Table 6 Performance comparison of feature representation methods using their respective optimized CNN architectures for Khib site prediction in the T. gondii 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	0.711	0.713	0.423	0.788	0.711	0.727	0.429	0.800
One hot	0.695	0.694	0.392	0.769	0.705	0.699	0.409	0.778
CTD	0.712	0.734	0.430	0.782	0.720	0.727	0.442	0.778
PSSM	0.731	0.733	0.462	0.810	0.747	0.738	0.493	0.820
AAP	0.800	0.804	0.601	0.881	0.800	0.793	0.600	0.881
BLOSUM	0.815	0.822	0.634	0.896	0.804	0.800	0.609	0.893

Quick links

Search