Cargando…

Antibody complementarity determining region design using high-capacity machine learning

MOTIVATION: The precise targeting of antibodies and other protein therapeutics is required for their proper function and the elimination of deleterious off-target effects. Often the molecular structure of a therapeutic target is unknown and randomized methods are used to design antibodies without a...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Ge, Zeng, Haoyang, Mueller, Jonas, Carter, Brandon, Wang, Ziheng, Schilz, Jonas, Horny, Geraldine, Birnbaum, Michael E, Ewert, Stefan, Gifford, David K
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7141872/
https://www.ncbi.nlm.nih.gov/pubmed/31778140
http://dx.doi.org/10.1093/bioinformatics/btz895
_version_ 1783519274531291136
author Liu, Ge
Zeng, Haoyang
Mueller, Jonas
Carter, Brandon
Wang, Ziheng
Schilz, Jonas
Horny, Geraldine
Birnbaum, Michael E
Ewert, Stefan
Gifford, David K
author_facet Liu, Ge
Zeng, Haoyang
Mueller, Jonas
Carter, Brandon
Wang, Ziheng
Schilz, Jonas
Horny, Geraldine
Birnbaum, Michael E
Ewert, Stefan
Gifford, David K
author_sort Liu, Ge
collection PubMed
description MOTIVATION: The precise targeting of antibodies and other protein therapeutics is required for their proper function and the elimination of deleterious off-target effects. Often the molecular structure of a therapeutic target is unknown and randomized methods are used to design antibodies without a model that relates antibody sequence to desired properties. RESULTS: Here, we present Ens-Grad, a machine learning method that can design complementarity determining regions of human Immunoglobulin G antibodies with target affinities that are superior to candidates derived from phage display panning experiments. We also demonstrate that machine learning can improve target specificity by the modular composition of models from different experimental campaigns, enabling a new integrative approach to improving target specificity. Our results suggest a new path for the discovery of therapeutic molecules by demonstrating that predictive and differentiable models of antibody binding can be learned from high-throughput experimental data without the need for target structural data. AVAILABILITY AND IMPLEMENTATION: Sequencing data of the phage panning experiment are deposited at NIH’s Sequence Read Archive (SRA) under the accession number SRP158510. We make our code available at https://github.com/gifford-lab/antibody-2019. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
format Online
Article
Text
id pubmed-7141872
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-71418722020-04-13 Antibody complementarity determining region design using high-capacity machine learning Liu, Ge Zeng, Haoyang Mueller, Jonas Carter, Brandon Wang, Ziheng Schilz, Jonas Horny, Geraldine Birnbaum, Michael E Ewert, Stefan Gifford, David K Bioinformatics Original Papers MOTIVATION: The precise targeting of antibodies and other protein therapeutics is required for their proper function and the elimination of deleterious off-target effects. Often the molecular structure of a therapeutic target is unknown and randomized methods are used to design antibodies without a model that relates antibody sequence to desired properties. RESULTS: Here, we present Ens-Grad, a machine learning method that can design complementarity determining regions of human Immunoglobulin G antibodies with target affinities that are superior to candidates derived from phage display panning experiments. We also demonstrate that machine learning can improve target specificity by the modular composition of models from different experimental campaigns, enabling a new integrative approach to improving target specificity. Our results suggest a new path for the discovery of therapeutic molecules by demonstrating that predictive and differentiable models of antibody binding can be learned from high-throughput experimental data without the need for target structural data. AVAILABILITY AND IMPLEMENTATION: Sequencing data of the phage panning experiment are deposited at NIH’s Sequence Read Archive (SRA) under the accession number SRP158510. We make our code available at https://github.com/gifford-lab/antibody-2019. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. Oxford University Press 2020-04-01 2019-11-28 /pmc/articles/PMC7141872/ /pubmed/31778140 http://dx.doi.org/10.1093/bioinformatics/btz895 Text en © The Author(s) 2019. Published by Oxford University Press. http://creativecommons.org/licenses/by/4.0/ This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Original Papers
Liu, Ge
Zeng, Haoyang
Mueller, Jonas
Carter, Brandon
Wang, Ziheng
Schilz, Jonas
Horny, Geraldine
Birnbaum, Michael E
Ewert, Stefan
Gifford, David K
Antibody complementarity determining region design using high-capacity machine learning
title Antibody complementarity determining region design using high-capacity machine learning
title_full Antibody complementarity determining region design using high-capacity machine learning
title_fullStr Antibody complementarity determining region design using high-capacity machine learning
title_full_unstemmed Antibody complementarity determining region design using high-capacity machine learning
title_short Antibody complementarity determining region design using high-capacity machine learning
title_sort antibody complementarity determining region design using high-capacity machine learning
topic Original Papers
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7141872/
https://www.ncbi.nlm.nih.gov/pubmed/31778140
http://dx.doi.org/10.1093/bioinformatics/btz895
work_keys_str_mv AT liuge antibodycomplementaritydeterminingregiondesignusinghighcapacitymachinelearning
AT zenghaoyang antibodycomplementaritydeterminingregiondesignusinghighcapacitymachinelearning
AT muellerjonas antibodycomplementaritydeterminingregiondesignusinghighcapacitymachinelearning
AT carterbrandon antibodycomplementaritydeterminingregiondesignusinghighcapacitymachinelearning
AT wangziheng antibodycomplementaritydeterminingregiondesignusinghighcapacitymachinelearning
AT schilzjonas antibodycomplementaritydeterminingregiondesignusinghighcapacitymachinelearning
AT hornygeraldine antibodycomplementaritydeterminingregiondesignusinghighcapacitymachinelearning
AT birnbaummichaele antibodycomplementaritydeterminingregiondesignusinghighcapacitymachinelearning
AT ewertstefan antibodycomplementaritydeterminingregiondesignusinghighcapacitymachinelearning
AT gifforddavidk antibodycomplementaritydeterminingregiondesignusinghighcapacitymachinelearning