Generative Model of Protein Dynamic Trajectory Based on Latent Diffusion with DynaFold

Generative Model of Protein Dynamic Trajectory Based on Latent Diffusion with DynaFold | 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 Biological Sciences - Article Generative Model of Protein Dynamic Trajectory Based on Latent Diffusion with DynaFold Haifeng Chen, Zirui Fan, Junjie Zhu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7798503/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The dynamic process of protein folding and conformation switching describes the basis of protein functions. Molecular dynamics (MD) simulations are precise computational tools for exploring protein dynamics, but the high computational costs make it difficult to scale up. Deep learning methods have been used to model the Boltzmann distribution of molecular simulations, but achieving MD-level accuracy remains a major challenge. Here, we present DynaFold, a generative deep learning framework based on latent diffusion for sampling protein dynamic trajectories. DynaFold accepts an initial structure and generalizes the conformational dynamics of different proteins with minimal trajectory data during training. It achieves state-of-the-art accuracy in predicting conformational ensembles and sampling conformational transition pathways, demonstrating superior generalization capability and computational efficiency compared to existing methods. Our framework provides a general solution for generating conformation distributions and transition processes between different conformations for proteins, enabling rapid sampling of structural ensembles and analysis of Boltzmann systems. Biological sciences/Computational biology and bioinformatics/Protein structure predictions Biological sciences/Computational biology and bioinformatics/Computational models Full Text Additional Declarations There is NO Competing Interest. Supplementary Files DynaFoldSl1003.docx Supplementary file Cite Share Download PDF Status: Posted Version 1 posted 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-7798503","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Biological Sciences - Article","associatedPublications":[],"authors":[{"id":526199832,"identity":"18d92a4e-fa25-4eb8-8b03-14e2d147b652","order_by":0,"name":"Haifeng Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAklEQVRIiWNgGAWjYBACAwbGhg8QBgPjAwYeqCABLY0zoMqYDRh4DIjRwsAI08ImAVWNX4s5++HGho87auXN2XuPVf6Q+ZPYwN68TYKh5g5OLZY9iY2NM88cN9zZcy7tNg+PQWIDz7EyCYZjz3A77EBi+2PetmMJBjdyzG4zgLRI5JhJMDYcxq3l/MPG5r8gLfffmBX+AGmRf0NAy43ExmbGthqgLTxmDGCHSfAQ0vKwsbG37YDhhjM5xtI8PMbGbTxpxRYJx/A5LP1hw8+2OnmD42cMP/7skZPtZz+88caHGtxaoACqgLEHGDsgRgIhDQwMdVD6B2Glo2AUjIJRMPIAADltWnnYO+50AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-7496-4182","institution":"Shanghai Jiao Tong University","correspondingAuthor":true,"prefix":"","firstName":"Haifeng","middleName":"","lastName":"Chen","suffix":""},{"id":526199833,"identity":"e5e934f9-e6ca-431c-8291-04769a3e354b","order_by":1,"name":"Zirui Fan","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Zirui","middleName":"","lastName":"Fan","suffix":""},{"id":526199834,"identity":"db12f18f-d790-487b-aedd-b9db4ea5f434","order_by":2,"name":"Junjie Zhu","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Junjie","middleName":"","lastName":"Zhu","suffix":""}],"badges":[],"createdAt":"2025-10-07 10:26:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7798503/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7798503/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94826039,"identity":"8a76518f-7b87-4f30-96f9-b6a890cd496e","added_by":"auto","created_at":"2025-10-31 06:50:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1751459,"visible":true,"origin":"","legend":"","description":"","filename":"DynaFold1003.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7798503/v1_covered_12dd01ec-0521-4319-b3d1-21c57d2ba6bd.pdf"},{"id":93106384,"identity":"0c5453fd-a477-4d78-874f-84e63354f1d9","added_by":"auto","created_at":"2025-10-09 06:50:13","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":3572798,"visible":true,"origin":"","legend":"Supplementary file","description":"","filename":"DynaFoldSl1003.docx","url":"https://assets-eu.researchsquare.com/files/rs-7798503/v1/d951388bc08d283ad2d23405.docx"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Generative Model of Protein Dynamic Trajectory Based on Latent Diffusion with DynaFold","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7798503/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7798503/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The dynamic process of protein folding and conformation switching describes the basis of protein functions. Molecular dynamics (MD) simulations are precise computational tools for exploring protein dynamics, but the high computational costs make it difficult to scale up. Deep learning methods have been used to model the Boltzmann distribution of molecular simulations, but achieving MD-level accuracy remains a major challenge. Here, we present DynaFold, a generative deep learning framework based on latent diffusion for sampling protein dynamic trajectories. DynaFold accepts an initial structure and generalizes the conformational dynamics of different proteins with minimal trajectory data during training. It achieves state-of-the-art accuracy in predicting conformational ensembles and sampling conformational transition pathways, demonstrating superior generalization capability and computational efficiency compared to existing methods. Our framework provides a general solution for generating conformation distributions and transition processes between different conformations for proteins, enabling rapid sampling of structural ensembles and analysis of Boltzmann systems.","manuscriptTitle":"Generative Model of Protein Dynamic Trajectory Based on Latent Diffusion with DynaFold","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-09 06:50:08","doi":"10.21203/rs.3.rs-7798503/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"beb617f9-1d8d-48d2-bf6d-e5780b64c969","owner":[],"postedDate":"October 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55927810,"name":"Biological sciences/Computational biology and bioinformatics/Protein structure predictions"},{"id":55927811,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"}],"tags":[],"updatedAt":"2026-03-20T14:15:44+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-09 06:50:08","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7798503","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7798503","identity":"rs-7798503","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}