AI-guided Autonomous Workflows Accelerate Kinetic Analysis of Polymer Depolymerization

AI-guided Autonomous Workflows Accelerate Kinetic Analysis of Polymer Depolymerization | 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 Physical Sciences - Article AI-guided Autonomous Workflows Accelerate Kinetic Analysis of Polymer Depolymerization Tomonori Saito, Nicholas Galan, Britney Baez, Ju-An Kim, Beibei Yao, and 9 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9182434/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Deep understanding of polymerization and depolymerization kinetic behavior enables precision synthesis and manufacturing. However, traditional kinetic experiments are bottlenecked by labor-intensive sample collection and analysis practices and suffer reproducibility challenges due to human error and bias. Here, we introduce an artificial intelligence (AI)-driven automated kinetics platform to facilitate kinetic analysis and produce large volumes of high-quality kinetic data with minimal human intervention. Our autonomous workflow, encompassing automated synthesis, analysis, and cloud computing capabilities navigated complex parameter space using an importance-guided Bayesian optimization algorithm, effectively reducing sampling burden while maintaining accuracy in calculating apparent reaction rate constants. Kinetic data from these experiments supported the development of a stochastic simulation model to extract valuable mechanistic information. These capabilities were exploited for “scale-up” synthesis by conducting automated reactions in parallel, facilitating reproducible access to highly precise polymeric building blocks and providing a powerful alternative to polycondensation for the synthesis of telechelics by depolymerization. This work demonstrates how the throughput and accuracy of kinetic experiments can be significantly enhanced by synergizing AI and automation, highlighting the significant potential of these tools to transform the practice of fundamental polymer science. Physical sciences/Chemistry/Polymer chemistry/Polymer synthesis Physical sciences/Chemistry/Polymer chemistry/Polymerization mechanisms Physical sciences/Mathematics and computing/Scientific data Physical sciences/Materials science/Soft materials/Polymers Physical sciences/Nanoscience and technology/Techniques and instrumentation/Design, synthesis and processing Full Text Additional Declarations There is NO Competing Interest. Supplementary Files ACLSINatureSubmission.pdf Supplementary Information Cite Share Download PDF Status: Under Review 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-9182434","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Physical Sciences - Article","associatedPublications":[],"authors":[{"id":610609061,"identity":"2fc95e5b-cd0a-4d2a-8aea-4f6a15a92a8b","order_by":0,"name":"Tomonori Saito","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsklEQVRIiWNgGAWjYFACxgYgYQPEzA1Ea2lsYEhIg+kl2pqEwyRokW8/3P7g44/zcuazGxsYv1QcJqzF4ExiY+OMhNvGMncONjDLnCFGC0NiYzNPwu3EGRKJDcySbWlEOKz/IUjLORK0MNwA23IArIXxY5sNEQ678bBx5oy0ZGMJoJbDDGeI0CLfn/7gwwcbOzkJieSDD39USBDhMGRwmIdEDcDI/EGyllEwCkbBKBgJAACEIDy1P9vjRAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-4536-7530","institution":"Oak Ridge National Laboratory","correspondingAuthor":true,"prefix":"","firstName":"Tomonori","middleName":"","lastName":"Saito","suffix":""},{"id":610609062,"identity":"819cfd4d-b657-4777-9e99-98fc31afdd48","order_by":1,"name":"Nicholas Galan","email":"","orcid":"","institution":"Oak Ridge National Laboraory","correspondingAuthor":false,"prefix":"","firstName":"Nicholas","middleName":"","lastName":"Galan","suffix":""},{"id":610609063,"identity":"112276da-872d-42a2-9737-3722dcc3b4af","order_by":2,"name":"Britney Baez","email":"","orcid":"","institution":"Oak Ridge National Laboraory","correspondingAuthor":false,"prefix":"","firstName":"Britney","middleName":"","lastName":"Baez","suffix":""},{"id":610609064,"identity":"459523e1-992c-4e32-b816-8281d25925f6","order_by":3,"name":"Ju-An Kim","email":"","orcid":"","institution":"Oak Ridge National Laboraory","correspondingAuthor":false,"prefix":"","firstName":"Ju-An","middleName":"","lastName":"Kim","suffix":""},{"id":610609065,"identity":"443630a2-d26e-47c4-bb0c-5670b91aade4","order_by":4,"name":"Beibei Yao","email":"","orcid":"","institution":"Oak Ridge National Laboraory","correspondingAuthor":false,"prefix":"","firstName":"Beibei","middleName":"","lastName":"Yao","suffix":""},{"id":610609066,"identity":"79823ba8-40c1-489d-8564-a9a25a8dc2a9","order_by":5,"name":"Nduka Ogbonna","email":"","orcid":"","institution":"Oak Ridge National Laboraory","correspondingAuthor":false,"prefix":"","firstName":"Nduka","middleName":"","lastName":"Ogbonna","suffix":""},{"id":610609067,"identity":"125f873c-4854-45da-8ffc-e764fb8ce3b7","order_by":6,"name":"Isaiah Dishner,","email":"","orcid":"","institution":"Oak Ridge National Laboraory","correspondingAuthor":false,"prefix":"","firstName":"","middleName":"Isaiah","lastName":"Dishner","suffix":""},{"id":610609068,"identity":"1cea14a7-0dc6-4eee-a7d4-e6fc5d3024be","order_by":7,"name":"Jared Bowman","email":"","orcid":"","institution":"Oak Ridge National Laboraory","correspondingAuthor":false,"prefix":"","firstName":"Jared","middleName":"","lastName":"Bowman","suffix":""},{"id":610609069,"identity":"6f22f67c-2849-4d7a-8508-550195cdc3f7","order_by":8,"name":"Jesse McGaha","email":"","orcid":"","institution":"Oak Ridge National