Table 7 Performance comparison of feature representation methods using their respective optimized CNN architectures for Khib site prediction in the rice dataset. Boldface values indicate the best performance for each metric.

Feature representation method	10-fold cross-validation set				Independent test set
Feature representation method	ACC	F1	MCC	AUC	ACC	F1	MCC	AUC
ESM	0.690	0.699	0.380	0.756	0.676	0.687	0.352	0.745
One hot	0.682	0.682	0.365	0.744	0.670	0.684	0.338	0.733
CTD	0.703	0.735	0.421	0.761	0.708	0.751	0.425	0.762
PSSM	0.725	0.736	0.453	0.789	0.733	0.746	0.464	0.807
AAP	0.777	0.785	0.556	0.852	0.764	0.771	0.529	0.852
BLOSUM	0.785	0.794	0.577	0.869	0.807	0.822	0.614	0.887

Quick links

Search