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

arXiv: https://arxiv.org/abs/2510.04377 · HTML: https://mlsanity.com/paper/2510.04377/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 47 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Builds on (most cited first, 7 of 7)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Quantifying Cross-Attention Interaction in Transformers for Interpreting TCR-pMHC Binding](https://mlsanity.com/paper/2507.03197/) (2025)
- [Rational Multi-Modal Transformers for TCR-pMHC Prediction](https://mlsanity.com/paper/2509.17305/) (2025)
- [iMIND: Insightful Multi-subject Invariant Neural Decoding](https://mlsanity.com/paper/2509.17313/) (2025)

## Built on by (most cited first, 2 of 2)

- [Why Does It Look There? Structured Explanations for Image Classification](https://mlsanity.com/paper/2603.10234/) (2026)
- [Explainability from Training with Applications to TCR-Epitope Prediction](https://mlsanity.com/paper/2609.36354/) (2026)

## Abstract (arXiv)

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.