[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121343-en":3,"doc-seo-121343-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121343,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","The Implementation of Machine Learning Algorithms for Breast Cancer Biomarker Validation in Metabolomics Studies","Breast cancer is a heterogeneous disease with distinct molecular and metabolic characteristics that complicates diagnosis and treatment. Metabolic reprogramming supports the use of metabolomics to identify biomarkers and enable more personalized therapeutic strategies. Machine learning models are applied to complex metabolomics patterns, validating 24 significant metabolites derived from in silico analyses. Pathway results suggest involvement of glycerolphosphate, glycerophospholipid, and glycerolipid metabolism. Model validation shows strong performance, with Neural Network, Logistic Regression, and Random Forest achieving high AUC and precision, improving biomarker validation accuracy for breast cancer diagnostic strategies.","Eksakta : Berkala Ilmiah Bidang MIPA VOLUME 25 NO 04 2024, pp 468-483  \nISSN : Print 1411-3724—Online 2549-7464  \nDOI : [https://doi.org/10.24036/eksakta/vol25-iss04/553](https://doi.org/10.24036/eksakta/vol25-iss04/553)  \nEksakta  \nBerkala Ilmiah Bidang MIPA  \n[http://www.eksakta.ppj.unp.ac.id/index.php/eksakta](http://www.eksakta.ppj.unp.ac.id/index.php/eksakta)  \nArticle  \nThe Implementation of Machine Learning Algorithms for Breast Cancer Biomarker Validation in Metabolomics Studies  \nArticle Info  \nArticle history :  \nReceived December 05, 2024 Revised December 20, 2024 Accepted December 26,2024 Published December 30, 2024  \nKeywords :  \nBreast cancer, biomarker, bioinformatics, metabolomics, machine learning  \nNindhyana Diwaratri Ratnaningayu 1*, Aryo Tedjo2 , Sonar Soni Panigoro3  \n1Master’s Programme in Biomedical Sciences, Faculty of Medicine, Universitas Indonesia, Jakarta, Indonesia 2Department of Medical Chemistry, Faculty of Medicine, Universitas Indonesia, Jakarta, Indonesia  \n3Surgical Oncology Division, Department of Surgery, Faculty of Medicine, Universitas Indonesia, Jakarta, Indonesia  \nAbstract. Breast cancer is a heterogeneous disease characterized by distinct molecular and metabolic characteristics, making its diagnostics and treatment challenging. The existence of metabolic reprogramming in breast cancer underscores the potential to identify biomarkers through metabolomics studies, offering new avenues for personalized therapeutic approaches. Machine learning algorithms are now increasingly used to uncover complex patterns in metabolomics data. A comprehensive analysis of in silicometabolomics had successfully identified 24 significant metabolites after rigorous univariate and multivariate tests. Pathway analysis highlighted the apparent involvement of glycerolphosphate inglycerophospholipid and glycerolipid metabolism, indicating its potential role in breast cancer pathology. Validation of these 24 metabolites using machine learning algorithms provided superior results, with Neural Network achieving an AUC of 0.979 and a precision of 93%, Logistic Regression showing an AUC of 0.945 anda precision of 95 .7%, as well as Random Forest reporting an AUC of 0.974 and a precision of 95.7% in predictive performance. These findings demonstrate the remarkable ability of machine learning to improve biomarker validation accuracy in metabolomics, facilitating better diagnostic strategies for breast cancer.  \nThis is an open acces article under the CC-BY license.  \nThis is an open access article distributed under the Creative Commons 4.0 Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. ©2024 by author.  \nCorresponding Author :  \nNindhyana Diwaratri Ratnaningayu  \nMaster’s Programme in Biomedical Science, Faculty of Medicine, Universitas Indonesia, Jakarta, Indonesia [Email: ](Email: nindhyana@gmail.com)[nindhyana@gmail.com](Email: nindhyana@gmail.com)  \n1. Introduction  \nBreast cancer becomes the most commonly diagnosed cancer and the first most common cancer in women, surpassing lung cancer cases. The increasing incidence and mortality of breast cancer is a global problem that needs special attention [1-2] . In Indonesia, 66.271 new cases of breast cancer were recorded in 2022, making it the most prevalent type of cancer in the country [3-4] . Most breast cancer patients diagnosed in Indonesia are in the late stage, which is associated with low survival and poor prognosis [5-6] . Early detection of disease and selection of appropriate treatment can improve the prognosis of breast cancer patients [7-10] .  \nConventional methods of breast cancer screening are performed with imaging techniques, such as mammography, ultrasonography, and magnetic resonance imaging (MRI) . Needle biopsies are commonly performed operatively to confirm and determine the histopathological classification and stage of breast cancer [11-12] . The gro","cbCaij8uvj383h4T","https://ap.wps.com/l/cbCaij8uvj383h4T","pdf",1286121,1,16,"English","en",105,"# Introduction\n## Breast cancer burden and clinical need\n## Conventional screening and molecular markers\n## Metabolism heterogeneity and biomarker discovery\n## Metabolomics and study aims\n# Methods\n## In silico metabolomics analysis\n## Feature selection and statistical testing\n## Pathway analysis\n## Machine learning validation models\n# Results\n## Identified metabolites and metabolic pathways\n## Predictive performance metrics\n# Discussion\n## Implications for biomarker validation accuracy\n# Conclusion","[{\"question\":\"Why is biomarker validation important in breast cancer metabolomics studies?\",\"answer\":\"Breast cancer heterogeneity and distinct metabolic features make diagnosis challenging. Validating biomarkers through metabolomics and modeling helps improve reliability and diagnostic decision-making.\"},{\"question\":\"How were significant metabolites identified in the study?\",\"answer\":\"A comprehensive in silico metabolomics analysis identified 24 significant metabolites after rigorous univariate and multivariate tests.\"},{\"question\":\"Which machine learning models were used and what performance was reported?\",\"answer\":\"Neural Network, Logistic Regression, and Random Forest were used. Reported results include high AUC values and precision around the mid-90% range, demonstrating strong predictive performance for the 24 validated metabolites.\"}]","The Implementation of Machine Learning Algorithms for Breast Cancer Biomarker Validation in Metabolomics Studies | PDF",1785735157,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"the-implementation-of-machine-learning-algorithms-for-breast-cancer-biomarker-validation-in-metabolomics-studies","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/the-implementation-of-machine-learning-algorithms-for-breast-cancer-biomarker-validation-in-metabolomics-studies/121343/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is biomarker validation important in breast cancer metabolomics studies?","Question",{"text":75,"@type":76},"Breast cancer heterogeneity and distinct metabolic features make diagnosis challenging. Validating biomarkers through metabolomics and modeling helps improve reliability and diagnostic decision-making.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were significant metabolites identified in the study?",{"text":80,"@type":76},"A comprehensive in silico metabolomics analysis identified 24 significant metabolites after rigorous univariate and multivariate tests.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning models were used and what performance was reported?",{"text":84,"@type":76},"Neural Network, Logistic Regression, and Random Forest were used. Reported results include high AUC values and precision around the mid-90% range, demonstrating strong predictive performance for the 24 validated metabolites.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]