RT Journal Article SR Electronic T1 Unlocking de novo antibody design with generative artificial intelligence JF bioRxiv FD Cold Spring Harbor Laboratory SP 2023.01.08.523187 DO 10.1101/2023.01.08.523187 A1 Amir Shanehsazzadeh A1 Sharrol Bachas A1 Matt McPartlon A1 George Kasun A1 John M. Sutton A1 Andrea K. Steiger A1 Richard Shuai A1 Christa Kohnert A1 Goran Rakocevic A1 Jahir M. Gutierrez A1 Chelsea Chung A1 Breanna K. Luton A1 Nicolas Diaz A1 Simon Levine A1 Julian Alverio A1 Bailey Knight A1 Macey Radach A1 Alex Morehead A1 Katherine Bateman A1 David A. Spencer A1 Zachary McDargh A1 Jovan Cejovic A1 Gaelin Kopec-Belliveau A1 Robel Haile A1 Edriss Yassine A1 Cailen McCloskey A1 Monica Natividad A1 Dalton Chapman A1 Joshua Bennett A1 Jubair Hossain A1 Abigail B. Ventura A1 Gustavo M. Canales A1 Muttappa Gowda A1 Kerianne A. Jackson A1 Jennifer T. Stanton A1 Marcin Ura A1 Luka Stojanovic A1 Engin Yapici A1 Katherine Moran A1 Rodante Caguiat A1 Amber Brown A1 Shaheed Abdulhaqq A1 Zheyuan Guo A1 Lillian R. Klug A1 Miles Gander A1 Joshua Meier YR 2023 UL http://biorxiv.org/content/early/2023/03/29/2023.01.08.523187.abstract AB Generative artificial intelligence (AI) has the potential to greatly increase the speed, quality and controllability of antibody design. Traditional de novo antibody discovery requires time and resource intensive screening of large immune or synthetic libraries. These methods also offer little control over the output sequences, which can result in lead candidates with sub-optimal binding and poor developability attributes. Several groups have introduced models for generative antibody design with promising in silico evidence [1–10], however, no such method has demonstrated generative AI-based de novo antibody design with experimental validation. Here we use generative deep learning models to de novo design antibodies against three distinct targets, in a zero-shot fashion, where all designs are the result of a single round of model generations with no follow-up optimization. In particular, we screen over 1 million antibody variants designed for binding to human epidermal growth factor receptor 2 (HER2) using our high-throughput wet lab capabilities. Our models successfully design all CDRs in the heavy chain of the antibody and compute likelihoods that are calibrated with binding. We achieve binding rates of 10.6% and 1.8% for heavy chain CDR3 (HCDR3) and HCDR123 designs respectively, which is four and eleven times higher than HCDR3s and HCDR123s randomly sampled from the Observed Antibody Space (OAS) [11]. We further characterize 421 AI-designed binders using surface plasmon resonance (SPR), finding three that bind tighter than the therapeutic antibody trastuzumab. The binders are highly diverse, have low sequence identity to known antibodies, and adopt variable structural conformations. Additionally, the binders score highly on our previously introduced Naturalness metric [12], indicating they are likely to possess desirable developability profiles and low immunogenicity. We open source1 the HER2 binders and report the measured binding affinities. These results unlock a path to accelerated drug creation for novel therapeutic targets using generative AI and high-throughput experimentation.Competing Interest StatementThe authors are current or former employees, contractors, interns, or executives of Absci Corporation and may hold shares in Absci Corporation. Methods and compositions described in this manuscript are the subject of one or more pending patent applications.