Skip to main content

Table 13 The performance of different modules on HLA-E*01:03 dataset

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

HLA-E*01:03

SN

SP

ACC

MCC

AUC

Model

     

 CNN

0.8507

0.8221

0.8377

0.6760

0.9130

 Bi-LSTM

0.8448

0.8063

0.8259

0.6518

0.9053

 CNN + Bi-LSTM (In series)

0.8905

0.8235

0.8575

0.7168

0.9287

 CNN + CNN (In parallel)

0.8509

0.8464

0.8488

0.6974

0.9164

 Bi-LSTM + Bi-LSTM (In parallel)

0.8511

0.8167

0.8346

0.6694

0.9031

 DeepHLAPred

0.8971

0.8656

0.8812

0.7631

0.9384