Introduction

This model based on deep learning method can be used to predict peptide binding MHC class I and II molecules. The advantage of this model is to ignore the length of peptide. In other words, the same model can be used to predict different peptides with different length. For predicting peptide binding MHC class I molecules, we have trained different models for 66 alleles, including 49 human alleles, three mouse alleles, eight macaque alleles, five chimpanzee alleles and one rat allele. For predicting peptide binding MHC class II molecules, we have trained different models for 29 alleles, including 27 human allelesand 2 mouse alleles.