Comparison results of the proposed MGraphDTA and baselines on the Davis and KIBA datasets (regression).

Dataset			Davis			KIBA
Model	Proteins	Compounds	MSE	CI	r m 2 index	MSE	CI	r m 2 index
DeepDTAa	CNN	CNN	0.261	0.878	0.630	0.194	0.863	0.673
WideDTAb	CNN + PDM	CNN + LMCS	0.262	0.886	—	0.179	0.875	—
GraphDTAc	CNN	GCN	0.254	0.880	—	0.139	0.889	—
GraphDTAc	CNN	GAT	0.232	0.892	—	0.179	0.866	—
GraphDTAc	CNN	GIN	0.229	0.893	—	0.147	0.882	—
GraphDTAc	CNN	GAT–GCN	0.245	0.881	—	0.139	0.891	—
DeepAffinityd	RNN	RNN	0.253	0.900	—	0.188	0.842	—
DeepAffinityd	RNN	GCN	0.260	0.881	—	0.288	0.797	—
DeepAffinityd	CNN	GCN	0.657	0.737	—	0.680	0.576	—
DeepAffinityd	HRNN	GCN	0.252	0.881	—	0.201	0.842	—
DeepAffinityd	HRNN	GIN	0.436	0.822	—	0.445	0.689	—
KronRLSa	SW	PS	0.379	0.871	0.407	0.411	0.782	0.342
SimBoosta	SW	PS	0.282	0.872	0.655	0.222	0.836	0.629
RF	ECFP	PSC	0.359 (0.003)	0.854 (0.002)	0.549 (0.005)	0.245 (0.001)	0.837 (0.000)	0.581 (0.000)
SVM	ECFP	PSC	0.383 (0.002)	0.857 (0.001)	0.513 (0.003)	0.308 (0.003)	0.799 (0.001)	0.513 (0.004)
FNN	ECFP	PSC	0.244 (0.009)	0.893 (0.003)	0.685 (0.015)	0.216 (0.010)	0.818 (0.005)	0.659 (0.015)
MGraphDTA	MCNN	MGNN	0.207 (0.001)	0.900 (0.004)	0.710 (0.005)	0.128 (0.001)	0.902 (0.001)	0.801 (0.001)

^aThese results are taken from DeepDTA.²

^bThese results are taken from WideDTA.²⁸

^cThese results are taken from GraphDTA.³¹

^dThese results are taken from DeepAffinity.³² — These results are not reported from original studies.