NeuRank: learning to rank with neural networks for drug–target interaction prediction

BMC Bioinformatics

Table 3 AUC and AUPR values of all methods on five data sets under the setting \(CV_{nd}\)

Data sets		PMF	CMF	RBM	BRDTI	DeepDTIs	NeuRank	pNeuRank	lNeuRank
DrugBank	AUC	0.7816	0.8427	0.6935	0.8520	0.8278	0.8659	0.8683	0.8694
DrugBank	AUPR	0.5371	0.6188	0.5607	0.6258	0.6043	0.6236	0.6285	0.6317
Enzymes	AUC	0.8259	0.8616	0.5093	0.8667	0.8538	0.9229	0.9268	0.9283
Enzymes	AUPR	0.5183	0.5591	0.4380	0.5604	0.5325	0.5775	0.5826	0.5863
Ion Channels	AUC	0.8086	0.8640	0.6476	0.8754	0.8539	0.9092	0.9118	0.9142
Ion Channels	AUPR	0.5273	0.5601	0.4269	0.5896	0.5634	0.6098	0.6130	0.6151
GPCRs	AUC	0.5645	0.6328	0.5006	0.6379	0.5993	0.6557	0.6532	0.6598
GPCRs	AUPR	0.3374	0.3742	0.3059	0.3865	0.3570	0.3988	0.4020	0.3781
Nuclear Receptors	AUC	0.6095	0.6537	0.5583	0.6610	0.6328	0.6645	0.6573	0.6522
Nuclear Receptors	AUPR	0.2396	0.3517	0.1470	0.3845	0.3329	0.4882	0.4796	0.4605

ISSN: 1471-2105