Unsupervised and Supervised Approaches for Breast Cancer Subtype Classification: Hierarchical Clustering and Machine Learning with Hyperparameter Optimization

Unsupervised and Supervised Approaches for Breast Cancer Subtype Classification: Hierarchical Clustering and Machine Learning with Hyperparameter Optimization | 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 Unsupervised and Supervised Approaches for Breast Cancer Subtype Classification: Hierarchical Clustering and Machine Learning with Hyperparameter Optimization Ana Beatriz Miranda Valentin, Glaucia Maria Bressan, Elisângela Lizzi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6779819/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Breast cancer is considered a public health problem and a disease of concern, which contains distinct subtypes, making accurate classification critical for personalized treatment. This study proposes a hybrid approach by applying supervised and unsupervised learning techniques for breast cancer subtype classification using gene expression data from The Cancer Genome Atlas (TCGA). First, hierarchical clustering with Pearson correlation and Euclidean distance as similarity metrics are employed to explore the intrinsic structure of the dataset. Subsequently, supervised machine learning models, including Logistic Regression, Support Vector Machine (SVM), Random Forest, and Multilayer Perceptron (MLP), are trained for the classification task. Hyperparameter tuning is performed using Optuna to improve predictive performance, and SHapley Additive exPlanations (SHAP) is applied to analyze feature importance library was applied to analyze the importance of variables and the influence of each dimension for each classifier. The results highlight the effectiveness of applying clustering methods and machine learning to improve classification accuracy and interpretability, contributing to the development of more accurate diagnostic tools and to personalize treatment strategies in breast cancer. Hierarchial clustering Machine learning Gene expression data Hybrid approach. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 19 Jan, 2026 Reviews received at journal 05 Jan, 2026 Reviewers agreed at journal 09 Dec, 2025 Reviewers agreed at journal 06 Dec, 2025 Reviews received at journal 02 Dec, 2025 Reviewers agreed at journal 15 Nov, 2025 Reviewers invited by journal 09 Nov, 2025 Editor assigned by journal 20 Jun, 2025 Submission checks completed at journal 29 May, 2025 First submitted to journal 29 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-6779819","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":545583888,"identity":"97ff90ca-913d-4c53-b897-71e3bcfe2ff5","order_by":0,"name":"Ana Beatriz Miranda Valentin","email":"","orcid":"","institution":"Federal University of Technology – Paraná","correspondingAuthor":false,"prefix":"","firstName":"Ana","middleName":"Beatriz Miranda","lastName":"Valentin","suffix":""},{"id":545583889,"identity":"5a9250b1-c19b-4eb4-aea5-518c6dc5ff8b","order_by":1,"name":"Glaucia Maria Bressan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4UlEQVRIiWNgGAWjYFAC5jYY4wCQkJAhQgsjTAtbAkgLDylaeAzAJEEN8u4H2x5XVNTZ88/u+fzqRo0FDwP74aMb8GkxPJPYbnjmzOHEGXfObrPOOQZ0GE9a2g28WhoS2yQb2w4kMNzI3WacwwbUIsFjhl9L/0Ogln919vI3cp4Z5/wjQou8BMiWBmbGDTdymB/nthGhxUDiYbthw7HDiRtvpJkx5/ZJ8LAR8ot8f/Kxhw01dfZyN5Iff875VifHz374GH5bDiDYbBJgEp9ysC0NCDbzB0KqR8EoGAWjYGQCANOrSnoQEKl0AAAAAElFTkSuQmCC","orcid":"","institution":"Federal University of Technology – Paraná","correspondingAuthor":true,"prefix":"","firstName":"Glaucia","middleName":"Maria","lastName":"Bressan","suffix":""},{"id":545583890,"identity":"255e0678-efd1-454d-9bbc-5b9abf42d8e2","order_by":2,"name":"Elisângela Lizzi","email":"","orcid":"","institution":"Federal University of Technology – Paraná","correspondingAuthor":false,"prefix":"","firstName":"Elisângela","middleName":"","lastName":"Lizzi","suffix":""}],"badges":[],"createdAt":"2025-05-30 00:38:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6779819/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6779819/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96253169,"identity":"265fa7ec-3c85-4e31-a458-da9275593607","added_by":"auto","created_at":"2025-11-19 