Cargando…

The RESP AI model accelerates the identification of tight-binding antibodies

High-affinity antibodies are often identified through directed evolution, which may require many iterations of mutagenesis and selection to find an optimal candidate. Deep learning techniques hold the potential to accelerate this process but the existing methods cannot provide the confidence interva...

Descripción completa

Detalles Bibliográficos
Autores principales: Parkinson, Jonathan, Hard, Ryan, Wang, Wei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9884274/
https://www.ncbi.nlm.nih.gov/pubmed/36709319
http://dx.doi.org/10.1038/s41467-023-36028-8
_version_ 1784879683025764352
author Parkinson, Jonathan
Hard, Ryan
Wang, Wei
author_facet Parkinson, Jonathan
Hard, Ryan
Wang, Wei
author_sort Parkinson, Jonathan
collection PubMed
description High-affinity antibodies are often identified through directed evolution, which may require many iterations of mutagenesis and selection to find an optimal candidate. Deep learning techniques hold the potential to accelerate this process but the existing methods cannot provide the confidence interval or uncertainty needed to assess the reliability of the predictions. Here we present a pipeline called RESP for efficient identification of high affinity antibodies. We develop a learned representation trained on over 3 million human B-cell receptor sequences to encode antibody sequences. We then develop a variational Bayesian neural network to perform ordinal regression on a set of the directed evolution sequences binned by off-rate and quantify their likelihood to be tight binders against an antigen. Importantly, this model can assess sequences not present in the directed evolution library and thus greatly expand the search space to uncover the best sequences for experimental evaluation. We demonstrate the power of this pipeline by achieving a 17-fold improvement in the K(D) of the PD-L1 antibody Atezolizumab and this success illustrates the potential of RESP in facilitating general antibody development.
format Online
Article
Text
id pubmed-9884274
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-98842742023-01-30 The RESP AI model accelerates the identification of tight-binding antibodies Parkinson, Jonathan Hard, Ryan Wang, Wei Nat Commun Article High-affinity antibodies are often identified through directed evolution, which may require many iterations of mutagenesis and selection to find an optimal candidate. Deep learning techniques hold the potential to accelerate this process but the existing methods cannot provide the confidence interval or uncertainty needed to assess the reliability of the predictions. Here we present a pipeline called RESP for efficient identification of high affinity antibodies. We develop a learned representation trained on over 3 million human B-cell receptor sequences to encode antibody sequences. We then develop a variational Bayesian neural network to perform ordinal regression on a set of the directed evolution sequences binned by off-rate and quantify their likelihood to be tight binders against an antigen. Importantly, this model can assess sequences not present in the directed evolution library and thus greatly expand the search space to uncover the best sequences for experimental evaluation. We demonstrate the power of this pipeline by achieving a 17-fold improvement in the K(D) of the PD-L1 antibody Atezolizumab and this success illustrates the potential of RESP in facilitating general antibody development. Nature Publishing Group UK 2023-01-28 /pmc/articles/PMC9884274/ /pubmed/36709319 http://dx.doi.org/10.1038/s41467-023-36028-8 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Parkinson, Jonathan
Hard, Ryan
Wang, Wei
The RESP AI model accelerates the identification of tight-binding antibodies
title The RESP AI model accelerates the identification of tight-binding antibodies
title_full The RESP AI model accelerates the identification of tight-binding antibodies
title_fullStr The RESP AI model accelerates the identification of tight-binding antibodies
title_full_unstemmed The RESP AI model accelerates the identification of tight-binding antibodies
title_short The RESP AI model accelerates the identification of tight-binding antibodies
title_sort resp ai model accelerates the identification of tight-binding antibodies
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9884274/
https://www.ncbi.nlm.nih.gov/pubmed/36709319
http://dx.doi.org/10.1038/s41467-023-36028-8
work_keys_str_mv AT parkinsonjonathan therespaimodelacceleratestheidentificationoftightbindingantibodies
AT hardryan therespaimodelacceleratestheidentificationoftightbindingantibodies
AT wangwei therespaimodelacceleratestheidentificationoftightbindingantibodies
AT parkinsonjonathan respaimodelacceleratestheidentificationoftightbindingantibodies
AT hardryan respaimodelacceleratestheidentificationoftightbindingantibodies
AT wangwei respaimodelacceleratestheidentificationoftightbindingantibodies