Common Interface Network for Multi-domain Biomolecular Interaction Learning

Common Interface Network for Multi-domain Biomolecular Interaction 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 Common Interface Network for Multi-domain Biomolecular Interaction Learning Xin Gao, Jiadong Lu, Yu Wang, Fuming Zeng, Yipin Lei, Fuli Feng, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9347720/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 Biomolecular interactions underlie core cellular processes and modern drug discovery, yet reliable prediction across interaction types remains limited by the lack of universal interface representations that transfer across molecular domains. Here, we proposed the Common Interface Network (ComIN), a framework that learns interface representations via contrastive learning on interface atom graphs. By training jointly on protein–protein, protein–peptide, and protein–small molecular interactions, ComIN synthesizes a unified embedding space that demonstrates superior performance over existing domain-specific models. Extensive validation across five distinct interaction-centric tasks in drug discovery and immune recognition underscores the broad transferability and robustness of ComIN as a representational tool. Leveraging this universality, we built ComINdex, a cross-domain search engine indexing million-scale interfaces with ComIN-generated representations to enable efficient retrieval in support of scalable biomolecular function analysis and design. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Computational models Full Text Additional Declarations There is NO Competing Interest. Supplementary Files ComINsupp.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-9347720","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":620393603,"identity":"ffc55ea4-f04c-44f1-9722-dab372233723","order_by":0,"name":"Xin Gao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYDACZgglJwHlMzYQq8UYrOUAUVqgIHEG0VoMjvMeYPxSY5M+s/2M8ecPDDayGw6wP/yAT4tkM18Cs8yxtNzZPDlmEgcY0ow3HOAxlsCnhZ+Zx4BZgu1w7jyGHDOgww4nArUw4NXCBtby73C6HP8b4w8HGP4DtbA//kHIFsaPbYcTpCVyDIAOOwDUwmCG1xbJZh6Dw4x9aYYzZzwrkzhjkGw88zCPmQU+LQbnzxg+/PHNRl7ifPLmDxUVdrJ9x9sf38CnBQQO8yBMYIBHLl7AiNe3o2AUjIJRMAoAWdhG/JqtslgAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-7108-3574","institution":"King Abdullah University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Xin","middleName":"","lastName":"Gao","suffix":""},{"id":620393604,"identity":"1f5a9543-915c-437c-9b8a-c17be6010d92","order_by":1,"name":"Jiadong Lu","email":"","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Jiadong","middleName":"","lastName":"Lu","suffix":""},{"id":620393605,"identity":"34a92b0b-37ab-44b8-9542-da440c5d1ec4","order_by":2,"name":"Yu Wang","email":"","orcid":"","institution":"Institute of Computing Technology, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Wang","suffix":""},{"id":620393606,"identity":"b1446705-2141-4014-aab5-ed63260e578f","order_by":3,"name":"Fuming Zeng","email":"","orcid":"","institution":"Institute of Computing Technology, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Fuming","middleName":"","lastName":"Zeng","suffix":""},{"id":620393607,"identity":"94453260-2da7-4281-8cc6-7c509531679b","order_by":4,"name":"Yipin Lei","email":"","orcid":"","institution":"Syneron Technology","correspondingAuthor":false,"prefix":"","firstName":"Yipin","middleName":"","lastName":"Lei","suffix":""},{"id":620393608,"identity":"08dc2fb6-9c9f-4757-a4bd-5ef32b5963b3","order_by":5,"name":"Fuli Feng","email":"","orcid":"https://orcid.org/0000-0002-5828-9842","institution":"University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Fuli","middleName":"","lastName":"Feng","suffix":""},{"id":620393609,"identity":"de15579a-fc16-4451-9c8b-63230466607e","order_by":6,"name":"Shiwei Sun","email":"","orcid":"","institution":"Key Lab of Intelligent Information Processing, Big Data Academy, Institute of Computing Technology, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Shiwei","middleName":"","lastName":"Sun","suffix":""}],"badges":[],"createdAt":"2026-04-07 16:26:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9347720/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9347720/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106726104,"identity":"3a563c09-6eea-4187-a4b2-33a14f8e7d65","added_by":"auto","created_at":"2026-04-12 18:35:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":8434852,"visible":true,"origin":"","legend":"Article File","description":"","filename":"ComINmain.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9347720/v1_covered_ab2928af-b308-455b-ac90-85ac70468336.pdf"},{"id":106599628,"identity":"41f20575-7ba8-4975-87bc-e50a43c539be","added_by":"auto","created_at":"2026-04-10 10:06:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":4863258,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"ComINsupp.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9347720/v1/3ae25cb17e1bbc81b86e6b0e.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Common Interface Network for Multi-domain Biomolecular Interaction 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-9347720/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9347720/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Biomolecular interactions underlie core cellular processes and modern drug discovery, yet reliable prediction across interaction types remains limited by the lack of universal interface representations that transfer across molecular domains. Here, we proposed the Common Interface Network (ComIN), a framework that learns interface representations via contrastive learning on interface atom graphs. By training jointly on protein–protein, protein–peptide, and protein–small molecular interactions, ComIN synthesizes a unified embedding space that demonstrates superior performance over existing domain-specific models. Extensive validation across five distinct interaction-centric tasks in drug discovery and immune recognition underscores the broad transferability and robustness of ComIN as a representational tool. Leveraging this universality, we built ComINdex, a cross-domain search engine indexing million-scale interfaces with ComIN-generated representations to enable efficient retrieval in support of scalable biomolecular function analysis and design.","manuscriptTitle":"Common Interface Network for Multi-domain Biomolecular Interaction Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-10 10:06:00","doi":"10.21203/rs.3.rs-9347720/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":"8c69ee9d-7c59-40ed-90a8-06dc6a6a0277","owner":[],"postedDate":"April 10th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"This content is not available.","date":"2026-05-07T02:52:43+00:00","index":3,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2026-05-06T06:00:05+00:00","index":2,"fulltext":"This content is not available."},{"type":"editorInvitedReview","content":"This content is not available.","date":"2026-05-04T19:24:29+00:00","index":1,"fulltext":"This content is not available."}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66024464,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":66024465,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"}],"tags":[],"updatedAt":"2026-04-10T10:06:00+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-10 10:06:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9347720","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9347720","identity":"rs-9347720","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}