Deep learning for discriminating non-trivial conformational changes in molecular dynamics simulations of SARS-CoV-2 spike-ACE2

Deep learning for discriminating non-trivial conformational changes in molecular dynamics simulations of SARS-CoV-2 spike-ACE2 | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Deep learning for discriminating non-trivial conformational changes in molecular dynamics simulations of SARS-CoV-2 spike-ACE2 Lucas Moraes dos Santos, José Gutembergue Mendonça, Yan Jeronimo Lobo, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4299409/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 30 Sep, 2024 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract Purpose: Molecular dynamics (MD) simulations produce a substantial volume of high-dimensional data, and traditional methods for analyzing these data pose significant computational demands. Advances in MD simulation analysis combined with deep learning-based approaches have led to the understanding of specific structural changes observed in MD trajectories, including those induced by mutations. In this study, we model the trajectories resulting from MD simulations of the SARS-CoV-2 spike protein-ACE2, specifically the receptor-binding domain (RBD), as interresidue distance maps, and use deep convolutional neural networks to predict the functional impact of point mutations, related to the virus's infectivity and immunogenicity. Results: Our model was successful in predicting mutant types that increase the affinity of the S protein for human receptors and reduce its immunogenicity, both based on MD trajectories (precision = 0.718; recall = 0.800; F1 = 0.757; MCC = 0.488; AUC = 0.800) and their centroids. In an additional analysis, we also obtained a strong positive Pearson's correlation coefficient equal to 0.776, indicating a significant relationship between the average sigmoid probability for the MD trajectories and binding free energy (BFE) changes. Furthermore, we obtained a coefficient of determination of 0.602. Our 2D-RMSD analysis also corroborated predictions for more infectious and immune-evading mutants and revealed fluctuating regions within the receptor-binding motif (RBM), especially in the the β1’/β2’ -C loop. This region presented a significant standard deviation for mutations that enable SARS-CoV-2 to evade the immune response, with RMSD values of 5Å in the simulation. Conclusion: This methodology offers an efficient alternative to identify potential strains of SARS-CoV-2, which may be potentially linked to more infectious and immune-evading mutations. Using clustering and deep learning techniques, our approach leverages information from the ensemble of MD trajectories to recognize a broad spectrum of multiple conformational patterns characteristic of mutant types. This represents a strategic advantage in identifying emerging variants, bypassing the need for long MD simulations. Furthermore, the present work tends to contribute substantially to the field of computational biology and virology, particularly to accelerate the design and optimization of new therapeutic agents and vaccines, offering a proactive stance against the constantly evolving threat of COVID-19 and potential future pandemics. Biological sciences/Computational biology and bioinformatics/Machine learning Physical sciences/Chemistry/Theoretical chemistry/Molecular dynamics Molecular Dynamics Distance Maps Deep Learning CNNs Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 30 Sep, 2024 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 12 Aug, 2024 Reviews received at journal 08 Jul, 2024 Reviewers agreed at journal 03 Jul, 2024 Reviewers agreed at journal 21 May, 2024 Reviews received at journal 16 May, 2024 Reviewers agreed at journal 06 May, 2024 Reviewers invited by journal 04 May, 2024 Editor assigned by journal 03 May, 2024 Editor invited by journal 30 Apr, 2024 Submission checks completed at journal 30 Apr, 2024 First submitted to journal 21 Apr, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4299409","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":299380729,"identity":"fd0383e1-83d3-4050-9970-570f927a4a99","order_by":0,"name":"Lucas Moraes dos Santos","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9ElEQVRIiWNgGAWjYBACPhTeBzYQyfgASBzAqYUNmcU4A8xlNiBeCzMPUVokkh9+/MFQJ28u33z4s02ZnTyDRDLrxi8Md/Jxa0kzluZhOGy4s40tTTrnXLJhg0Qy220ZhmeWDTi15DBIA53BuOEYjxlzbtuBBAaJ/GO3JRgOG+C2JYf5J9Bh9kAtxp8twVqAthDQwibBw8CcCNRiIM0I1XLzAz4tPM/MrHkMDidvOJaWJtkD9Esbz2O22wwGz3Bq4WdPfnzzR0Wd7YbDhw9/+AEMMaAIG1DkDk4tEIAsDYoaZh4CGjAB4w9SdYyCUTAKRsFwBgDDu02qH44S4AAAAABJRU5ErkJggg==","orcid":"","institution":"Federal University of Minas Gerais","correspondingAuthor":true,"prefix":"","firstName":"Lucas","middleName":"Moraes dos","lastName":"Santos","suffix":""},{"id":299380730,"identity":"c66ce9eb-6db0-414f-a096-f0433fc63a88","order_by":1,"name":"José Gutembergue Mendonça","email":"","orcid":"","institution":"Federal University of Paraíba","correspondingAuthor":false,"prefix":"","firstName":"José","middleName":"Gutembergue","lastName":"Mendonça","suffix":""},{"id":299380732,"identity":"d338eeac-0e84-4969-bfe3-81dbcd86a8f5","order_by":2,"name":"Yan Jeronimo Lobo","email":"","orcid":"","institution":"Federal University of São João Del Rei","correspondingAuthor":false,"prefix":"","firstName":"Yan","middleName":"Jeronimo","lastName":"Lobo","suffix":""},{"id":299380736,"identity":"e0ecbd01-23b5-4d1d-833b-1a4f0c213451","order_by":3,"name":"Leonardo Henrique Franca de Lima","email":"","orcid":"","institution":"Federal University of São João Del Rei","correspondingAuthor":false,"prefix":"","firstName":"Leonardo","middleName":"Henrique Franca","lastName":"de Lima","suffix":""},{"id":299380740,"identity":"6f377dc3-681c-4a24-b891-dc3959d504fc","order_by":4,"name":"Gerd Bruno Rocha","email":"","orcid":"","institution":"Federal University of Paraíba","correspondingAuthor":false,"prefix":"","firstName":"Gerd","middleName":"Bruno","lastName":"Rocha","suffix":""},{"id":299380744,"identity":"bbcb94bc-ef1e-4158-af6f-64a7393fb4f2","order_by":5,"name":"Raquel Cardoso de Melo-Minardi","email":"","orcid":"","institution":"Federal University