Personalized Cancer Diagonisis Using Genetic Dataset and ML Models

Personalized Cancer Diagonisis Using Genetic Dataset and ML 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 Research Article Personalized Cancer Diagonisis Using Genetic Dataset and ML Models B. D.K Patro, Gunjan Sengar, Shalinee sahu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6587007/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 genetic mutation classification is critical for precision medicine, but traditional models struggle with the complexity of unstructured textual data. This research addresses these challenges by transforming mutation descriptions into structured numerical representations, improving machine interpretability and model performance.Our approach utilizes TF-IDF vectorization to represent text data and applies Singular Value Decomposition (SVD) for dimensionality reduction, capturing essential information while reducing noise. To handle class imbalance, we employ SMOTE, enhancing the training dataset with synthetic minority samples. We further introduce a multi-level encoding strategy that combines statistical features with semantic word embeddings, enriching the feature set and capturing deeper patterns in the data.A range of machine learning models—SVM, Naïve Bayes, Random Forest, and KNN—are trained and optimized using GridSearchCV. Additionally, a Stacking Classifier integrates multiple models to boost predictive performance. Validation through Stratified K-Fold Cross-Validation ensures reliability and maintains balanced class distributions across folds.Our results show that structured feature encoding significantly improves classification accuracy over traditional methods. This work advances computational genomics by offering a robust solution for handling clinical text data, supporting more effective precision medicine initiatives. Genetic Mutation Classification Precision Medicine Machine Learning Text Mining TF-IDF SVD SMOTE Word Embeddings Stacking Classifier Computational Genomics Full Text Additional Declarations No competing interests reported. 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-6587007","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":454890316,"identity":"d6f94413-0f2a-4a94-8f01-8726d759e7ad","order_by":0,"name":"B. D.K Patro","email":"","orcid":"","institution":"Rajkiya Engineering College Kannauj","correspondingAuthor":false,"prefix":"","firstName":"B.","middleName":"D.K","lastName":"Patro","suffix":""},{"id":454890317,"identity":"55b06313-9b5b-43c2-a4a3-4304654b55cf","order_by":1,"name":"Gunjan Sengar","email":"data:image/png;base64,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","orcid":"","institution":"Rajkiya Engineering College Kannauj","correspondingAuthor":true,"prefix":"","firstName":"Gunjan","middleName":"","lastName":"Sengar","suffix":""},{"id":454890318,"identity":"a9cec1d8-84e5-435c-85a1-ddcb1d6e8891","order_by":2,"name":"Shalinee sahu","email":"","orcid":"","institution":"Rajkiya Engineering College Kannauj","correspondingAuthor":false,"prefix":"","firstName":"Shalinee","middleName":"","lastName":"sahu","suffix":""}],"badges":[],"createdAt":"2025-05-04 06:53:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6587007/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6587007/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":82966278,"identity":"dc5e74e5-2681-4c95-af73-2e390d6dfd64","added_by":"auto","created_at":"2025-05-17 22:16:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1897342,"visible":true,"origin":"","legend":"","description":"","filename":"PersonalizedCancerDiagonisisUsingGeneticDataset1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6587007/v1_covered_561381b3-ab3d-423d-a5c3-7f973410b85b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Personalized Cancer Diagonisis Using Genetic Dataset and ML Models","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Genetic Mutation Classification, Precision Medicine, Machine Learning, Text Mining, TF-IDF, SVD, SMOTE, Word Embeddings, Stacking Classifier, Computational Genomics","lastPublishedDoi":"10.21203/rs.3.rs-6587007/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6587007/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate genetic mutation classification is critical for precision medicine, but traditional models struggle with the complexity of unstructured textual data. This research addresses these challenges by transforming mutation descriptions into structured numerical representations, improving machine interpretability and model performance.Our approach utilizes TF-IDF vectorization to represent text data and applies Singular Value Decomposition (SVD) for dimensionality reduction, capturing essential information while reducing noise. To handle class imbalance, we employ SMOTE, enhancing the training dataset with synthetic minority samples. We further introduce a multi-level encoding strategy that combines statistical features with semantic word embeddings, enriching the feature set and capturing deeper patterns in the data.A range of machine learning models—SVM, Naïve Bayes, Random Forest, and KNN—are trained and optimized using GridSearchCV. Additionally, a Stacking Classifier integrates multiple models to boost predictive performance. Validation through Stratified K-Fold Cross-Validation ensures reliability and maintains balanced class distributions across folds.Our results show that structured feature encoding significantly improves classification accuracy over traditional methods. This work advances computational genomics by offering a robust solution for handling clinical text data, supporting more effective precision medicine initiatives.","manuscriptTitle":"Personalized Cancer Diagonisis Using Genetic Dataset and ML Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-12 11:40:29","doi":"10.21203/rs.3.rs-6587007/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":"69cdb552-391b-4f84-8b1f-c4ca638c2fbb","owner":[],"postedDate":"May 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-05-17T22:08:13+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-12 11:40:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6587007","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6587007","identity":"rs-6587007","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}