Iterative attack-and-defend framework for improving TCR-epitope binding prediction models

Pengfei Zhang ^1,2, Hao Mei ^1,2, Seojin Bang ³

⁰School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ 85281, United States.

Bioinformatics +

|

July 15, 2025

View abstract on PubMed

Summary

This study introduces an attack-and-defend framework to improve T cell receptor (TCR)-epitope binding prediction models by generating and learning from false positives. The method enhances model robustness against adversarial examples, crucial for T cell therapies and vaccines.

Area Of Science

Immunology
Computational Biology
Artificial Intelligence

Background

TCR-epitope binding prediction is vital for adoptive T cell therapy and vaccine design.
Existing models suffer from false positives due to limited negative sample data.
Current negative sample generation methods fail to address model-specific vulnerabilities.

Purpose Of The Study

To develop a novel framework for systematically identifying and mitigating weaknesses in TCR-epitope prediction models.
To enhance the robustness of TCR-epitope binding prediction models against false positives.
To create a comprehensive adversarial negative dataset for model improvement.

Main Methods

Propose an iterative attack-and-defend framework using reinforcement learning from AI feedback (RLAIF).
Attack phase: Generate biologically implausible sequences to deceive prediction models.
Defense phase: Incorporate identified false positives into fine-tuning datasets to improve detection.

Main Results

Successfully applied the framework to five diverse TCR-epitope prediction models.
Demonstrated significant improvement in models' ability to detect adversarial false positives.
Created a combined dataset serving as a benchmarking tool for prediction models.

Conclusions

The attack-and-defend framework effectively enhances TCR-epitope prediction model robustness.
The generated adversarial dataset improves model performance and reduces false positives.
This approach offers a new strategy for improving biological prediction models with limited negative sampling.