ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks
Graph neural networks are a quickly emerging field for non-Euclidean data that leverage the inherent graphical structure to predict node, edge, and global-level properties of a system. Protein properties can not easily be understood as a simple sum of their parts (i.e. amino acids), therefore, under...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2019-10 |
---|---|
Hauptverfasser: | , , , , |
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 | Madani, Ali Cyna Shirazinejad Jia Rui Ong Shams, Hengameh Mofrad, Mohammad |
description | Graph neural networks are a quickly emerging field for non-Euclidean data that leverage the inherent graphical structure to predict node, edge, and global-level properties of a system. Protein properties can not easily be understood as a simple sum of their parts (i.e. amino acids), therefore, understanding their dynamical properties in the context of graphs is attractive for revealing how perturbations to their structure can affect their global function. To tackle this problem, we generate a database of 2020 mutated calponin homology (CH) domains undergoing large-scale separation in molecular dynamics. To predict the mechanosensitive force response, we develop neural message passing networks and residual gated graph convnets which predict the protein dependent force separation at 86.63 percent, 81.59 kJ/mol/nm MAE, 76.99 psec MAE for force mode classification, max force magnitude, max force time respectively-- significantly better than non-graph-based deep learning techniques. Towards uniting geometric learning techniques and biophysical observables, we premiere our simulation database as a benchmark dataset for further development/evaluation of graph neural network architectures. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2307884301</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2307884301</sourcerecordid><originalsourceid>FETCH-proquest_journals_23078843013</originalsourceid><addsrcrecordid>eNqNik8LgjAcQEcQJOV3GHQW5qYpXftD3Tp06yDLptN0P_vNFX77FPoAnR6P92bE40KEQRpxviC-tTVjjG8SHsfCI7cLwn4wbEvPplCIlSlpLpsOTGWohhYaKAf6gFaObntUfa6n5660fFeA1NlJS5SdpkY5lM2I_gP4tCsyL2Rjlf_jkqyPh-vuFHQIL6dsn9Xg0Iwp44IlaRoJFor_ri_Qf0PT</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2307884301</pqid></control><display><type>article</type><title>ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks</title><source>Free E- Journals</source><creator>Madani, Ali ; Cyna Shirazinejad ; Jia Rui Ong ; Shams, Hengameh ; Mofrad, Mohammad</creator><creatorcontrib>Madani, Ali ; Cyna Shirazinejad ; Jia Rui Ong ; Shams, Hengameh ; Mofrad, Mohammad</creatorcontrib><description>Graph neural networks are a quickly emerging field for non-Euclidean data that leverage the inherent graphical structure to predict node, edge, and global-level properties of a system. Protein properties can not easily be understood as a simple sum of their parts (i.e. amino acids), therefore, understanding their dynamical properties in the context of graphs is attractive for revealing how perturbations to their structure can affect their global function. To tackle this problem, we generate a database of 2020 mutated calponin homology (CH) domains undergoing large-scale separation in molecular dynamics. To predict the mechanosensitive force response, we develop neural message passing networks and residual gated graph convnets which predict the protein dependent force separation at 86.63 percent, 81.59 kJ/mol/nm MAE, 76.99 psec MAE for force mode classification, max force magnitude, max force time respectively-- significantly better than non-graph-based deep learning techniques. Towards uniting geometric learning techniques and biophysical observables, we premiere our simulation database as a benchmark dataset for further development/evaluation of graph neural network architectures.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Amino acids ; Computer simulation ; Domains ; Euclidean geometry ; Graph neural networks ; Homology ; Machine learning ; Message passing ; Molecular dynamics ; Neural networks ; Properties (attributes) ; Proteins ; Separation</subject><ispartof>arXiv.org, 2019-10</ispartof><rights>2019. This work is published under http://creativecommons.org/publicdomain/zero/1.0/ (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>780,784</link.rule.ids></links><search><creatorcontrib>Madani, Ali</creatorcontrib><creatorcontrib>Cyna Shirazinejad</creatorcontrib><creatorcontrib>Jia Rui Ong</creatorcontrib><creatorcontrib>Shams, Hengameh</creatorcontrib><creatorcontrib>Mofrad, Mohammad</creatorcontrib><title>ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks</title><title>arXiv.org</title><description>Graph neural networks are a quickly emerging field for non-Euclidean data that leverage the inherent graphical structure to predict node, edge, and global-level properties of a system. Protein properties can not easily be understood as a simple sum of their parts (i.e. amino acids), therefore, understanding their dynamical properties in the context of graphs is attractive for revealing how