RT Journal Article
SR Electronic
T1 Interpretable deep learning to uncover the molecular binding patterns determining TCR–epitope interactions
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2022.05.02.490264
DO 10.1101/2022.05.02.490264
A1 Ceder Dens
A1 Wout Bittremieux
A1 Fabio Affaticati
A1 Kris Laukens
A1 Pieter Meysman
YR 2022
UL http://biorxiv.org/content/early/2022/10/04/2022.05.02.490264.abstract
AB The recognition of an epitope by a T-cell receptor (TCR) is crucial for eliminating pathogens and establishing immunological memory. Prediction of the binding of any TCR–epitope pair is still a challenging task, especially for novel epitopes, because the underlying patterns are largely unknown to domain experts and machine learning models. To achieve a deeper understanding of TCR–epitope interactions, we have used interpretable deep learning techniques to gain insights into the performance of TCR–epitope binding machine learning models. We demonstrate how interpretable AI techniques can be linked to the three-dimensional structure of molecules to offer novel insights into the factors that determine TCR affinity on a molecular level. Additionally, our results show the importance of using interpretability techniques to verify the predictions of machine learning models for challenging molecular biology problems where small hard-to-detect problems can accumulate to inaccurate results.Competing Interest StatementKL and PM hold shares in ImmuneWatch BV, an immunoinformatics company.