Improving classification on imbalanced genomic data via KDE–based synthetic sampling

Improving classification on imbalanced genomic data via KDE–based synthetic sampling | 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 Improving classification on imbalanced genomic data via KDE–based synthetic sampling Edoardo Taccaliti, Jesus S. Aguilar--Ruiz This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6513655/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 29 Aug, 2025 Read the published version in BioData Mining → Version 1 posted 9 You are reading this latest preprint version Abstract Class imbalance poses a serious challenge in biomedical machine learning, particularly in genomics, where datasets are characterized by extremely high dimensionality and very limited sample sizes. In such settings, standard classifiers tend to favor the majority class, leading to biased predictions --- an especially problematic issue in clinical diagnostics where rare conditions must not be overlooked. In this study, we introduce a Kernel Density Estimation (KDE)--based oversampling approach to rebalance imbalanced genomic datasets by generating synthetic minority class samples. Unlike conventional methods such as SMOTE, KDE estimates the global probability distribution of the minority class and resamples accordingly, avoiding local interpolation pitfalls. We evaluate our method on 15 real--world genomic datasets using three classifiers --Naïve Bayes, Decision Trees, and Random Forests-- and compare it to SMOTE and baseline training. Experimental results demonstrate that KDE oversampling consistently improves classification performance, especially in metrics robust to imbalance, such as AUC of the IMCP curve. Notably, KDE achieves superior results in tree-based models while dramatically simplifying the sampling process. This approach offers a statistically grounded and effective solution for balancing genomic datasets, with strong potential for improving fairness and accuracy in high--stakes medical decision--making. Imbalance Oversampling Kernel Density Estimation Classification. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 29 Aug, 2025 Read the published version in BioData Mining → Version 1 posted Editorial decision: Revision requested 02 Jun, 2025 Reviews received at journal 01 Jun, 2025 Reviews received at journal 12 May, 2025 Reviewers agreed at journal 05 May, 2025 Reviewers agreed at journal 05 May, 2025 Reviewers invited by journal 05 May, 2025 Editor assigned by journal 04 May, 2025 Submission checks completed at journal 04 May, 2025 First submitted to journal 23 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-6513655","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":452142807,"identity":"98bd6500-ed1f-4067-8d15-1692cdf9e1ea","order_by":0,"name":"Edoardo Taccaliti","email":"","orcid":"","institution":"University of Naples Federico II","correspondingAuthor":false,"prefix":"","firstName":"Edoardo","middleName":"","lastName":"Taccaliti","suffix":""},{"id":452142809,"identity":"a36038b8-0dbb-41a8-9215-76b8fcfe55e9","order_by":1,"name":"Jesus S. Aguilar--Ruiz","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtUlEQVRIiWNgGAWjYJCCAw8YGORI1JLAwGBMojVALYkNRKvm719jeCCh5l76htvNBxg+/CFCi8SNNwYHEo4V5264cyyBcWYbMdbcOAPUwpaQu+FGjgEzLzHOkwdr+ZeQbgDS8ocYhxmc7zE4kNiWkADWwsBGhBbDG2wFBxL7EgxnAv1ysJcYv8idP7z5w4dvCfJ8t5sPPvhBjMMYJBJgDGCcEqMBGDEwdRLEqR8Fo2AUjIIRCABRLz/sxZiQQAAAAABJRU5ErkJggg==","orcid":"","institution":"Pablo de Olavide University","correspondingAuthor":true,"prefix":"","firstName":"Jesus","middleName":"S.","lastName":"Aguilar--Ruiz","suffix":""}],"badges":[],"createdAt":"2025-04-23 14:38:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6513655/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6513655/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13040-025-00474-5","type":"published","date":"2025-08-29T15:57:40+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":90344878,"identity":"47ac5101-42e9-48e6-8dc2-61f4774ec752","added_by":"auto","created_at":"2025-09-01 16:07:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":494942,"visible":true,"origin":"","legend":"","description":"","filename":"KDEBioDataMiningPaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6513655/v1_covered_3dbc01d0-f6c7-4d8a-87d6-02ff11e21636.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Improving classification on imbalanced genomic data via KDE–based synthetic sampling","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":"biodata-mining","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bidm","sideBox":"Learn more about [BioData Mining](http://biodatamining.biomedcentral.com/)","snPcode":"13040","submissionUrl":"https://submission.nature.com/new-submission/13040/3","title":"BioData Mining","twitterHandle":"@BioMedCentral","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Imbalance, Oversampling, Kernel Density Estimation, Classification.","lastPublishedDoi":"10.21203/rs.3.rs-6513655/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6513655/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eClass imbalance poses a serious challenge in biomedical machine learning, particularly in genomics, where datasets are characterized by extremely high dimensionality and very limited sample sizes. In such settings, standard classifiers tend to favor the majority class, leading to biased predictions --- an especially problematic issue in clinical diagnostics where rare conditions must not be overlooked. In this study, we introduce a Kernel Density Estimation (KDE)--based oversampling approach to rebalance imbalanced genomic datasets by generating synthetic minority class samples. Unlike conventional methods such as SMOTE, KDE estimates the global probability distribution of the minority class and resamples accordingly, avoiding local interpolation pitfalls. We evaluate our method on 15 real--world genomic datasets using three classifiers --Na\u0026iuml;ve Bayes, Decision Trees, and Random Forests-- and compare it to SMOTE and baseline training. Experimental results demonstrate that KDE oversampling consistently improves classification performance, especially in metrics robust to imbalance, such as AUC of the IMCP curve. Notably, KDE achieves superior results in tree-based models while dramatically simplifying the sampling process. This approach offers a statistically grounded and effective solution for balancing genomic datasets, with strong potential for improving fairness and accuracy in high--stakes medical decision--making.\u003c/p\u003e","manuscriptTitle":"Improving classification on imbalanced genomic data via KDE–based synthetic sampling","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-08 10:03:57","doi":"10.21203/rs.3.rs-6513655/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-02T11:48:48+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-01T17:02:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-12T17:47:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"337508058516650912814053246838300997057","date":"2025-05-05T14:20:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"245326313188300452635201585399101761160","date":"2025-05-05T14:18:33+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-05T14:13:18+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-05T02:18:39+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-04T23:47:02+00:00","index":"","fulltext":""},{"type":"submitted","content":"BioData Mining","date":"2025-04-23T14:34:56+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"biodata-mining","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bidm","sideBox":"Learn more about [BioData Mining](http://biodatamining.biomedcentral.com/)","snPcode":"13040","submissionUrl":"https://submission.nature.com/new-submission/13040/3","title":"BioData Mining","twitterHandle":"@BioMedCentral","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"4d2626da-91f0-41b5-9071-2f97a482d521","owner":[],"postedDate":"May 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-09-01T16:01:28+00:00","versionOfRecord":{"articleIdentity":"rs-6513655","link":"https://doi.org/10.1186/s13040-025-00474-5","journal":{"identity":"biodata-mining","isVorOnly":false,"title":"BioData Mining"},"publishedOn":"2025-08-29 15:57:40","publishedOnDateReadable":"August 29th, 2025"},"versionCreatedAt":"2025-05-08 10:03:57","video":"","vorDoi":"10.1186/s13040-025-00474-5","vorDoiUrl":"https://doi.org/10.1186/s13040-025-00474-5","workflowStages":[]},"version":"v1","identity":"rs-6513655","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6513655","identity":"rs-6513655","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}