Multi-property directed generative design of inorganic materials through Wyckoff-augmented transfer learning

Multi-property directed generative design of inorganic materials through Wyckoff-augmented transfer 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 Multi-property directed generative design of inorganic materials through Wyckoff-augmented transfer learning Kedar Hippalgaonkar, Shuya Yamazaki, Wei Nong, Ruiming Zhu, Kostya S. Novoselov, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6193239/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 Accelerated materials discovery is an urgent demand to drive advancements in fields such as energy conversion, storage, and catalysis. Property-directed generative design has emerged as a transformative approach for rapidly discovering new functional inorganic materials with multiple desired properties within vast and complex search spaces. However, this approach faces two primary challenges: data scarcity for functional properties and the multi-objective optimization required to balance competing tasks. Here, we present a multi-property-directed generative framework designed to overcome these limitations and enhance site symmetry-compliant crystal generation beyond P1 (translational) symmetry. By incorporating Wyckoff-position-based data augmentation and transfer learning, our framework effectively handles sparse and small functional datasets, enabling the generation of new stable materials simultaneously conditioned on targeted space group, band gap, and formation energy. Using this approach, we identified Cs₂Pt₃Se₇, Cd₂Ge₂O₃, Tl₃As₃S₄, Na₃MnSe₄, Al₆Ge₅S₁₁, Cd₃P₂Se₆, Rb₆Hg₂S₅, and Zr₂MnO₆ as previously unknown thermodynamically and lattice-dynamically stable semiconductors in tetragonal, trigonal, and cubic systems, with bandgaps ranging from 0.13 to 2.20 eV, as validated by density functional theory (DFT) calculations. Additionally, we assessed their thermoelectric descriptors using DFT, indicating their potential suitability for thermoelectric applications. We believe our integrated framework represents a significant step forward in generative design of inorganic materials. Physical sciences/Materials science/Theory and computation/Computational methods Physical sciences/Materials science/Condensed-matter physics Full Text Additional Declarations Yes there is potential Competing Interest. K.H. holds equity in a startup focused on using AI for new materials development. Supplementary Files MultipropertydirecteddesignmanuscriptSI.pdf Supplementary Information SourceData.csv Dataset 1 machinelearningchecklist.pdf Machine Learning Checklist nrsoftwarepolicy.pdf Software Policy Checklist 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-6193239","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":433282351,"identity":"df894677-862a-4243-b8d5-7f38fe839c57","order_by":0,"name":"Kedar Hippalgaonkar","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxklEQVRIiWNgGAWjYBACCQYGAwaGCjiHaC1nIKpJ0MLYRooWyfbmjZ8r592pMzjAfPA2D0OdXQMhLdI8x4olz257JmFwgC3ZmofhcDJBLXISOQaSjdsOA7XwmEnzMBxIJugwOfk3xj8b54C08H8DaqkjrEVagsdMsrEBbAsbUAuzHUEtkj1pZZYNxw5LzjzMZmw5x+BwAkEtEscPb77ZUHOYn+9488Mbbyrq7AlqQQBmEGHAkNhAgh4IIMWWUTAKRsEoGCEAAKvRNxxeNFE5AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-1270-9047","institution":"Nanyang Technological University","correspondingAuthor":true,"prefix":"","firstName":"Kedar","middleName":"","lastName":"Hippalgaonkar","suffix":""},{"id":433282352,"identity":"db0158a4-1e61-4f61-95e5-358bf98102de","order_by":1,"name":"Shuya Yamazaki","email":"","orcid":"https://orcid.org/0009-0004-5649-4756","institution":"Nanyang Technological University","correspondingAuthor":false,"prefix":"","firstName":"Shuya","middleName":"","lastName":"Yamazaki","suffix":""},{"id":433282353,"identity":"e42df026-c639-43c6-83b8-a57d8e17af6c","order_by":2,"name":"Wei Nong","email":"","orcid":"https://orcid.org/0000-0002-6838-7155","institution":"Nanyang Technological University","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Nong","suffix":""},{"id":433282354,"identity":"0e4e3615-35df-4938-a151-5fa38158f534","order_by":3,"name":"Ruiming Zhu","email":"","orcid":"","institution":"Nanyang Technological University","correspondingAuthor":false,"prefix":"","firstName":"Ruiming","middleName":"","lastName":"Zhu","suffix":""},{"id":433282355,"identity":"2ecdc987-20b2-4c47-bdc3-ea29fff74f5c","order_by":4,"name":"Kostya S. Novoselov","email":"","orcid":"https://orcid.org/0000-0003-4972-5371","institution":"National University of Singapore","correspondingAuthor":false,"prefix":"","firstName":"Kostya","middleName":"S.","lastName":"Novoselov","suffix":""},{"id":433282356,"identity":"866243ce-2aa7-4074-a018-4a2fa02a0336","order_by":5,"name":"Andrey Ustyuzhanin","email":"","orcid":"https://orcid.org/0000-0001-7865-2357","institution":"Constructor University","correspondingAuthor":false,"prefix":"","firstName":"Andrey","middleName":"","lastName":"Ustyuzhanin","suffix":""}],"badges":[],"createdAt":"2025-03-10 