Exploring the Chemical Space of Metal Clusters via Machine Learning

Exploring the Chemical Space of Metal Clusters via Machine Learning | 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 Exploring the Chemical Space of Metal Clusters via Machine Learning Sheng-Gui He, Ning-Zheng Li, Zi-Yue Wang, Zi-Yu Li, Qiang Shi, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8784571/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 Atomic clusters serve as the embryos of materials, yet their enormous and compositionally complex chemical space has long hindered systematic exploration of thermodynamic stability. Here, a unified first-principles and machine-learning framework is developed to enable large-scale mapping of metal cluster thermodynamics. By introducing a progressive sampling strategy integrated with a composition-based deep learning model, the intrinsic sampling bottleneck associated with exponentially expanding chemical spaces is alleviated. Based on ~45,000 global-minimum structures obtained via automated first-principles calculations, a composition-based deep learning model, the Cluster Transformer Encoder Network, enables reliable predictions of atomization energies (~50 meV/atom accuracy) for 9.13 million metal cluster compositions, covering 30 d-block metals and 4 main-group elements. The resulting thermodynamic trends reveal strong correlations between cluster atomization energies and bulk cohesive energies and highlight heteronuclear stabilization and the stability of noble-metal-doped oxide clusters. This work establishes a general strategy for efficient exploration of chemically complex cluster spaces and advances a holistic understanding of the collective properties of metal clusters. Physical sciences/Chemistry/Physical chemistry/Thermodynamics Physical sciences/Chemistry/Theoretical chemistry/Computational chemistry Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupportingInformationNatChem02024.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-8784571","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":587036294,"identity":"82550685-fcc5-4282-82fb-20df66560235","order_by":0,"name":"Sheng-Gui He","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIiWNgGAWjYDACCQjFY8DAfOAAqVrYEkjTwmAA0kUUkJ/dfOzhl1+HZczZez4e+FFjZ8/AfvgBw88duLUY3DmWbizbd5jHsufshoM9x5ITG3jSDBh7z+DRIpFjJi3Zc5jH4EbuhsOMDcwJDAw5DMyMbXgcNiP/G0TL/TcPgFrq7Rn43+DXwnAjh03yww+QLTwMQC1AJEHAFoMbaWbSjA3pPAZn0gyAfjme2CbxzOBgL16HJT+T/PHH2t7g+OHHH37UVNvz8yc/fPATn8OAgJkXWQEbEB/Ar4GBgfHHH0JKRsEoGAWjYEQDABVrUzGQiu7kAAAAAElFTkSuQmCC","orcid":"","institution":"Institute of Chemistry, Chinese Academy of Sciences","correspondingAuthor":true,"prefix":"","firstName":"Sheng-Gui","middleName":"","lastName":"He","suffix":""},{"id":587036295,"identity":"8f136d94-805f-4df3-b7fd-5b2516ada3c6","order_by":1,"name":"Ning-Zheng Li","email":"","orcid":"","institution":"Key Laboratory for Structural Chemistry of Unstable and Stable Species, Institute of Chemistry, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Ning-Zheng","middleName":"","lastName":"Li","suffix":""},{"id":587036296,"identity":"9aca20b0-bb2c-4dc4-8cc9-0dc3dabda72b","order_by":2,"name":"Zi-Yue Wang","email":"","orcid":"","institution":"Institute of Software, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Zi-Yue","middleName":"","lastName":"Wang","suffix":""},{"id":587036297,"identity":"82ad5454-068b-4bc2-aa98-ec73f55a97ee","order_by":3,"name":"Zi-Yu Li","email":"","orcid":"","institution":"Institute of Chemistry, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Zi-Yu","middleName":"","lastName":"Li","suffix":""},{"id":587036298,"identity":"ab7403a0-65e1-4ed1-857f-4fe2785957e5","order_by":4,"name":"Qiang Shi","email":"","orcid":"","institution":"Institute of Chemistry, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Qiang","middleName":"","lastName":"Shi","suffix":""},{"id":587036299,"identity":"3c07087a-5e84-4fd1-b376-1fc1982a19ce","order_by":5,"name":"Qing-Yu Liu","email":"","orcid":"","institution":"Institute of Chemistry, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Qing-Yu","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2026-02-04 09:50:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8784571/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8784571/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102746773,"identity":"2d83e533-cfc9-48f2-9fd7-3f97956a30fa","added_by":"auto","created_at":"2026-02-16 09:01:12","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1644687,"visible":true,"origin":"","legend":"Article File","description":"","filename":"ManuscriptNatChem0204rev.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8784571/v1_covered_b6cb4449-172d-49d6-9f8c-7b6778cf2d93.pdf"},{"id":102484949,"identity":"67ae52dd-989a-4f87-8b7a-a219dd7bded9","added_by":"auto","created_at":"2026-02-12 07:33:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":991015,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"SupportingInformationNatChem02024.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8784571/v1/d6c183fb54f3005c24024f5e.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Exploring the Chemical Space of Metal Clusters via Machine Learning","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-8784571/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8784571/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Atomic clusters serve as the embryos of materials, yet their enormous and compositionally complex chemical space has long hindered systematic exploration of thermodynamic stability. Here, a unified first-principles and machine-learning framework is developed to enable large-scale mapping of metal cluster thermodynamics. By introducing a progressive sampling strategy integrated with a composition-based deep learning model, the intrinsic sampling bottleneck associated with exponentially expanding chemical spaces is alleviated. Based on ~45,000 global-minimum structures obtained via automated first-principles calculations, a composition-based deep learning model, the Cluster Transformer Encoder Network, enables reliable predictions of atomization energies (~50 meV/atom accuracy) for 9.13 million metal cluster compositions, covering 30 d-block metals and 4 main-group elements. The resulting thermodynamic trends reveal strong correlations between cluster atomization energies and bulk cohesive energies and highlight heteronuclear stabilization and the stability of noble-metal-doped oxide clusters. This work establishes a general strategy for efficient exploration of chemically complex cluster spaces and advances a holistic understanding of the collective properties of metal clusters.","manuscriptTitle":"Exploring the Chemical Space of Metal Clusters via Machine Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-12 07:33:45","doi":"10.21203/rs.3.rs-8784571/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":"4bc32c39-f4fe-4238-a0c0-721e0004547a","owner":[],"postedDate":"February 12th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":62460812,"name":"Physical sciences/Chemistry/Physical chemistry/Thermodynamics"},{"id":62460813,"name":"Physical sciences/Chemistry/Theoretical chemistry/Computational chemistry"}],"tags":[],"updatedAt":"2026-02-12T07:33:45+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-12 07:33:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8784571","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8784571","identity":"rs-8784571","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}