Deep learning-guided selection of antibody therapies with enhanced resistance to current and prospective SARS-CoV-2 Omicron variants
Most COVID-19 antibody therapies rely on binding the SARS-CoV-2 receptor binding domain (RBD). However, heavily mutated variants such as Omicron and its sublineages, which are characterized by an ever increasing number of mutations in the RBD, have rendered prior antibody therapies ineffective, leav...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Report |
Language: | English |
Published: |
Cold Spring Harbor Laboratory
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/20.500.11850/652262 https://doi.org/10.3929/ethz-b-000652262 |
id |
ftethz:oai:www.research-collection.ethz.ch:20.500.11850/652262 |
---|---|
record_format |
openpolar |
spelling |
ftethz:oai:www.research-collection.ethz.ch:20.500.11850/652262 2024-02-27T08:40:00+00:00 Deep learning-guided selection of antibody therapies with enhanced resistance to current and prospective SARS-CoV-2 Omicron variants Frei, Lester Gao, Beichen Han, Jiami Taft, Joseph M. Irvine, Edward B. Weber, Cédric id_orcid:0 000-0003-4802-8996 Kumar, Rachita id_orcid:0 000-0003-4863-403X Eisinger, Benedikt N. Reddy, Sai T. 2023-10-10 application/application/pdf https://hdl.handle.net/20.500.11850/652262 https://doi.org/10.3929/ethz-b-000652262 en eng Cold Spring Harbor Laboratory info:eu-repo/semantics/altIdentifier/doi/10.1101/2023.10.09.561492 http://hdl.handle.net/20.500.11850/652262 doi:10.3929/ethz-b-000652262 info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nd/4.0/ Creative Commons Attribution-NoDerivatives 4.0 International bioRxiv info:eu-repo/semantics/workingPaper 2023 ftethz https://doi.org/20.500.11850/65226210.3929/ethz-b-00065226210.1101/2023.10.09.561492 2024-01-29T00:52:49Z Most COVID-19 antibody therapies rely on binding the SARS-CoV-2 receptor binding domain (RBD). However, heavily mutated variants such as Omicron and its sublineages, which are characterized by an ever increasing number of mutations in the RBD, have rendered prior antibody therapies ineffective, leaving no clinically approved antibody treatments for SARS-CoV-2. Therefore, the capacity of therapeutic antibody candidates to bind and neutralize current and prospective SARS-CoV-2 variants is a critical factor for drug development. Here, we present a deep learning-guided approach to identify antibodies with enhanced resistance to SARS-CoV-2 evolution. We apply deep mutational learning (DML), a machine learning-guided protein engineering method to interrogate a massive sequence space of combinatorial RBD mutations and predict their impact on angiotensin-converting enzyme 2 (ACE2) binding and antibody escape. A high mutational distance library was constructed based on the full-length RBD of Omicron BA.1, which was experimentally screened for binding to the ACE2 receptor or neutralizing antibodies, followed by deep sequencing. The resulting data was used to train ensemble deep learning models that could accurately predict binding or escape for a panel of therapeutic antibody candidates targeting diverse RBD epitopes. Furthermore, antibody breadth was assessed by predicting binding or escape to synthetic lineages that represent millions of sequences generated using in silico evolution, revealing combinations with complementary and enhanced resistance to viral evolution. This deep learning approach may enable the design of next-generation antibody therapies that remain effective against future SARS-CoV-2 variants. Report DML ETH Zürich Research Collection |
institution |
Open Polar |
collection |
ETH Zürich Research Collection |
op_collection_id |
ftethz |
language |
English |
description |
Most COVID-19 antibody therapies rely on binding the SARS-CoV-2 receptor binding domain (RBD). However, heavily mutated variants such as Omicron and its sublineages, which are characterized by an ever increasing number of mutations in the RBD, have rendered prior antibody therapies ineffective, leaving no clinically approved antibody treatments for SARS-CoV-2. Therefore, the capacity of therapeutic antibody candidates to bind and neutralize current and prospective SARS-CoV-2 variants is a critical factor for drug development. Here, we present a deep learning-guided approach to identify antibodies with enhanced resistance to SARS-CoV-2 evolution. We apply deep mutational learning (DML), a machine learning-guided protein engineering method to interrogate a massive sequence space of combinatorial RBD mutations and predict their impact on angiotensin-converting enzyme 2 (ACE2) binding and antibody escape. A high mutational distance library was constructed based on the full-length RBD of Omicron BA.1, which was experimentally screened for binding to the ACE2 receptor or neutralizing antibodies, followed by deep sequencing. The resulting data was used to train ensemble deep learning models that could accurately predict binding or escape for a panel of therapeutic antibody candidates targeting diverse RBD epitopes. Furthermore, antibody breadth was assessed by predicting binding or escape to synthetic lineages that represent millions of sequences generated using in silico evolution, revealing combinations with complementary and enhanced resistance to viral evolution. This deep learning approach may enable the design of next-generation antibody therapies that remain effective against future SARS-CoV-2 variants. |
format |
Report |
author |
Frei, Lester Gao, Beichen Han, Jiami Taft, Joseph M. Irvine, Edward B. Weber, Cédric id_orcid:0 000-0003-4802-8996 Kumar, Rachita id_orcid:0 000-0003-4863-403X Eisinger, Benedikt N. Reddy, Sai T. |
spellingShingle |
Frei, Lester Gao, Beichen Han, Jiami Taft, Joseph M. Irvine, Edward B. Weber, Cédric id_orcid:0 000-0003-4802-8996 Kumar, Rachita id_orcid:0 000-0003-4863-403X Eisinger, Benedikt N. Reddy, Sai T. Deep learning-guided selection of antibody therapies with enhanced resistance to current and prospective SARS-CoV-2 Omicron variants |
author_facet |
Frei, Lester Gao, Beichen Han, Jiami Taft, Joseph M. Irvine, Edward B. Weber, Cédric id_orcid:0 000-0003-4802-8996 Kumar, Rachita id_orcid:0 000-0003-4863-403X Eisinger, Benedikt N. Reddy, Sai T. |
author_sort |
Frei, Lester |
title |
Deep learning-guided selection of antibody therapies with enhanced resistance to current and prospective SARS-CoV-2 Omicron variants |
title_short |
Deep learning-guided selection of antibody therapies with enhanced resistance to current and prospective SARS-CoV-2 Omicron variants |
title_full |
Deep learning-guided selection of antibody therapies with enhanced resistance to current and prospective SARS-CoV-2 Omicron variants |
title_fullStr |
Deep learning-guided selection of antibody therapies with enhanced resistance to current and prospective SARS-CoV-2 Omicron variants |
title_full_unstemmed |
Deep learning-guided selection of antibody therapies with enhanced resistance to current and prospective SARS-CoV-2 Omicron variants |
title_sort |
deep learning-guided selection of antibody therapies with enhanced resistance to current and prospective sars-cov-2 omicron variants |
publisher |
Cold Spring Harbor Laboratory |
publishDate |
2023 |
url |
https://hdl.handle.net/20.500.11850/652262 https://doi.org/10.3929/ethz-b-000652262 |
genre |
DML |
genre_facet |
DML |
op_source |
bioRxiv |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1101/2023.10.09.561492 http://hdl.handle.net/20.500.11850/652262 doi:10.3929/ethz-b-000652262 |
op_rights |
info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nd/4.0/ Creative Commons Attribution-NoDerivatives 4.0 International |
op_doi |
https://doi.org/20.500.11850/65226210.3929/ethz-b-00065226210.1101/2023.10.09.561492 |
_version_ |
1792047081805840384 |