Remodeling Peptide-MHC-TCR Triad Binding as Sequence Fusion for Immunogenicity Prediction

TL;DR

This paper introduces a novel sequence fusion approach for modeling peptide-MHC-TCR interactions, significantly improving immunogenicity prediction accuracy by leveraging biological sequence data and representation learning.

Contribution

It presents a new modeling framework that effectively fuses sequence information from MHCs, peptides, and TCRs, outperforming traditional methods in immunogenicity prediction.

Findings

Achieved 2.8 to 13.3% improvement in prediction accuracy

Validated model effectiveness through extensive ablation studies

Provided open-source implementation and supplementary materials

Abstract

The complex nature of tripartite peptide-MHC-TCR interactions is a critical yet underexplored area in immunogenicity prediction. Traditional studies on TCR-antigen binding have not fully addressed the complex dependencies in triad binding. In this paper, we propose new modeling approaches for these tripartite interactions, utilizing sequence information from MHCs, peptides, and TCRs. Our methods adhere to native sequence forms and align with biological processes to enhance prediction accuracy. By incorporating representation learning techniques, we introduce a fusion mechanism to integrate the three sequences effectively. Empirical experiments show that our models outperform traditional methods, achieving a 2.8 to 13.3 percent improvement in prediction accuracy across existing benchmarks. We further validate our approach with extensive ablation studies, demonstrating the effectiveness of the proposed model components. The model implementation, code, and supplementary materials, including a manuscript with colored hyperlinks and a technical appendix for digital viewing, will be open-sourced upon publication.