A Deep Learning-Augmented Density Functional Framework for Reaction Modeling with Chemical Accuracy

A Deep Learning-Augmented Density Functional Framework for Reaction Modeling with Chemical Accuracy | 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 Research Article A Deep Learning-Augmented Density Functional Framework for Reaction Modeling with Chemical Accuracy Jin Xiao, Yingfeng Zhang, Bowen Li, Shuwen Zhang, Ya Gao, Han Wang, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6041159/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 Accurate prediction of reaction energetics remains a fundamental challenge in computational chemistry, as conventional density functional theory (DFT) often fails to reconcile high accuracy with computational effi ciency. Here, we introduce Deep post-Hartree-Fock (DeePHF), a machine learning framework that synergistically integrates neural networks with quantum mechanical descriptors to achieve CCSD(T)-level precision while retaining the efficiency of DFT. By establishing a direct mapping between the eigenvalues of local density matrices and high-level correlation energies, DeePHF circumvents the traditional accuracy-scalability trade-off . Trained on a limited dataset of small-molecule reactions, our method demonstrates unprecedented performance across multiple benchmark datasets, exhibiting exceptional transferability. In fact, its accuracy even surpasses that of advanced double-hybrid functionals, all while maintaining O(N^3) scaling. DeePHF offers a promising pathway to bridge the gap between high-level quantum chemistry methods and the practical demands for scalable, accurate models in computational chemistry, and with further refinement, it is poised to make significant contributions to the advancement of chemical reaction modeling. Density Functional Theory Machine Learning Density Functional Theory Reaction Energy Barrier Height Full Text Additional Declarations The authors declare no competing interests. Supplementary Files SI.pdf 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-6041159","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":416432890,"identity":"7ec07b6d-69e7-4cc3-9bc5-0c48bfce6242","order_by":0,"name":"Jin Xiao","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Jin","middleName":"","lastName":"Xiao","suffix":""},{"id":416432891,"identity":"93cd49da-1782-423f-a376-5996c3d5dbf9","order_by":1,"name":"Yingfeng Zhang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Yingfeng","middleName":"","lastName":"Zhang","suffix":""},{"id":416432892,"identity":"887beaea-e797-4c47-83b9-f1e7cd86d5fe","order_by":2,"name":"Bowen Li","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Bowen","middleName":"","lastName":"Li","suffix":""},{"id":416432893,"identity":"6086931b-18ca-4ca0-bdc4-5ebe2278798f","order_by":3,"name":"Shuwen Zhang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Shuwen","middleName":"","lastName":"Zhang","suffix":""},{"id":416432894,"identity":"6f5314af-8e7f-427a-8424-6e86169c803e","order_by":4,"name":"Ya Gao","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Ya","middleName":"","lastName":"Gao","suffix":""},{"id":416432895,"identity":"64ae3611-3423-42e2-ab0b-8f873f720e8b","order_by":5,"name":"Han Wang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Han","middleName":"","lastName":"Wang","suffix":""},{"id":416432896,"identity":"d1623ace-9296-4f70-83bf-42f5129873b4","order_by":6,"name":"John Z.H. Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2ElEQVRIiWNgGAWjYBACxgYeEHUAiJkPQIQOEK+FLYE4LQwMcC08BsRpYW7vPfaA4c8deXP+Nd8e87YxyPHdSCDgsJ5z6QYMPM8Md854u90YqMVYkqCWGTlmEgwShxk33Di7TRqoJXEDcVoMDttvuHHmGUhLPZFaEg4nbjjfwwbSkmBA2C9nzCQSDhxO3nCDzUxyzjkJw5lnHuDXYtjeYybx4c9h2w3nDz+TeFNmI893nIAthg1AAqxGIoGBiYdBAr9yEJCHs/gPMDD+IKxhFIyCUTAKRiAAANRRSUGDsRNDAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"John","middleName":"Z.H.","lastName":"Zhang","suffix":""},{"id":416432897,"identity":"2919b9fe-8b11-4d84-9191-4bd36603516d","order_by":7,"name":"Tong Zhu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYLACxgYwxczwAUiysRNQzYOshXEGSAszKVqYeSCW4Qf27L2HX/7ccZjB4HjvY2ObX9vk+ZgZGD98zMFjC8+5NAvJM0AtZ44bJ+f23TZsY2Zglpy5DY8WiRwzA8O2wwxmN9KYD+f23GYEamFj5iWkJRGmxbLntj0xWowfHIRqSWb4cTuRsJYzZ8wYG9vSeezPHGM27G24ndzGzNiM1y/s7T3GH3+2WctJtrcxS/z4c9t2fnvzwQ8f8WgBAjYJBmj8MDC2gckGvOqBgPkDgv2HkOJRMApGwSgYiQAA22xMXtyojb8AAAAASUVORK5CYII=","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Tong","middleName":"","lastName":"Zhu","suffix":""}],"badges":[],"createdAt":"2025-02-16 12:41:34","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6041159/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6041159/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":76636114,"identity":"eee703c8-0042-4e69-8290-0b0375868cfd","added_by":"auto","created_at":"2025-02-19 07:34:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2304854,"visible":true,"origin":"","legend":"","description":"","filename":"DeePHFforReactionI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6041159/v1_covered_05983514-d226-423c-8d25-2afaea5cec83.pdf"},{"id":76635926,"identity":"167d13b3-6e22-45eb-b108-a9e9be94d948","added_by":"auto","created_at":"2025-02-19 07:26:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":75066,"visible":true,"origin":"","legend":"","description":"","filename":"SI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6041159/v1/33bb6bf7d8308c2338afdbfc.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eA Deep Learning-Augmented Density Functional Framework for Reaction Modeling with Chemical Accuracy\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Shanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, School of Chemistry and Molecular Engineering, East China Normal University at Shanghai, 200062, China","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":"Density Functional Theory, Machine Learning Density Functional Theory, Reaction Energy, Barrier Height","lastPublishedDoi":"10.21203/rs.3.rs-6041159/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6041159/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate prediction of reaction energetics remains a fundamental challenge in computational chemistry, as conventional density functional theory (DFT) often fails to reconcile high accuracy with computational effi ciency. Here, we introduce Deep post-Hartree-Fock (DeePHF), a machine learning framework that synergistically integrates neural networks with quantum mechanical descriptors to achieve CCSD(T)-level precision while retaining the efficiency of DFT. By establishing a direct mapping between the eigenvalues of local density matrices and high-level correlation energies, DeePHF circumvents the traditional accuracy-scalability trade-off . Trained on a limited dataset of small-molecule reactions, our method demonstrates unprecedented performance across multiple benchmark datasets, exhibiting exceptional transferability. In fact, its accuracy even surpasses that of advanced double-hybrid functionals, all while maintaining O(N^3) scaling. DeePHF offers a promising pathway to bridge the gap between high-level quantum chemistry methods and the practical demands for scalable, accurate models in computational chemistry, and with further refinement, it is poised to make significant contributions to the advancement of chemical reaction modeling.\u003c/p\u003e","manuscriptTitle":"A Deep Learning-Augmented Density Functional Framework for Reaction Modeling with Chemical Accuracy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-19 07:26:27","doi":"10.21203/rs.3.rs-6041159/v1","editorialEvents":[{"type":"communityComments","content":0}],"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":"c64349e4-57d9-4c70-beb2-fb1fb3af85e3","owner":[],"postedDate":"February 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-02-19T07:26:27+00:00","versionOfRecord":[],"versionCreatedAt":"2025-02-19 07:26:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6041159","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6041159","identity":"rs-6041159","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}