Table 1.

Performance of various classifiers on the benchmark dataset.

Dataset	Encoding	MCC	Accuracy	Sensitivity	Specificity	AUC
AntiTb_MD	AAC	0.594	0.797	0.764	0.829	0.853
	AAI	0.588	0.792	0.724	0.859	0.857
	CTD	0.559	0.769	0.633	0.905	0.809
	CTF	0.599	0.799	0.774	0.824	0.849
	DPC	0.664	0.832	0.809	0.854	0.886
	GDPC	0.506	0.751	0.694	0.809	0.798
	GTPC	0.604	0.802	0.774	0.829	0.837
	NC5	0.568	0.784	0.779	0.789	0.826
	QSO	0.548	0.774	0.769	0.779	0.845
AntiTb_RD	AAC	0.715	0.852	0.764	0.940	0.909
	AAI	0.708	0.844	0.729	0.960	0.906
	CTD	0.665	0.832	0.799	0.864	0.883
	CTF	0.765	0.882	0.859	0.905	0.908
	DPC	0.820	0.910	0.889	0.930	0.945
	GDPC	0.635	0.817	0.779	0.853	0.883
	GTPC	0.674	0.837	0.814	0.859	0.889
	NC5	0.684	0.839	0.774	0.905	0.878
	QSO	0.708	0.849	0.769	0.930	0.881

The first and the second column represent the dataset and the feature encoding employed in this study. The third, fourth, fifth, sixth, and the seventh columns, respectively represent the MCC, accuracy, sensitivity, specificity, and AUC.