| Autor: |
Amir Shanehsazzadeh, Sharrol Bachas, Matt McPartlon, George Kasun, John M. Sutton, Andrea K. Steiger, Richard Shuai, Christa Kohnert, Goran Rakocevic, Jahir M. Gutierrez, Chelsea Chung, Breanna K. Luton, Nicolas Diaz, Simon Levine, Julian Alverio, Bailey Knight, Macey Radach, Alex Morehead, Katherine Bateman, David A. Spencer, Zachary McDargh, Jovan Cejovic, Gaelin Kopec-Belliveau, Robel Haile, Edriss Yassine, Cailen McCloskey, Monica Natividad, Dalton Chapman, Joshua Bennett, Jubair Hossain, Abigail B. Ventura, Gustavo M. Canales, Muttappa Gowda, Kerianne A. Jackson, Jennifer T. Stanton, Marcin Ura, Luka Stojanovic, Engin Yapici, Katherine Moran, Rodante Caguiat, Amber Brown, Shaheed Abdulhaqq, Zheyuan Guo, Lillian R. Klug, Miles Gander, Joshua Meier |
| Rok vydání: |
2023 |
| Popis: |
Generative artificial intelligence (AI) has the potential to greatly increase the speed, quality and controllability of antibody design. Traditionalde novoantibody 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 promisingin silicoevidence [1–10], however, no such method has demonstrated generative AI-basedde novoantibody design with experimental validation. Here we use generative deep learning models tode novodesign antibodies against three distinct targets, in azero-shotfashion, 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 introducedNaturalnessmetric [12], indicating they are likely to possess desirable developability profiles and low immunogenicity. We open source1the 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. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
