Validation and analysis of 12,000 AI-driven CAR-T designs in the Bits to Binders competition
Authors:
- Clayton W. KosonockyCKClayton W. Kosonocky
- Alex M. AbelAAAlex M. Abel
- Aaron L. FellerAFAaron L. Feller
- Amanda E. Cifuentes RiefferARAmanda E. Cifuentes Rieffer
- Phillip R. WoolleyPWPhillip R. Woolley
- Jakub LálaJLJakub Lála
- Daryl R. BarthDBDaryl R. Barth
- Tynan GardnerTGTynan Gardner
- Bits To Binders CompetitorsBCBits To Binders Competitors
- Stephen C. EkkerSEStephen C. Ekker
- Andrew D. EllingtonAEAndrew D. Ellington
- Wesley A. WiersonWWWesley A. Wierson
Preprint
Abstract
Artificial intelligence (AI) methods for proteins have advanced rapidly, improving structure prediction and design, particularly for de novo binders. However, most evaluations emphasize binding affinity rather than higher-order biological function. We present Bits to Binders , a global competition benchmarking de novo binder design in the context of chimeric antigen receptor (CAR) T cells. Teams from 42 countries submitted 12,000 designs of 80-amino acid binders targeting human CD20 as CAR binding domains. Designs were screened by pooled CAR-T proliferation, identifying 707 designs exhibiting significant CD20-specific enrichment, with team hit rates from 0.6% to 38.4%. Top-performing candidates were validated as individual constructs, measuring CD20-specific proliferation, expansion, cytokine production, and targeted cell lysis. We identified common design methodologies and factors correlated with DNA synthesis, expression, and target-specific T cell activation which nearly double the success rates when applied as a retrospective filter. We release this dataset as an open resource, with practical recommendations to support more effective AI-driven binder design.Keywords
Funding Information
- Winkler Family Foundation
- National Institute of Health (R35GM122480)
- BioMade (T-OC-A-04-0087)
- DTRA-AI (HDTRA1201001)
This publication has 89 references indexed in Scilit:
- Results of the Protein Engineering Tournament: An Open Science Benchmark for Protein Modeling and DesignProteins: Structure, Function, and Bioinformatics, 2025
- Analysis of the Confidence in the Prediction of the Protein Folding by Artificial Intelligence2023
- De novo protein design by inversion of the AlphaFold structure prediction networkProtein Science, 2023
- High‐accuracy protein structure prediction in CASP14Proteins: Structure, Function, and Bioinformatics, 2021
- PolyA tracks, polybasic peptides, poly‐translational hurdlesWIREs RNA, 2018
- A comparison of successful and failed protein interface designs highlights the challenges of designing buried hydrogen bondsProtein Science, 2012
- Generation of High-Expressing Cells by Methotrexate Amplification of Destabilized Dihydrofolate Reductase Selection Marker2011
- GROMACS: Fast, flexible, and freeJournal of Computational Chemistry, 2005
- Recognition of Proline‐Rich Motifs by Protein–Protein‐Interaction DomainsAngewandte Chemie International Edition, 2005
- CAPRI: A Critical Assessment of PRedicted InteractionsProteins: Structure, Function, and Bioinformatics, 2003