Table 3.

Prediction results with and without Seq-GAN on the training dataset.

Layer	Method	$\mathbf{Acc}$	$\mathbf{Sn}$	$\mathbf{Sp}$	$\mathbf{MCC}$
First Layer (Enhancer Identification)	Without Seq-GAN	0.784	0.765	0.803	0.569
	With Seq-GAN	0.951	0.951	0.951	0.902
Second Layer (Enhancer Strength Identification)	Without Seq-GAN	0.675	0.737	0.613	0.353
	With Seq-GAN	0.872	0.873	0.871	0.744