Running summarizing tools on a new article
Check the paper below, then start its synthesis.
Validation and analysis of 12,000 AI-driven CAR-T designs in the Bits to Binders competition
Clayton W. Kosonocky (The University of Texas at Austin), Alex M. Abel, Aaron L. Feller (The University of Texas at Austin), Amanda Cifuentes Rieffer, Phillip R. Woolley (The University of Texas at Austin), Jakub Lála (Imperial College London), Delbert S. Barth (The University of Texas at Austin), Tynan Gardner (The University of Texas at Austin), Bits to Binders Competitors, Daniel Acosta (The University of Texas at Austin), Stefano Angioletti‐Uberti (Imperial College London), Vinayak Annapure (Monash University), Neil Anthony, Rana A Barghout (University of Toronto), Max Beining (Leipzig University), Parth Bibekar (École Polytechnique Fédérale de Lausanne), Dionessa Biton (Carl von Ossietzky Universität Oldenburg), Patrick Bryant (Stockholm University), Anton Bushuiev (Czech Technical University in Prague), Cianna N. Calia (University of California San Diego), Ava Chan (University of Oxford), Jie Chen (The University of Texas Southwestern Medical Center), Akshay Chenna, Nicole Chiang (University of Illinois Urbana-Champaign), Vivian Chu (University of Toronto), Joseph Clark (University of Illinois Urbana-Champaign), Alia Clark‐ElSayed (The University of Texas at Austin), Elliot Cole (McGill University), Qian Cong (The University of Texas Southwestern Medical Center), Shreyasi Das (Sungkyunkwan University), Tanner Dean (University of Illinois Urbana-Champaign), Tyler Derr (Vanderbilt University), Alejandro Diaz (Uppsala University), Jesse Durham (The University of Texas Southwestern Medical Center), Moritz Ertelt (Leipzig University), Antonio Fonseca, Ora Schueler‐Furman (Hebrew University of Jerusalem), Tynan Gardner (The University of Texas at Austin), Jokent T. Gaza (University of Florida), Nathaniel Greenwood (University of Washington), Rui Guo (The University of Texas Southwestern Medical Center), Abel Gurung (Purdue University West Lafayette), Vivian Haas (Leipzig University), Seyed Alireza Hashemi (University of Tehran), Dieter Hoffmann (Leipzig University), Sofiia Hoian (Taras Shevchenko National University of Kyiv), Corey Howe (Myriad Genetics), Calvin XiaoYang Hu (Harvard University), Jinling Huang, Nader Ibrahim (Uppsala University), Satoshi Ishida (The University of Texas at Austin), Ansar Ahmad Javed (Sungkyunkwan University), Aswini Javvadi, Roman Jerala (National Institute of Chemistry), Daksh Joshi, Even Kiely, Haelyn Kim (Seoul National University), Diego Kleiman (University of Illinois Urbana-Champaign), Sarah Knapp (Hebrew University of Jerusalem), Huan Koh (Monash University), Petr Kouba (Czech Technical University in Prague), Yong Youn Kwon (Uppsala University), Duško Lainšček (National Institute of Chemistry), Jakub Lála (Imperial College London), Hakyung Lee (Seoul National University), Qiuzhen Li (Stockholm University), Max Lingner (Leipzig University), Yuxuan Liu (Vanderbilt University, Texas A&M University), Yunchao Liu (Vanderbilt University, Texas A&M University), Qianchen Liu (University of Florida), Ajasja Ljubetič (National Institute of Chemistry), Marko Ludaic (Uppsala University), Karl Lundquist, ASHISH MAKANI, Javier Marchena-Hurtado (Charité – Universitätsmedizin Berlin), Freddie Martin (University of Copenhagen), Jens Meiler (Vanderbilt University), Fernando Meireles (École Polytechnique Fédérale de Lausanne), David Miller (Imperial College London), Núria Mitjavila-Domènech (Uppsala University), Tjaša Mlakar (National Institute of Chemistry), Rajarshi Mondal (Indraprastha Institute of Information Technology Delhi), Saeideh Moradvandi (Monash University), Rocco Moretti (Vanderbilt University), Sai Jaideep Reddy Mure (Texas A&M University), Pragati Naikare (Texas A&M University), Fatemeh Nasiri (University of Tehran), Kaveh Nasrollahi (University of Tehran), Yisel Martínez‐Noa (University of Florida), Joseph Openy (TU Dortmund University), Aoi Otani (Harvard University), Vikrant Parmar (Monash University), Jimin Pei (The University of Texas Southwestern Medical Center), Alberto Perez (University of Florida), Rajat Punia, Francisco Requena (Weill Cornell Medicine), Dominic Rieger (Leipzig University), Aparna Sahu (University of Florida), Elias Sanchez (Uppsala University), Rohit Satija, Tadej Satler (National Institute of Chemistry), T Schlegel (Leipzig University), Yang Shen (Texas A&M University), Diwakar Shukla (University of Illinois Urbana-Champaign), Rangana De Silva (University of Florida), Benedikt Singer (École Polytechnique Fédérale de Lausanne), Arjun Singh (University of Pittsburgh, University of Toronto), Amardeep Singh (University of Pittsburgh, University of Toronto), Bhumika Singh (University of Florida), Jinwoong Song (Seoul National University), Harish Srinivasan (The University of Texas Southwestern Medical Center), Hannah Stewart (University of Michigan), Zhaoqian Su (Vanderbilt University), Julia Varga (Hebrew University of Jerusalem), Xin Wang (Vanderbilt University), Dion Whitehead (Astera Institute), Matthew Williams (Northwestern University), Max Witwer (Vanderbilt University), Rujie Yin (Texas A&M University), Song Yin (University of Illinois Urbana-Champaign), Rongqing Yuan (The University of Texas Southwestern Medical Center), Nikola Zadorozhny (Czech Technical University in Prague), Dishant Zaveri (Texas A&M University), Genhui Zheng (The University of Texas at Austin), Yizhen Zheng (Monash University), Jian Zhou (The University of Texas Southwestern Medical Center), Shaowen Zhu (Texas A&M University), Lin Zhu (University of Illinois Urbana-Champaign), Stephen Carl Ekker (The University of Texas at Austin), Andrew D. Ellington (The University of Texas at Austin), Wesley A. Wierson, Edward M. Marcotte (The University of Texas at Austin)
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 evaluating 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 de novo minibinders 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.