perturbations to their structure can affect their global function. To tackle this problem, we generate a database of 2020 mutated calponin homology (CH) domains undergoing large-scale separation in molecular dynamics. To predict the mechanosensitive force response, we develop neural message passing networks and residual gated graph convnets which predict the protein dependent force separation at 86.63 percent, 81.59 kJ/mol/nm MAE, 76.99 psec MAE for force mode classification, max force magnitude, max force time respectively-- significantly better than non-graph-based deep learning techniques. Towards uniting geometric learning techniques and biophysical observables, we premiere our simulation database as a benchmark dataset for further development/evaluation of graph neural network architectures.</description><subject>Amino acids</subject><subject>Computer simulation</subject><subject>Domains</subject><subject>Euclidean geometry</subject><subject>Graph neural networks</subject><subject>Homology</subject><subject>Machine learning</subject><subject>Message passing</subject><subject>Molecular dynamics</subject><subject>Neural networks</subject><subject>Properties (attributes)</subject><subject>Proteins</subject><subject>Separation</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNik8LgjAcQEcQJOV3GHQW5qYpXftD3Tp06yDLptN0P_vNFX77FPoAnR6P92bE40KEQRpxviC-tTVjjG8SHsfCI7cLwn4wbEvPplCIlSlpLpsOTGWohhYaKAf6gFaObntUfa6n5660fFeA1NlJS5SdpkY5lM2I_gP4tCsyL2Rjlf_jkqyPh-vuFHQIL6dsn9Xg0Iwp44IlaRoJFor_ri_Qf0PT</recordid><startdate>20191022</startdate><enddate>20191022</enddate><creator>Madani, Ali</creator><creator>Cyna Shirazinejad</creator><creator>Jia Rui Ong</creator><creator>Shams, Hengameh</creator><creator>Mofrad, Mohammad</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>20191022</creationdate><title>ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks</title><author>Madani, Ali ; Cyna Shirazinejad ; Jia Rui Ong ; Shams, Hengameh ; Mofrad, Mohammad</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_23078843013</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Amino acids</topic><topic>Computer simulation</topic><topic>Domains</topic><topic>Euclidean geometry</topic><topic>Graph neural networks</topic><topic>Homology</topic><topic>Machine learning</topic><topic>Message passing</topic><topic>Molecular dynamics</topic><topic>Neural networks</topic><topic>Properties (attributes)</topic><topic>Proteins</topic><topic>Separation</topic><toplevel>online_resources</toplevel><creatorcontrib>Madani, Ali</creatorcontrib><creatorcontrib>Cyna Shirazinejad</creatorcontrib><creatorcontrib>Jia Rui Ong</creatorcontrib><creatorcontrib>Shams, Hengameh</creatorcontrib><creatorcontrib>Mofrad, Mohammad</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</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>Madani, Ali</au><au>Cyna Shirazinejad</au><au>Jia Rui Ong</au><au>Shams, Hengameh</au><au>Mofrad, Mohammad</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks</atitle><jtitle>arXiv.org</jtitle><date>2019-10-22</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>Graph neural networks are a quickly emerging field for non-Euclidean data that leverage the inherent graphical structure to predict node, edge, and global-level properties of a system. Protein properties can not easily be understood as a simple sum of their parts (i.e. amino acids), therefore, understanding their dynamical properties in the context of graphs is attractive for revealing how perturbations to their structure can affect their global function. To tackle this problem, we generate a database of 2020 mutated calponin homology (CH) domains undergoing large-scale separation in molecular dynamics. To predict the mechanosensitive force response, we develop neural message passing networks and residual gated graph convnets which predict the protein dependent force separation at 86.63 percent, 81.59 kJ/mol/nm MAE, 76.99 psec MAE for force mode classification, max force magnitude, max force time respectively-- significantly better than non-graph-based deep learning techniques. Towards uniting geometric learning techniques and biophysical observables, we premiere our simulation database as a benchmark dataset for further development/evaluation of graph neural network architectures.</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, 2019-10 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2307884301 |
source | Free E- Journals |
subjects | Amino acids Computer simulation Domains Euclidean geometry Graph neural networks Homology Machine learning Message passing Molecular dynamics Neural networks Properties (attributes) Proteins Separation |
title | ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T04%3A05%3A14IST&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=ProDyn0:%20Inferring%20calponin%20homology%20domain%20stretching%20behavior%20using%20graph%20neural%20networks&rft.jtitle=arXiv.org&rft.au=Madani,%20Ali&rft.date=2019-10-22&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2307884301%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2307884301&rft_id=info:pmid/&rfr_iscdi=true |