doc_id	sent_index	relation_id	relation	trigger	trigger_offset	arg_num	arg_base_np	arg_protein	arg_domain	arg_site	arg_sugar	PSource	SiteSource	NProtein	NID	SiteName	sent_text
31577193	6	81	gly	N-glycosylation	704:718	arg2	N-glycosylation site			N-glycosylation site						site	METHODS: In this article, we report a random forest method, Nglyc, to predict N-glycosylation site from protein sequence, using 315 sequence features.
31577193	5	3	gly	Nglycosylation	572:585	arg2	Nglycosylation sites			Nglycosylation sites						sites	OBJECTIVE: In this article, our motivation is to develop a computational method to predict Nglycosylation sites in eukaryotic protein sequences.
31577193	14	17	gly	N-glycosylation	1670:1684	arg2	human and mouse N-glycosylation sites			human and mouse N-glycosylation sites						sites	Applicability and success of our method was further evaluated using human and mouse N-glycosylation sites.
31577193	7	8	gly	non-glycosylation	947:963	arg2	253 non-glycosylation sites			253 non-glycosylation sites						sites	The method was trained using a dataset of 600 N-glycosylation sites and 600 non-glycosylation sites and tested on the dataset containing 295 Nglycosylation sites and 253 non-glycosylation sites.
31577193	7	24	gly	N-glycosylation	823:837	arg2	600 N-glycosylation sites			600 N-glycosylation sites						sites	The method was trained using a dataset of 600 N-glycosylation sites and 600 non-glycosylation sites and tested on the dataset containing 295 Nglycosylation sites and 253 non-glycosylation sites.
31577193	7	48	gly	non-glycosylation	853:869	arg2	600 non-glycosylation sites			600 non-glycosylation sites						sites	The method was trained using a dataset of 600 N-glycosylation sites and 600 non-glycosylation sites and tested on the dataset containing 295 Nglycosylation sites and 253 non-glycosylation sites.
31577193	7	69	gly	Nglycosylation	918:931	arg2	295 Nglycosylation sites			295 Nglycosylation sites						sites	The method was trained using a dataset of 600 N-glycosylation sites and 600 non-glycosylation sites and tested on the dataset containing 295 Nglycosylation sites and 253 non-glycosylation sites.
30903686	5	78	gly	glycoproteins	1013:1025	arg1	human glycoproteins	human glycoproteins				Fterm		glycoproteins			For N-glycosylation, a mouse-trained model performs equally well in human glycoproteins and vice versa, however, due to significant differences in O-linked sites separate models were generated.
31577193	4	80	gly	N-glycosylation	406:420	arg2	N-glycosylation sites			N-glycosylation sites						sites	Therefore, accurate prediction of N-glycosylation sites is essential to understand Nglycosylation mechanism.
21389326	4	50	part_of	Flt3	915:918	arg1	extracellular domain 3	Flt3		extracellular domain 3		PUBTATOR	Site	Flt3	2322	domain	FL induces dimerization of Flt3 via a remarkably compact binding epitope localized at the tip of extracellular domain 3 of Flt3, and it invokes a ternary complex devoid of homotypic receptor interactions.
31958346	11	71	gly	N401-glycosite	1764:1777	arg1	GluA1	GluA1		N401		PUBTATOR		GluA1	2890	N401	Taken together, we propose that the N401-glycosite of GluA1 receives a unique control of modification, and we also propose a novel N-glycosylation occupancy regulatory mechanism by Bip that might be associated with α-amino-3-hydroxy-5-methyl-4-isoxazole-propionate receptors function in the brain.
31577193	6	56	part_of	sequence	738:745	arg1	N-glycosylation site	sequence		N-glycosylation site						site	METHODS: In this article, we report a random forest method, Nglyc, to predict N-glycosylation site from protein sequence, using 315 sequence features.
30903686	2	3	gly	glycosylation	456:468	arg2	glycosylation sites			glycosylation sites						sites	However, due to the poor ionization efficiency and microheterogeneity of glycopeptides identifying glycosylation sites is a challenging task, and there is a demand for computational methods.
30903686	2	11	gly	glycopeptides	430:442	arg2	glycopeptides			glycopeptides						glycopeptides	However, due to the poor ionization efficiency and microheterogeneity of glycopeptides identifying glycosylation sites is a challenging task, and there is a demand for computational methods.
30903686	2	16	gly	microheterogeneity	408:425	arg1	glycopeptides			glycopeptides						glycopeptides	However, due to the poor ionization efficiency and microheterogeneity of glycopeptides identifying glycosylation sites is a challenging task, and there is a demand for computational methods.
31577193	2	61	gly	N-glycosylation	204:218	arg2	N-X-[S/T] sequon			N-X-[S/T] sequon						sequon	N-glycosylation predominantly occurs in N-X-[S/T] sequon where X is any amino acid other than proline.
31577193	3	45	part_of	sequons	334:340	arg1	proteins	proteins		sequons		Fterm		proteins			However, not all N-X-[S/T] sequons in proteins are glycosylated.
31958346	0	77	gly	glycosylation	15:27	arg1	α-amino-3-hydroxy-5-methyl-4-isoxazole-propionate-type glutamate receptors	α-amino-3-hydroxy-5-methyl-4-isoxazole-propionate-type glutamate receptors				Fterm		receptors			Monitoring the glycosylation of α-amino-3-hydroxy-5-methyl-4-isoxazole-propionate-type glutamate receptors using specific antibodies reveals a novel regulatory mechanism of N-glycosylation occupancy by molecular chaperones in mice.
