	14	pittsburgh	pittsburgh	PROPN
cajgh-121	2	15	as	as	ADP
cajgh-121	2	16	part	part	NOUN
cajgh-121	2	17	of	of	ADP
cajgh-121	2	18	its	its	PRON
cajgh-121	2	19	d	d	NOUN
cajgh-121	2	20	-	-	PUNCT
cajgh-121	2	21	scribe	scribe	VERB
cajgh-121	2	22	digital	digital	ADJ
cajgh-121	2	23	publishing	publishing	NOUN
cajgh-121	2	24	program	program	NOUN
cajgh-121	2	25	and	and	CCONJ
cajgh-121	2	26	is	be	AUX
cajgh-121	2	27	cosponsored	cosponsor	VERB
cajgh-121	2	28	by	by	ADP
cajgh-121	2	29	the	the	DET
cajgh-121	2	30	university	university	PROPN
cajgh-121	2	31	of	of	ADP
cajgh-121	2	32	pittsburgh	pittsburgh	PROPN
cajgh-121	2	33	press	press	NOUN
cajgh-121	2	34	.	.	PUNCT
cajgh-121	3	1	whole	whole	ADJ
cajgh-121	3	2	genome	genome	NOUN
cajgh-121	3	3	sequencing	sequencing	NOUN
cajgh-121	3	4	of	of	ADP
cajgh-121	3	5	m.tuberculosis	m.tuberculosis	NOUN
cajgh-121	3	6	in	in	ADP
cajgh-121	3	7	kazakhstan	kazakhstan	PROPN
cajgh-121	3	8	:	:	PUNCT
cajgh-121	3	9	preliminary	preliminary	ADJ
cajgh-121	3	10	data	data	PROPN
cajgh-121	3	11	ulykbek	ulykbek	PROPN
cajgh-121	3	12	kairov1	kairov1	PROPN
cajgh-121	3	13	,	,	PUNCT
cajgh-121	3	14	ulan	ulan	PROPN
cajgh-121	3	15	kozhamkulov1	kozhamkulov1	PROPN
cajgh-121	3	16	,	,	PUNCT
cajgh-121	3	17	saule	saule	PROPN
cajgh-121	3	18	rakhimova1	rakhimova1	NOUN
cajgh-121	3	19	,	,	PUNCT
cajgh-121	3	20	ayken	ayken	VERB
cajgh-121	3	21	askapuli1	askapuli1	NOUN
cajgh-121	3	22	,	,	PUNCT
cajgh-121	3	23	maxat	maxat	PROPN
cajgh-121	3	24	zhabagin1	zhabagin1	NOUN
cajgh-121	3	25	,	,	PUNCT
cajgh-121	3	26	venera	venera	PROPN
cajgh-121	3	27	bismilda2	bismilda2	PROPN
cajgh-121	3	28	,	,	PUNCT
cajgh-121	3	29	leyla	leyla	PROPN
cajgh-121	3	30	chingissova2	chingissova2	PROPN
cajgh-121	3	31	,	,	PUNCT
cajgh-121	3	32	zhaxybay	zhaxybay	PROPN
cajgh-121	3	33	zhumadilov1	zhumadilov1	PROPN
cajgh-121	3	34	,	,	PUNCT
cajgh-121	3	35	ainur	ainur	NOUN
cajgh-121	3	36	akilzhanova1	akilzhanova1	VERB
cajgh-121	3	37	1center	1center	NUM
cajgh-121	3	38	for	for	ADP
cajgh-121	3	39	life	life	NOUN
cajgh-121	3	40	sciences	science	NOUN
cajgh-121	3	41	,	,	PUNCT
cajgh-121	3	42	nazarbayev	nazarbayev	ADJ
cajgh-121	3	43	university	university	NOUN
cajgh-121	3	44	,	,	PUNCT
cajgh-121	3	45	astana	astana	PROPN
cajgh-121	3	46	,	,	PUNCT
cajgh-121	3	47	kazakhstan	kazakhstan	PROPN
cajgh-121	3	48	;	;	PUNCT
cajgh-121	3	49	2national	2national	NUM
cajgh-121	3	50	center	center	NOUN
cajgh-121	3	51	for	for	ADP
cajgh-121	3	52	problems	problem	NOUN
cajgh-121	3	53	of	of	ADP
cajgh-121	3	54	tuberculosis	tuberculosis	NOUN