07:42:03","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4633,"visible":true,"origin":"","legend":"","description":"","filename":"fe2b751c78b341d39b9fc20ce91cce4b.json","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/e50be7e92ba04e1280e4466a.json"},{"id":96211374,"identity":"16521364-99c4-45c9-9906-f19c238c2a87","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"png","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56109,"visible":true,"origin":"","legend":"","description":"","filename":"Dendrogrameuclidean.png","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/8e406657da15bed2f6f4ab93.png"},{"id":96211370,"identity":"c2946751-8078-4114-9850-a5c4da95bc9f","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38817,"visible":true,"origin":"","legend":"","description":"","filename":"Dendrogrampearson.png","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/8c4d2b386560b68045e56e5e.png"},{"id":96211372,"identity":"ad8943db-3be3-4e9e-8149-64f340a7a12c","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":130380,"visible":true,"origin":"","legend":"","description":"","filename":"SHAP1tcgaoptuna8.png","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/400b76db2dc3c8ee0151a5f9.png"},{"id":96211375,"identity":"c5311d9f-f9da-4044-9ecb-1fbd811dfe46","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":995605,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerRBE.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/6d8515c722492d397ce54290.pdf"},{"id":96211376,"identity":"c431b0cb-f447-4e60-b228-119d5c558cab","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":305260,"visible":true,"origin":"","legend":"","description":"","filename":"coverletter.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/c9aa58163bc05bce4304281b.pdf"},{"id":96250759,"identity":"2788c19c-9e5a-4b7f-bacb-2b5144fb7e77","added_by":"auto","created_at":"2025-11-19 07:38:57","extension":"eps","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":357553,"visible":true,"origin":"","legend":"","description":"","filename":"fig1.eps","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/1e5b93a53f5875af0ceb933e.eps"},{"id":96211382,"identity":"b01e98dd-521f-47c6-960d-9a606943114c","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"txt","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8394,"visible":true,"origin":"","legend":"","description":"","filename":"history.txt","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/e35def21777178a11de9de1e.txt"},{"id":96211381,"identity":"989feaf1-06ae-44da-b3c9-e754296c3daa","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":119329,"visible":true,"origin":"","legend":"","description":"","filename":"image.png","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/cf8471775f7f2a62986a3576.png"},{"id":96251455,"identity":"3736bd79-4fae-4baf-9a63-511ad1c35c70","added_by":"auto","created_at":"2025-11-19 07:39:44","extension":"cls","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":43402,"visible":true,"origin":"","legend":"","description":"","filename":"llncs.cls","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/5e7dc64762f13b995781d03b.cls"},{"id":96211377,"identity":"9af7d4cc-a9e5-4a40-be5d-9ec5da32e996","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"pdf","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":232527,"visible":true,"origin":"","legend":"","description":"","filename":"llncsdoc.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/61969306cc464801706c95dd.pdf"},{"id":96211386,"identity":"be837e2b-4ebe-40f6-b7ec-6cddb9f5eea3","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86980,"visible":true,"origin":"","legend":"","description":"","filename":"matriz.png","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/0031127190b54d491ff83cae.png"},{"id":96211385,"identity":"885fab40-7a3b-4d5b-8455-2bc0c382a7a7","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":162326,"visible":true,"origin":"","legend":"","description":"","filename":"matriztcgaoptuna2.png","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/b8b92b90e87774676777f20b.png"},{"id":96211387,"identity":"882b9931-c750-4dc1-bdac-57b3346a0ba7","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"txt","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":573,"visible":true,"origin":"","legend":"","description":"","filename":"readme.txt","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/4d8052624c728cb345711202.txt"},{"id":96251963,"identity":"3a101c6d-2938-4fd7-bacb-4f0a05ebedda","added_by":"auto","created_at":"2025-11-19 07:40:14","extension":"bst","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32146,"visible":true,"origin":"","legend":"","description":"","filename":"splncs04.bst","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/ed7cb5d0ba21b470c5b98640.bst"},{"id":96253100,"identity":"fbc04b26-5028-470b-a242-7057365200fb","added_by":"auto","created_at":"2025-11-19 07:41:58","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":179755,"visible":true,"origin":"","legend":"","description":"","filename":"tcgaop3.png","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/b8e279b62fb4b47b31d58c4f.png"},{"id":96211373,"identity":"0bb4d66d-6dec-4771-8416-1234f17e4933","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":101634,"visible":true,"origin":"","legend":"","description":"","filename":"workflow.png","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/55d2e81072de6b094d98be0b.png"},{"id":96211380,"identity":"32cf0c4d-789b-4c17-aa05-c10238fa3684","added_by":"auto","created_at":"2025-11-18 18:49:52","extension":"xml","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48758,"visible":true,"origin":"","legend":"","description":"","filename":"fe2b751c78b341d39b9fc20ce91cce4b1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1/03a52190122af08791e4dea8.xml"},{"id":96257114,"identity":"43a2f61b-fa05-4927-90f4-39b9fa717ffb","added_by":"auto","created_at":"2025-11-19 07:51:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":780007,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerRBE.