Molecular dynamics without molecules: searching the conformational space of proteins with generative neural networks

All-atom and coarse-grained molecular dynamics are two widely used computational tools to study the conformational states of proteins. Yet, these two simulation methods suffer from the fact that without access to supercomputing resources, the time and length scales at which these states become detec...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-06
Hauptverfasser: Schwing, Gregory, Palese, Luigi L, Fernández, Ariel, Schwiebert, Loren, Gatti, Domenico L
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Schwing, Gregory
Palese, Luigi L
Fernández, Ariel
Schwiebert, Loren
Gatti, Domenico L
description All-atom and coarse-grained molecular dynamics are two widely used computational tools to study the conformational states of proteins. Yet, these two simulation methods suffer from the fact that without access to supercomputing resources, the time and length scales at which these states become detectable are difficult to achieve. One alternative to such methods is based on encoding the atomistic trajectory of molecular dynamics as a shorthand version devoid of physical particles, and then learning to propagate the encoded trajectory through the use of artificial intelligence. Here we show that a simple textual representation of the frames of molecular dynamics trajectories as vectors of Ramachandran basin classes retains most of the structural information of the full atomistic representation of a protein in each frame, and can be used to generate equivalent atom-less trajectories suitable to train different types of generative neural networks. In turn, the trained generative models can be used to extend indefinitely the atom-less dynamics or to sample the conformational space of proteins from their representation in the models latent space. We define intuitively this methodology as molecular dynamics without molecules, and show that it enables to cover physically relevant states of proteins that are difficult to access with traditional molecular dynamics.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2675833980</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2675833980</sourcerecordid><originalsourceid>FETCH-proquest_journals_26758339803</originalsourceid><addsrcrecordid>eNqNjkEKwjAQRYMgWLR3GHAt1MRqdSuKG3fuJcSpjbaZmkkUb29AD-DqL97j8Qcik0rNZ9VCypHImW9FUcjlSpalykQ4UosmttrD5e10Zw3Dy4aGYoDui5A3wKi9aay7QmgQDLmafKeDJadb4F4bBKqh9xTQum8BrujQJ-eJ4DD6JDoML_J3nohhrVvG_LdjMd3vTtvDLAUeETmcbxR9SvM5HS0rpdZVof6zPie0TiI</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2675833980</pqid></control><display><type>article</type><title>Molecular dynamics without molecules: searching the conformational space of proteins with generative neural networks</title><source>Free E- Journals</source><creator>Schwing, Gregory ; Palese, Luigi L ; Fernández, Ariel ; Schwiebert, Loren ; Gatti, Domenico L</creator><creatorcontrib>Schwing, Gregory ; Palese, Luigi L ; Fernández, Ariel ; Schwiebert, Loren ; Gatti, Domenico L</creatorcontrib><description>All-atom and coarse-grained molecular dynamics are two widely used computational tools to study the conformational states of proteins. Yet, these two simulation methods suffer from the fact that without access to supercomputing resources, the time and length scales at which these states become detectable are difficult to achieve. One alternative to such methods is based on encoding the atomistic trajectory of molecular dynamics as a shorthand version devoid of physical particles, and then learning to propagate the encoded trajectory through the use of artificial intelligence. Here we show that a simple textual representation of the frames of molecular dynamics trajectories as vectors of Ramachandran basin classes retains most of the structural information of the full atomistic representation of a protein in each frame, and can be used to generate equivalent atom-less trajectories suitable to train different types of generative neural networks. In turn, the trained generative models can be used to extend indefinitely the atom-less dynamics or to sample the conformational space of proteins from their representation in the models latent space. We define intuitively this methodology as molecular dynamics without molecules, and show that it enables to cover physically relevant states of proteins that are difficult to access with traditional molecular dynamics.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial intelligence ; Molecular dynamics ; Neural networks ; Proteins ; Representations ; Software</subject><ispartof>arXiv.org, 2022-06</ispartof><rights>2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Schwing, Gregory</creatorcontrib><creatorcontrib>Palese, Luigi L</creatorcontrib><creatorcontrib>Fernández, Ariel</creatorcontrib><creatorcontrib>Schwiebert, Loren</creatorcontrib><creatorcontrib>Gatti, Domenico L</creatorcontrib><title>Molecular dynamics without molecules: searching the conformational space of proteins with generative neural networks</title><title>arXiv.org</title><description>All-atom and coarse-grained molecular dynamics are two widely used computational tools to study the conformational states of proteins. Yet, these two simulation methods suffer from the fact that without access to supercomputing resources, the time and length