Evaluating the prognostic potential of telomerase signature in breast cancer through advanced machine learning model

Aug 4, 2026

Breast cancer prognosis remains difficult due to molecular heterogeneity and complex disease biology, limiting the reliability of existing risk models for individualized treatment planning. This research develops a machine learning–assisted telomerase signature (MLTS) by integrating multi-omics information from nine independent breast cancer datasets and training multiple algorithms to select telomerase-related genes linked to survival outcomes. MLTS is benchmarked against 66 published prognostic models and validated through genomic, single-cell transcriptomic, and immune microenvironment analyses to support more stable prediction and potential clinical translation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Introduction

Clinical challenge and rationale

Telomerase and prior prognostic modeling

Methods

Data acquisition from public cohorts

Machine learning–assisted telomerase signature construction

Performance evaluation and comparison

Results

Predictive accuracy and stability versus existing models

Genomic features linked to MLTS scores

Single-cell and immune microenvironment findings

Conclusions

MLTS as a prognostic biomarker and future directions

TYPE Original Research PUBLISHED 28 November 2024 DOI 10.3389/fimmu.2024.1462953 OPEN ACCESS EDITED BY Wei Wang, First Afﬁliated Hospital of Anhui Medical University, China REVIEWED BY Rishi Kumar Jaiswal, Loyola University Chicago, United States Heba Taher, Cairo University, Egypt *CORRESPONDENCE Tao Wang [wangtaoGPPH@gzu.edu.cn](wangtaoGPPH@gzu.edu.cn) †These authors have contributed equally to this work RECEIVED 10 July 2024 ACCEPTED 14 November 2024 PUBLISHED 28 November 2024 CITATION Guo X, Cao Y, Shi X, Xing J, Feng C and Wang T (2024) Evaluating the prognostic potential of telomerase signature in breast cancer through advanced machine learning model. Front. Immunol. 15:1462953 . doi: 10.3389/fimmu.2024.1462953 COPYRIGHT © 2024 Guo, Cao, Shi, Xing, Feng and Wang. 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. Evaluating the prognostic potential of telomerase signature in breast cancer through advanced machine learning model Xiao Guo 1†, Yuyan Cao 1†, Xinlin Shi 1, Jiaying Xing 1, Chuanbo Feng 1 and Tao Wang 2* 1School of Pharmacy, Beihua University, Jilin, Jilin, China, 2 Research Laboratory Center, Guizhou Provincial People’s Hospital, Guiyang, Guizhou, China Background: Breast cancer prognosis remains a signiﬁcant challenge due to the disease's molecular heterogeneity and complexity. Accurate predictive models are critical for improving patient outcomes and tailoring personalized therapies. Methods: We developed a Machine Learning-assisted Telomerase Signature (MLTS) by integrating multi-omics data from nine independent breast cancer datasets. Using multiple machine learning algorithms, we identiﬁed six telomerase-related genes signiﬁcantly associated with patient survival. The predictive performance of MLTS was evaluated against 66 existing breast cancer prognostic models across diverse cohorts. Results: The MLTS demonstrated superior predictive accuracy, stability, and reliability compared to other models. Patients with high MLTS scores exhibited increased tumor mutational burden, chromosomal instability, and poor survival outcomes. Single-cell RNA sequencing analysis further revealed higher MLTS scores in aneuploid tumor cells, suggesting a role in cancer progression. Immune proﬁling indicated distinct tumor microenvironment characteristics associated with MLTS scores, potentially guiding therapeutic decisions. Conclusions: Our ﬁndings highlight the utility of MLTS as a robust prognostic biomarker for breast cancer. The ability of MLTS to predict patient outcomes and its association with key genomic and cellular features underscore its potential asa target for personalized therapy. Future research may focus on integrating MLTS with additional molecular signatures to enhance its clinical application in precision oncology. KEYWORDS breast cancer, telomerase genes, machine learning, PD-1, gemcitabine Frontiers in Immunology 01 [frontiersin.org](frontiersin.org) Introduction Breast cancer, historically labeled as the “invisible killer” in middle-aged and older women, has alarmingly started to proliferate among younger demographics at an unprecedented rate. Recent ﬁndings from the International Agency for Research on Cancer reveal a striking 24.2% incidence rate of breast cancer, underscoring a critical, escalating public health issue that continues to rise annually (1) . While various prognostic models have been developed, such as those by Sui et al. using immune cell inﬁltration scores (2), and by [Elke M. et](Elke M. et) al. integrating genetic polymorphis

FAQs

What is the main goal of the study on telomerase signatures in breast cancer?

To build and evaluate a machine learning–assisted telomerase signature (MLTS) that predicts breast cancer patient survival more accurately than existing prognostic models.

How is the MLTS model constructed in this research?

The study integrates multi-omics data from nine independent breast cancer datasets and uses multiple machine learning algorithms to identify six telomerase-related genes associated with survival.

What biological features are associated with high MLTS scores?

High MLTS scores relate to increased tumor mutational burden and chromosomal instability, worse survival outcomes, higher MLTS scores in aneuploid tumor cells, and distinct immune microenvironment characteristics.

Aug 4, 2026

Upload by Theodore