Generation of structure-guided pMHC-I libraries using Diffusion Models

TL;DR

This paper introduces a structure-guided benchmark for pMHC-I peptide design using diffusion models, revealing limitations of current predictors and providing a diverse, unbiased resource for improved immunotherapy development.

Contribution

The study develops a novel structure-guided benchmark for pMHC-I peptides using diffusion models, enabling unbiased evaluation and design of peptides across multiple HLA alleles.

Findings

State-of-the-art predictors perform poorly on the new benchmark.

Designed peptides show high structural integrity and diversity.

The resource enables unbiased model training and evaluation.

Abstract

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.