A random set scoring model for prioritization of disease candidate genes using protein complexes and data-mining of GeneRIF, OMIM and PubMed records

Table 2 Comparison with other network-based approaches

Testing sets	Evaluation metrics	Random-set scoring model		Bayesian/regression method
		*PPI evidence incl. co-mention	PPI evidence excl. co-mention
Bayesian	Recall	0.55	0.43	0.21
	Precision	0.58	0.56	0.45
Regression	Recall	0.57	0.43	0.30 − 0.55
	Precision	0.52	0.47	0.73 − 0.55

ISSN: 1471-2105