Predicting Drug-Target Interactions via Within-Score and Between-Score

Table 3

Comparison with other three methods under LOOCV.

	BLM^*	BLM-GIP^*	Our^*	NBI#	BLM-GIP#	BLM-NII#	Our#
EN	0.976/0.833	0.966/0.845	0.985/0.849	0.975	0.978/0.915	0.988/0.929	0.999/0.998
IC	0.973/0.781	0.971/0.807	0.977/0.820	0.976	0.984/0.943	0.990/0.950	0.997/0.897
GPCR	0.955/0.667	0.947/0.660	0.975/0.772	0.946	0.954/0.790	0.984/0.865	0.998/0.971
NR	0.881/0.612	0.864/0.547	0.946/0.774	0.838	0.922/0.684	0.981/0.866	0.982/0.949

Using chemical similarity for drugs and sequence similarity for targets only.
#Combining topological similarities (MI) with chemical similarity and sequence similarity, respectively. NBI only provides AUC values and run tests under 5-fold cross validation (5CV) which is statistically same as LOOCV when the number of samples is enough.