BATMAN: Improved T cell receptor cross-reactivity prediction benchmarked on a comprehensive mutational scan database.
bioRxiv
; 2024 Feb 08.
Article
in En
| MEDLINE
| ID: mdl-38370810
ABSTRACT
Predicting T cell receptor (TCR) activation is challenging due to the lack of both unbiased benchmarking datasets and computational methods that are sensitive to small mutations to a peptide. To address these challenges, we curated a comprehensive database encompassing complete single amino acid mutational assays of 10,750 TCR-peptide pairs, centered around 14 immunogenic peptides against 66 TCRs. We then present an interpretable Bayesian model, called BATMAN, that can predict the set of peptides that activates a TCR. When validated on our database, BATMAN outperforms existing methods by 20% and reveals important biochemical predictors of TCR-peptide interactions.
Full text:
1
Collection:
01-internacional
Database:
MEDLINE
Language:
En
Journal:
BioRxiv
Year:
2024
Type:
Article
Affiliation country:
United States