Integrating machine learning algorithms to systematically assess reactive oxygen species levels to aid prognosis and novel treatments for triple-negative breast cancer patients

Sep 24, 2026

Uploaded by Connor

Integrating machine learning to build a robust reactive oxygen species (ROS) signature (ROSig) for triple-negative breast cancer. The study searched driver ROS prognostic indicators using univariate Cox regression, then used a pipeline combining nine machine learning algorithms to generate ROSig and resolve heterogeneity across cellular communication crosstalk, pathways, immune microenvironment, genomic variation, and therapy response. A total of 24 prognostic ROS indicators were identified, and ROSig outperformed as a risk predictor. Functional assays showed that HSF1 knockdown reduced TNBC proliferation and invasion. High ROSig associated with stronger heterogeneity and immune suppression; low ROSig linked to higher mutation and treatment sensitivity.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Methods

Results

Conclusion

Keywords

References

TYPE Original Research PUBLISHED 19 June 2023 DOI 10.3389/fimmu.2023.1196054 OPEN ACCESS EDITED BY Dongmei Zhang, Sichuan University, China REVIEWED BY Shaohua Chen, Guangxi Medical University Cancer Hospital, China Zheng Yuan, China Academy of Chinese Medical Sciences, China Ting Yu, Sichuan University, China *CORRESPONDENCE Xiaochen Zhao [casslias@126.com](casslias@126.com)[ ](casslias@126.com)Chihua Wu [18749019@qq.com](18749019@qq.com) †These authors share ﬁrst authorship RECEIVED 29 March 2023 ACCEPTED 02 June 2023 PUBLISHED 19 June 2023 CITATION Li J, Liang Y, Zhao X and Wu C (2023) Integrating machine learning algorithms to systematically assess reactive oxygen species levels to aid prognosis and novel treatments for triple-negative breast cancer patients. Front. Immunol. 14:1196054 . doi: 10.3389/fimmu.2023.1196054 COPYRIGHT © 2023 Li, Liang, Zhao and Wu. This is an 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. Integrating machine learning algorithms to systematically assess reactive oxygen species levels to aid prognosis and novel treatments for triple-negative breast cancer patients Juan Li 1,2†, Yu Liang 1,2†, Xiaochen Zhao 2,3* and Chihua Wu 1,2* 1 Department of Breast Surgery, Sichuan Provincial People’s Hospital, University of Electronic Science and Technology of China, Chengdu, China, 2Chinese Academy of Sciences Sichuan Translational Medicine Research Hospital, Chengdu, China, 3 Department of Hepatobiliary Surgery, Sichuan Provincial People’s Hospital, University of Electronic Science and Technology of China, Chengdu, China Introduction: Breast cancer has become one of the top health concerns for women, and triple-negative breast cancer (TNBC) leads to treatment resistance and poor prognosis due to its high degree of heterogeneity and malignancy. Reactive oxygen species (ROS) have been found to play a dual role in tumors, and modulating ROS levels may provide new insights into prognosis and tumor treatment. Methods: This study attempted to establish a robust and valid ROS signature (ROSig) to aid in assessing ROS levels. The driver ROS prognostic indicators were searched based on univariate Cox regression . A well-established pipeline integrating 9 machine learning algorithms was used to generate the ROSig. Subsequently, the heterogeneity of different ROSig levels was resolved in terms of cellular communication crosstalk, biological pathways, immune microenvironment, genomic variation, and response to chemotherapy and immunotherapy. In addition, the effect of the core ROS regulator HSF1 on TNBC cell proliferation was detected by cell counting kit-8 and transwell assays. Results: A total of 24 prognostic ROS indicators were detected. A combination of the Coxboost+ Survival Support Vector Machine (survival-SVM) algorithm was chosen to generate ROSig. ROSig proved to be the superior risk predictor for TNBC. Cellular assays show that knockdown of HSF1 can reduce the proliferation and invasion of TNBC cells. The individual risk stratiﬁcation based on ROSig showed good predictive accuracy. High ROSig was identiﬁed to be associated with higher cell replication activity, stronger tumor heterogeneity, and an immunosuppressive microenvironment. In contrast, low ROSig indicated amore abundant cellular matrix and more active immune signaling. Low ROSig has a higher tumor mutation load and copy number load. Finally, we found that low ROSig patients were more sensitive to doxorubicin and immunotherapy. Frontiers in Immunology 01 [frontiersin.org](frontiersin.org) Conclus

FAQs

What is the main goal of the study?

To develop a ROS signature (ROSig) using machine learning that systematically assesses ROS levels and supports prognosis and treatment decisions for triple-negative breast cancer patients.

How were the ROS prognostic indicators and ROSig constructed?

The driver ROS prognostic indicators were identified using univariate Cox regression, and ROSig was generated through a pipeline integrating nine machine learning algorithms, with the Coxboost + survival-SVM combination selected.

What biological and clinical differences were associated with high versus low ROSig?

High ROSig correlated with higher replication activity, stronger tumor heterogeneity, and an immunosuppressive microenvironment, while low ROSig showed more abundant cellular matrix, more active immune signaling, higher mutation and copy number loads, and greater sensitivity to doxorubicin and immunotherapy.

Sep 24, 2026

Uploaded by Connor