Robust prediction of HLA class II epitopes by deep motif deconvolution of immunopeptidomes
J Racle, J Michaux, GA Rockinger, M Arnaud… - Nature …, 2019 - nature.com
Nature biotechnology, 2019•nature.com
Predictions of epitopes presented by class II human leukocyte antigen molecules (HLA-II)
have limited accuracy, restricting vaccine and therapy design. Here we combined unbiased
mass spectrometry with a motif deconvolution algorithm to profile and analyze a total of
99,265 unique peptides eluted from HLA-II molecules. We then trained an epitope prediction
algorithm with these data and improved prediction of pathogen and tumor-associated class II
neoepitopes.
have limited accuracy, restricting vaccine and therapy design. Here we combined unbiased
mass spectrometry with a motif deconvolution algorithm to profile and analyze a total of
99,265 unique peptides eluted from HLA-II molecules. We then trained an epitope prediction
algorithm with these data and improved prediction of pathogen and tumor-associated class II
neoepitopes.
Abstract
Predictions of epitopes presented by class II human leukocyte antigen molecules (HLA-II) have limited accuracy, restricting vaccine and therapy design. Here we combined unbiased mass spectrometry with a motif deconvolution algorithm to profile and analyze a total of 99,265 unique peptides eluted from HLA-II molecules. We then trained an epitope prediction algorithm with these data and improved prediction of pathogen and tumor-associated class II neoepitopes.
nature.com