Table 2.

The prediction performances in 5CV,10CV and denovo validation, the best results are in the bold face

	The prediction performances(AUC)
Method	Feature	5CV	10CV	Denovo
WAE	Chemical data, biological data, phenotypic data	0.9502	0.9530	0.9073
L1E	Chemical data, biological data, phenotypic data	0.9570	0.9599	∅
L2E	Chemical data, biological data, phenotypic data	0.9561	0.9594	∅
LP	Drug-sub	0.9356	0.9359	0.8993
	Drug-Label	0.9364	0.9368	0.8994
	Drug-Off Label	0.9374	0.9378	0.8997
DDIGIP	Chemical data, biological data, phenotypic data	0.9600	0.9636	0.9262

The ∅ represents that we did not compute the prediction performance because the prediction limit for new drugs.