Table 2.

The performance comparison of our model AMMVF-DTI with existing models on the human dataset. The best performance values are highlighted in bold.

Model	AUC	Precision	Recall
KNN	0.860	0.927	0.798
RF	0.940	0.897	0.861
L2	0.911	0.913	0.867
SVM	0.910	0.966	0.969
MDL-CPI	0.959	0.924	0.905
GNN	0.970	0.918	0.923
GCN	0.956 ± 0.004	0.862 ± 0.006	0.928 ± 0.010
GraphDTA	0.960 ± 0.005	0.882 ± 0.040	0.912 ± 0.040
DrugVQA (VQA-seq)	0.964 ± 0.005	0.897 ± 0.004	0.948 ± 0.003
TransformerCPI	0.973 ± 0.002	0.916 ± 0.006	0.925 ± 0.006
AMMVF-DTI (this work)	0.986	0.976	0.938