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6779819/v1_covered_ce9ca054-25de-452b-93dc-201218294293.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Unsupervised and Supervised Approaches for Breast Cancer Subtype Classification: Hierarchical Clustering and Machine Learning with Hyperparameter Optimization","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"research-on-biomedical-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rbme","sideBox":"Learn more about [Research on Biomedical Engineering](http://link.springer.com/journal/42600)","snPcode":"42600","submissionUrl":"https://submission.nature.com/new-submission/42600/3","title":"Research on Biomedical Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Hierarchial clustering, Machine learning, Gene expression data, Hybrid approach.","lastPublishedDoi":"10.21203/rs.3.rs-6779819/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6779819/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Breast cancer is considered a public health problem and a disease of concern, which contains distinct subtypes, making accurate classification critical for personalized treatment. This study proposes a hybrid approach by applying supervised and unsupervised learning techniques for breast cancer subtype classification using gene expression data from The Cancer Genome Atlas (TCGA). First, hierarchical clustering with Pearson correlation and Euclidean distance as similarity metrics are employed to explore the intrinsic structure of the dataset. Subsequently, supervised machine learning models, including Logistic Regression, Support Vector Machine (SVM), Random Forest, and Multilayer Perceptron (MLP), are trained for the classification task. Hyperparameter tuning is performed using Optuna to improve predictive performance, and SHapley Additive exPlanations (SHAP) is applied to analyze feature importance library was applied to analyze the importance of variables and the influence of each dimension for each classifier. The results highlight the effectiveness of applying clustering methods and machine learning to improve classification accuracy and interpretability, contributing to the development of more accurate diagnostic tools and to personalize treatment strategies in breast cancer.","manuscriptTitle":"Unsupervised and Supervised Approaches for Breast Cancer Subtype Classification: Hierarchical Clustering and Machine Learning with Hyperparameter Optimization","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-18 18:49:47","doi":"10.21203/rs.3.rs-6779819/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-19T23:00:38+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-05T17:38:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"17980449404091681878832455424184622604","date":"2025-12-09T11:50:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"153625728573451257725395871063251882039","date":"2025-12-06T13:47:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-02T13:49:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"180734305410443557055789000172990889854","date":"2025-11-15T16:00:55+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-09T20:19:08+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-20T21:01:53+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-30T01:41:09+00:00","index":"","fulltext":""},{"type":"submitted","content":"Research on Biomedical Engineering","date":"2025-05-30T00:22:27+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"research-on-biomedical-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rbme","sideBox":"Learn more about [Research on Biomedical Engineering](http://link.springer.com/journal/42600)","snPcode":"42600","submissionUrl":"https://submission.nature.com/new-submission/42600/3","title":"Research on Biomedical Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"5dd006ca-2ed4-49bd-8a1a-14d7c8c9447f","owner":[],"postedDate":"November 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T18:38:48+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-18 18:49:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6779819","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6779819","identity":"rs-6779819","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}