TABLE 2.

Summary of the performance of the best model with different classification algorithms on two datasets.

Classification algorithm	Kraken dataset			SHOGUN dataset
	Number of features	ACC	MCC	Number of features	ACC	MCC
Random forest	582	0.921	0.918	146	0.884	0.878
Support vector machine	1989	0.588	0.575	1592	0.633	0.616
k-nearest neighbor	682	0.812	0.804	277	0.895	0.889
Decision tree	580	0.736	0.724	1481	0.824	0.814