DIKUL - logo
E-viri
Recenzirano Odprti dostop
  • Robust prediction of HLA cl...
    Racle, Julien; Michaux, Justine; Rockinger, Georg Alexander; Arnaud, Marion; Bobisse, Sara; Chong, Chloe; Guillaume, Philippe; Coukos, George; Harari, Alexandre; Jandus, Camilla; Bassani-Sternberg, Michal; Gfeller, David

    Nature biotechnology, 11/2019, Letnik: 37, Številka: 11
    Journal Article

    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.