https://github.com/theislab/tcellmatch
https://github.com/theislab/tcellmatch
Last synced: 10 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/theislab/tcellmatch
- Owner: theislab
- License: bsd-3-clause
- Created: 2019-08-13T12:51:22.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2020-08-18T09:15:24.000Z (almost 6 years ago)
- Last Synced: 2024-12-30T12:46:56.001Z (over 1 year ago)
- Language: Python
- Size: 72.3 KB
- Stars: 37
- Watchers: 9
- Forks: 7
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# TcellMatch: Predicting T-cell to epitope specificity.
TcellMatch is a collection of models to predict antigen specificity of single T cells based on CDR3 sequences and other
single cell modalities, such as RNA counts and surface protein counts.
As labeled training data, either defined CDR3-antigen pairs from data bases such as IEDB or VDJdb are used, or
pMHC multimer "stained" single cells in which pMHC binding is used as a label indicating specificity to the loaded
peptide.
This package can be used to train such models and contains the model code, data loaders and
grid search helper functions.
Accompanying paper: https://www.embopress.org/doi/full/10.15252/msb.20199416
# Installation
This package can be locally installed via pip by first cloning a copy of this repository into you local directory
and then running `pip install -e .` at the top level of this clone's directory.