cajgh-121	3	55	,	,	PUNCT
cajgh-121	3	56	almaty	almaty	PROPN
cajgh-121	3	57	,	,	PUNCT
cajgh-121	3	58	kazakhstan	kazakhstan	PROPN
cajgh-121	3	59	vol	vol	NOUN
cajgh-121	3	60	.	.	PROPN
cajgh-121	4	1	2	2	NUM
cajgh-121	4	2	,	,	PUNCT
cajgh-121	4	3	suppl	suppl	ADJ
cajgh-121	4	4	.	.	PUNCT
cajgh-121	5	1	(	(	PUNCT
cajgh-121	5	2	2013	2013	NUM
cajgh-121	5	3	)	)	PUNCT
cajgh-121	5	4	|	|	ADV
cajgh-121	5	5	issn	issn	VERB
cajgh-121	5	6	2166	2166	NUM
cajgh-121	5	7	-	-	SYM
cajgh-121	5	8	7403	7403	NUM
cajgh-121	5	9	(	(	PUNCT
cajgh-121	5	10	online	online	ADJ
cajgh-121	5	11	)	)	PUNCT
cajgh-121	5	12	doi	doi	NOUN
cajgh-121	5	13	10.5195	10.5195	NUM
cajgh-121	5	14	/	/	SYM
cajgh-121	5	15	cajgh.2013.121	cajgh.2013.121	NOUN
cajgh-121	5	16	|	|	NOUN
cajgh-121	5	17	http://cajgh.pitt.edu	http://cajgh.pitt.edu	VERB
cajgh-121	5	18	http://www.library.pitt.edu/	http://www.library.pitt.edu/	PROPN
cajgh-121	5	19	http://www.pitt.edu/	http://www.pitt.edu/	NOUN
cajgh-121	5	20	http://www.library.pitt.edu/articles/digpubtype/index.html	http://www.library.pitt.edu/articles/digpubtype/index.html	X
cajgh-121	6	1	http://www.upress.pitt.edu/upressindex.aspx	http://www.upress.pitt.edu/upressindex.aspx	NUM
cajgh-121	6	2	http://creativecommons.org/licenses/by/3.0/us/	http://creativecommons.org/licenses/by/3.0/us/	NOUN
cajgh-121	6	3	kairov	kairov	ADJ
cajgh-121	6	4	this	this	DET
cajgh-121	6	5	work	work	NOUN
cajgh-121	6	6	is	be	AUX
cajgh-121	6	7	licensed	license	VERB
cajgh-121	6	8	under	under	ADP
cajgh-121	6	9	a	a	DET
cajgh-121	6	10	creative	creative	ADJ
cajgh-121	6	11	commons	common	NOUN
cajgh-121	6	12	attribution	attribution	NOUN
cajgh-121	6	13	3.0	3.0	NUM
cajgh-121	6	14	united	unite	VERB
cajgh-121	6	15	states	states	PROPN
cajgh-121	6	16	license	license	NOUN
cajgh-121	6	17	.	.	PUNCT
cajgh-121	7	1	this	this	DET
cajgh-121	7	2	journal	journal	NOUN
cajgh-121	7	3	is	be	AUX
cajgh-121	7	4	published	publish	VERB
cajgh-121	7	5	by	by	ADP
cajgh-121	7	6	the	the	DET
cajgh-121	7	7	university	university	NOUN
cajgh-121	7	8	library	library	NOUN
cajgh-121	7	9	system	system	NOUN
cajgh-121	7	10	of	of	ADP
cajgh-121	7	11	the	the	DET
cajgh-121	7	12	university	university	PROPN
cajgh-121	7	13	of	of	ADP
cajgh-121	7	14	pittsburgh	pittsburgh	PROPN
cajgh-121	7	15	as	as	ADP
cajgh-121	7	16	part	part	NOUN
cajgh-121	7	17	of	of	ADP
cajgh-121	7	18	its	its	PRON
cajgh-121	7	19	d	d	NOUN
cajgh-121	7	20	-	-	PUNCT
cajgh-121	7	21	scribe	scribe	VERB
cajgh-121	7	22	digital	digital	ADJ
cajgh-121	7	23	publishing	publishing	NOUN
cajgh-121	7	24	program	program	NOUN
