Machine learning on transcription factor expression profiles for precision breast cancer therapy.

IF 6 2区医学 Q1 ONCOLOGY

Cancer Cell International Pub Date : 2025-10-09 DOI:10.1186/s12935-025-03987-5

Xiaonan Zhang, Simin Min, Ning Zhang, Xiaoyu Shi, Zhaogen Cai, Di Yang, Zixin Meng, Yunxia Zhao, Ni Ni, Tao Wang

{"title":"Machine learning on transcription factor expression profiles for precision breast cancer therapy.","authors":"Xiaonan Zhang, Simin Min, Ning Zhang, Xiaoyu Shi, Zhaogen Cai, Di Yang, Zixin Meng, Yunxia Zhao, Ni Ni, Tao Wang","doi":"10.1186/s12935-025-03987-5","DOIUrl":null,"url":null,"abstract":"Background: Although breast cancer is a significant heterogeneous disease with an increasing global prevalence, precise prognostic evaluation is a vital aspect of designing personalized therapy strategies and upholding patients' survival rates. With the incorporation of artificial intelligence technology, in particular, machine learning, cancer prognosis and prediction have significantly been redefined.Methods: In this study, we adopted a ten-fold cross-validation method to construct a Machine Learning-Derived Transcription Factor Signature (MDTS) across 108 algorithmic combinations. The optimal model was selected based on the highest average C-index across ten cohorts. We integrated single-cell data with multi-omics analysis to comprehensively assess the robustness of the MDTS model at both molecular and genomic levels. The MDTS demonstrated superior predictive power, outperforming 103 existing signatures and accurately predicting breast cancer outcomes across 10 independent cohorts.Results: Our findings revealed that patients with low MDTS scores are more likely to benefit from immunotherapy, while the PAC-1 drug was identified as the most targeted agents to the chemotherapy with high MDTS score.Conclusions: These insights will open the door to delivering cutting-edge MDTS strategies to customizing breast cancer therapies.","PeriodicalId":9385,"journal":{"name":"Cancer Cell International","volume":"25 1","pages":"346"},"PeriodicalIF":6.0000,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12512818/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cancer Cell International","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12935-025-03987-5","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Although breast cancer is a significant heterogeneous disease with an increasing global prevalence, precise prognostic evaluation is a vital aspect of designing personalized therapy strategies and upholding patients' survival rates. With the incorporation of artificial intelligence technology, in particular, machine learning, cancer prognosis and prediction have significantly been redefined.

Methods: In this study, we adopted a ten-fold cross-validation method to construct a Machine Learning-Derived Transcription Factor Signature (MDTS) across 108 algorithmic combinations. The optimal model was selected based on the highest average C-index across ten cohorts. We integrated single-cell data with multi-omics analysis to comprehensively assess the robustness of the MDTS model at both molecular and genomic levels. The MDTS demonstrated superior predictive power, outperforming 103 existing signatures and accurately predicting breast cancer outcomes across 10 independent cohorts.

Results: Our findings revealed that patients with low MDTS scores are more likely to benefit from immunotherapy, while the PAC-1 drug was identified as the most targeted agents to the chemotherapy with high MDTS score.

Conclusions: These insights will open the door to delivering cutting-edge MDTS strategies to customizing breast cancer therapies.

查看原文本刊更多论文

转录因子表达谱的机器学习用于精确乳腺癌治疗。

背景：虽然乳腺癌是一种重要的异质性疾病，全球患病率不断上升，但精确的预后评估是设计个性化治疗策略和维护患者生存率的重要方面。随着人工智能技术，特别是机器学习的引入，癌症的预后和预测得到了显著的重新定义。方法：在本研究中，我们采用十倍交叉验证方法构建了108种算法组合的机器学习衍生转录因子签名（MDTS）。根据10个队列中c -指数的最高平均值选择最优模型。我们将单细胞数据与多组学分析结合起来，在分子和基因组水平上全面评估MDTS模型的稳健性。MDTS显示出卓越的预测能力，优于103个现有特征，并在10个独立队列中准确预测乳腺癌结局。结果：我们的研究结果显示，MDTS评分低的患者更有可能从免疫治疗中获益，而PAC-1药物被确定为MDTS评分高的化疗的最靶向药物。结论：这些见解将为提供尖端MDTS策略以定制乳腺癌治疗打开大门。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Cancer Cell International ONCOLOGY-

CiteScore

10.90

自引率

1.70%

发文量

360

审稿时长

1 months

期刊介绍： Cancer Cell International publishes articles on all aspects of cancer cell biology, originating largely from, but not limited to, work using cell culture techniques. The journal focuses on novel cancer studies reporting data from biological experiments performed on cells grown in vitro, in two- or three-dimensional systems, and/or in vivo (animal experiments). These types of experiments have provided crucial data in many fields, from cell proliferation and transformation, to epithelial-mesenchymal interaction, to apoptosis, and host immune response to tumors. Cancer Cell International also considers articles that focus on novel technologies or novel pathways in molecular analysis and on epidemiological studies that may affect patient care, as well as articles reporting translational cancer research studies where in vitro discoveries are bridged to the clinic. As such, the journal is interested in laboratory and animal studies reporting on novel biomarkers of tumor progression and response to therapy and on their applicability to human cancers.