Mechanism-Aware Protein-Protein Interaction Prediction via Contact-Guided Dual Attention on Protein Language Models

Mechanism-Aware Protein-Protein Interaction Prediction via Contact-Guided Dual Attention on Protein Language Models | 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 Mechanism-Aware Protein-Protein Interaction Prediction via Contact-Guided Dual Attention on Protein Language Models Chengfei Yan, Shuchen Deng, Xuanjun Wan, Zichun Mu, Sheng-You Huang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7050339/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 Accurate prediction of protein-protein interactions (PPIs) is essential for understanding cellular mechanisms and disease. However, existing deep learning models often fail to generalize to novel proteins with low sequence similarity to training data. Here, we present a mechanism-aware deep learning framework to enhance generalization by incorporating residue-level interaction modeling. Our model integrates a dual-attention-based PPI prediction module with an inter-protein contact predictor based on protein language model-embedded geometric graphs. Joint training on structure-informed PPIs from the Protein Data Bank (PDB) enables the model to predict both interactions and the key residue pairs that mediate them. The model generalizes well to unseen proteins across species in the high-quality interactome dataset (HINT). Fine-tuning on Homo sapiens PPI data from HINT further improves the performance. Compared to D-SCRIPT, Topsy-Turvy, and TT3D, our model, referred to as PLMDA-PPI, achieves superior accuracy and robustness under strict sequence dissimilarity settings. This work provides a generalizable framework for biomolecular interaction prediction through the integration of structural and non-structural interaction data. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/High-throughput screening Full Text Additional Declarations There is NO Competing Interest. 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-7050339","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":481989593,"identity":"11f2bdb5-f14c-480b-bc7d-81fc5b4122ce","order_by":0,"name":"Chengfei Yan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBklEQVRIiWNgGAWjYDACCRBhw8ADJBkfQ8UMiNCSBtbCbAzlE6cFBNikidLCP7v52MMvCTYyBsfPHqsubKurY2Bv3ibBUHMHtyV3jqUbyySk8RicyUu7PbPtsAQDz7EyCYZjz3BqMZDIMZOW/HGYx+BAjtlt3rYDEgxAEQnGhsN4tOR/k5ZI+M9jcP6NWTFvW50Eg/wbQlpy2CQ/JBzgMbiRY8bM28YMtIUHvxaJG2lm0gwJyTySN94YS/OcOyzZxpNWbJFwDLcW/hnJzyR/JNjZ853PMfzMU1bHz89+eOONDzW4tYAAMygeFQ5AeWwgIgGvBmBC+QEk5BsIqBoFo2AUjIKRCwAxJEyyd9CbdQAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-2010-6668","institution":"Huazhong University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Chengfei","middleName":"","lastName":"Yan","suffix":""},{"id":481989594,"identity":"e16ee245-40e3-452b-8ac1-1b138ed403e7","order_by":1,"name":"Shuchen Deng","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Shuchen","middleName":"","lastName":"Deng","suffix":""},{"id":481989595,"identity":"bed669e2-58ef-4745-9d4a-4111090724c5","order_by":2,"name":"Xuanjun Wan","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xuanjun","middleName":"","lastName":"Wan","suffix":""},{"id":481989596,"identity":"ee0554ec-cf43-4d85-bf5c-db5e7f71f7a0","order_by":3,"name":"Zichun Mu","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zichun","middleName":"","lastName":"Mu","suffix":""},{"id":481989597,"identity":"7c4851dc-1bee-4995-b1ee-0b19742faca0","order_by":4,"name":"Sheng-You Huang","email":"","orcid":"https://orcid.org/0000-0002-4209-4565","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Sheng-You","middleName":"","lastName":"Huang","suffix":""}],"badges":[],"createdAt":"2025-07-05 04:10:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7050339/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7050339/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":87605026,"identity":"d9438859-7f50-4a6b-b521-d6fcd59dac87","added_by":"auto","created_at":"2025-07-25 17:59:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1518760,"visible":true,"origin":"","legend":"Article File","description":"","filename":"PLMDAPPI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7050339/v1_covered_52fa2557-f78d-4aae-99ce-1d248561d6c3.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Mechanism-Aware Protein-Protein Interaction Prediction via Contact-Guided Dual Attention on Protein Language Models","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-7050339/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7050339/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate prediction of protein-protein interactions (PPIs) is essential for understanding cellular mechanisms and disease. However, existing deep learning models often fail to generalize to novel proteins with low sequence similarity to training data. Here, we present a mechanism-aware deep learning framework to enhance generalization by incorporating residue-level interaction modeling. Our model integrates a dual-attention-based PPI prediction module with an inter-protein contact predictor based on protein language model-embedded geometric graphs. Joint training on structure-informed PPIs from the Protein Data Bank (PDB) enables the model to predict both interactions and the key residue pairs that mediate them. The model generalizes well to unseen proteins across species in the high-quality interactome dataset (HINT). Fine-tuning on Homo sapiens PPI data from HINT further improves the performance. Compared to D-SCRIPT, Topsy-Turvy, and TT3D, our model, referred to as PLMDA-PPI, achieves superior accuracy and robustness under strict sequence dissimilarity settings. This work provides a generalizable framework for biomolecular interaction prediction through the integration of structural and non-structural interaction data.","manuscriptTitle":"Mechanism-Aware Protein-Protein Interaction Prediction via Contact-Guided Dual Attention on Protein Language Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-08 02:19:56","doi":"10.21203/rs.3.rs-7050339/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":"05a29ed6-e147-42ea-b3fb-5c512c3796a5","owner":[],"postedDate":"July 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":51175800,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":51175801,"name":"Biological sciences/Computational biology and bioinformatics/High-throughput screening"}],"tags":[],"updatedAt":"2025-10-30T18:30:59+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-08 02:19:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7050339","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7050339","identity":"rs-7050339","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}