Flexible machine learning prediction of antigen presentation for rare and common HLA-I alleles - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Cell Systems Année : 2021

Flexible machine learning prediction of antigen presentation for rare and common HLA-I alleles

Résumé

The recent increase of immunopeptidomic data, obtained by mass spectrometry or binding assays, opens unprecedented possibilities for investigating endogenous antigen presentation by the highly polymorphic human leukocyte antigen class I (HLA-I) protein. We introduce a flexible and easily interpretable peptide presentation prediction method, RBM-MHC. We validate its performance as a predictor of cancer neoantigens and viral epitopes and we use it to reconstruct peptide motifs presented on specific HLA-I molecules. By benchmarking RBM-MHC performance on a wide range of HLA-I alleles, we show its importance to improve prediction accuracy for rarer alleles.
Fichier principal
Vignette du fichier
2020.04.25.061069v2.full.pdf (9.73 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02988474 , version 1 (05-11-2020)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

Citer

Barbara Bravi, Jérôme Tubiana, Simona Cocco, Rémi Monasson, Thierry Mora, et al.. Flexible machine learning prediction of antigen presentation for rare and common HLA-I alleles. Cell Systems, 2021, 12 (2), pp.195-202.e9. ⟨10.1016/j.cels.2020.11.005⟩. ⟨hal-02988474⟩
146 Consultations
60 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More