31958346	2	22	part_of	possesses	532:540	arg1	α-amino-3-hydroxy-5-methyl-4-isoxazole-propionate type glutamate receptor AND six potential N-glycosylation sites	α-amino-3-hydroxy-5-methyl-4-isoxazole-propionate type glutamate receptor		six potential N-glycosylation sites		Fterm	Site	receptor		sites	In this study, we performed a comprehensive N-glycosylation analysis of mouse GluA1, one of the major subunits of α-amino-3-hydroxy-5-methyl-4-isoxazole-propionate type glutamate receptor, which possesses six potential N-glycosylation sites in the N-terminal domain.
30903686	3	38	gly	glycosylation	608:620	arg2	human and mouse glycosylation sites			human and mouse glycosylation sites						sites	Here, we constructed the largest dataset of human and mouse glycosylation sites to train deep learning neural networks and support vector machine classifiers to predict N-/O-linked glycosylation sites, respectively.
30903686	3	50	gly	glycosylation	729:741	arg2	N-/O-linked glycosylation sites			N-/O-linked glycosylation sites						sites	Here, we constructed the largest dataset of human and mouse glycosylation sites to train deep learning neural networks and support vector machine classifiers to predict N-/O-linked glycosylation sites, respectively.
30903686	4	22	gly	glycosylation	918:930	arg2	human and mouse glycosylation sites			human and mouse glycosylation sites						sites	RESULTS: The method, called SPRINT-Gly, achieved consistent results between ten-fold cross validation and independent test for predicting human and mouse glycosylation sites.
31958346	2	37	gly	N-glycosylation	556:570	arg2	six potential N-glycosylation sites			six potential N-glycosylation sites						sites	In this study, we performed a comprehensive N-glycosylation analysis of mouse GluA1, one of the major subunits of α-amino-3-hydroxy-5-methyl-4-isoxazole-propionate type glutamate receptor, which possesses six potential N-glycosylation sites in the N-terminal domain.
27480293	4	31	gly	N-glycosylation	595:609	arg2	the identified N-glycosylation sites			the identified N-glycosylation sites						sites	On the basis of our results, the identified N-glycosylation sites were 1891, 1241, 891, 869, and 710 and the FDR values were 3.29, 5.62, 9.54, 9.54, and 20.02%, respectively.
31577193	3	30	gly	glycosylated	358:369	arg1	not all N-X-[S/T] sequons			not all N-X-[S/T] sequons							However, not all N-X-[S/T] sequons in proteins are glycosylated.
27480293	3	26	gly	N-glycosylation	513:527	arg2	mapping N-glycosylation sites			mapping N-glycosylation sites						sites	Five enrichment methods, including IP-ZIC-HILIC, hydrazide chemistry, lectin affinity, ZIC-HILIC-FA, and TiO2 affinity were evaluated and compared in the study of mapping N-glycosylation sites in mouse brain.
27480293	6	9	gly	N-glycoproteins	987:1001	arg1	1597 N-glycoproteins	1597 N-glycoproteins				Fterm		N-glycoproteins			In this work, we identified a total of 3446 unique glycosylation sites conforming to the N-glycosylation consensus motif (N-X-T/S/C; X ≠ P) with (18)O labeling in 1597 N-glycoproteins.
27480293	6	36	gly	glycosylation	870:882	arg2	3446 unique glycosylation sites			3446 unique glycosylation sites						sites	In this work, we identified a total of 3446 unique glycosylation sites conforming to the N-glycosylation consensus motif (N-X-T/S/C; X ≠ P) with (18)O labeling in 1597 N-glycoproteins.
27480293	6	57	gly	N-glycosylation	908:922	arg2	the N-glycosylation consensus motif			the N-glycosylation consensus motif						motif	In this work, we identified a total of 3446 unique glycosylation sites conforming to the N-glycosylation consensus motif (N-X-T/S/C; X ≠ P) with (18)O labeling in 1597 N-glycoproteins.
31958346	4	46	gly	N401-glycosylation	782:799	arg2	only the N401-glycosylation site			only the N401-glycosylation site						site	In addition, only the N401-glycosylation site demonstrated incomplete N-glycosylation occupancy.
31577193	9	0	gly	N-glycosylation	1116:1130	arg2	human and mouse N-glycosylation sites			human and mouse N-glycosylation sites						sites	Further, the performance of Nglyc was evaluated using human and mouse N-glycosylation sites.
27480293	1	19	gly	N-Glycosylation	108:122	arg1	proteins	proteins				Fterm		proteins			N-Glycosylation of proteins plays a critical role in many biological pathways.
30903686	0	62	gly	N-	23:24	arg1	sites			sites						sites	SPRINT-Gly: predicting N- and O-linked glycosylation sites of human and mouse proteins by using sequence and predicted structural properties.
30903686	0	73	gly	glycosylation	39:51	arg1	human and mouse proteins	human and mouse proteins				Fterm		proteins			SPRINT-Gly: predicting N- and O-linked glycosylation sites of human and mouse proteins by using sequence and predicted structural properties.
27480293	2	44	gly	N-glycopeptides	216:230	arg2	highly heterogeneous N-glycopeptides			highly heterogeneous N-glycopeptides						N-glycopeptides	Because highly heterogeneous N-glycopeptides are present in biological sources, the enrichment procedure is a crucial step for mass spectrometry analysis.
27480293	7	10	gly	N-glycoproteins	1125:1139	arg1	the 57 novel transmembrane N-glycoproteins	the 57 novel transmembrane N-glycoproteins				Fterm		N-glycoproteins			N-glycosylation site information was used to confirm or correct the transmembrane topology of the 57 novel transmembrane N-glycoproteins.
27480293	7	58	gly	N-glycosylation	1004:1018	arg2	N-glycosylation site information			N-glycosylation site information						site	N-glycosylation site information was used to confirm or correct the transmembrane topology of the 57 novel transmembrane N-glycoproteins.