Prediction of drug hypersensitivity by comprehensive modeling of HLA-peptidomes.

Abstract

Human leukocyte antigen (HLA)-B*57:01 associated with abacavir-induced hypersensitivity syndrome (ABC-HSS) is one of the most extensively studied immune-mediated drug hypersensitivity reactions (DHRs). The high odds ratio and strong predictive values of HLA-B*57:01 for ABC-HSS have prompted the Food and Drug Administration and European Medicines Agency to require genetic testing before abacavir treatment. Abacavir binds to HLA-B*57:01 and alters the repertoire of presented peptides, resulting in the activation of autoimmunity. Previous studies employing computational approaches to investigate such DHRs have relied solely on a few crystallized tripartite structures, thus overlooking the full presented peptidome, leading to unsatisfactory predictive results. Here, we employed a state-of-the-art modeling approach to generate HLA structures complexed with over 13 000 presented peptides. We then established a novel computational modeling pipeline to simulate the binding of abacavir to these HLA-peptide complexes. Benchmarking against experimentally determined structures showed that this approach successfully recapitulated the crystalized tripartite structures with high accuracy (RMSD<2.2 Å). We then profiled alterations of the peptide repertoire at key positions in the presence of abacavir and proposed a method that accurately predicts compounds known to trigger T-cell activation. Overall, these results show that comprehensive modeling of the HLA-bound peptidome using advanced structural approaches can enhance the prediction and mechanistic understanding of immune-mediated DHRs.