DapPep: Domain Adaptive Peptide-agnostic Learning for Universal T-cell Receptor-antigen Binding Affinity Prediction

TL;DR

DapPep is a novel domain-adaptive learning framework that enhances universal TCR-antigen binding affinity prediction, especially for unseen peptides, by combining a pre-trained protein language model with self-supervised training.

Contribution

It introduces a peptide-agnostic, domain-adaptive framework that improves generalization in TCR-antigen binding prediction, addressing limitations of existing deep learning methods.

Findings

Outperforms existing tools across multiple benchmarks.

Shows strong generalization for data-scarce and unseen peptide scenarios.

Effective in clinical tasks like neoantigen T cell sorting.

Abstract

Identifying T-cell receptors (TCRs) that interact with antigenic peptides provides the technical basis for developing vaccines and immunotherapies. The emergent deep learning methods excel at learning antigen binding patterns from known TCRs but struggle with novel or sparsely represented antigens. However, binding specificity for unseen antigens or exogenous peptides is critical. We introduce a domain-adaptive peptide-agnostic learning framework DapPep for universal TCR-antigen binding affinity prediction to address this challenge. The lightweight self-attention architecture combines a pre-trained protein language model with an inner-loop self-supervised regime to enable robust TCR-peptide representations. Extensive experiments on various benchmarks demonstrate that DapPep consistently outperforms existing tools, showcasing robust generalization capability, especially for data-scarce settings and unseen peptides. Moreover, DapPep proves effective in challenging clinical tasks such as sorting reactive T cells in tumor neoantigen therapy and identifying key positions in 3D structures.