A unified language model bridging de novo and fragment-based 3D molecule design

A unified language model bridging de novo and fragment-based 3D molecule design | 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 A unified language model bridging de novo and fragment-based 3D molecule design Bo Huang, Han Wang, Bin Xi, Zhenming Liu, Guanglong Sun, Yang Wang, and 13 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8558464/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 The rational design of small molecules is central to drug discovery, yet current artificial intelligence (AI) methodologies for generating three-dimensional (3D) molecules are often siloed, focusing on either de novo design or fragment-based design. The lack of a holistic framework limits AI’s application across the complex and multi-step pipeline spanning from novel scaffold identification to lead compound optimization, and prevents AI from effectively learning from the entire process. Here, we introduce UniLingo3DMol, a language model for 3D molecular generation, empowered by fragment permutation-capable molecular representation alongside multi-stage and multi-task training strategy. This integrated design enables UniLingo3DMol to seamlessly span both de novo and fragment-retained molecular design, demonstrating superior performance over existing generation models in in silico evaluations across more than 100 diverse biological targets. We further leveraged UniLingo3DMol in the design of inhibitors targeting CBL-B, a crucial immune E3 ubiquitin ligase and attractive immunotherapy target. This strategy led to a lead compound demonstrating excellent in vitro activity and robust in vivo anti-tumor efficacy. Our findings establish UniLingo3DMol as a generalized and powerful platform, showing the strong potential to advance AI-driven drug discovery. Biological sciences/Drug discovery/Medicinal chemistry/Structure-based drug design Biological sciences/Drug discovery/Medicinal chemistry/Structure-based drug design Biological sciences/Computational biology and bioinformatics/Computational models Biological sciences/Computational biology and bioinformatics/Computational models Biological sciences/Drug discovery/Drug screening/Virtual screening Biological sciences/Drug discovery/Drug screening/Virtual screening Full Text Additional Declarations There is NO Competing Interest. Supplementary Files D1300062747valreportannotateP1.pdf wwPDB X-ray Structure Validation Summary Report UniLingo3DMolsupplementarymaterialsNMI.pdf supplementary materials 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-8558464","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":586148349,"identity":"bb185b02-cec2-467f-90c2-8788e76873fd","order_by":0,"name":"Bo Huang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYBACAwYeCIONmbHxQUJFDQla+NmZmw0enDlGghbJfvY2yYctzIS1mLP3HpP4uaOWweAwY1tFYgMbA397dwJeLZY959Ike88cB2u5kbhDhkHizNkN+B12I8dMgrftGFTLGTYGA4lcwlok/0K1FCS2MROnRZq3rYZBspmxjYEoLZY9Z4ytZdsOMPAzMzZLJJw5xkPQL+bsPYY337bVMbDxH3/48UdFjRx/ey9+LVBwuL4ByuIhRjkI1BGrcBSMglEwCkYiAAAeN0dOAB0whAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-3822-9110","institution":"College of Pharmaceutical Sciences, Capital Medical University","correspondingAuthor":true,"prefix":"","firstName":"Bo","middleName":"","lastName":"Huang","suffix":""},{"id":586148350,"identity":"fec33705-5864-4390-97dd-13172c0e8c93","order_by":1,"name":"Han Wang","email":"","orcid":"https://orcid.org/0000-0001-9282-2105","institution":"State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University","correspondingAuthor":false,"prefix":"","firstName":"Han","middleName":"","lastName":"Wang","suffix":""},{"id":586148352,"identity":"d240e262-5277-4277-84ee-13acdea7fee6","order_by":2,"name":"Bin Xi","email":"","orcid":"https://orcid.org/0000-0003-0141-2157","institution":"Peking University","correspondingAuthor":false,"prefix":"","firstName":"Bin","middleName":"","lastName":"Xi","suffix":""},{"id":586148354,"identity":"5fec2272-101f-491b-b308-20977356ced4","order_by":3,"name":"Zhenming Liu","email":"","orcid":"https://orcid.org/0000-0002-8993-4015","institution":"Peking