scales at which these states become detectable are difficult to achieve. One alternative to such methods is based on encoding the atomistic trajectory of molecular dynamics as a shorthand version devoid of physical particles, and then learning to propagate the encoded trajectory through the use of artificial intelligence. Here we show that a simple textual representation of the frames of molecular dynamics trajectories as vectors of Ramachandran basin classes retains most of the structural information of the full atomistic representation of a protein in each frame, and can be used to generate equivalent atom-less trajectories suitable to train different types of generative neural networks. In turn, the trained generative models can be used to extend indefinitely the atom-less dynamics or to sample the conformational space of proteins from their representation in the models latent space. We define intuitively this methodology as molecular dynamics without molecules, and show that it enables to cover physically relevant states of proteins that are difficult to access with traditional molecular dynamics.</description><subject>Artificial intelligence</subject><subject>Molecular dynamics</subject><subject>Neural networks</subject><subject>Proteins</subject><subject>Representations</subject><subject>Software</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNjkEKwjAQRYMgWLR3GHAt1MRqdSuKG3fuJcSpjbaZmkkUb29AD-DqL97j8Qcik0rNZ9VCypHImW9FUcjlSpalykQ4UosmttrD5e10Zw3Dy4aGYoDui5A3wKi9aay7QmgQDLmafKeDJadb4F4bBKqh9xTQum8BrujQJ-eJ4DD6JDoML_J3nohhrVvG_LdjMd3vTtvDLAUeETmcbxR9SvM5HS0rpdZVof6zPie0TiI</recordid><startdate>20220609</startdate><enddate>20220609</enddate><creator>Schwing, Gregory</creator><creator>Palese, Luigi L</creator><creator>Fernández, Ariel</creator><creator>Schwiebert, Loren</creator><creator>Gatti, Domenico L</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20220609</creationdate><title>Molecular dynamics without molecules: searching the conformational space of proteins with generative neural networks</title><author>Schwing, Gregory ; Palese, Luigi L ; Fernández, Ariel ; Schwiebert, Loren ; Gatti, Domenico L</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26758339803</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Artificial intelligence</topic><topic>Molecular dynamics</topic><topic>Neural networks</topic><topic>Proteins</topic><topic>Representations</topic><topic>Software</topic><toplevel>online_resources</toplevel><creatorcontrib>Schwing, Gregory</creatorcontrib><creatorcontrib>Palese, Luigi L</creatorcontrib><creatorcontrib>Fernández, Ariel</creatorcontrib><creatorcontrib>Schwiebert, Loren</creatorcontrib><creatorcontrib>Gatti, Domenico L</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Schwing, Gregory</au><au>Palese, Luigi L</au><au>Fernández, Ariel</au><au>Schwiebert, Loren</au><au>Gatti, Domenico L</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Molecular dynamics without molecules: searching the conformational space of proteins with generative neural networks</atitle><jtitle>arXiv.org</jtitle><date>2022-06-09</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>All-atom and coarse-grained molecular dynamics are two widely used computational tools to study the conformational states of proteins. Yet, these two simulation methods suffer from the fact that without access to supercomputing resources, the time and length scales at which these states become detectable are difficult to achieve. One alternative to such methods is based on encoding the atomistic trajectory of molecular dynamics as a shorthand version devoid of physical particles, and then learning to propagate the encoded trajectory through the use of artificial intelligence. Here we show that a simple textual representation of the frames of molecular dynamics trajectories as vectors of Ramachandran basin classes retains most of the structural information of the full atomistic representation of a protein in each frame, and can be used to generate equivalent atom-less trajectories suitable to train different types of generative neural networks. In turn, the trained generative models can be used to extend indefinitely the atom-less dynamics or to sample the conformational space of proteins from their representation in the models latent space. We define intuitively this methodology as molecular dynamics without molecules, and show that it enables to cover physically relevant states of proteins that are difficult to access with traditional molecular dynamics.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2022-06
issn 2331-8422
language eng
recordid cdi_proquest_journals_2675833980
source Free E- Journals
subjects Artificial intelligence
Molecular dynamics
Neural networks
Proteins
Representations
Software
title Molecular dynamics without molecules: searching the conformational space of proteins with generative neural networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T21%3A40%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Molecular%20dynamics%20without%20molecules:%20searching%20the%20conformational%20space%20of%20proteins%20with%20generative%20neural%20networks&rft.jtitle=arXiv.org&rft.au=Schwing,%20Gregory&rft.date=2022-06-09&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2675833980%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2675833980&rft_id=info:pmid/&rfr_iscdi=true