PepCL: A replay-based continual learning framework for updating peptide-MHC models

Abstract

Understanding peptide-major histocompatibility complex (MHC) class I binding is critical for effective vaccine and immunotherapy design but is a combinatorially complex challenge for which prediction models have become essential. MHC ligands are typically identified at scale via untargeted mass spectrometry (MS), and this has built a strong base for peptide-MHC model training. However, MS incompletely captures the vast peptide-MHC space due to technical, sampling, and biological biases. Although recently developed experimental assays have queried such blind spots yielding complementary information, existing peptide-MHC predictors have not yet incorporated these orthogonal data and are not designed to be updated as new data are generated. Here, we introduce PepCL (Peptide-MHC Continual Learning), a continual learning framework for updating peptide-MHC predictors with new assay data while explicitly preserving prior MS knowledge. To enable PepCL, we also develop MHCPrime, a new state-of-the-art pan-allelic peptide-MHC prediction model, trained on publicly available MS data, that can be effectively updated under our framework. We demonstrate that PepCL allows MHCPrime to learn previously unseen, assay-specific information while preventing catastrophic forgetting that is typically observed with conventional fine-tuning. We evaluate PepCL and MHCPrime in a variety of biological contexts, including infectious disease and cancer, and show improved peptide-MHC prediction that transfers across alleles for broader applicability in clinical settings. Overall, our results establish PepCL as a flexible framework for extending the utility of peptide-MHC models by improving their predictive performance as immunopeptidomics assays continue to evolve and new data become available.