University","correspondingAuthor":false,"prefix":"","firstName":"Zhenming","middleName":"","lastName":"Liu","suffix":""},{"id":586148356,"identity":"863576c2-9bd4-4445-9e9d-29b319179de0","order_by":4,"name":"Guanglong Sun","email":"","orcid":"","institution":"Beijing StoneWise Technology Co Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Guanglong","middleName":"","lastName":"Sun","suffix":""},{"id":586148358,"identity":"7c715bd0-4205-4e16-b0db-b8751b9c28ca","order_by":5,"name":"Yang Wang","email":"","orcid":"","institution":"Beijing StoneWise Technology Co Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Wang","suffix":""},{"id":586148359,"identity":"dd8cd93b-08e8-4e73-b646-ea123ad9c089","order_by":6,"name":"Minjian Yang","email":"","orcid":"","institution":"Beijing StoneWise Technology Co Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Minjian","middleName":"","lastName":"Yang","suffix":""},{"id":586148362,"identity":"99dfc2d9-3101-4c6d-85e4-8034f2de4cbd","order_by":7,"name":"Yuyang Ge","email":"","orcid":"","institution":"Beijing StoneWise Technology Co Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Yuyang","middleName":"","lastName":"Ge","suffix":""},{"id":586148364,"identity":"3a8b264a-e044-48d8-86a9-4f807043b2e6","order_by":8,"name":"Fan Fan","email":"","orcid":"","institution":"Beijing StoneWise Technology Co Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Fan","middleName":"","lastName":"Fan","suffix":""},{"id":586148365,"identity":"85888b87-d4ce-4446-985d-b47d873f2d7e","order_by":9,"name":"Wei Feng","email":"","orcid":"https://orcid.org/0009-0007-1220-1458","institution":"Beijing StoneWise Technology Co Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Feng","suffix":""},{"id":586148367,"identity":"c2ca98de-cec9-4ea9-9028-042c5b11c1c5","order_by":10,"name":"Yanhao Zhu","email":"","orcid":"","institution":"Beijing StoneWise Technology Co Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Yanhao","middleName":"","lastName":"Zhu","suffix":""},{"id":586148368,"identity":"ec5c5efa-0311-4588-a247-b8f789ce4d5e","order_by":11,"name":"Yang Xiao","email":"","orcid":"","institution":"Beijing StoneWise Technology Co Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Xiao","suffix":""},{"id":586148369,"identity":"f2417031-a368-4377-9c0f-5f9d9afd74ed","order_by":12,"name":"Huting Wang","email":"","orcid":"","institution":"Beijing StoneWise Technology Co Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Huting","middleName":"","lastName":"Wang","suffix":""},{"id":586148372,"identity":"42121698-fd42-47a8-939c-d8bb5da81c4d","order_by":13,"name":"Wenbiao Zhou","email":"","orcid":"https://orcid.org/0000-0002-7168-3676","institution":"Beijing StoneWise Technology Co Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Wenbiao","middleName":"","lastName":"Zhou","suffix":""},{"id":586148375,"identity":"c5310389-d13f-430b-9c82-7f922fa8fa75","order_by":14,"name":"Bowen Zhang","email":"","orcid":"","institution":"Peking University","correspondingAuthor":false,"prefix":"","firstName":"Bowen","middleName":"","lastName":"Zhang","suffix":""},{"id":586148376,"identity":"eda88aa3-426a-4086-a904-64a1b4de11f1","order_by":15,"name":"Chuanyu Liu","email":"","orcid":"","institution":"Laboratory of Soft Matter Physics, Institute of Physics, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Chuanyu","middleName":"","lastName":"Liu","suffix":""},{"id":586148378,"identity":"25461344-00e8-4ec8-9ab0-03f7b275047b","order_by":16,"name":"Daohua Jiang","email":"","orcid":"https://orcid.org/0000-0002-4397-5807","institution":"Institute of Physics, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Daohua","middleName":"","lastName":"Jiang","suffix":""},{"id":586148379,"identity":"040a310c-b0aa-4f47-9bcd-92ddaf15404e","order_by":17,"name":"Xiaojian Xu","email":"","orcid":"","institution":"Beijing Neurosurgical Institute, Capital Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xiaojian","middleName":"","lastName":"Xu","suffix":""},{"id":586148380,"identity":"29e7925a-0102-4329-8e84-45996f28bf5b","order_by":18,"name":"Yuji Wang","email":"","orcid":"","institution":"Department of Medicinal Chemistry, College of Pharmaceutical Sciences of Capital Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yuji","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2026-01-09 