cajgh-121	7	25	and	and	CCONJ
cajgh-121	7	26	is	be	AUX
cajgh-121	7	27	cosponsored	cosponsor	VERB
cajgh-121	7	28	by	by	ADP
cajgh-121	7	29	the	the	DET
cajgh-121	7	30	university	university	PROPN
cajgh-121	7	31	of	of	ADP
cajgh-121	7	32	pittsburgh	pittsburgh	PROPN
cajgh-121	7	33	press	press	NOUN
cajgh-121	7	34	.	.	PUNCT
cajgh-121	8	1	central	central	ADJ
cajgh-121	8	2	asian	asian	ADJ
cajgh-121	8	3	journal	journal	NOUN
cajgh-121	8	4	of	of	ADP
cajgh-121	8	5	global	global	ADJ
cajgh-121	8	6	health	health	NOUN
cajgh-121	8	7	volume	volume	NOUN
cajgh-121	8	8	2	2	NUM
cajgh-121	8	9	,	,	PUNCT
cajgh-121	8	10	suppl	suppl	ADJ
cajgh-121	8	11	.	.	PUNCT
cajgh-121	9	1	(	(	PUNCT
cajgh-121	9	2	2013	2013	NUM
cajgh-121	9	3	)	)	PUNCT
cajgh-121	9	4	|	|	ADV
cajgh-121	9	5	issn	issn	VERB
cajgh-121	9	6	2166	2166	NUM
cajgh-121	9	7	-	-	SYM
cajgh-121	9	8	7403	7403	NUM
cajgh-121	9	9	(	(	PUNCT
cajgh-121	9	10	online	online	ADJ
cajgh-121	9	11	)	)	PUNCT
cajgh-121	9	12	|	|	ADV
cajgh-121	9	13	doi	doi	X
cajgh-121	9	14	10.5195	10.5195	NUM
cajgh-121	9	15	/	/	SYM
cajgh-121	9	16	cajgh.2013.121	cajgh.2013.121	NOUN
cajgh-121	9	17	|	|	NOUN
cajgh-121	9	18	http://cajgh.pitt.edu	http://cajgh.pitt.edu	NOUN
cajgh-121	9	19	abstract	abstract	ADJ
cajgh-121	9	20	background	background	NOUN
cajgh-121	9	21	:	:	PUNCT
cajgh-121	9	22	tuberculosis	tuberculosis	NOUN
cajgh-121	9	23	is	be	AUX
cajgh-121	9	24	a	a	DET
cajgh-121	9	25	major	major	ADJ
cajgh-121	9	26	public	public	ADJ
cajgh-121	9	27	health	health	NOUN
cajgh-121	9	28	problem	problem	NOUN
cajgh-121	9	29	which	which	PRON
cajgh-121	9	30	infects	infect	VERB
cajgh-121	9	31	one	one	NUM
cajgh-121	9	32	third	third	NOUN
cajgh-121	9	33	of	of	ADP
cajgh-121	9	34	the	the	DET
cajgh-121	9	35	world	world	NOUN
cajgh-121	9	36	’s	’s	PART
cajgh-121	9	37	population	population	NOUN
cajgh-121	9	38	,	,	PUNCT
cajgh-121	9	39	resulting	result	VERB
cajgh-121	9	40	in	in	ADP
cajgh-121	9	41	more	more	ADJ
cajgh-121	9	42	than	than	ADP
cajgh-121	9	43	two	two	NUM
cajgh-121	9	44	million	million	NUM
cajgh-121	9	45	deaths	death	NOUN
cajgh-121	9	46	every	every	DET
cajgh-121	9	47	year	year	NOUN
cajgh-121	9	48	.	.	PUNCT
cajgh-121	10	1	the	the	DET
cajgh-121	10	2	emergence	emergence	NOUN
cajgh-121	10	3	of	of	ADP
cajgh-121	10	4	whole	whole	ADJ
cajgh-121	10	5	genome	genome	NOUN
cajgh-121	10	6	sequencing	sequence	VERB
cajgh-121	10	7	(	(	PUNCT
cajgh-121	10	8	wgs	wgs	NOUN
cajgh-121	10	9	)	)	PUNCT
cajgh-121	10	10	technologies	technology	NOUN
cajgh-121	10	11	as	as	ADP
cajgh-121	10	12	a	a	DET
