Table 3.

Comparison of our method with six competitve methods on KIBA dataset.

Method	CI	${\mathit{r}}_{\mathit{m}}^2$	AUPR	MSE
KronRLS	0.782	0.342	0.635	0.411
SimBoost	0.836	0.629	0.760	0.222
DeepCPI	0.852	0.657	0.782	0.211
DeepDTA	0.863	0.673	0.788	0.194
GANsDTA	0.866	0.675	0.753	0.224
DeepGS	0.860	0.684	0.801	0.193
DeepMHADTA1	0.873	0.704	0.799	0.195
DeepMHADTA2	0.876	0.719	0.806	0.186