MHCflurry: open-source class I MHC binding affinity prediction

By Tim O’Donnell, A. Rubinsteyn, M. Bonsack, A. Riemer, Uri Laserson, Jeff Hammerbacher. 2017

361 citations recorded by the source corpus.

Machine learning prediction of the interaction between major histocompatibility complex I (MHC I) proteins and their small peptide ligands is important for vaccine design and other applications in adaptive immunity. We describe and benchmark a new open-source MHC I binding prediction package, MHCflurry. The software is a collection of allele-specific binding predictors incorporating a novel neural network architecture and adhering to software development best practices. MHCflurry outperformed the standard predictors NetMHC 4.0 and NetMHCpan 3.0 on a benchmark of mass spec-identified MHC ligands and showed competitive accuracy on a benchmark of affinity measurements. The accuracy improvement was due to substantially better prediction of non-9-mer peptide ligands, which offset a narrowly lower accuracy on 9-mers. MHCflurry was on average 8.6X faster than NetMHC and 44X faster than NetMHCpan; performance is further increased when a graphics processing unit (GPU) is available. MHCflurry is freely available to use, retrain, or extend, includes Python library and command line interfaces, and may be installed using standard package managers.

Subfields: Immunology, Molecular Biology

Citations in the corpus

• NetMHCpan-4.1 and NetMHCIIpan-4.0: improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data (2020, neutral): “The second category covers methods that are either trained with data retrieved from mass spectrometry (MS) experiments, known as eluted ligands (EL) (7–11), or trained integrating both BA and EL data (5,12–15).”