Autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitors

Autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitors

Abstract We developed a computational method named Molecule Optimization by Reinforcement Learning and Docking (MORLD) that automatically generates and optimizes lead compounds by combining reinforcement learning and docking to develop predicted novel inhibitors. This model requires only a target pr...

Full description

Bibliographic Details
Main Authors: Woosung Jeon, Dongsup Kim
Format: Article
Language:English
Published: Nature Publishing Group 2020-12-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-020-78537-2
id doaj-183053f197494873ae10dd6fed21e202
record_format Article
spelling doaj-183053f197494873ae10dd6fed21e2022020-12-20T12:33:21ZengNature Publishing GroupScientific Reports2045-23222020-12-0110111110.1038/s41598-020-78537-2Autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitorsWoosung Jeon0Dongsup Kim1Department of Bio and Brain Engineering, Korea Advanced Institute of Science and TechnologyDepartment of Bio and Brain Engineering, Korea Advanced Institute of Science and TechnologyAbstract We developed a computational method named Molecule Optimization by Reinforcement Learning and Docking (MORLD) that automatically generates and optimizes lead compounds by combining reinforcement learning and docking to develop predicted novel inhibitors. This model requires only a target protein structure and directly modifies ligand structures to obtain higher predicted binding affinity for the target protein without any other training data. Using MORLD, we were able to generate potential novel inhibitors against discoidin domain receptor 1 kinase (DDR1) in less than 2 days on a moderate computer. We also demonstrated MORLD’s ability to generate predicted novel agonists for the D4 dopamine receptor (D4DR) from scratch without virtual screening on an ultra large compound library. The free web server is available at http://morld.kaist.ac.kr .https://doi.org/10.1038/s41598-020-78537-2
collection DOAJ
language English
format Article
sources DOAJ
author Woosung Jeon
Dongsup Kim
spellingShingle Woosung Jeon
Dongsup Kim
Autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitors
Scientific Reports
author_facet Woosung Jeon
Dongsup Kim
author_sort Woosung Jeon
title Autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitors
title_short Autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitors
title_full Autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitors
title_fullStr Autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitors
title_full_unstemmed Autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitors
title_sort autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitors
publisher Nature Publishing Group
series Scientific Reports
issn 2045-2322
publishDate 2020-12-01
description Abstract We developed a computational method named Molecule Optimization by Reinforcement Learning and Docking (MORLD) that automatically generates and optimizes lead compounds by combining reinforcement learning and docking to develop predicted novel inhibitors. This model requires only a target protein structure and directly modifies ligand structures to obtain higher predicted binding affinity for the target protein without any other training data. Using MORLD, we were able to generate potential novel inhibitors against discoidin domain receptor 1 kinase (DDR1) in less than 2 days on a moderate computer. We also demonstrated MORLD’s ability to generate predicted novel agonists for the D4 dopamine receptor (D4DR) from scratch without virtual screening on an ultra large compound library. The free web server is available at http://morld.kaist.ac.kr .
url https://doi.org/10.1038/s41598-020-78537-2
work_keys_str_mv AT woosungjeon autonomousmoleculegenerationusingreinforcementlearninganddockingtodeveloppotentialnovelinhibitors
AT dongsupkim autonomousmoleculegenerationusingreinforcementlearninganddockingtodeveloppotentialnovelinhibitors
_version_ 1724376456027439104

Similar Items