@article {Rubinsteyn054775, author = {Alex Rubinsteyn and Timothy O{\textquoteright}Donnell and Nandita Damaraju and Jeff Hammerbacher}, title = {Predicting Peptide-MHC Binding Affinities With Imputed Training Data}, elocation-id = {054775}, year = {2016}, doi = {10.1101/054775}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Predicting the binding affinity between MHC proteins and their peptide ligands is a key problem in computational immunology. State of the art performance is currently achieved by the allele-specific predictor NetMHC and the pan-allele predictor NetMHCpan, both of which are ensembles of shallow neural networks. We explore an intermediate between allele-specific and pan-allele prediction: training allele-specific predictors with synthetic samples generated by imputation of the peptide-MHC affinity matrix. We find that the imputation strategy is useful on alleles with very little training data. We have implemented our predictor as an open-source software package called MHCflurry and show that MHCflurry achieves competitive performance to NetMHC and NetMHCpan.}, URL = {https://www.biorxiv.org/content/early/2016/05/22/054775}, eprint = {https://www.biorxiv.org/content/early/2016/05/22/054775.full.pdf}, journal = {bioRxiv} }