Predicting TCR-epitope recognition: How good are we?

Abstract

Accurate TCR-epitope interaction predictions have the potential to unlock the use of TCR repertoires for diagnostics, TCR discovery, and cross-reactivity predictions. In this issue of Cell Genomics, Drost et al.¹ developed a streamlined framework for benchmarking such predictions. Careful understanding of the strengths and limitations of existing approaches will be instrumental to improve them and expand the scope of TCR-epitope recognition predictions.