New Benchmarking Shows Limited Generalization Power of TCR Antigenic Epitope Prediction Models
For researchers developing TCR-antigen prediction models, this work provides a necessary evaluation framework to assess and improve model generalizability.
The paper identifies the lack of rigorous benchmark datasets for TCR-antigen prediction models, proposes two complementary dataset classes for unbiased evaluation, and argues that existing models show limited generalization power.
Accurate computational prediction of T cell receptor (TCR) antigen specificity would transform the study of T cell biology and enable scalable immune engineering, yet existing models lack sufficient sensitivity and specificity for broad applications. A major limitation is the absence of rigorously defined, unseen benchmark datasets that allow unbiased evaluation of model performance and generalizability. Here, we describe two complementary classes of datasets that meet this criterion and argue that they provide both a robust framework for model assessment and a foundation for next-generation TCR-antigen prediction algorithm development.