Table 1.

Evaluation assessment between our proposed method and individual classifiers based on a benchmark set.

Method	MCC	ACC	SN	SP	AUC	p-Value
4mCpred-EL	0.591 ± 0.001	0.795 ± 0.001	0.804 ± 0.002	0.787 ± 0.002	0.874 ± 0.001	—
SVM	0.559 ± 0.005	0.780 ± 0.002	0.775 ± 0.004	0.784 ± 0.005	0.854 ± 0.003	0.127
ERT	0.559 ± 0.008	0.779 ± 0.004	0.758 ± 0.008	0.800 ± 0.004	0.848 ± 0.005	0.049
RF	0.558 ± 0.009	0.779 ± 0.004	0.762 ± 0.014	0.796 ± 0.008	0.849 ± 0.007	0.058
GB	0.556 ± 0.011	0.778 ± 0.006	0.762 ± 0.011	0.793 ± 0.002	0.845 ± 0.010	0.029
AB	0.537 ± 0.014	0.769 ± 0.007	0.755 ± 0.010	0.782 ± 0.006	0.777 ± 0.008	<0.000001
LR	0.537 ± 0.003	0.768 ± 0.002	0.758 ± 0.003	0.778 ± 0.001	0.842 ± 0.004	0.016602
KNN	0.474 ± 0.003	0.736 ± 0.002	0.692 ± 0.010	0.780 ± 0.006	0.815 ± 0.003	0.000023

Note: p < 0.05 shows a statistically significant difference between 4mCpred-EL and other method that is depicted in bold. Values are expressed as mean ± standard deviation.