T-cell receptor specificity landscape revealed through de novo peptide design

2025-03-01

AI Summary

Accurate prediction of TCR–pMHC interactions remains challenging due to structural complexity and scarcity of functional binding data. Method: We propose HERMES, a structure- and physics-informed deep learning framework that requires no experimentally resolved TCR–pMHC complex structures for training. HERMES integrates structure-aware physical modeling, de novo peptide generation, and joint affinity–immunogenicity prediction to quantitatively characterize the diversity of TCR recognition landscapes. Contribution/Results: HERMES achieves high-accuracy cross-pathogen and neoantigen-specific binding prediction and enables *de novo* design of immunogenic peptides. Experimental validation shows a 72% correlation between predicted and wet-lab measured binding affinities. Designed peptides with ≤5 mutations achieve up to 50% T-cell activation success across three distinct TCR–MHC systems. Notably, HERMES is the first method to quantitatively map human–murine TCR specificity spaces, establishing a scalable computational paradigm for targeted immunotherapy development.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Structured Learning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

T-cells play a key role in adaptive immunity by mounting specific responses against diverse pathogens. An effective binding between T-cell receptors (TCRs) and pathogen-derived peptides presented on Major Histocompatibility Complexes (MHCs) mediate an immune response. However, predicting these interactions remains challenging due to limited functional data on T-cell reactivities. Here, we introduce a computational approach to predict TCR interactions with peptides presented on MHC class I alleles, and to design novel immunogenic peptides for specified TCR-MHC complexes. Our method leverages HERMES, a structure-based, physics-guided machine learning model trained on the protein universe to predict amino acid preferences based on local structural environments. Despite no direct training on TCR-pMHC data, the implicit physical reasoning in HERMES enables us to make accurate predictions of both TCR-pMHC binding affinities and T-cell activities across diverse viral epitopes and cancer neoantigens, achieving up to 72% correlation with experimental data. Leveraging our TCR recognition model, we develop a computational protocol for de novo design of immunogenic peptides. Through experimental validation in three TCR-MHC systems targeting viral and cancer peptides, we demonstrate that our designs--with up to five substitutions from the native sequence--activate T-cells at success rates of up to 50%. Lastly, we use our generative framework to quantify the diversity of the peptide recognition landscape for various TCR-MHC complexes, offering key insights into T-cell specificity in both humans and mice. Our approach provides a platform for immunogenic peptide and neoantigen design, opening new computational paths for T-cell vaccine development against viruses and cancer.

Problem

• Predict TCR interactions with MHC-presented peptides.
• Design novel immunogenic peptides for TCR-MHC complexes.
• Quantify peptide recognition diversity for TCR-MHC systems.

Innovation

• HERMES model predicts TCR-pMHC interactions
• De novo design of immunogenic peptides
• Quantifies peptide recognition landscape diversity