08:22:41","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8558464/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8558464/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106960204,"identity":"c78019e2-4a6f-4d8b-9f6b-30fbe47f8c35","added_by":"auto","created_at":"2026-04-15 09:19:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3539243,"visible":true,"origin":"","legend":"Article File","description":"","filename":"UniLingo3DMolmainNMI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8558464/v1_covered_247c282a-3d56-4128-95fa-032c2b6e11e8.pdf"},{"id":102845234,"identity":"1ba7e2ec-ffff-47e2-89d7-b81989680f61","added_by":"auto","created_at":"2026-02-17 13:04:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1282650,"visible":true,"origin":"","legend":"wwPDB X-ray Structure Validation Summary Report","description":"","filename":"D1300062747valreportannotateP1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8558464/v1/f541954adcc9e43e214dabc2.pdf"},{"id":102845235,"identity":"3ab2c0ec-a2bd-4d5c-9fe4-a5963c8901e4","added_by":"auto","created_at":"2026-02-17 13:04:24","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":4671143,"visible":true,"origin":"","legend":"supplementary materials","description":"","filename":"UniLingo3DMolsupplementarymaterialsNMI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8558464/v1/acf5f90f709f1cfe3d0d5687.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"A unified language model bridging de novo and fragment-based 3D molecule design","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-8558464/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8558464/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The rational design of small molecules is central to drug discovery, yet current artificial intelligence (AI) methodologies for generating three-dimensional (3D) molecules are often siloed, focusing on either de novo design or fragment-based design. The lack of a holistic framework limits AI’s application across the complex and multi-step pipeline spanning from novel scaffold identification to lead compound optimization, and prevents AI from effectively learning from the entire process. Here, we introduce UniLingo3DMol, a language model for 3D molecular generation, empowered by fragment permutation-capable molecular representation alongside multi-stage and multi-task training strategy. This integrated design enables UniLingo3DMol to seamlessly span both de novo and fragment-retained molecular design, demonstrating superior performance over existing generation models in in silico evaluations across more than 100 diverse biological targets. We further leveraged UniLingo3DMol in the design of inhibitors targeting CBL-B, a crucial immune E3 ubiquitin ligase and attractive immunotherapy target. This strategy led to a lead compound demonstrating excellent in vitro activity and robust in vivo anti-tumor efficacy. Our findings establish UniLingo3DMol as a generalized and powerful platform, showing the strong potential to advance AI-driven drug discovery.","manuscriptTitle":"A unified language model bridging de novo and fragment-based 3D molecule design","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-17 13:04:16","doi":"10.21203/rs.3.rs-8558464/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":"8be7a661-e7c1-4113-bfeb-706992a837f9","owner":[],"postedDate":"February 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":62363268,"name":"Biological sciences/Drug discovery/Medicinal chemistry/Structure-based drug design"},{"id":62363269,"name":"Biological sciences/Drug discovery/Medicinal chemistry/Structure-based drug design"},{"id":62363270,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"},{"id":62363271,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"},{"id":62363272,"name":"Biological sciences/Drug discovery/Drug screening/Virtual screening"},{"id":62363273,"name":"Biological sciences/Drug discovery/Drug screening/Virtual screening"}],"tags":[],"updatedAt":"2026-04-14T06:05:21+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-17 13:04:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8558464","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8558464","identity":"rs-8558464","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}