Learning predictive signatures of HLA type from T-cell repertoires

T cells recognize a wide range of pathogens using surface receptors that interact directly with peptides presented on major histocompatibility complexes (MHC) encoded by the HLA loci in humans. Understanding the association between T cell receptors (TCR) and HLA alleles is an important step towards predicting TCR-antigen specificity from sequences. Here we analyze the TCR alpha and beta repertoires of large cohorts of HLA-typed donors to systematically infer such associations, by looking for overrepresentation of TCRs in individuals with a common allele.TCRs, associated with a specific HLA allele, exhibit sequence similarities that suggest prior antigen exposure. Immune repertoire sequencing has produced large numbers of datasets, however the HLA type of the corresponding donors is rarely available. Using our TCR-HLA associations, we trained a computational model to predict the HLA type of individuals from their TCR repertoire alone. We propose an iterative procedure to refine this model by using data from large cohorts of untyped individuals, by recursively typing them using the model itself. The resulting model shows good predictive performance, even for relatively rare HLA alleles.Author Summary: The deep sequencing of immune repertoires from blood samples promises to offer diagnostic and precision medicine tools, and to help with the analysis of treatments and vaccinations and the design of immunotherapies. This study shows how, by training models on large datasets of annotated and unannotated repertoire sequencing, the human leukocyte antigen (HLA) type of patients can be computationally determined from their T-cell repertoire. This tool could be useful for typing repertoires for which the HLA is unknown, and to gain insight into the HLA restriction of T-cell receptor epitope specificity. It also provides lists of T-cell receptors that are associated to each HLA allele.