cajgh-121	10	13	primary	primary	ADJ
cajgh-121	10	14	research	research	NOUN
cajgh-121	10	15	tool	tool	NOUN
cajgh-121	10	16	has	have	AUX
cajgh-121	10	17	allowed	allow	VERB
cajgh-121	10	18	for	for	ADP
cajgh-121	10	19	the	the	DET
cajgh-121	10	20	detection	detection	NOUN
cajgh-121	10	21	of	of	ADP
cajgh-121	10	22	genetic	genetic	ADJ
cajgh-121	10	23	diversity	diversity	NOUN
cajgh-121	10	24	in	in	ADP
cajgh-121	10	25	mycobacterium	mycobacterium	NOUN
cajgh-121	10	26	tuberculosis	tuberculosis	NOUN
cajgh-121	10	27	(	(	PUNCT
cajgh-121	10	28	mtb	mtb	NOUN
cajgh-121	10	29	)	)	PUNCT
cajgh-121	10	30	with	with	ADP
cajgh-121	10	31	unprecedented	unprecedented	ADJ
cajgh-121	10	32	resolution	resolution	NOUN
cajgh-121	10	33	.	.	PUNCT
cajgh-121	11	1	wgs	wgs	PROPN
cajgh-121	11	2	has	have	AUX
cajgh-121	11	3	been	be	AUX
cajgh-121	11	4	used	use	VERB
cajgh-121	11	5	to	to	PART
cajgh-121	11	6	address	address	VERB
cajgh-121	11	7	a	a	DET
cajgh-121	11	8	broad	broad	ADJ
cajgh-121	11	9	range	range	NOUN
cajgh-121	11	10	of	of	ADP
cajgh-121	11	11	topics	topic	NOUN
cajgh-121	11	12	,	,	PUNCT
cajgh-121	11	13	including	include	VERB
cajgh-121	11	14	the	the	DET
cajgh-121	11	15	dynamics	dynamic	NOUN
cajgh-121	11	16	of	of	ADP
cajgh-121	11	17	evolution	evolution	NOUN
cajgh-121	11	18	,	,	PUNCT
cajgh-121	11	19	transmission	transmission	NOUN
cajgh-121	11	20	,	,	PUNCT
cajgh-121	11	21	and	and	CCONJ
cajgh-121	11	22	treatment	treatment	NOUN
cajgh-121	11	23	.	.	PUNCT
cajgh-121	12	1	to	to	ADP
cajgh-121	12	2	our	our	PRON
cajgh-121	12	3	knowledge	knowledge	NOUN
cajgh-121	12	4	,	,	PUNCT
cajgh-121	12	5	studies	study	NOUN
cajgh-121	12	6	involving	involve	VERB
cajgh-121	12	7	wgs	wgs	NOUN
cajgh-121	12	8	of	of	ADP
cajgh-121	12	9	kazakhstani	kazakhstani	NOUN
cajgh-121	12	10	strains	strain	NOUN
cajgh-121	12	11	of	of	ADP
cajgh-121	12	12	m.	m.	NOUN
cajgh-121	12	13	tuberculosis	tuberculosis	NOUN
cajgh-121	12	14	have	have	AUX
cajgh-121	12	15	not	not	PART
cajgh-121	12	16	yet	yet	ADV
cajgh-121	12	17	been	be	AUX
cajgh-121	12	18	performed	perform	VERB
cajgh-121	12	19	.	.	PUNCT
cajgh-121	13	1	aim	aim	VERB
cajgh-121	13	2	:	:	PUNCT
cajgh-121	13	3	to	to	PART
cajgh-121	13	4	perform	perform	VERB
cajgh-121	13	5	whole	whole	ADJ
cajgh-121	13	6	genome	genome	NOUN
cajgh-121	13	7	sequencing	sequencing	NOUN
cajgh-121	13	8	of	of	ADP
cajgh-121	13	9	m.	m.	NOUN
cajgh-121	13	10	tuberculosis	tuberculosis	NOUN
cajgh-121	13	11	strains	strain	NOUN
cajgh-121	13	12	isolated	isolate	VERB
cajgh-121	13	13	in	in	ADP
cajgh-121	13	14	kazakhstan	kazakhstan	PROPN