08:15:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6193239/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6193239/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83128949,"identity":"3e0f8d61-f810-47f1-8ae2-5f318a673d14","added_by":"auto","created_at":"2025-05-20 09:59:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1092635,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Multipropertydirecteddesignmanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6193239/v1_covered_a6494f95-a59b-4655-99a6-6aab01e58e5e.pdf"},{"id":79144375,"identity":"3b2bb7ac-a40e-42c0-8856-27a0a5f82d6e","added_by":"auto","created_at":"2025-03-25 02:39:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":770306,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"MultipropertydirecteddesignmanuscriptSI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6193239/v1/e23ba86ca16a2dc98dce5b8f.pdf"},{"id":79144373,"identity":"7ba2f28c-ccbb-44b6-9029-b3bb6eaab5db","added_by":"auto","created_at":"2025-03-25 02:39:38","extension":"csv","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":1462632,"visible":true,"origin":"","legend":"Dataset 1","description":"","filename":"SourceData.csv","url":"https://assets-eu.researchsquare.com/files/rs-6193239/v1/d4d05fe1c00481c8a4ee8439.csv"},{"id":79143835,"identity":"fdd65d6a-60fe-4ecf-95ab-cdf87a3be72a","added_by":"auto","created_at":"2025-03-25 02:31:38","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":381678,"visible":true,"origin":"","legend":"Machine Learning Checklist","description":"","filename":"machinelearningchecklist.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6193239/v1/8130f8dcff21c0ea7bd97159.pdf"},{"id":79144886,"identity":"b7deca52-7195-411c-b1cf-802ad69c726c","added_by":"auto","created_at":"2025-03-25 02:47:38","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":1317034,"visible":true,"origin":"","legend":"Software Policy Checklist","description":"","filename":"nrsoftwarepolicy.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6193239/v1/6e7fc1c9f2e229f4a545bc46.pdf"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nK.H. holds equity in a startup focused on using AI for new materials development.","formattedTitle":"Multi-property directed generative design of inorganic materials through Wyckoff-augmented transfer learning","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-6193239/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6193239/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accelerated materials discovery is an urgent demand to drive advancements in fields such as energy conversion, storage, and catalysis. Property-directed generative design has emerged as a transformative approach for rapidly discovering new functional inorganic materials with multiple desired properties within vast and complex search spaces. However, this approach faces two primary challenges: data scarcity for functional properties and the multi-objective optimization required to balance competing tasks. Here, we present a multi-property-directed generative framework designed to overcome these limitations and enhance site symmetry-compliant crystal generation beyond P1 (translational) symmetry. By incorporating Wyckoff-position-based data augmentation and transfer learning, our framework effectively handles sparse and small functional datasets, enabling the generation of new stable materials simultaneously conditioned on targeted space group, band gap, and formation energy. Using this approach, we identified Cs₂Pt₃Se₇, Cd₂Ge₂O₃, Tl₃As₃S₄, Na₃MnSe₄, Al₆Ge₅S₁₁, Cd₃P₂Se₆, Rb₆Hg₂S₅, and Zr₂MnO₆ as previously unknown thermodynamically and lattice-dynamically stable semiconductors in tetragonal, trigonal, and cubic systems, with bandgaps ranging from 0.13 to 2.20 eV, as validated by density functional theory (DFT) calculations. Additionally, we assessed their thermoelectric descriptors using DFT, indicating their potential suitability for thermoelectric applications. We believe our integrated framework represents a significant step forward in generative design of inorganic materials.","manuscriptTitle":"Multi-property directed generative design of inorganic materials through Wyckoff-augmented transfer learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-25 02:31:34","doi":"10.21203/rs.3.rs-6193239/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":"e7453598-8c33-492c-a062-689e4d30c913","owner":[],"postedDate":"March 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46136153,"name":"Physical sciences/Materials science/Theory and computation/Computational methods"},{"id":46136154,"name":"Physical sciences/Materials science/Condensed-matter physics"}],"tags":[],"updatedAt":"2025-05-20T09:51:41+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-25 02:31:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6193239","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6193239","identity":"rs-6193239","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}