GIL-DDI: Multi-View Graph Invariant Learning for Unknown Drug-Drug Interaction Prediction

GIL-DDI: Multi-View Graph Invariant Learning for Unknown Drug-Drug Interaction 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 Research Article GIL-DDI: Multi-View Graph Invariant Learning for Unknown Drug-Drug Interaction Prediction Yuanxian Li, Yuan Du, Hong Peng, Zhenli He, Xin Jin, Cheng Xie This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6731543/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 07 Jan, 2026 Read the published version in Knowledge and Information Systems → Version 1 posted 10 You are reading this latest preprint version Abstract Drug-Drug Interaction (DDI) prediction is essential for evaluating the side effects of a new drug and adverse interactions before the clinical application.The latest research applies multi-view data to enhance the generalization ability of models to predict new drug interactions, mainly unknown Drug-Drug Interaction (uDDI).However, a new drug's feature inevitably encounters the feature-shift problem; the trained models have not previously learned information about the new drug, significantly decreasing the uDDI prediction's accuracy.Thus, we proposed the GIL-DDI model that tries to extract the invariant features of known drugs, alleviating the impact of the feature-shift problem on the prediction of uDDI.In detail, the graph attention network(GAT) models embed multi-view drug graphs, including drug-chemical entities, drug substructures, drug-drug interactions, and molecular structures. Then, invariant features corresponding to the new drug are learned from the knowledge graph of the previous drugs.After that, a variant feature of the new drug is embedded through the GAT models and fused with learned invariant drug features to predict the DDI.Extensive experiments on real-world drug datasets indicate that the proposed method achieves new state-of-the-art records on new drug DDI prediction tasks. The source code is available at https://anonymous.4open.science/r/GIL-DDI-F701/README.md. Invariant Learning Multi-View Graph Drug-Drug Interaction Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 07 Jan, 2026 Read the published version in Knowledge and Information Systems → Version 1 posted Editorial decision: Revision requested 03 Aug, 2025 Reviews received at journal 25 Jul, 2025 Reviews received at journal 22 Jul, 2025 Reviewers agreed at journal 25 Jun, 2025 Reviewers agreed at journal 21 Jun, 2025 Reviewers agreed at journal 16 Jun, 2025 Reviewers invited by journal 16 Jun, 2025 Editor assigned by journal 31 May, 2025 Submission checks completed at journal 24 May, 2025 First submitted to journal 23 May, 2025 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-6731543","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":471802005,"identity":"cd7e2499-c9d7-4c70-ae30-55152aa2a1ab","order_by":0,"name":"Yuanxian Li","email":"","orcid":"","institution":"Yunnan University","correspondingAuthor":false,"prefix":"","firstName":"Yuanxian","middleName":"","lastName":"Li","suffix":""},{"id":471802006,"identity":"d4917d08-8603-4dee-af2d-b99eed31813a","order_by":1,"name":"Yuan Du","email":"","orcid":"","institution":"Yunnan University","correspondingAuthor":false,"prefix":"","firstName":"Yuan","middleName":"","lastName":"Du","suffix":""},{"id":471802007,"identity":"cd9d1173-bf03-4e45-9bfd-4eff62c9671b","order_by":2,"name":"Hong Peng","email":"","orcid":"","institution":"Yunnan University","correspondingAuthor":false,"prefix":"","firstName":"Hong","middleName":"","lastName":"Peng","suffix":""},{"id":471802008,"identity":"874af0ec-ddf3-4fa8-ab68-9721cb965e10","order_by":3,"name":"Zhenli He","email":"","orcid":"","institution":"Yunnan University","correspondingAuthor":false,"prefix":"","firstName":"Zhenli","middleName":"","lastName":"He","suffix":""},{"id":471802009,"identity":"e00f3148-b0b9-4a2b-baab-2adac5c9b3d2","order_by":4,"name":"Xin Jin","email":"","orcid":"","institution":"Yunnan University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Jin","suffix":""},{"id":471802010,"identity":"85f47c58-bc5a-48eb-ada6-5d41a68268e4","order_by":5,"name":"Cheng Xie","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYDACZjBiYOCHc4nWItlAtBaYMoMDxGoxOM588HNBxR27zTdyj0kwVFgnNrCfPYBXi2QzW7L0jDPPkrfdyEuTYDiTntjAk5eAVws/M48ZM2/b4WSzGzlmEoxthxMbJHgM8GphY+b/xsz773Cy8QyQln9EaAHawsbM23DYzkACpKWBCC1AvxhL8xw7nCBx5o2xRcKxdOM2nhz8WgzOH374mafmsD1/e47hjQ811rL97Gfwa4GBxAaBBAaGBJDviFIPBPYM/AeIVTsKRsEoGAUjDQAA6v4+LZzW+HYAAAAASUVORK5CYII=","orcid":"","institution":"Yunnan University","correspondingAuthor":true,"prefix":"","firstName":"Cheng","middleName":"","lastName":"Xie","suffix":""}],"badges":[],"createdAt":"2025-05-23 09:38:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6731543/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6731543/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10115-025-02636-7","type":"published","date":"2026-01-07T15:57:58+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100070209,"identity":"c16d4ecf-d7d4-4130-8dc6-9c5b336167f6","added_by":"auto","created_at":"2026-01-12 16:17:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1007881,"visible":true,"origin":"","legend":"","description":"","filename":"GILDDI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6731543/v1_covered_645411e5-fb8e-48f2-9cb0-05ac68554963.