BMC Bioinformatics

Table 1 Area under ROC curves for the S. cerevisiae PPI dataset

From: An improved method for scoring protein-protein interactions using semantic similarity within the gene ontology

		IEA -			IEA+
		CC	BP	MF	CC	BP	MF
TCSS	max	0.83	0.89	0.73	0.83	0.89	0.75
	bma	0.82	0.88	0.72	0.83	0.88	0.74
Resnik	max	0.83	0.89	0.73	0.83	0.89	0.75
	bma	0.81	0.87	0.72	0.83	0.88	0.74
Lin	max	0.80	0.87	0.70	0.79	0.87	0.72
	bma	0.79	0.85	0.68	0.80	0.86	0.72
Jiang	max	0.75	0.85	0.72	0.73	0.85	0.73
	bma	0.73	0.84	0.70	0.72	0.84	0.73
Schlicker	max	0.70	0.81	0.65	0.70	0.81	0.67
	bma	0.69	0.82	0.64	0.71	0.82	0.68
SimGIC		0.73	0.75	0.64	0.73	0.76	0.68
Wang		0.74	0.83	0.72	0.76	0.82	0.73

Tests were performed separately for cellular component (CC), biological process (BP) and molecular function (MF) ontologies. Best-match average and maximum approaches were used for datasets with (IEA+) and without (IEA-) electronic annotations. The best ROC scores are in bold.

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com