Article

Measuring peptide–MHC generalization to unseen alleles across both HLA classes

2026-06-23

Abstract excerpt

Reported peptide–MHC (pMHC) AUROCs of 0.85–0.95 overstate generalization to unseen alleles: because immunopeptidome data are dense on a few well-studied alleles and sparse on the rest, training and test sets come to share near-identical alleles, so the numbers partly reflect interpolation rather than extrapolation to new MHC grooves. This is a property of the data, not of any one method. We assembled an open, harm...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 6447a6bc-940a-53f1-af32-90697de1f307
DOI: 10.64898/2026.06.18.733075

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Measuring peptide–MHC generalization to unseen alleles across both HLA classesDOI 10.64898/2026.06.18.733075Read

Discordant results among major histocompatibility complex binding affinity prediction toolsSemantic proximity Read

HLAEquity: Examining biases in pan-allele peptide-HLA binding predictorsSemantic proximity Read

AI-MHC: an allele-integrated deep learning framework for improving Class I & Class II HLA-binding predictionsSemantic proximity Read

Towards designing improved cancer immunotherapy targets with a peptide-MHC-I presentation model, HLApollo.Semantic proximity Read

Deciphering HLA-I motifs across HLA peptidomes improves neo-antigen predictions and identifies allostery regulating HLA specificitySemantic proximity Read

Deciphering HLA-I motifs across HLA peptidomes improves neo-antigen predictions and identifies allostery regulating HLA specificitySemantic proximity Read

The digital keystone: how artificial intelligence is reshaping HLA research and clinical practice.Semantic proximity Read

Precision neoantigen discovery using large-scale immunopeptidomes and composite modeling of MHC peptide presentationSemantic proximity Read

HLApollo: A superior transformer model for pan-allelic peptide-MHC-I presentation prediction, with diverse negative coverage, deconvolution and protein language featuresSemantic proximity Read

FairTCR: Equity-Aware TCR–pMHC Binding Prediction Across HLA Alleles and Cohort StrataSemantic proximity Read

Flexible machine learning prediction of antigen presentation for rare and common HLA-I allelesSemantic proximity Read

MHC Attention: Identifying HLA-E presented cancer antigens through deep learning and high-throughput screeningSemantic proximity Read