Generation of structure-guided pMHC-I libraries using Diffusion Models
This provides an unbiased resource for training and evaluating pMHC-I models, addressing a critical bottleneck in personalized immunotherapies, though it is incremental as it builds on existing diffusion model techniques.
The authors tackled the problem of biased peptide-MHC class I (pMHC-I) datasets limiting discovery of novel ligands for vaccines and immunotherapies by generating a structure-guided benchmark using diffusion models, which reproduces canonical anchor residue preferences and reveals poor performance of state-of-the-art sequence-based predictors on these designs.
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.