GraphLooper: Predicting Chromatin Loops Based on Hierarchical Multi-View Graph Pooling Method

GraphLooper: Predicting Chromatin Loops Based on Hierarchical Multi-View Graph Pooling Method | 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 Method Article GraphLooper: Predicting Chromatin Loops Based on Hierarchical Multi-View Graph Pooling Method Siguo Wang, Zhipeng Li, Zhen Cui, Zhenhao Guo, Qinhu Zhang, De-Shuang Huang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7099129/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 Chromatin loops serve as fundamental functional units of three-dimensional genome organization, playing a pivotal role in regulating gene expression and maintaining genomic spatial organization. Accurate identification of these fine-scale structures is crucial for advancing our understanding of cellular biological processes and the mechanisms underlying disease. However, due to the inherent complexity and dynamic of chromatin interactions, existing prediction methods often fail to adequately characterize and comprehensively capture their multi-dimensional features. To address this limitation, we present GraphLooper, a novel framework based on hierarchical multi-view graph pooling for training and inference on large-scale data. GraphLooper first transforms Hi-C data into a graph-structured representation and integrates multi-dimensional epigenomic features, constructing a comprehensive system for chromatin interaction representation. By introducing a hierarchical pooling mechanism, GraphLooper effectively aggregates multi-scale features, significantly enhancing the model's representation learning capabilities. Systematic evaluation across various cell lines demonstrates that GraphLooper not only surpasses existing state-of-the-art methods in prediction accuracy but also exhibits strong generalization performance. Notably, it demonstrates exceptional ability in capturing long-range chromatin interactions, which are critical for remote gene regulation through precise spatial organization. chromatin loops multi-view graph pooling epigenomic data graph neural networks Full Text Additional Declarations No competing interests reported. Supplementary Files Supplementarymaterial.pdf 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-7099129","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Method Article","associatedPublications":[],"authors":[{"id":483903388,"identity":"1db8c473-5ef4-4fa4-8383-1c5b30fbd074","order_by":0,"name":"Siguo Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIiWNgGAWjYDACZgTrwIEPP0jTwpZ4cGYPafbxGB/mYCNCnXw7+zWJDwyH5c3513w4zMDDIM8vdgC/FoPDPGWSMxgOG+6c8XbD4QILBsOZsxMIaGHmSZPmYbjNuOHG2Q2HZ/AwJBjcJqBFvhmixX7DjTMPDvOwEaGF4TD7MZCWxA3nexiI0wL0C7PlDIb/yRtusBkAA1mCsF/k+48/vPGBIc12w/nDjz98+GEjzy9NyGEMPAYMjP+AtARYpQQh5SDA/gBC8x8gRvUoGAWjYBSMRAAAv0xGqSk5NM0AAAAASUVORK5CYII=","orcid":"","institution":"Ningbo Institute of Digital Twin, Eastern Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Siguo","middleName":"","lastName":"Wang","suffix":""},{"id":483903389,"identity":"915d3c18-e07f-4fd9-a3f9-a8c8815d11ac","order_by":1,"name":"Zhipeng Li","email":"","orcid":"","institution":"Ningbo Institute of Digital Twin, Eastern Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhipeng","middleName":"","lastName":"Li","suffix":""},{"id":483903390,"identity":"97f39c00-2ea9-47a5-930d-cc86f4e7dde4","order_by":2,"name":"Zhen Cui","email":"","orcid":"","institution":"Shandong Women's University","correspondingAuthor":false,"prefix":"","firstName":"Zhen","middleName":"","lastName":"Cui","suffix":""},{"id":483903391,"identity":"db402ad3-da44-4a66-8917-87b25580947b","order_by":3,"name":"Zhenhao Guo","email":"","orcid":"","institution":"Ningbo Institute of Digital Twin, Eastern Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhenhao","middleName":"","lastName":"Guo","suffix":""},{"id":483903392,"identity":"aa8505e0-249b-43bc-aa27-9b602fd820d6","order_by":4,"name":"Qinhu Zhang","email":"","orcid":"","institution":"Ningbo Institute of Digital Twin, Eastern Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Qinhu","middleName":"","lastName":"Zhang","suffix":""},{"id":483903393,"identity":"c02919f2-cd05-4aec-979f-a97be0dc72b5","order_by":5,"name":"De-Shuang Huang","email":"","orcid":"","institution":"Ningbo Institute of Digital Twin, Eastern Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"De-Shuang","middleName":"","lastName":"Huang","suffix":""}],"badges":[],"createdAt":"2025-07-11 07:53:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7099129/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7099129/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92709926,"identity":"ab923742-26b7-47ca-84bb-865d762fd738","added_by":"auto","created_at":"2025-10-03 10:47:10","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1276395,"visible":true,"origin":"","legend":"","description":"","filename":"GraphLooper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7099129/v1_covered_5fb3b246-8364-44dc-bd38-473c78f06d7b.pdf"},{"id":86620574,"identity":"3efb0742-ce4a-4f11-a4ae-df92265dca55","added_by":"auto","created_at":"2025-07-14 03:13:08","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":886316,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementarymaterial.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7099129/v1/8b2681c8dda1cf841fc2c849.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"GraphLooper: Predicting Chromatin Loops Based on Hierarchical Multi-View Graph Pooling Method","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":"chromatin loops, multi-view graph pooling, epigenomic data, graph neural networks","lastPublishedDoi":"10.21203/rs.3.rs-7099129/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7099129/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Chromatin loops serve as fundamental functional units of three-dimensional genome organization, playing a pivotal role in regulating gene expression and maintaining genomic spatial organization. Accurate identification of these fine-scale structures is crucial for advancing our understanding of cellular biological processes and the mechanisms underlying disease. However, due to the inherent complexity and dynamic of chromatin interactions, existing prediction methods often fail to adequately characterize and comprehensively capture their multi-dimensional features. To address this limitation, we present GraphLooper, a novel framework based on hierarchical multi-view graph pooling for training and inference on large-scale data. GraphLooper first transforms Hi-C data into a graph-structured representation and integrates multi-dimensional epigenomic features, constructing a comprehensive system for chromatin interaction representation. By introducing a hierarchical pooling mechanism, GraphLooper effectively aggregates multi-scale features, significantly enhancing the model's representation learning capabilities. Systematic evaluation across various cell lines demonstrates that GraphLooper not only surpasses existing state-of-the-art methods in prediction accuracy but also exhibits strong generalization performance. Notably, it demonstrates exceptional ability in capturing long-range chromatin interactions, which are critical for remote gene regulation through precise spatial organization.","manuscriptTitle":"GraphLooper: Predicting Chromatin Loops Based on Hierarchical Multi-View Graph Pooling Method","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-14 03:13:03","doi":"10.21203/rs.3.rs-7099129/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":"1e07dcdf-3bea-411f-a9db-d034984eda05","owner":[],"postedDate":"July 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-03T10:39:02+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-14 03:13:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7099129","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7099129","identity":"rs-7099129","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}