Combining metabolomics and machine learning to discover biomarkers for early-stage breast cancer diagnosis

Sep 21, 2026

There is an urgent need for better biomarkers for early-stage breast cancer detection. By using untargeted metabolomics and lipidomics with advanced data-mining methods focused on metabolism-centric biomarker discovery and validation, the study aimed to differentiate breast cancer patients from individuals with benign tumors. Ether-linked phosphatidylcholine distinguished invasive ductal carcinoma from benign tumors, including some cases with inconsistent mammography results.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Abstract

Introduction

PLOS ONE OPEN ACCESS Citation: Anh NK, Lee A, Phat NK, Yen NTH, Thu NQ, Tien NTN, et al. (2024) Combining metabolomics and machine learning to discover biomarkers for early-stage breast cancer diagnosis. PLoS ONE 19(10): e0311810 . [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.1371/journal.pone](10.1371/journal.pone).0311810 Editor: Anil Bhatia, University of California Riverside, UNITED STATES OF AMERICA Received: May 3, 2024 Accepted: September 25, 2024 Published: October 21, 2024 Copyright: © 2024 Anh et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data Availability Statement: All relevant data for this study are within the paper and its Supporting information files. Funding: This work was supported by 2022 Inje University Busan Paik Hospital Research Grant. The funding organization did not participate in the study design, data acquisition, data analysis and interpretation, or the content of the manuscript. Competing interests: The authors have declared that no competing interests exist. RESEARCH ARTICLE Combining metabolomics and machine learning to discover biomarkers for earlystage breast cancer diagnosis Nguyen KyAnh1,2☯, Anbok Lee3☯, Nguyen Ky Phat2, Nguyen Thi Hai Yen2, Nguyen Quang Thu2, Nguyen Tran Nam Tien2, Ho-Sook Kim2, Tae Hyun Kim4, Dong Hyun Kim2, Hee-Yeon Kim4 *, Nguyen Phuoc Long2 * 1 Faculty of Pharmacy, Ton Duc Thang University, Ho Chi Minh City, Vietnam, 2 Department of Pharmacology and PharmacoGenomics Research Center, Inje University College of Medicine, Busan, Republic of Korea, 3 Department of Surgery, Chung-Ang University Gwangmyeong Hospital, Chung-Ang University College of Medicine, Gyeonggi-do, Republic of Korea, 4 Department of Surgery, Busan Paik Hospital, Inje University College of Medicine, Busan, Republic of Korea ☯ These authors contributed equally to this work. * [gsrcq@naver.com](gsrcq@naver.com) (HYK); [phuoclong@inje.ac.kr](phuoclong@inje.ac.kr) (NPL) Abstract There is an urgent need for better biomarkers for the detection of early-stage breast cancer. Utilizing untargeted metabolomics and lipidomics in conjunction with advanced data mining approaches for metabolism-centric biomarker discovery and validation may enhance the identification and validation of novel biomarkers for breast cancer screening. In this study, we employed a multimodal omics approach to identify and validate potential biomarkers capable of differentiating between patients with breast cancer and those with benign tumors. Our findings indicated that ether-linked phosphatidylcholine exhibited a significant difference between invasive ductal carcinoma and benign tumors, including cases with inconsistent mammography results. We observed alterations in numerous lipid species, including sphingomyelin, triacylglycerol, and free fatty acids, in the breast cancer group. Furthermore, we identified several dysregulated hydrophilic metabolites in breast cancer, such as glutamate, glycochenodeoxycholate, and dimethyluric acid. Through robust multivariate receiver operating characteristic analysis utilizing machine learning models, either linear support vector machines or random forest models, we successfully distinguished between cancerous and benign cases with promising outcomes. These results emphasize the potential of metabolic biomarkers to complement other criteria in breast cancer screening. Future studies are essential to further validate the metabolic biomarkers identified in our study and to develop assays for clinical applications. Introduction Breast cancer (BC) ranks among the most prevalent malignant neoplasms in women. The World Health Organization (WHO) reported alarming estimates of over 2.3 million BC diagnoses and 685,000 BC fatalities in 2020 [ 1] . Particularly con

FAQs

What is the main goal of this study?

To identify and validate potential metabolic biomarkers that distinguish early-stage breast cancer from benign tumors using multimodal omics and machine-learning-based analysis.

Which biomarker showed a significant difference between cancer and benign tumors?

Ether-linked phosphatidylcholine was reported as significantly different between invasive ductal carcinoma and benign tumors.

How did the researchers distinguish cancerous from benign cases?

They applied robust multivariate receiver operating characteristic analyses using machine-learning models, including linear support vector machines and random forest models.

Sep 21, 2026

Uploaded by River Wang