DeepHLAPred: a deep learning-based method for non-classical HLA binder prediction

BMC Genomics

Table 9 The performance of different modules on HLA-G*01:01 dataset

HLA-G*01:01	SN	SP	ACC	MCC	AUC
Model
CNN	0.9467	0.9626	0.9548	0.9099	0.9872
Bi-LSTM	0.9482	0.9615	0.9550	0.9101	0.9863
CNN + Bi-LSTM (In series)	0.9533	0.9619	0.9577	0.9154	0.9873
CNN + CNN (In parallel)	0.9582	0.9593	0.9588	0.9176	0.9864
Bi-LSTM + Bi-LSTM (In parallel)	0.9529	0.9528	0.9529	0.9058	0.9861
DeepHLAPred	0.9620	0.9685	0.9653	0.9305	0.9892

ISSN: 1471-2164