Cargando…

Chemical Space Exploration with Active Learning and Alchemical Free Energies

[Image: see text] Drug discovery can be thought of as a search for a needle in a haystack: searching through a large chemical space for the most active compounds. Computational techniques can narrow the search space for experimental follow up, but even they become unaffordable when evaluating large...

Descripción completa

Detalles Bibliográficos
Autores principales: Khalak, Yuriy, Tresadern, Gary, Hahn, David F., de Groot, Bert L., Gapsys, Vytautas
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2022
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9558370/
https://www.ncbi.nlm.nih.gov/pubmed/36148968
http://dx.doi.org/10.1021/acs.jctc.2c00752
_version_ 1784807429639241728
author Khalak, Yuriy
Tresadern, Gary
Hahn, David F.
de Groot, Bert L.
Gapsys, Vytautas
author_facet Khalak, Yuriy
Tresadern, Gary
Hahn, David F.
de Groot, Bert L.
Gapsys, Vytautas
author_sort Khalak, Yuriy
collection PubMed
description [Image: see text] Drug discovery can be thought of as a search for a needle in a haystack: searching through a large chemical space for the most active compounds. Computational techniques can narrow the search space for experimental follow up, but even they become unaffordable when evaluating large numbers of molecules. Therefore, machine learning (ML) strategies are being developed as computationally cheaper complementary techniques for navigating and triaging large chemical libraries. Here, we explore how an active learning protocol can be combined with first-principles based alchemical free energy calculations to identify high affinity phosphodiesterase 2 (PDE2) inhibitors. We first calibrate the procedure using a set of experimentally characterized PDE2 binders. The optimized protocol is then used prospectively on a large chemical library to navigate toward potent inhibitors. In the active learning cycle, at every iteration a small fraction of compounds is probed by alchemical calculations and the obtained affinities are used to train ML models. With successive rounds, high affinity binders are identified by explicitly evaluating only a small subset of compounds in a large chemical library, thus providing an efficient protocol that robustly identifies a large fraction of true positives.
format Online
Article
Text
id pubmed-9558370
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-95583702022-10-14 Chemical Space Exploration with Active Learning and Alchemical Free Energies Khalak, Yuriy Tresadern, Gary Hahn, David F. de Groot, Bert L. Gapsys, Vytautas J Chem Theory Comput [Image: see text] Drug discovery can be thought of as a search for a needle in a haystack: searching through a large chemical space for the most active compounds. Computational techniques can narrow the search space for experimental follow up, but even they become unaffordable when evaluating large numbers of molecules. Therefore, machine learning (ML) strategies are being developed as computationally cheaper complementary techniques for navigating and triaging large chemical libraries. Here, we explore how an active learning protocol can be combined with first-principles based alchemical free energy calculations to identify high affinity phosphodiesterase 2 (PDE2) inhibitors. We first calibrate the procedure using a set of experimentally characterized PDE2 binders. The optimized protocol is then used prospectively on a large chemical library to navigate toward potent inhibitors. In the active learning cycle, at every iteration a small fraction of compounds is probed by alchemical calculations and the obtained affinities are used to train ML models. With successive rounds, high affinity binders are identified by explicitly evaluating only a small subset of compounds in a large chemical library, thus providing an efficient protocol that robustly identifies a large fraction of true positives. American Chemical Society 2022-09-23 2022-10-11 /pmc/articles/PMC9558370/ /pubmed/36148968 http://dx.doi.org/10.1021/acs.jctc.2c00752 Text en © 2022 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by/4.0/Permits the broadest form of re-use including for commercial purposes, provided that author attribution and integrity are maintained (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Khalak, Yuriy
Tresadern, Gary
Hahn, David F.
de Groot, Bert L.
Gapsys, Vytautas
Chemical Space Exploration with Active Learning and Alchemical Free Energies
title Chemical Space Exploration with Active Learning and Alchemical Free Energies
title_full Chemical Space Exploration with Active Learning and Alchemical Free Energies
title_fullStr Chemical Space Exploration with Active Learning and Alchemical Free Energies
title_full_unstemmed Chemical Space Exploration with Active Learning and Alchemical Free Energies
title_short Chemical Space Exploration with Active Learning and Alchemical Free Energies
title_sort chemical space exploration with active learning and alchemical free energies
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9558370/
https://www.ncbi.nlm.nih.gov/pubmed/36148968
http://dx.doi.org/10.1021/acs.jctc.2c00752
work_keys_str_mv AT khalakyuriy chemicalspaceexplorationwithactivelearningandalchemicalfreeenergies
AT tresaderngary chemicalspaceexplorationwithactivelearningandalchemicalfreeenergies
AT hahndavidf chemicalspaceexplorationwithactivelearningandalchemicalfreeenergies
AT degrootbertl chemicalspaceexplorationwithactivelearningandalchemicalfreeenergies
AT gapsysvytautas chemicalspaceexplorationwithactivelearningandalchemicalfreeenergies