mhcflurry | Peptide-MHC I binding affinity prediction | Machine Learning library

mhcflurry is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Tensorflow applications. mhcflurry has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has low support. You can install using 'pip install mhcflurry' or download it from GitHub, PyPI.

MHC I ligand prediction package with competitive accuracy and a fast and documented implementation. MHCflurry implements class I peptide/MHC binding affinity prediction. The current version provides pan-MHC I predictors supporting any MHC allele of known sequence. MHCflurry runs on Python 3.4+ using the tensorflow neural network library. It exposes command-line and Python library interfaces. Starting in version 1.6.0, MHCflurry also includes two expermental predictors, an "antigen processing" predictor that attempts to model MHC allele-independent effects such as proteosomal cleavage and a "presentation" predictor that integrates processing predictions with binding affinity predictions to give a composite "presentation score." Both models are trained on mass spec-identified MHC ligands. These models were updated to incorporate minor improvements for the MHCflurry 2.0 release.