Explore Protein Conformational Space With Variational Autoencoder.
conformational space
deep learning
molecular dynamics
protein system
variational autoencoder
Journal
Frontiers in molecular biosciences
ISSN: 2296-889X
Titre abrégé: Front Mol Biosci
Pays: Switzerland
ID NLM: 101653173
Informations de publication
Date de publication:
2021
2021
Historique:
received:
23
09
2021
accepted:
28
10
2021
entrez:
6
12
2021
pubmed:
7
12
2021
medline:
7
12
2021
Statut:
epublish
Résumé
Molecular dynamics (MD) simulations have been actively used in the study of protein structure and function. However, extensive sampling in the protein conformational space requires large computational resources and takes a prohibitive amount of time. In this study, we demonstrated that variational autoencoders (VAEs), a type of deep learning model, can be employed to explore the conformational space of a protein through MD simulations. VAEs are shown to be superior to autoencoders (AEs) through a benchmark study, with low deviation between the training and decoded conformations. Moreover, we show that the learned latent space in the VAE can be used to generate unsampled protein conformations. Additional simulations starting from these generated conformations accelerated the sampling process and explored hidden spaces in the conformational landscape.
Identifiants
pubmed: 34869602
doi: 10.3389/fmolb.2021.781635
pii: 781635
pmc: PMC8633506
doi:
Types de publication
Journal Article
Langues
eng
Pagination
781635Subventions
Organisme : NIGMS NIH HHS
ID : R15 GM122013
Pays : United States
Informations de copyright
Copyright © 2021 Tian, Jiang, Trozzi, Xiao, Larson and Tao.
Déclaration de conflit d'intérêts
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
PLoS Comput Biol. 2016 Apr 28;12(4):e1004619
pubmed: 27124275
Molecules. 2020 Mar 04;25(5):
pubmed: 32143444
J Chem Phys. 2004 Jun 22;120(24):11919-29
pubmed: 15268227
Proc Natl Acad Sci U S A. 2012 Apr 3;109(14):5196-201
pubmed: 22427357
Sci Rep. 2015 Feb 12;5:8425
pubmed: 25672826
Nat Methods. 2020 Mar;17(3):261-272
pubmed: 32015543
Curr Opin Struct Biol. 2009 Apr;19(2):120-7
pubmed: 19361980
J Phys Chem B. 2011 Oct 27;115(42):12315-24
pubmed: 21902225
Structure. 2019 Jun 4;27(6):1034-1040.e3
pubmed: 31031199
Proc Natl Acad Sci U S A. 2006 Jun 27;103(26):9885-90
pubmed: 16785435
PLoS Comput Biol. 2017 Jul 26;13(7):e1005659
pubmed: 28746339
J Chem Inf Model. 2020 Oct 26;60(10):4569-4581
pubmed: 32820912
J Phys Chem B. 2021 May 20;125(19):5022-5034
pubmed: 33973773
J Chem Inf Model. 2019 Sep 23;59(9):4043-4051
pubmed: 31386362
Proteins. 2021 Feb 25;:
pubmed: 33629765
J Chem Theory Comput. 2010;6(3):787-94
pubmed: 23626502
Top Curr Chem. 2013;337:95-121
pubmed: 23543318
Curr Protoc Bioinformatics. 2006 Oct;Chapter 5:Unit-5.6
pubmed: 18428767
Bioinformation. 2015 Aug 31;11(8):393-400
pubmed: 26420920
J Chem Theory Comput. 2019 Feb 12;15(2):1209-1215
pubmed: 30632745
Structure. 2008 Aug 6;16(8):1175-82
pubmed: 18682219
J Chem Theory Comput. 2018 Apr 10;14(4):1887-1894
pubmed: 29529369
Protein Sci. 2006 Nov;15(11):2507-24
pubmed: 17075131
Proc Natl Acad Sci U S A. 2007 Nov 20;104(47):18496-501
pubmed: 18000050
Nat Struct Biol. 2000 Nov;7 Suppl:957-9
pubmed: 11103999
Proc Natl Acad Sci U S A. 2007 Nov 13;104(46):18055-60
pubmed: 17989222
Phys Rev E. 2017 Aug;96(2-1):022140
pubmed: 28950564
Proteins. 2019 Apr;87(4):326-336
pubmed: 30615225
J Chem Theory Comput. 2015 Nov 10;11(11):5525-42
pubmed: 26574340