A Multimodal Semi-Supervised Learning Framework for Pharmaceutical Cocrystals Prediction

A Multimodal Semi-Supervised Learning Framework for Pharmaceutical Cocrystals Prediction | 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 Multimodal Semi-Supervised Learning Framework for Pharmaceutical Cocrystals Prediction Sohrab Rohani, Mohammad Ghanavati, Seyed Mohamad Moosavi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9140169/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 Cocrystal formation is a widely used strategy in solid-state chemistry and pharmaceutical development to improve the solubility, stability, and bioavailability of molecules with otherwise poor physicochemical properties. Identifying viable coformer combinations remains laborious and uncertain. A key but underappreciated challenge is that experimental databases overwhelmingly report successful cocrystals, while unsuccessful attempts are rarely documented, creating biased datasets that cause many machine-learning models to make overly optimistic and unreliable predictions when applied to new chemical systems. Here, we address this limitation by reframing cocrystal prediction as a learning problem with missing negative information and by adopting a conservative strategy that focuses on identifying molecular pairs that are very unlikely to form cocrystals. We leverage multiple, independent molecular descriptions—including structural, electronic, and physicochemical characteristics—that provide complementary views for identifying reliable negatives, and use their agreement to exclude implausible combinations from large sets of untested pairs. These highly confident pseudo-negative examples are then used to mitigate data imbalance and to fine-tune a pretrained graph attention network for cocrystal prediction. Across large and chemically diverse datasets, this data-centric strategy significantly improves the reliability and generalization of cocrystal prediction models compared with existing deep-learning approaches, demonstrating that carefully correcting for missing negative information is critical for making computational screening more realistic and more useful for guiding future experimental discovery. Health sciences/Molecular medicine Physical sciences/Chemistry Cocrystal prediction Multimodal learning Self-supervised learning Semi-supervised learning Molecular representation Pharmaceuticals Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryInformationFeb262026.docx 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-9140169","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":607521069,"identity":"8a414587-beec-4f1e-9535-e9dcfe0f6c0a","order_by":0,"name":"Sohrab Rohani","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAp0lEQVRIiWNgGAWjYHACNiCWkCNdizHJWhgSG4hWLz/78LEHP3dYpG+4kXyA4UcNEVoMzqWlG/aekcjdcCMtgbHnGDFaeHjMJHjbgFpu5xgwQxxJyGE9PGaSf9sk0g3AWv4RoYXhDI+ZNNCWBLAWxjZiHHaGLU1atk3CcOb9ZwkHe/uIchjzMcm3bXXyfGcOH3zw4xsxDkMGB0jVMApGwSgYBaMABwAAKdAxB3HEIWcAAAAASUVORK5CYII=","orcid":"","institution":"Western University","correspondingAuthor":true,"prefix":"","firstName":"Sohrab","middleName":"","lastName":"Rohani","suffix":""},{"id":607521070,"identity":"9296e0ce-9d65-4f83-b024-1ba1ded0d75e","order_by":1,"name":"Mohammad Ghanavati","email":"","orcid":"","institution":"Western University","correspondingAuthor":false,"prefix":"","firstName":"Mohammad","middleName":"","lastName":"Ghanavati","suffix":""},{"id":607521071,"identity":"ed1c835f-3352-46a5-8a3e-b589b225e53b","order_by":2,"name":"Seyed Mohamad Moosavi","email":"","orcid":"https://orcid.org/0000-0002-0357-5729","institution":"University of Toronto","correspondingAuthor":false,"prefix":"","firstName":"Seyed","middleName":"Mohamad","lastName":"Moosavi","suffix":""}],"badges":[],"createdAt":"2026-03-16 16:19:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9140169/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9140169/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105734731,"identity":"1d5ea65a-2f13-4bb8-bee0-ea39de51c8f3","added_by":"auto","created_at":"2026-03-30 11:47:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1787706,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptdraftMarch162026.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9140169/v1_covered_7993a14d-94d7-4ffa-96a3-2b17c5d76306.pdf"},{"id":105734482,"identity":"b03fc26c-957e-4cae-8959-37ef6774f819","added_by":"auto","created_at":"2026-03-30 11:46:00","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":716853,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"SupplementaryInformationFeb262026.docx","url":"https://assets-eu.researchsquare.com/files/rs-9140169/v1/41ecf1d731b0a7384d9e6555.docx"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"A Multimodal Semi-Supervised Learning Framework for Pharmaceutical Cocrystals Prediction","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":"Cocrystal prediction, Multimodal learning, Self-supervised learning, Semi-supervised learning, Molecular representation, Pharmaceuticals","lastPublishedDoi":"10.21203/rs.3.rs-9140169/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9140169/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Cocrystal formation is a widely used strategy in solid-state chemistry and pharmaceutical development to improve the solubility, stability, and bioavailability of molecules with otherwise poor physicochemical properties. Identifying viable coformer combinations remains laborious and uncertain. A key but underappreciated challenge is that experimental databases overwhelmingly report successful cocrystals, while unsuccessful attempts are rarely documented, creating biased datasets that cause many machine-learning models to make overly optimistic and unreliable predictions when applied to new chemical systems. Here, we address this limitation by reframing cocrystal prediction as a learning problem with missing negative information and by adopting a conservative strategy that focuses on identifying molecular pairs that are very unlikely to form cocrystals. We leverage multiple, independent molecular descriptions—including structural, electronic, and physicochemical characteristics—that provide complementary views for identifying reliable negatives, and use their agreement to exclude implausible combinations from large sets of untested pairs. These highly confident pseudo-negative examples are then used to mitigate data imbalance and to fine-tune a pretrained graph attention network for cocrystal prediction. Across large and chemically diverse datasets, this data-centric strategy significantly improves the reliability and generalization of cocrystal prediction models compared with existing deep-learning approaches, demonstrating that carefully correcting for missing negative information is critical for making computational screening more realistic and more useful for guiding future experimental discovery.","manuscriptTitle":"A Multimodal Semi-Supervised Learning Framework for Pharmaceutical Cocrystals Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-30 11:35:23","doi":"10.21203/rs.3.rs-9140169/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":"4085c4da-0be3-4db0-b76e-d5b9daf3b04b","owner":[],"postedDate":"March 30th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":64645002,"name":"Health sciences/Molecular medicine"},{"id":64645003,"name":"Physical sciences/Chemistry"}],"tags":[],"updatedAt":"2026-04-17T12:42:31+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-30 11:35:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9140169","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9140169","identity":"rs-9140169","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}