Incorporating significant amino acid pairs to identify O-linked glycosylation sites on transmembrane proteins and non-transmembrane proteins

Table 1 The statistics of experimentally verified O-linked glycosylation sites on transmembrane (TM) proteins and non-transmembrane (non-TM) proteins.

Database	Original data (UniProt release 15.0)		Independent test data (HPRD release 8.0)
	TM proteins	non-TM proteins	TM proteins	non-TM proteins
Number of O-linked glycosylated proteins	40	199	9	13
Number of O-linked glycosylated serine	87	281	7	10
Number of O-linked glycosylated threonine	115	356	7	34
Number of non-glycosylated serine and threonine	2,450	14,234	1,238	662

The experimental O-linked glycosylated proteins extracted from UniProt release 15.0 are regarded as the original data. To evaluate the real performance of the constructed models, the experimental O-linked glycosylated proteins collected from HPRD release 8.0 are used for independent testing.

ISSN: 1471-2105