Author:
Shanehsazzadeh Amir,McPartlon Matt,Kasun George,Steiger Andrea K.,Sutton John M.,Yassine Edriss,McCloskey Cailen,Haile Robel,Shuai Richard,Alverio Julian,Rakocevic Goran,Levine Simon,Cejovic Jovan,Gutierrez Jahir M.,Morehead Alex,Dubrovskyi Oleksii,Chung Chelsea,Luton Breanna K.,Diaz Nicolas,Kohnert Christa,Consbruck Rebecca,Carter Hayley,LaCombe Chase,Bist Itti,Vilaychack Phetsamay,Anderson Zahra,Xiu Lichen,Bringas Paul,Alarcon Kimberly,Knight Bailey,Radach Macey,Bateman Katherine,Kopec-Belliveau Gaelin,Chapman Dalton,Bennett Joshua,Ventura Abigail B.,Canales Gustavo M.,Gowda Muttappa,Jackson Kerianne A.,Caguiat Rodante,Brown Amber,Ganini da Silva Douglas,Guo Zheyuan,Abdulhaqq Shaheed,Klug Lillian R.,Gander Miles,Yapici Engin,Meier Joshua,Bachas Sharrol
Abstract
AbstractGenerative AI has the potential to redefine the process of therapeutic antibody discovery. In this report, we describe and validate deep generative models for thede novo designof antibodies against human epidermal growth factor receptor (HER2) without additional optimization. The models enabled an efficient workflow that combinedin silicodesign methods with high-throughput experimental techniques to rapidly identify binders from a library of ∼106heavy chain complementarity-determining region (HCDR) variants. We demonstrated that the workflow achieves binding rates of 10.6% for HCDR3 and 1.8% for HCDR123 designs and is statistically superior to baselines. We further characterized 421 diverse binders using surface plasmon resonance (SPR), finding 71 with low nanomolar affinity similar to the therapeutic anti-HER2 antibody trastuzumab. A selected subset of 11 diverse high-affinity binders were functionally equivalent or superior to trastuzumab, with most demonstrating suitable developability features. We designed one binder with ∼3x higher cell-based potency compared to trastuzumab and another with improved cross-species reactivity1. Our generative AI approach unlocks an accelerated path to designing therapeutic antibodies against diverse targets.
Publisher
Cold Spring Harbor Laboratory