Introduction
Major Histocompatibility Complex (MHC) has an important research value in treatment of complex human
disease. Here, the BVLSTM-MHC model based on Bilateral and Variable Long Short-Term Memory (BVLSTM) was designed to overcome
limitation of dependenting on the length of peptides. In other words, the same model can be used to predict different
peptides with different length. We have trained four models for four species covering a total of 77 alleles,
including 62 human alleles, three mouse alleles, ten Macaque alleles and two chimpanzee alleles.
Instructions
All steps to use the model to predict peptide binding MHC class I are as follow:
To paste a peptide sequence into the text area, or to upload a file containing peptide sequences.
To select a species.
To select allele or to upload a file containing some alleles.
To select a output types including ic50 or score.
Dataset and code download
This dataset including four species subdatasets, including hunman, mouse, Macaque and chimpanzee.
Every dataset contains three files, including training set, test set, validation set. In addition, human dataset also
includes an independent test set. We also supply python code of our BVLSTM models. Please download datasets and python code by
clicking the link below:
Human and
Other species
and
BVdLSTM
Framework