BATMAN: Improved T cell receptor cross-reactivity prediction benchmarked on a comprehensive mutational scan database DOI Creative Commons
Amitava Banerjee, David Pattinson, Cornelia L. Wincek

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Янв. 25, 2024

ABSTRACT Predicting T cell receptor (TCR) activation is challenging due to the lack of both unbiased benchmarking datasets and computational methods that are sensitive small mutations a peptide. To address these challenges, we curated comprehensive database, called BATCAVE, encompassing complete single amino acid mutational assays more than 22,000 TCR-peptide pairs, centered around 25 immunogenic human mouse epitopes, across major histocompatibility complex classes, against 151 TCRs. We then present an interpretable Bayesian model, BATMAN, can predict set peptides activates TCR. also developed active learning version which efficiently learn binding profile novel TCR by selecting informative yet number assay. When validated on our BATMAN outperforms existing reveals important biochemical predictors interactions. Finally, demonstrate broad applicability including for predicting off-target effects TCR-based therapies polyclonal responses.

Язык: Английский

Decoding the adaptive immune repertoire for disease prediction DOI
Laura F. Su

Nature Reviews Rheumatology, Год журнала: 2025, Номер unknown

Опубликована: Апрель 10, 2025

Язык: Английский

Процитировано

0
BATMAN: Improved T cell receptor cross-reactivity prediction benchmarked on a comprehensive mutational scan database DOI Creative Commons
Amitava Banerjee, David Pattinson, Cornelia L. Wincek

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Янв. 25, 2024

ABSTRACT Predicting T cell receptor (TCR) activation is challenging due to the lack of both unbiased benchmarking datasets and computational methods that are sensitive small mutations a peptide. To address these challenges, we curated comprehensive database, called BATCAVE, encompassing complete single amino acid mutational assays more than 22,000 TCR-peptide pairs, centered around 25 immunogenic human mouse epitopes, across major histocompatibility complex classes, against 151 TCRs. We then present an interpretable Bayesian model, BATMAN, can predict set peptides activates TCR. also developed active learning version which efficiently learn binding profile novel TCR by selecting informative yet number assay. When validated on our BATMAN outperforms existing reveals important biochemical predictors interactions. Finally, demonstrate broad applicability including for predicting off-target effects TCR-based therapies polyclonal responses.

Язык: Английский

Процитировано

2