DeepCAC: a deep learning approach on DNA transcription factors classification based on multi-head self-attention and concatenate convolutional neural network

Table 1 The AUC result for each class

TFs	DeepCAC	DanQ	DeepSite	CNN-Zeng	CNN-BiGRU
Arid3a	0.808	0.785	0.678	0.699	0.781
CEBPB	0.940	0.896	0.706	0.774	0.886
FOSL1	0.909	0.805	0.645	0.760	0.851
Gabpa	0.832	0.826	0.776	0.788	0.818
MAFK	0.925	0.891	0.721	0.773	0.886
MAX	0.848	0.835	0.784	0.805	0.813
MEF2A	0.735	0.712	0.555	0.622	0.723
NFYB	0.950	0.926	0.680	0.842	0.919
SP1	0.797	0.808	0.765	0.780	0.792
SRF	0.774	0.790	0.665	0.706	0.792
STAT1	0.790	0.776	0.594	0.667	0.785
YY1	0.885	0.884	0.845	0.858	0.879

ISSN: 1471-2105