Table 7. Second experiment, trained on the imbalanced training dataset.

Model	Acc	F1	Sens	Spec	MCC	AUC
Validated on the imbalanced validation dataset
DeepRMethylSite CNN	0.8948	0.8550	0.9072	0.8916	0.7242	0.8283
DeepRMethylSite LSTM	0.9092	0.8782	0.9044	0.9106	0.7634	0.8576
DeepRMethylSite Merged	0.9114	0.8808	0.9047	0.9115	0.7693	0.8589
SMLP	0.9071	0.8670	0.9973	0.8873	0.7635	0.8295
SSMFN Merged	0.9078	0.8774	0.8895	0.9133	0.7598	0.8596
Validated on the balanced validation dataset
DeepRMethylSite CNN	0.8289	0.8249	0.9709	0.7527	0.6899	0.8283
DeepRMethylSite LSTM	0.8576	0.8557	0.9644	0.7908	0.7350	0.8576
DeepRMethylSite Merged	0.8585	0.8567	0.9645	0.7919	0.7365	0.8589
SMLP	0.7582	0.7432	1.0000	0.6740	0.5899	0.8295
SSMFN Merged	0.8656	0.8640	0.9672	0.8003	0.7491	0.8596
Tested on the test dataset
DeepRMethylSite CNN	0.7808	0.7727	0.9506	0.7039	0.6063	0.7808
DeepRMethylSite LSTM	0.8115	0.8070	0.9500	0.7382	0.6548	0.8115
DeepRMethylSite Merged	0.8135	0.8088	0.9553	0.7390	0.6598	0.8135
SMLP	0.7250	0.7025	1.0000	0.6452	0.5388	0.7250
SSMFN Merged	0.8462	0.8435	0.9688	0.7744	0.7173	0.8462

Note.

The highest value of each parameter from each measurement experiment is shown in bold.