2025/07/11 by Sergio E. Mares, Mares, Sergio, Nilah M. Ioannidis +2
Biochemistry, Genetics and Molecular Biology · Immunology and Microbiology · Medicine · #Artificial Intelligence (cs.AI) #FOS: Biological sciences #FOS: Computer and information sciences #Immunotherapy and Immune Responses #Monoclonal and Polyclonal Antibodies Research #Quantitative Methods (q-bio.QM) #vaccines and immunoinformatics approaches
paper · pdf · doi:10.48550/arxiv.2507.08902
openalex publication_date 2025/07/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Personalized vaccines and T-cell immunotherapies depend critically on identifying peptide-MHC class I (pMHC-I) interactions capable of eliciting potent immune responses. However, current benchmarks and models inherit biases present in mass-spectrometry and binding-assay datasets, limiting discovery of novel peptide ligands. To address this issue, we introduce a structure-guided benchmark of pMHC-I peptides designed using diffusion models conditioned on crystal structure interaction distances. Spanning twenty high-priority HLA alleles, this benchmark is independent of previously characterized peptides yet reproduces canonical anchor residue preferences, indicating structural generalization without experimental dataset bias. Using this resource, we demonstrate that state-of-the-art sequence-based predictors perform poorly at recognizing the binding potential of these structurally stable designs, indicating allele-specific limitations invisible in conventional evaluations. Our geometry-aware design pipeline yields peptides with high predicted structural integrity and higher residue diversity than existing datasets, representing a key resource for unbiased model training and evaluation. Our code, and data are available at: https://github.com/sermare/struct-mhc-dev.