Cargando…

Enhancing Biomolecular Sampling with Reinforcement Learning: A Tree Search Molecular Dynamics Simulation Method

[Image: see text] This paper proposes a novel molecular simulation method, called tree search molecular dynamics (TS-MD), to accelerate the sampling of conformational transition pathways, which require considerable computation. In TS-MD, a tree search algorithm, called upper confidence bounds for tr...

Descripción completa

Detalles Bibliográficos
Autores principales: Shin, Kento, Tran, Duy Phuoc, Takemura, Kazuhiro, Kitao, Akio, Terayama, Kei, Tsuda, Koji
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2019
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6714528/
https://www.ncbi.nlm.nih.gov/pubmed/31497702
http://dx.doi.org/10.1021/acsomega.9b01480
_version_ 1783447090284724224
author Shin, Kento
Tran, Duy Phuoc
Takemura, Kazuhiro
Kitao, Akio
Terayama, Kei
Tsuda, Koji
author_facet Shin, Kento
Tran, Duy Phuoc
Takemura, Kazuhiro
Kitao, Akio
Terayama, Kei
Tsuda, Koji
author_sort Shin, Kento
collection PubMed
description [Image: see text] This paper proposes a novel molecular simulation method, called tree search molecular dynamics (TS-MD), to accelerate the sampling of conformational transition pathways, which require considerable computation. In TS-MD, a tree search algorithm, called upper confidence bounds for trees, which is a type of reinforcement learning algorithm, is applied to sample the transition pathway. By learning from the results of the previous simulations, TS-MD efficiently searches conformational space and avoids being trapped in local stable structures. TS-MD exhibits better performance than parallel cascade selection molecular dynamics, which is one of the state-of-the-art methods, for the folding of miniproteins, Chignolin and Trp-cage, in explicit water.
format Online
Article
Text
id pubmed-6714528
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-67145282019-09-06 Enhancing Biomolecular Sampling with Reinforcement Learning: A Tree Search Molecular Dynamics Simulation Method Shin, Kento Tran, Duy Phuoc Takemura, Kazuhiro Kitao, Akio Terayama, Kei Tsuda, Koji ACS Omega [Image: see text] This paper proposes a novel molecular simulation method, called tree search molecular dynamics (TS-MD), to accelerate the sampling of conformational transition pathways, which require considerable computation. In TS-MD, a tree search algorithm, called upper confidence bounds for trees, which is a type of reinforcement learning algorithm, is applied to sample the transition pathway. By learning from the results of the previous simulations, TS-MD efficiently searches conformational space and avoids being trapped in local stable structures. TS-MD exhibits better performance than parallel cascade selection molecular dynamics, which is one of the state-of-the-art methods, for the folding of miniproteins, Chignolin and Trp-cage, in explicit water. American Chemical Society 2019-08-19 /pmc/articles/PMC6714528/ /pubmed/31497702 http://dx.doi.org/10.1021/acsomega.9b01480 Text en Copyright © 2019 American Chemical Society This is an open access article published under a Creative Commons Non-Commercial No Derivative Works (CC-BY-NC-ND) Attribution License (http://pubs.acs.org/page/policy/authorchoice_ccbyncnd_termsofuse.html) , which permits copying and redistribution of the article, and creation of adaptations, all for non-commercial purposes.
spellingShingle Shin, Kento
Tran, Duy Phuoc
Takemura, Kazuhiro
Kitao, Akio
Terayama, Kei
Tsuda, Koji
Enhancing Biomolecular Sampling with Reinforcement Learning: A Tree Search Molecular Dynamics Simulation Method
title Enhancing Biomolecular Sampling with Reinforcement Learning: A Tree Search Molecular Dynamics Simulation Method
title_full Enhancing Biomolecular Sampling with Reinforcement Learning: A Tree Search Molecular Dynamics Simulation Method
title_fullStr Enhancing Biomolecular Sampling with Reinforcement Learning: A Tree Search Molecular Dynamics Simulation Method
title_full_unstemmed Enhancing Biomolecular Sampling with Reinforcement Learning: A Tree Search Molecular Dynamics Simulation Method
title_short Enhancing Biomolecular Sampling with Reinforcement Learning: A Tree Search Molecular Dynamics Simulation Method
title_sort enhancing biomolecular sampling with reinforcement learning: a tree search molecular dynamics simulation method
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6714528/
https://www.ncbi.nlm.nih.gov/pubmed/31497702
http://dx.doi.org/10.1021/acsomega.9b01480
work_keys_str_mv AT shinkento enhancingbiomolecularsamplingwithreinforcementlearningatreesearchmoleculardynamicssimulationmethod
AT tranduyphuoc enhancingbiomolecularsamplingwithreinforcementlearningatreesearchmoleculardynamicssimulationmethod
AT takemurakazuhiro enhancingbiomolecularsamplingwithreinforcementlearningatreesearchmoleculardynamicssimulationmethod
AT kitaoakio enhancingbiomolecularsamplingwithreinforcementlearningatreesearchmoleculardynamicssimulationmethod
AT terayamakei enhancingbiomolecularsamplingwithreinforcementlearningatreesearchmoleculardynamicssimulationmethod
AT tsudakoji enhancingbiomolecularsamplingwithreinforcementlearningatreesearchmoleculardynamicssimulationmethod