of Minas Gerais","correspondingAuthor":false,"prefix":"","firstName":"Raquel","middleName":"Cardoso","lastName":"de Melo-Minardi","suffix":""}],"badges":[],"createdAt":"2024-04-21 04:56:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4299409/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4299409/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-024-72842-w","type":"published","date":"2024-09-30T15:57:24+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":66097117,"identity":"2b47febc-2ebc-44b3-94c9-bac26d15c9e7","added_by":"auto","created_at":"2024-10-07 16:13:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3824355,"visible":true,"origin":"","legend":"","description":"","filename":"MainmanuscriptDeeplearningfordiscriminatingnontrivialconformationalchangesinmoleculardynamicssimulationsofSARSCoV2spikeACE2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4299409/v1_covered_3e5269ae-effd-486c-a9bd-5d828636af3d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep learning for discriminating non-trivial conformational changes in molecular dynamics simulations of SARS-CoV-2 spike-ACE2","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Molecular Dynamics, Distance Maps, Deep Learning, CNNs","lastPublishedDoi":"10.21203/rs.3.rs-4299409/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4299409/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePurpose: Molecular dynamics (MD) simulations produce a substantial volume of high-dimensional data, and traditional methods for analyzing these data pose significant computational demands. Advances in MD simulation analysis combined with deep learning-based approaches have led to the understanding of specific structural changes observed in MD trajectories, including those induced by mutations. In this study, we model the trajectories resulting from MD simulations of the SARS-CoV-2 spike protein-ACE2, specifically the receptor-binding domain (RBD), as interresidue distance maps, and use deep convolutional neural networks to predict the functional impact of point mutations, related to the virus's infectivity and immunogenicity.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eResults:\u0026nbsp;Our model was successful in predicting mutant types that increase the affinity of the S protein for human receptors and reduce its immunogenicity, both based on MD trajectories (precision = 0.718; recall = 0.800; F1 = 0.757; MCC = 0.488; AUC = 0.800) and their centroids. In an additional analysis, we also obtained a strong positive Pearson's correlation coefficient equal to 0.776, indicating a significant relationship between the average sigmoid probability for the MD trajectories and binding free energy (BFE) changes. Furthermore, we obtained a coefficient of determination of 0.602. Our 2D-RMSD analysis also corroborated predictions for more infectious and immune-evading mutants and revealed fluctuating regions within the receptor-binding motif (RBM), especially in the the β1’/β2’ -C loop. This region presented a significant standard deviation for mutations that enable SARS-CoV-2 to evade the immune response, with RMSD values of 5Å in the simulation.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConclusion: This methodology offers an efficient alternative to identify potential strains of SARS-CoV-2, which may be potentially linked to more infectious and immune-evading mutations. Using clustering and deep learning techniques, our approach leverages information from the ensemble of MD trajectories to recognize a broad spectrum of multiple conformational patterns characteristic of mutant types. This represents a strategic advantage in identifying emerging variants, bypassing the need for long MD simulations. Furthermore, the present work tends to contribute substantially to the field of computational biology and virology, particularly to accelerate the design and optimization of new therapeutic agents and vaccines, offering a proactive stance against the constantly evolving threat of COVID-19 and potential future pandemics.\u003c/p\u003e","manuscriptTitle":"Deep learning for discriminating non-trivial conformational changes in molecular dynamics simulations of SARS-CoV-2 spike-ACE2","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-07 06:41:17","doi":"10.21203/rs.3.rs-4299409/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-08-12T05:40:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-08T15:33:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"153009235215519691208059163545820824975","date":"2024-07-03T09:16:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"109901344891797176739002316203206674293","date":"2024-05-21T23:54:13+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-16T13:09:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"269243285268124305230351893828125137305","date":"2024-05-06T06:46:34+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-05-04T18:11:55+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-05-03T18:41:36+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-04-30T12:37:19+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-04-30T12:32:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-04-21T04:54:12+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"15c62679-7d2f-4261-81f4-ce7f571b6341","owner":[],"postedDate":"May 7th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":31583903,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":31583905,"name":"Physical sciences/Chemistry/Theoretical chemistry/Molecular dynamics"}],"tags":[],"updatedAt":"2024-10-07T16:07:15+00:00","versionOfRecord":{"articleIdentity":"rs-4299409","link":"https://doi.org/10.1038/s41598-024-72842-w","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2024-09-30 15:57:24","publishedOnDateReadable":"September 30th, 2024"},"versionCreatedAt":"2024-05-07 06:41:17","video":"","vorDoi":"10.1038/s41598-024-72842-w","vorDoiUrl":"https://doi.org/10.1038/s41598-024-72842-w","workflowStages":[]},"version":"v1","identity":"rs-4299409","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4299409","identity":"rs-4299409","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}