Laboraory","correspondingAuthor":false,"prefix":"","firstName":"Jesse","middleName":"","lastName":"McGaha","suffix":""},{"id":610609070,"identity":"5881f1f4-7380-4053-add5-875902ad5784","order_by":9,"name":"Ankit Shrivastava","email":"","orcid":"","institution":"Oak Ridge National Laboraory","correspondingAuthor":false,"prefix":"","firstName":"Ankit","middleName":"","lastName":"Shrivastava","suffix":""},{"id":610609071,"identity":"f29022de-899d-4d70-96df-48e685740797","order_by":10,"name":"Stephen DeWitt","email":"","orcid":"","institution":"Oak Ridge National Laboraory","correspondingAuthor":false,"prefix":"","firstName":"Stephen","middleName":"","lastName":"DeWitt","suffix":""},{"id":610609072,"identity":"52dd0771-be13-42ed-bc73-9d7c9f069c7f","order_by":11,"name":"Sheng Dai","email":"","orcid":"https://orcid.org/0000-0002-8046-3931","institution":"Oak Ridge National laboratory","correspondingAuthor":false,"prefix":"","firstName":"Sheng","middleName":"","lastName":"Dai","suffix":""},{"id":610609073,"identity":"da8e4d02-3825-4f60-b0d3-cb342d71502a","order_by":12,"name":"Craig Bridges","email":"","orcid":"https://orcid.org/0000-0002-3543-463X","institution":"Oak Ridge National Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Craig","middleName":"","lastName":"Bridges","suffix":""},{"id":610609074,"identity":"c280ab9b-547d-4a6e-98c2-412e7df38522","order_by":13,"name":"Jeffrey C. Foster","email":"","orcid":"https://orcid.org/0000-0002-9097-8680","institution":"ORNL","correspondingAuthor":false,"prefix":"","firstName":"Jeffrey","middleName":"C.","lastName":"Foster","suffix":""}],"badges":[],"createdAt":"2026-03-21 01:01:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9182434/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9182434/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106094200,"identity":"d33b4434-8ebd-4884-bb3e-d1df593b2fc6","added_by":"auto","created_at":"2026-04-03 11:41:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1517253,"visible":true,"origin":"","legend":"","description":"","filename":"ACLManuscriptFinalNatureSubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9182434/v1_covered_eab671aa-aa9b-499e-972b-d6db287dfc59.pdf"},{"id":105780038,"identity":"18b85ae1-060d-4289-9e92-562a61ac1500","added_by":"auto","created_at":"2026-03-31 04:40:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":4246790,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"ACLSINatureSubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9182434/v1/7b11f5ab7f35c5d4e1cf8d3d.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"AI-guided Autonomous Workflows Accelerate Kinetic Analysis of Polymer Depolymerization","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9182434/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9182434/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Deep understanding of polymerization and depolymerization kinetic behavior enables precision synthesis and manufacturing. However, traditional kinetic experiments are bottlenecked by labor-intensive sample collection and analysis practices and suffer reproducibility challenges due to human error and bias. Here, we introduce an artificial intelligence (AI)-driven automated kinetics platform to facilitate kinetic analysis and produce large volumes of high-quality kinetic data with minimal human intervention. Our autonomous workflow, encompassing automated synthesis, analysis, and cloud computing capabilities navigated complex parameter space using an importance-guided Bayesian optimization algorithm, effectively reducing sampling burden while maintaining accuracy in calculating apparent reaction rate constants. Kinetic data from these experiments supported the development of a stochastic simulation model to extract valuable mechanistic information. These capabilities were exploited for “scale-up” synthesis by conducting automated reactions in parallel, facilitating reproducible access to highly precise polymeric building blocks and providing a powerful alternative to polycondensation for the synthesis of telechelics by depolymerization. This work demonstrates how the throughput and accuracy of kinetic experiments can be significantly enhanced by synergizing AI and automation, highlighting the significant potential of these tools to transform the practice of fundamental polymer science.","manuscriptTitle":"AI-guided Autonomous Workflows Accelerate Kinetic Analysis of Polymer Depolymerization","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-31 04:39:42","doi":"10.21203/rs.3.rs-9182434/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"928f6909-d5e5-49a7-82f4-c3924b5fc596","owner":[],"postedDate":"March 31st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":64964797,"name":"Physical sciences/Chemistry/Polymer chemistry/Polymer synthesis"},{"id":64964798,"name":"Physical sciences/Chemistry/Polymer chemistry/Polymerization mechanisms"},{"id":64964799,"name":"Physical sciences/Mathematics and computing/Scientific data"},{"id":64964800,"name":"Physical sciences/Materials science/Soft materials/Polymers"},{"id":64964801,"name":"Physical sciences/Nanoscience and technology/Techniques and instrumentation/Design, synthesis and processing"}],"tags":[],"updatedAt":"2026-04-27T14:57:28+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-31 04:39:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9182434","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9182434","identity":"rs-9182434","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}