TABLE 1.

10‐fold cross‐validation results of seven feature extraction methods using random forest (RF), XGBoost, and fully connected neural network (FCNN).

Algorithm	Kmer	PseEIIP	Z‐curve	CKSNAP	MMI	RCKmer	NAC
RF	0.779	0.778	0.773	0.769	0.761	0.726	0.636
XGBoost	0.789	0.795	0.777	0.788	0.766	0.736	0.689
FCNN	0.830	0.810	0.720	0.810	0.760	0.750	0.660

Note: Bold values represent the best statistically results.