TCR-EML: Explainable Model Layers for TCR-pMHC Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Jiarui, Yin, Zixiang, Ding, Zhengming, Landry, Samuel J., Mettu, Ramgopal R.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914372516839424
author Li, Jiarui
Yin, Zixiang
Ding, Zhengming
Landry, Samuel J.
Mettu, Ramgopal R.
author_facet Li, Jiarui
Yin, Zixiang
Ding, Zhengming
Landry, Samuel J.
Mettu, Ramgopal R.
contents T cell receptor (TCR) recognition of peptide-MHC (pMHC) complexes is a central component of adaptive immunity, with implications for vaccine design, cancer immunotherapy, and autoimmune disease. While recent advances in machine learning have improved prediction of TCR-pMHC binding, the most effective approaches are black-box transformer models that cannot provide a rationale for predictions. Post-hoc explanation methods can provide insight with respect to the input but do not explicitly model biochemical mechanisms (e.g. known binding regions), as in TCR-pMHC binding. ``Explain-by-design'' models (i.e., with architectural components that can be examined directly after training) have been explored in other domains, but have not been used for TCR-pMHC binding. We propose explainable model layers (TCR-EML) that can be incorporated into protein-language model backbones for TCR-pMHC modeling. Our approach uses prototype layers for amino acid residue contacts drawn from known TCR-pMHC binding mechanisms, enabling high-quality explanations for predicted TCR-pMHC binding. Experiments of our proposed method on large-scale datasets demonstrate competitive predictive accuracy and generalization, and evaluation on the TCR-XAI benchmark demonstrates improved explainability compared with existing approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04377
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TCR-EML: Explainable Model Layers for TCR-pMHC Prediction
Li, Jiarui
Yin, Zixiang
Ding, Zhengming
Landry, Samuel J.
Mettu, Ramgopal R.
Quantitative Methods
Computational Engineering, Finance, and Science
Machine Learning
T cell receptor (TCR) recognition of peptide-MHC (pMHC) complexes is a central component of adaptive immunity, with implications for vaccine design, cancer immunotherapy, and autoimmune disease. While recent advances in machine learning have improved prediction of TCR-pMHC binding, the most effective approaches are black-box transformer models that cannot provide a rationale for predictions. Post-hoc explanation methods can provide insight with respect to the input but do not explicitly model biochemical mechanisms (e.g. known binding regions), as in TCR-pMHC binding. ``Explain-by-design'' models (i.e., with architectural components that can be examined directly after training) have been explored in other domains, but have not been used for TCR-pMHC binding. We propose explainable model layers (TCR-EML) that can be incorporated into protein-language model backbones for TCR-pMHC modeling. Our approach uses prototype layers for amino acid residue contacts drawn from known TCR-pMHC binding mechanisms, enabling high-quality explanations for predicted TCR-pMHC binding. Experiments of our proposed method on large-scale datasets demonstrate competitive predictive accuracy and generalization, and evaluation on the TCR-XAI benchmark demonstrates improved explainability compared with existing approaches.
title TCR-EML: Explainable Model Layers for TCR-pMHC Prediction
topic Quantitative Methods
Computational Engineering, Finance, and Science
Machine Learning
url https://arxiv.org/abs/2510.04377