MCL-DTI: using drug multimodal information and bi-directional cross-attention learning method for predicting drug–target interaction

Table 2 Performance comparison

Dataset	Method	ROC–AUC	PR–AUC	Recall
Human	GNN-CPI [39]	0.974 ± 0.004	0.973 ± 0.005	0.953 ± 0.019
	DeepDTA [34]	0.953 ± 0.002	0.981 ± 0.003	0.946 ± 0.024
	DeepConv-DTI [61]	0.985 ± 0.001	0.982 ± 0.001	0.963 ± 0.002
	TransformerCPI [36]	0.971 ± 0.002	0.973 ± 0.002	0.942 ± 0.004
	PWO-CPI [44]	0.982 ± 0.003	0.980 ± 0.002	0.962 ± 0.001
	MolTrans [37]	0.978 ± 0.002	0.978 ± 0.001	0.933 ± 0.003
	MCL-DTI	0.987 ± 0.001	0.989 ± 0.001	0.961 ± 0.002
C. elegans	GNN-CPI [39]	0.978 ± 0.002	0.975 ± 0.005	0.949 ± 0.003
	DeepDTA [34]	0.987 ± 0.001	0.990 ± 0.002	0.964 ± 0.011
	DeepConv-DTI [61]	0.980 ± 0.002	0.981 ± 0.001	0.937 ± 0.003
	TransformerCPI [36]	0.985 ± 0.001	0.985 ± 0.002	0.952 ± 0.002
	PWO-CPI [44]	0.979 ± 0.002	0.978 ± 0.003	0.933 ± 0.003
	MolTrans [37]	0.985 ± 0.001	0.984 ± 0.002	0.962 ± 0.001
	MCL-DTI	0.992 ± 0.001	0.994 ± 0.001	0.959 ± 0.002
Davis	GNN-CPI [39]	0.840 ± 0.012	0.269 ± 0.020	0.696 ± 0.047
	DeepDTA [34]	0.860 ± 0.002	0.238 ± 0.001	0.818 ± 0.003
	DeepConv-DTI [61]	0.822 ± 0.003	0.192 ± 0.005	0.905 ± 0.004
	TransformerCPI [36]	0.841 ± 0.001	0.227 ± 0.003	0.842 ± 0.004
	PWO-CPI [44]	0.835 ± 0.004	0.188 ± 0.004	0.798 ± 0.003
	MolTrans [37]	0.907 ± 0.002	0.404 ± 0.016	0.800 ± 0.022
	MCL-DTI	0.922 ± 0.002	0.492 ± 0.002	0.895 ± 0.003

ISSN: 1471-2105