cajgh-121	13	15	and	and	CCONJ
cajgh-121	13	16	analyze	analyze	VERB
cajgh-121	13	17	sequence	sequence	NOUN
cajgh-121	13	18	data	datum	NOUN
cajgh-121	13	19	(	(	PUNCT
cajgh-121	13	20	first	first	ADJ
cajgh-121	13	21	experience	experience	NOUN
cajgh-121	13	22	and	and	CCONJ
cajgh-121	13	23	preliminary	preliminary	ADJ
cajgh-121	13	24	data	datum	NOUN
cajgh-121	13	25	)	)	PUNCT
cajgh-121	13	26	.	.	PUNCT
cajgh-121	14	1	results	result	NOUN
cajgh-121	14	2	:	:	PUNCT
cajgh-121	14	3	in	in	ADP
cajgh-121	14	4	the	the	DET
cajgh-121	14	5	present	present	ADJ
cajgh-121	14	6	report	report	NOUN
cajgh-121	14	7	,	,	PUNCT
cajgh-121	14	8	we	we	PRON
cajgh-121	14	9	announce	announce	VERB
cajgh-121	14	10	the	the	DET
cajgh-121	14	11	whole	whole	ADJ
cajgh-121	14	12	-	-	PUNCT
cajgh-121	14	13	genome	genome	NOUN
cajgh-121	14	14	sequences	sequence	NOUN
cajgh-121	14	15	of	of	ADP
cajgh-121	14	16	the	the	DET
cajgh-121	14	17	two	two	NUM
cajgh-121	14	18	clinical	clinical	ADJ
cajgh-121	14	19	isolates	isolate	NOUN
cajgh-121	14	20	of	of	ADP
cajgh-121	14	21	mycobacterium	mycobacterium	NOUN
cajgh-121	14	22	tuberculosis	tuberculosis	NOUN
cajgh-121	14	23	,	,	PUNCT
cajgh-121	14	24	mtb-489	mtb-489	NOUN
cajgh-121	14	25	and	and	CCONJ
cajgh-121	14	26	mtb-476	mtb-476	NOUN
cajgh-121	14	27	,	,	PUNCT
cajgh-121	14	28	isolated	isolate	VERB
cajgh-121	14	29	from	from	ADP
cajgh-121	14	30	the	the	DET
cajgh-121	14	31	almaty	almaty	PROPN
cajgh-121	14	32	region	region	NOUN
cajgh-121	14	33	.	.	PUNCT
cajgh-121	15	1	these	these	DET
cajgh-121	15	2	strains	strain	NOUN
cajgh-121	15	3	were	be	AUX
cajgh-121	15	4	part	part	NOUN
cajgh-121	15	5	of	of	ADP
cajgh-121	15	6	a	a	DET
cajgh-121	15	7	repository	repository	NOUN
cajgh-121	15	8	that	that	PRON
cajgh-121	15	9	was	be	AUX
cajgh-121	15	10	created	create	VERB
cajgh-121	15	11	during	during	ADP
cajgh-121	15	12	our	our	PRON
cajgh-121	15	13	project	project	NOUN
cajgh-121	15	14	“	"	PUNCT
cajgh-121	15	15	creating	create	VERB
cajgh-121	15	16	prerequisites	prerequisite	NOUN
cajgh-121	15	17	of	of	ADP
cajgh-121	15	18	personalized	personalized	ADJ
cajgh-121	15	19	approach	approach	NOUN
cajgh-121	15	20	in	in	ADP
cajgh-121	15	21	the	the	DET
cajgh-121	15	22	diagnosis	diagnosis	NOUN
cajgh-121	15	23	and	and	CCONJ
cajgh-121	15	24	treatment	treatment	NOUN
cajgh-121	15	25	of	of	ADP
cajgh-121	15	26	tuberculosis	tuberculosis	NOUN
cajgh-121	15	27	,	,	PUNCT
cajgh-121	15	28	based	base	VERB
cajgh-121	15	29	on	on	ADP
cajgh-121	15	30	whole	whole	ADJ
cajgh-121	15	31	genome	genome	NOUN
