Integration of Transcriptomics and Machine Learning for Insights into Breast Cancer - Exploring Lipid Metabolism and Immune Interactions

Aug 5, 2026

Upload by Liam

Breast cancer remains a major global health challenge with limited early detection, and its tumor immune microenvironment is tightly linked to fatty acid metabolism. This study integrates transcriptomics with machine learning to characterize lipid metabolism–related prognostic genes and to evaluate immune infiltration across risk subgroups. ESTIMATE-based analyses assess immune infiltration and immunotherapy responsiveness, while tailored treatments are screened by subgroup. Key gene expression is further validated through in vitro experiments, supporting mechanistic and therapeutic insight into breast cancer.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Background

Methods

Results

Conclusion

Keywords

TYPE Original Research PUBLISHED 25 October 2024 DOI 10.3389/fimmu.2024.1470167 OPEN ACCESS EDITED BY Lisha Mou, Shenzhen Second People ’s Hospital, China REVIEWED BY Qi Yan, University at Buffalo, United States Xin Xu, Bristol Myers Squibb, United States Li Li, University of California, San Francisco, United States Pei-Ching Huang, Metagenomi, United States Yuan Li, Stanford University, United States *CORRESPONDENCE Baogang Liu liubaogang [1962@sina.com](1962@sina.com) Meisi Yan [msyan@hrbmu.edu.cn](msyan@hrbmu.edu.cn) †These authors have contributed equally to this work RECEIVED 25 July 2024 ACCEPTED 08 October 2024 PUBLISHED 25 October 2024 CITATION Chen X, Yi J, Xie L, Liu T, Liu B and Yan M (2024) Integration of transcriptomics and machine learning for insights into breast cancer: exploring lipid metabolism and immune interactions. Front. Immunol. 15:1470167 . doi: 10.3389/fimmu.2024.1470167 COPYRIGHT © 2024 Chen, Yi, Xie, Liu, Liu and Yan. This isan open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Integration of transcriptomicsand machine learning for insights into breast cancer: exploring lipid metabolism and immune interactions Xiaohan Chen 1†, Jinfeng Yi 2†, Lili Xie 1, Tong Liu 1,3, Baogang Liu 1* and Meisi Yan 2* 1 Harbin Medical University Cancer Hospital, Harbin Medical University, Harbin, China, 2 Department of Basic Medical Sciences, Harbin Medical University, Harbin, China, 3 National Health Commission (NHC) Key Laboratory of Cell Transplantation, The First Afﬁliated Hospital of Harbin Medical University, Harbin, China Background: Breast cancer (BRCA) represents a substantial global health challenge marked by inadequate early detection rates. The complex interplay between the tumor immune microenvironment and fatty acid metabolism in BRCA requires further investigation to elucidate the speciﬁc role of lipid metabolism in this disease. Methods: We systematically integrated nine machine learning algorithms into 184 unique combinations to develop a consensus model for lipid metabolismrelated prognostic genes (LMPGS) . Additionally, transcriptomics analysis provided a comprehensive understanding of this prognostic signature. Using the ESTIMATE method, we evaluated immune inﬁltration among different risk subgroups and assessed their responsiveness to immunotherapy. Tailored treatments were screened for speciﬁc risk subgroups. Finally, we veriﬁed the expression of key genes through in vitro experiments. Results: We identiﬁed 259 differentially expressed genes (DEGs) related to lipid metabolism through analysis of the cancer genome atlas program (TCGA) database. Subsequently, via univariate Cox regression analysis and C-index analysis, we developed an optimal machine learning algorithm to construct a 21-gene LMPGS model. We used optimal cutoff values to divide the lipid metabolism prognostic gene scores into two groups according to high and low scores. Our study revealed distinct biological functions and mutation landscapes between high-scoring and low-scoring patients. The low-scoring group presented a greater immune score, whereas the high-scoring group presented enhanced responses to both immunotherapy and chemotherapy drugs. Single-cell analysis highlighted signiﬁcant upregulation of CPNE3 in epithelial cells. Moreover, by employing molecular docking, we identiﬁed niclosamide as a potential targeted therapeutic drug. Finally, our experiments demonstrated high expression of MTMR9 and CPNE3 in BRCA and their signiﬁcant correlation with prognosis. Frontiers in Imm

FAQs

What is the main research focus of this study on breast cancer?

The study focuses on integrating transcriptomics and machine learning to investigate lipid metabolism–related prognostic genes and their connections to the tumor immune microenvironment in breast cancer.

How were immune infiltration and immunotherapy responsiveness evaluated?

Immune infiltration was assessed among different risk subgroups using the ESTIMATE method, and subgroup-specific responsiveness to immunotherapy was evaluated accordingly.

What gene signatures and potential therapeutics did the study identify?

The researchers developed a 21-gene lipid metabolism prognostic model and found distinct functional and mutational patterns between high- and low-score groups. They highlighted niclosamide as a potential targeted therapeutic drug and validated key gene expression and prognosis correlations experimentally.

Aug 5, 2026

Upload by Liam