Expanding frontiers of complex reaction network exploration through a general reactive machine learning potential

Expanding frontiers of complex reaction network exploration through a general reactive machine learning potential | 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 Expanding frontiers of complex reaction network exploration through a general reactive machine learning potential Shuhua Li, Guoao Li, Haobo Ling, Guoqiang Wang, Manyi Yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6458754/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 Developing general machine learning potentials (MLPs) for complex reactive systems remains a fundamental challenge, due to insufficient sampling of critical transition states (TSs) and non-equilibrium structures in training datasets. Here, we introduce an MD/CD-AL framework integrating molecular dynamics/coordinate driving (MD/CD) method with active learning to generate the MDCD20 dataset that encompasses diverse reactive configurations with up to 20 heavy atoms. With this dataset, we develop a general reactive MLP with quantum mechanics (QM) accuracy, MDCD-NN, for H-/C-/N-/O-containing gas-phase reactions. Leveraging MD/CD searching, MDCD-NN enables automated and efficient construction of complex reaction networks with 10 4 -fold acceleration compared to the reference QM method, as demonstrated in three real-world reaction systems featuring intricate regio-/stereo-selectivities. In each case, our approach successfully identifies thousands of intermediates and TSs, constructing multistep networks that rationalize experimental observations and extend established mechanisms. Furthermore, MDCD-NN enables nanosecond-scale dynamics simulations for calculating reactive free energy surface, bridging quantum-level accuracy with scalable simulations. Our framework provides a paradigm for developing general reactive MLPs, enabling high-throughput mechanistic insights for complex chemical systems. Physical sciences/Chemistry/Theoretical chemistry/Computational chemistry Physical sciences/Chemistry/Theoretical chemistry/Method development Physical sciences/Chemistry/Theoretical chemistry/Reaction mechanisms Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryInfo0415.docx Supplementary Information for Expanding frontiers of complex reaction network exploration through a general reactive machine learning potential 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-6458754","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":455513412,"identity":"ffdcd902-cd04-48fb-9a58-9ba722dd3eeb","order_by":0,"name":"Shuhua Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwUlEQVRIiWNgGAWjYDACCQY2IGnDwNgApHhI0JJGupbDEA5RWuRn95g95qk5n8c8I4Hxwds2BnlzQloM7pwxN+Y5druYcUYCs+HcNgbDnQ2EtEjkmEnzsN1ObJyRwCbN28aQYHCAkMNmgLT8OwfSwv6bKC0MN4BaeNsOgG1hJkqLwY20Msm5fcmJjT0PmyXnnJMw3EDYYcnbJN58s0vc2J588MObMht5wg6DAcMGcGRKEKseZB0JakfBKBgFo2CEAQDLCzy4XRjWqQAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-6756-057X","institution":"State Key Laboratory of Coordination Chemistry, Key Laboratory of Mesoscopic Chemistry of Ministry of Education, School of Chemistry and Chemical Engineering, Nanjing University","correspondingAuthor":true,"prefix":"","firstName":"Shuhua","middleName":"","lastName":"Li","suffix":""},{"id":455513413,"identity":"b489f9ee-6b09-477d-a41b-93abb7dadb2a","order_by":1,"name":"Guoao Li","email":"","orcid":"https://orcid.org/0009-0001-0450-6119","institution":"Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Guoao","middleName":"","lastName":"Li","suffix":""},{"id":455513414,"identity":"c2df2706-c2d2-40d3-a4fe-c0e4afe9b89c","order_by":2,"name":"Haobo Ling","email":"","orcid":"","institution":"State Key Laboratory of Coordination Chemistry, Key Laboratory of Mesoscopic Chemistry of Ministry of Education, School of Chemistry and Chemical Engineering, Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Haobo","middleName":"","lastName":"Ling","suffix":""},{"id":455513415,"identity":"986d6354-64d1-4183-94d0-1e4af4df2c78","order_by":3,"name":"Guoqiang Wang","email":"","orcid":"https://orcid.org/0000-0001-9666-1919","institution":"Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Guoqiang","middleName":"","lastName":"Wang","suffix":""},{"id":455513416,"identity":"935a4070-c4d9-493d-9d27-59008c13f4e4","order_by":4,"name":"Manyi Yang","email":"","orcid":"","institution":"The Institute of Green Chemistry and Engineering, Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Manyi","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2025-04-16 02:25:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6458754/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6458754/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":87600731,"identity":"b6d045fc-e552-4e87-958c-79a077290d01","added_by":"auto","created_at":"2025-07-25 16:49:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1880740,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript0415.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6458754/v1_covered_256eb7c3-0985-4658-9374-97210c0379e0.pdf"},{"id":83592464,"identity":"1f0cd665-2a80-4888-86ff-ba2c314390c9","added_by":"auto","created_at":"2025-05-29 06:48:10","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":4763445,"visible":true,"origin":"","legend":"Supplementary Information for Expanding frontiers of complex reaction network exploration through a general reactive machine learning potential","description":"","filename":"SupplementaryInfo0415.docx","url":"https://assets-eu.researchsquare.com/files/rs-6458754/v1/dece0fb2b7e9f9a993254829.docx"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Expanding frontiers of complex reaction network exploration through a general reactive machine learning potential","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-6458754/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6458754/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDeveloping general machine learning potentials (MLPs) for complex reactive systems remains a fundamental challenge, due to insufficient sampling of critical transition states (TSs) and non-equilibrium structures in training datasets. Here, we introduce an MD/CD-AL framework integrating molecular dynamics/coordinate driving (MD/CD) method with active learning to generate the MDCD20 dataset that encompasses diverse reactive configurations with up to 20 heavy atoms. With this dataset, we develop a general reactive MLP with quantum mechanics (QM) accuracy, MDCD-NN, for H-/C-/N-/O-containing gas-phase reactions. Leveraging MD/CD searching, MDCD-NN enables automated and efficient construction of complex reaction networks with 10\u003csup\u003e4\u003c/sup\u003e-fold acceleration compared to the reference QM method, as demonstrated in three real-world reaction systems featuring intricate regio-/stereo-selectivities. In each case, our approach successfully identifies thousands of intermediates and TSs, constructing multistep networks that rationalize experimental observations and extend established mechanisms. Furthermore, MDCD-NN enables nanosecond-scale dynamics simulations for calculating reactive free energy surface, bridging quantum-level accuracy with scalable simulations. Our framework provides a paradigm for developing general reactive MLPs, enabling high-throughput mechanistic insights for complex chemical systems.\u003c/p\u003e","manuscriptTitle":"Expanding frontiers of complex reaction network exploration through a general reactive machine learning potential","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-29 06:48:05","doi":"10.21203/rs.3.rs-6458754/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":"3ca8f372-8cad-4a8e-8e8a-daf42c7dfaab","owner":[],"postedDate":"May 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":48420586,"name":"Physical sciences/Chemistry/Theoretical chemistry/Computational chemistry"},{"id":48420587,"name":"Physical sciences/Chemistry/Theoretical chemistry/Method development"},{"id":48420588,"name":"Physical sciences/Chemistry/Theoretical chemistry/Reaction mechanisms"}],"tags":[],"updatedAt":"2025-10-29T03:48:35+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-29 06:48:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6458754","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6458754","identity":"rs-6458754","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}