cajgh-121	15	32	-	-	PUNCT
cajgh-121	15	33	sequencing	sequencing	NOUN
cajgh-121	15	34	of	of	ADP
cajgh-121	15	35	m.	m.	NOUN
cajgh-121	15	36	tuberculosis	tuberculosis	NOUN
cajgh-121	15	37	”	"	PUNCT
cajgh-121	15	38	.	.	PUNCT
cajgh-121	16	1	two	two	NUM
cajgh-121	16	2	strains	strain	NOUN
cajgh-121	16	3	were	be	AUX
cajgh-121	16	4	isolated	isolate	VERB
cajgh-121	16	5	from	from	ADP
cajgh-121	16	6	sputum	sputum	NOUN
cajgh-121	16	7	samples	sample	NOUN
cajgh-121	16	8	of	of	ADP
cajgh-121	16	9	patients	patient	NOUN
cajgh-121	16	10	p1	p1	NOUN
cajgh-121	16	11	and	and	CCONJ
cajgh-121	16	12	p2	p2	NOUN
cajgh-121	16	13	.	.	PUNCT
cajgh-121	17	1	phenotypically	phenotypically	ADV
cajgh-121	17	2	,	,	PUNCT
cajgh-121	17	3	two	two	NUM
cajgh-121	17	4	isolates	isolate	NOUN
cajgh-121	17	5	were	be	AUX
cajgh-121	17	6	drug	drug	NOUN
cajgh-121	17	7	-	-	PUNCT
cajgh-121	17	8	susceptible	susceptible	ADJ
cajgh-121	17	9	m.	m.	NOUN
cajgh-121	17	10	tuberculosis	tuberculosis	NOUN
cajgh-121	17	11	.	.	PUNCT
cajgh-121	18	1	sequence	sequence	NOUN
cajgh-121	18	2	data	datum	NOUN
cajgh-121	18	3	was	be	AUX
cajgh-121	18	4	compared	compare	VERB
cajgh-121	18	5	with	with	ADP
cajgh-121	18	6	the	the	DET
cajgh-121	18	7	publicly	publicly	ADV
cajgh-121	18	8	available	available	ADJ
cajgh-121	18	9	data	datum	NOUN
cajgh-121	18	10	on	on	ADP
cajgh-121	18	11	m.	m.	NOUN
cajgh-121	18	12	tuberculosis	tuberculosis	NOUN
cajgh-121	18	13	laboratory	laboratory	NOUN
cajgh-121	18	14	strain	strain	NOUN
cajgh-121	18	15	h37rv	h37rv	PROPN
cajgh-121	18	16	and	and	CCONJ
cajgh-121	18	17	others	other	NOUN
cajgh-121	18	18	.	.	PUNCT
cajgh-121	19	1	the	the	DET
cajgh-121	19	2	sequencing	sequencing	NOUN
cajgh-121	19	3	of	of	ADP
cajgh-121	19	4	the	the	DET
cajgh-121	19	5	strains	strain	NOUN
cajgh-121	19	6	was	be	AUX
cajgh-121	19	7	performed	perform	VERB
cajgh-121	19	8	on	on	ADP
cajgh-121	19	9	a	a	DET
cajgh-121	19	10	roche	roche	NOUN
cajgh-121	19	11	454	454	NUM
cajgh-121	19	12	gs	gs	INTJ
cajgh-121	19	13	flx+	flx+	ADJ
cajgh-121	19	14	next	next	ADJ
cajgh-121	19	15	-	-	PUNCT
cajgh-121	19	16	generation	generation	NOUN
cajgh-121	19	17	sequencing	sequence	VERB
cajgh-121	19	18	platform	platform	NOUN
cajgh-121	19	19	using	use	VERB
cajgh-121	19	20	a	a	DET
cajgh-121	19	21	standard	standard	ADJ
cajgh-121	19	22	protocol	protocol	NOUN
cajgh-121	19	23	for	for	ADP
cajgh-121	19	24	a	a	DET
cajgh-121	19	25	shotgun	shotgun	NOUN
cajgh-121	19	26	genome	genome	NOUN
cajgh-121	19	27	library	library	NOUN
cajgh-121	19	28	.	.	PUNCT
cajgh-121	20	1	the	the	DET
cajgh-121	20	2	whole	whole	ADJ
