The performance of the test set of GPCRs and kinases using different methods by 10 simulation times test of 10-fold cross validation.

All performances were evaluated based on top 5 predicted lists. NBI, network-based inference; NWNBI, node weighted network-based inference; EWNBI, edge weighted network-based inference; DBSI-T, drug-based similarity inference with Tanimoto similarity score; DBSI-C, DBSI with Cosine similarity score; DBSI-F, DBSI with Forbes similarity score; DBSI-R, DBSI with Russell-rao similarity score; TBSI, target-based similarity inference; R, recall; ER, recall enhancement; AUC, the area under the receiver operating characteristic curve; Ci (Pa, Pb, …, Pm) represents the prioritization of new targets for a given chemical; Pj (Ca, Cb, …, Cn) represents the prioritization of new chemicals for a given protein. *The standard deviation of the performance measured by 10 independent simulation times test of 10-fold cross validation.