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"GIL-DDI: Multi-View Graph Invariant Learning for Unknown Drug-Drug Interaction Prediction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"knowledge-and-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"kais","sideBox":"Learn more about [Knowledge and Information Systems](http://link.springer.com/journal/10115)","snPcode":"10115","submissionUrl":"https://submission.nature.com/new-submission/10115/3","title":"Knowledge and Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Invariant Learning, Multi-View Graph, Drug-Drug Interaction","lastPublishedDoi":"10.21203/rs.3.rs-6731543/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6731543/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDrug-Drug Interaction (DDI) prediction is essential for evaluating the side effects of a new drug and adverse interactions before the clinical application.The latest research applies multi-view data to enhance the generalization ability of models to predict new drug interactions, mainly unknown Drug-Drug Interaction (uDDI).However, a new drug's feature inevitably encounters the feature-shift problem; the trained models have not previously learned information about the new drug, significantly decreasing the uDDI prediction's accuracy.Thus, we proposed the GIL-DDI model that tries to extract the invariant features of known drugs, alleviating the impact of the feature-shift problem on the prediction of uDDI.In detail, the graph attention network(GAT) models embed multi-view drug graphs, including drug-chemical entities, drug substructures, drug-drug interactions, and molecular structures. Then, invariant features corresponding to the new drug are learned from the knowledge graph of the previous drugs.After that, a variant feature of the new drug is embedded through the GAT models and fused with learned invariant drug features to predict the DDI.Extensive experiments on real-world drug datasets indicate that the proposed method achieves new state-of-the-art records on new drug DDI prediction tasks. The source code is available at https://anonymous.4open.science/r/GIL-DDI-F701/README.md.\u003c/p\u003e","manuscriptTitle":"GIL-DDI: Multi-View Graph Invariant Learning for Unknown Drug-Drug Interaction Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-18 05:29:54","doi":"10.21203/rs.3.rs-6731543/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-03T04:49:03+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-25T08:59:29+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-22T09:42:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"276862468018181361445108289280553158932","date":"2025-06-25T19:41:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"176225115022554843032482957144099945705","date":"2025-06-21T16:33:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"281783094406096538817021666823329563819","date":"2025-06-16T08:02:40+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-16T06:49:29+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-31T08:51:10+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-24T04:42:31+00:00","index":"","fulltext":""},{"type":"submitted","content":"Knowledge and Information Systems","date":"2025-05-23T09:31:08+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"knowledge-and-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"kais","sideBox":"Learn more about [Knowledge and Information Systems](http://link.springer.com/journal/10115)","snPcode":"10115","submissionUrl":"https://submission.nature.com/new-submission/10115/3","title":"Knowledge and Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e7f7812c-57ee-4909-95d3-3df4dd36123e","owner":[],"postedDate":"June 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-01-12T16:12:08+00:00","versionOfRecord":{"articleIdentity":"rs-6731543","link":"https://doi.org/10.1007/s10115-025-02636-7","journal":{"identity":"knowledge-and-information-systems","isVorOnly":false,"title":"Knowledge and Information Systems"},"publishedOn":"2026-01-07 15:57:58","publishedOnDateReadable":"January 7th, 2026"},"versionCreatedAt":"2025-06-18 05:29:54","video":"","vorDoi":"10.1007/s10115-025-02636-7","vorDoiUrl":"https://doi.org/10.1007/s10115-025-02636-7","workflowStages":[]},"version":"v1","identity":"rs-6731543","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6731543","identity":"rs-6731543","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}