Bayesian Flow Is All You Need to Sample Out-of-Distribution Chemical Spaces

Bayesian Flow Is All You Need to Sample Out-of-Distribution Chemical Spaces | 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 Bayesian Flow Is All You Need to Sample Out-of-Distribution Chemical Spaces Nianze Tao, Minori Abe This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8517216/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Generating novel molecules with higher properties than the training space, namely the out-of-distribution generation, is important for de novo drug design. However, it is not easy for distribution learning-based models, for example diffusion models, to solve this challenge as these methods are designed to fit the distribution of training data as close as possible. In this paper, we show that Bayesian flow network is capable of effortlessly generating high quality out-of-distribution samples that meet several scenarios. We introduce a semi-autoregressive training/sampling method that helps to enhance the model performance and surpass the state-of-the-art models. Out-of-distribution sampling semi-autoregressive de novo design Bayesian Flow Networks Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 07 Feb, 2026 Reviews received at journal 03 Feb, 2026 Reviewers agreed at journal 28 Jan, 2026 Reviews received at journal 26 Jan, 2026 Reviews received at journal 25 Jan, 2026 Reviewers agreed at journal 21 Jan, 2026 Reviewers agreed at journal 19 Jan, 2026 Reviewers invited by journal 19 Jan, 2026 Editor assigned by journal 05 Jan, 2026 Submission checks completed at journal 05 Jan, 2026 First submitted to journal 05 Jan, 2026 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-8517216","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":576788697,"identity":"c1e9db3e-b9fb-4b0f-9075-84c6528797c7","order_by":0,"name":"Nianze Tao","email":"data:image/png;base64,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","orcid":"","institution":"Tokyo University of Agriculture and Technology","correspondingAuthor":true,"prefix":"","firstName":"Nianze","middleName":"","lastName":"Tao","suffix":""},{"id":576788698,"identity":"2f208746-87ee-43b0-b31f-bc5ec8ef718f","order_by":1,"name":"Minori Abe","email":"","orcid":"","institution":"Tokyo University of Agriculture and Technology","correspondingAuthor":false,"prefix":"","firstName":"Minori","middleName":"","lastName":"Abe","suffix":""}],"badges":[],"createdAt":"2026-01-05 05:38:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8517216/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8517216/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100751547,"identity":"690fd8cb-3260-4e2f-b27f-a5405e079dec","added_by":"auto","created_at":"2026-01-21 04:52:23","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3551,"visible":true,"origin":"","legend":"","description":"","filename":"3d8336b78424469487389b1fa836a5e4.json","url":"https://assets-eu.researchsquare.com/files/rs-8517216/v1/0b4831dfff962878b470f339.json"},{"id":100804063,"identity":"4ebe4b36-4064-4825-bf1e-2cade9d4a45e","added_by":"auto","created_at":"2026-01-21 14:35:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":10444085,"visible":true,"origin":"","legend":"","description":"","filename":"chembfnood.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8517216/v1_covered_837c6f9b-e697-42ff-9733-0441244109ef.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Bayesian Flow Is All You Need to Sample Out-of-Distribution Chemical Spaces","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"journal-of-cheminformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"chin","sideBox":"Learn more about [Journal of Cheminformatics](https://jcheminf.biomedcentral.com/)","snPcode":"13321","submissionUrl":"https://submission.nature.com/new-submission/13321/3","title":"Journal of Cheminformatics","twitterHandle":"@jcheminf","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Out-of-distribution sampling, semi-autoregressive, de novo design, Bayesian Flow Networks","lastPublishedDoi":"10.21203/rs.3.rs-8517216/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8517216/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Generating novel molecules with higher properties than the training space, namely the out-of-distribution generation, is important for de novo drug design. However, it is not easy for distribution learning-based models, for example diffusion models, to solve this challenge as these methods are designed to fit the distribution of training data as close as possible. In this paper, we show that Bayesian flow network is capable of effortlessly generating high quality out-of-distribution samples that meet several scenarios. We introduce a semi-autoregressive training/sampling method that helps to enhance the model performance and surpass the state-of-the-art models.","manuscriptTitle":"Bayesian Flow Is All You Need to Sample Out-of-Distribution Chemical Spaces","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-21 04:52:19","doi":"10.21203/rs.3.rs-8517216/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-07T09:16:38+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-03T11:38:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"201003951887244377029620674530388440218","date":"2026-01-28T12:48:05+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-26T07:50:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-25T08:03:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"80109716695360616318401648637616812519","date":"2026-01-21T11:31:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"308149077441649017670944502346618506603","date":"2026-01-19T11:09:17+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-19T11:01:08+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-05T09:22:08+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-05T06:37:02+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Cheminformatics","date":"2026-01-05T05:25:39+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-cheminformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"chin","sideBox":"Learn more about [Journal of Cheminformatics](https://jcheminf.biomedcentral.com/)","snPcode":"13321","submissionUrl":"https://submission.nature.com/new-submission/13321/3","title":"Journal of Cheminformatics","twitterHandle":"@jcheminf","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"34139b91-aabd-4616-93d2-f7543f28c783","owner":[],"postedDate":"January 21st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-11T09:38:40+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-21 04:52:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8517216","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8517216","identity":"rs-8517216","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}