cajgh-121	20	3	genome	genome	NOUN
cajgh-121	20	4	sequencing	sequencing	NOUN
cajgh-121	20	5	was	be	AUX
cajgh-121	20	6	performed	perform	VERB
cajgh-121	20	7	for	for	ADP
cajgh-121	20	8	two	two	NUM
cajgh-121	20	9	m.tuberculosis	m.tuberculosis	NOUN
cajgh-121	20	10	isolates	isolate	VERB
cajgh-121	20	11	mtb-476	mtb-476	NOUN
cajgh-121	20	12	and	and	CCONJ
cajgh-121	20	13	mtb-489	mtb-489	NOUN
cajgh-121	20	14	.	.	PUNCT
cajgh-121	21	1	96	96	NUM
cajgh-121	21	2	m	m	PROPN
cajgh-121	21	3	bp	bp	PROPN
cajgh-121	21	4	with	with	ADP
cajgh-121	21	5	an	an	DET
cajgh-121	21	6	average	average	ADJ
cajgh-121	21	7	read	read	NOUN
cajgh-121	21	8	length	length	NOUN
cajgh-121	21	9	of	of	ADP
cajgh-121	21	10	520	520	NUM
cajgh-121	21	11	bp	bp	NOUN
cajgh-121	21	12	,	,	PUNCT
cajgh-121	21	13	approximately	approximately	ADV
cajgh-121	21	14	21.8x	21.8x	NUM
cajgh-121	21	15	coverage	coverage	NOUN
cajgh-121	21	16	and	and	CCONJ
cajgh-121	21	17	104.2	104.2	NUM
cajgh-121	21	18	m	m	NOUN
cajgh-121	21	19	bp	bp	PROPN
cajgh-121	21	20	with	with	ADP
cajgh-121	21	21	an	an	DET
cajgh-121	21	22	average	average	ADJ
cajgh-121	21	23	read	read	NOUN
cajgh-121	21	24	length	length	NOUN
cajgh-121	21	25	of	of	ADP
cajgh-121	21	26	589	589	NUM
cajgh-121	21	27	bp	bp	NOUN
cajgh-121	21	28	and	and	CCONJ
cajgh-121	21	29	approximately	approximately	ADV
cajgh-121	21	30	23.7x	23.7x	NUM
cajgh-121	21	31	coverage	coverage	NOUN
cajgh-121	21	32	were	be	AUX
cajgh-121	21	33	generated	generate	VERB
cajgh-121	21	34	for	for	ADP
cajgh-121	21	35	the	the	DET
cajgh-121	21	36	mtb-476	mtb-476	NOUN
cajgh-121	21	37	and	and	CCONJ
cajgh-121	21	38	mtb-489	mtb-489	NOUN
cajgh-121	21	39	,	,	PUNCT
cajgh-121	21	40	respectively	respectively	ADV
cajgh-121	21	41	.	.	PUNCT
cajgh-121	22	1	the	the	DET
cajgh-121	22	2	genome	genome	NOUN
cajgh-121	22	3	of	of	ADP
cajgh-121	22	4	mtb-476	mtb-476	NOUN
cajgh-121	22	5	consists	consist	NOUN
cajgh-121	22	6	of	of	ADP
cajgh-121	22	7	257	257	NUM
cajgh-121	22	8	contigs	contig	NOUN
cajgh-121	22	9	,	,	PUNCT
cajgh-121	22	10	4204	4204	NUM
cajgh-121	22	11	cds	cd	NOUN
cajgh-121	22	12	,	,	PUNCT
cajgh-121	22	13	46	46	NUM
cajgh-121	22	14	trnas	trnas	NOUN
cajgh-121	22	15	and	and	CCONJ
cajgh-121	22	16	3	3	NUM
cajgh-121	22	17	rrnas	rrna	NOUN
cajgh-121	22	18	.	.	PUNCT
cajgh-121	23	1	mtb-489	mtb-489	PROPN
cajgh-121	23	2	has	have	VERB
cajgh-121	23	3	187	187	NUM
cajgh-121	23	4	contigs	contig	NOUN
cajgh-121	23	5	,	,	PUNCT
cajgh-121	23	6	4183	4183	NUM
cajgh-121	23	7	cds	cd	NOUN
cajgh-121	23	8	,	,	PUNCT
cajgh-121	23	9	45	45	NUM
