Skip to content

PGB-LIV/MHCVision-RF

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

39 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MHCVision-RF

A predicition tool for a probability of MHC I binding and T cell recognition

Introduction

MHCVision-RF is an assemble pipeline of MHCVision and the immunogenicity prediction model using the Random Forest. A probability score produced from MHCVision-RF is computed from a true MHC binding probabillity and an immunogegenic probability. The current version is feasible for MHC-peptide binding prediction using NetMHCpan (version >= 4.0) or MHCflurry.

Client software requirement

  1. The model requires Python 3 ( >= 3.7) and the following python packages:
pandas (>= 1.1.2)
numpy (>= 1.19.1)
scipy (>=1.5.2)
scikit-learn (>=0.23.2)

For python installing packages, please see here

If your system has both Python 2 and Python 3, please ensure that Python 3 is being used when following these instructions.

  1. Standalone BLAST (version 2.7.1)

For BLAST installation, please see here

How to install?

  1. Clone this repository
git clone https://github.com/PGB-LIV/MHCVision-RF

For other methods for cloning a GitHub repository, please see here

  1. Install the latest version of 'pip' and 'setuptools' packages for Python 3 if your system does not already have them
python -m ensurepip --default-pip
pip install setuptools

For more information, please see here

  1. Run Setup.py inside MHCVision directory to install the model
cd MHCVision-RF
python Setup.py install

Usage

usage: mhcvision-rf.py [options] input_file.csv -o/--output output_file.csv
options:
-a, --allele   REQUIRED: type the allele name i.e. HLA-A0101, which are supported in the "supplied_alleles.txt"
-t, --tool     REQUIRED: Specify the MHC-peptide prediction tool you used, type NetMHCpan or MHCflurry
-i, --input    REQUIRED: specify the input filename, the input file must be in ".CSV" format (comma-separated values), the column headers must contain 'Peptide', 'IC50'
-o, --output   Optional: specify the output filename 
-h, --help     Print the usage information

Sample scripts

You can use sample.csv as the input file

python mhcvision-rf.py -a HLA-A1101 -t NetMHCpan -i sample.csv

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages