Class-balanced negative training sets for improving classifier model predictions of enhancer-promoter interactions

Class-balanced negative training sets for improving classifier model predictions of enhancer-promoter interactions | 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 Class-balanced negative training sets for improving classifier model predictions of enhancer-promoter interactions Osamu Maruyama, Tsukasa Koga This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6324031/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 Jun, 2025 Read the published version in BMC Bioinformatics → Version 1 posted 10 You are reading this latest preprint version Abstract Background: Enhancers regulate gene expression by forming DNA loops, thereby bringing themselves in close proximity to the target gene promoter. The human genome contains hundreds of thousands of enhancers, vastly outnum- bering its 20,000-25,000 protein-coding genes, highlighting the importance of enhancer-promoter interactions (EPIs) in gene regulation. Supervised learning models have been developed to predict EPIs, often using experimentally validated interacting enhancer-promoter pairs and artificially gen- erated negative samples. However, the lack of reliable negative samples presents a challenge. Current methods randomly select pairs from unlabeled data, leading to class imbalance and reduced predictive performance. This imbalance, where enhancers and promoters are unevenly distributed between the positive and negative sets, hinders classifiers from learning meaningful patterns. Therefore, constructing more reliable negative samples is crucial for improving the accuracy of EPI predictions. Results: We developed two methods to generate class-balanced negative train- ing sets for EPI classifiers: one based on maximum ow and the other on Gibbs sampling. We evaluated these methods with the TargetFinder and TransEPI classifiers across five and six cell lines, respectively. The trained models were tested using a common negative test set. Our negative training sets significantly improved the prediction performance across several metrics, including precision, recall, and area under the receiver operating characteristic curve. Conclusions: Our findings demonstrate that carefully designed negative samples can enhance the performance of EPI classifiers. Further advanced methods in generating negative EPIs should further improve prediction accuracy. The source code is available at https://github.com/maruyama-lab-design/CBOEP2. Class balance Enhancer-promoter interactions Negative training set Maximum ow Gibbs sampling Full Text Additional Declarations No competing interests reported. Supplementary Files supplement.pdf Cite Share Download PDF Status: Published Journal Publication published 02 Jun, 2025 Read the published version in BMC Bioinformatics → Version 1 posted Editorial decision: Revision requested 28 Apr, 2025 Reviews received at journal 26 Apr, 2025 Reviewers agreed at journal 20 Apr, 2025 Reviews received at journal 13 Apr, 2025 Reviewers agreed at journal 05 Apr, 2025 Reviewers invited by journal 03 Apr, 2025 Editor assigned by journal 03 Apr, 2025 Editor invited by journal 03 Apr, 2025 Submission checks completed at journal 02 Apr, 2025 First submitted to journal 02 Apr, 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-6324031","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":445423758,"identity":"8b0304fc-cf3c-4a93-ae97-f87ce6c15541","order_by":0,"name":"Osamu Maruyama","email":"data:image/png;base64,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","orcid":"","institution":"Kyushu University","correspondingAuthor":true,"prefix":"","firstName":"Osamu","middleName":"","lastName":"Maruyama","suffix":""},{"id":445423761,"identity":"3fc53c1d-5f08-405d-8924-81a53618ddd6","order_by":1,"name":"Tsukasa Koga","email":"","orcid":"","institution":"Kyushu University","correspondingAuthor":false,"prefix":"","firstName":"Tsukasa","middleName":"","lastName":"Koga","suffix":""}],"badges":[],"createdAt":"2025-03-28 02:08:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6324031/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6324031/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12859-025-06171-8","type":"published","date":"2025-06-02T15:57:28+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":84243129,"identity":"b76803cb-3194-439c-a10a-86b805033834","added_by":"auto","created_at":"2025-06-09 16:12:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":610939,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6324031/v1_covered_3dca9edb-d1ba-4473-97cc-873d08fc215e.pdf"},{"id":81312517,"identity":"3dd07b2a-5779-4737-8b54-e08b1b0b02ef","added_by":"auto","created_at":"2025-04-24 15:39:18","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":634528,"visible":true,"origin":"","legend":"","description":"","filename":"supplement.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6324031/v1/aedbc2025dd8c906f9484f6a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Class-balanced negative training sets for improving classifier model predictions of enhancer-promoter interactions","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":"bmc-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Class balance, Enhancer-promoter interactions, Negative training set, Maximum ow, Gibbs sampling","lastPublishedDoi":"10.21203/rs.3.rs-6324031/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6324031/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground:\u003c/strong\u003e Enhancers regulate gene expression by forming DNA loops, thereby bringing themselves in close proximity to the target gene promoter. The human genome contains hundreds of thousands of enhancers, vastly outnum- bering its 20,000-25,000 protein-coding genes, highlighting the importance of enhancer-promoter interactions (EPIs) in gene regulation. Supervised learning models have been developed to predict EPIs, often using experimentally validated interacting enhancer-promoter pairs and artificially gen- erated negative samples. However, the lack of reliable negative samples presents a challenge. Current methods randomly select pairs from unlabeled data, leading to class imbalance and reduced predictive performance. This imbalance, where enhancers and promoters are unevenly distributed between the positive and negative sets, hinders classifiers from learning meaningful patterns. Therefore, constructing more reliable negative samples is crucial for improving the accuracy of EPI predictions.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e We developed two methods to generate class-balanced negative train- ing sets for EPI classifiers: one based on maximum ow and the other on Gibbs sampling. We evaluated these methods with the TargetFinder and TransEPI classifiers across five and six cell lines, respectively. The trained models were tested using a common negative test set. Our negative training sets significantly improved the prediction performance across several metrics, including precision, recall, and area under the receiver operating characteristic curve.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions: \u003c/strong\u003eOur findings demonstrate that carefully designed negative samples can enhance the performance of EPI classifiers. Further advanced methods in generating negative EPIs should further improve prediction accuracy. The source code is available at https://github.com/maruyama-lab-design/CBOEP2.\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","manuscriptTitle":"Class-balanced negative training sets for improving classifier model predictions of enhancer-promoter interactions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-24 15:39:13","doi":"10.21203/rs.3.rs-6324031/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-28T10:00:40+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-26T10:41:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"159415914157182662340958397291907782695","date":"2025-04-20T21:42:21+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-13T16:02:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"152405871463919738807701265922845186754","date":"2025-04-06T03:04:13+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-03T14:39:12+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-04-03T14:31:03+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-04-03T12:48:34+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-02T15:02:28+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Bioinformatics","date":"2025-04-02T15:01:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"0ab84b00-1e9b-4896-9990-167add4b88e1","owner":[],"postedDate":"April 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-06-09T16:09:24+00:00","versionOfRecord":{"articleIdentity":"rs-6324031","link":"https://doi.org/10.1186/s12859-025-06171-8","journal":{"identity":"bmc-bioinformatics","isVorOnly":false,"title":"BMC Bioinformatics"},"publishedOn":"2025-06-02 15:57:28","publishedOnDateReadable":"June 2nd, 2025"},"versionCreatedAt":"2025-04-24 15:39:13","video":"","vorDoi":"10.1186/s12859-025-06171-8","vorDoiUrl":"https://doi.org/10.1186/s12859-025-06171-8","workflowStages":[]},"version":"v1","identity":"rs-6324031","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6324031","identity":"rs-6324031","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}