cajgh-121	23	10	trnas	trnas	NOUN
cajgh-121	23	11	and	and	CCONJ
cajgh-121	23	12	3rrnas	3rrnas	NUM
cajgh-121	23	13	.	.	PUNCT
cajgh-121	24	1	conclusion	conclusion	NOUN
cajgh-121	24	2	:	:	PUNCT
cajgh-121	24	3	the	the	DET
cajgh-121	24	4	results	result	NOUN
cajgh-121	24	5	of	of	ADP
cajgh-121	24	6	genome	genome	NOUN
cajgh-121	24	7	assembling	assembling	NOUN
cajgh-121	24	8	have	have	AUX
cajgh-121	24	9	been	be	AUX
cajgh-121	24	10	submitted	submit	VERB
cajgh-121	24	11	into	into	ADP
cajgh-121	24	12	ncbi	ncbi	PROPN
cajgh-121	24	13	genbank	genbank	PROPN
cajgh-121	24	14	and	and	CCONJ
cajgh-121	24	15	are	be	AUX
cajgh-121	24	16	available	available	ADJ
cajgh-121	24	17	for	for	ADP
cajgh-121	24	18	public	public	ADJ
cajgh-121	24	19	access	access	NOUN
cajgh-121	24	20	under	under	ADP
cajgh-121	24	21	the	the	DET
cajgh-121	24	22	accession	accession	NOUN
cajgh-121	24	23	numbers	number	NOUN
cajgh-121	24	24	azba00000000	azba00000000	PROPN
cajgh-121	24	25	and	and	CCONJ
cajgh-121	24	26	azaz00000000	azaz00000000	PROPN
cajgh-121	24	27	.	.	PUNCT
cajgh-121	25	1	these	these	DET
cajgh-121	25	2	genome	genome	NOUN
cajgh-121	25	3	assemblies	assembly	NOUN
cajgh-121	25	4	can	can	AUX
cajgh-121	25	5	be	be	AUX
cajgh-121	25	6	useful	useful	ADJ
cajgh-121	25	7	for	for	ADP
cajgh-121	25	8	comparative	comparative	ADJ
cajgh-121	25	9	genome	genome	NOUN
cajgh-121	25	10	analysis	analysis	NOUN
cajgh-121	25	11	and	and	CCONJ
cajgh-121	25	12	for	for	ADP
cajgh-121	25	13	identification	identification	NOUN
cajgh-121	25	14	of	of	ADP
cajgh-121	25	15	novel	novel	ADJ
cajgh-121	25	16	snps	snps	NOUN
cajgh-121	25	17	and	and	CCONJ
cajgh-121	25	18	gene	gene	NOUN
cajgh-121	25	19	variants	variant	NOUN
cajgh-121	25	20	in	in	ADP
cajgh-121	25	21	genomes	genome	NOUN
cajgh-121	25	22	of	of	ADP
cajgh-121	25	23	m.tuberculosis	m.tuberculosis	NOUN
cajgh-121	25	24	.	.	PUNCT
cajgh-121	26	1	keywords	keyword	NOUN
cajgh-121	26	2	:	:	PUNCT
cajgh-121	26	3	tuberculosis	tuberculosis	NOUN
cajgh-121	26	4	,	,	PUNCT
cajgh-121	26	5	genome	genome	NOUN
cajgh-121	26	6	sequencing	sequencing	NOUN
cajgh-121	26	7	,	,	PUNCT
cajgh-121	26	8	kazakhstan	kazakhstan	PROPN
cajgh-121	26	9	http://www.library.pitt.edu/	http://www.library.pitt.edu/	PROPN
cajgh-121	26	10	http://www.pitt.edu/	http://www.pitt.edu/	NOUN
cajgh-121	26	11	http://www.library.pitt.edu/articles/digpubtype/index.html	http://www.library.pitt.edu/articles/digpubtype/index.html	X
cajgh-121	26	12	http://www.upress.pitt.edu/upressindex.aspx	http://www.upress.pitt.edu/upressindex.aspx	X
