使用细胞外基质蛋白酶转录特征和临床变量的癌症综合生存预测：机器学习方法
Integrative Survival Prediction in Breast Cancer Using Extracellular Matrix Protease Transcript Signatures and Clinical Variables: A Machine Learning Approach.
摘要(中文译文)
传统乳腺癌预后工具依赖临床分期，往往忽略分子异质性，导致患者结局出现差异。由基质金属蛋白酶（MMP）、ADAM和ADAMTS酶家族驱动的细胞外基质（ECM）重塑对肿瘤进展至关重要。本研究评估将ECM蛋白酶转录本丰度与标准临床变量整合是否能提高生存预测准确性和个性化风险分层。分析来自癌症基因组图谱（TCGA）乳腺癌队列的临床和转录组数据。我们将排名靠前的蛋白酶基因的蛋白质编码转录本每百万（pTPM）与标准临床协变量（年龄、有序分期）整合。在分层70/30训练-测试划分下评估Cox比例风险（CoxPH）、惩罚Cox（CoxNet）、随机生存森林（RSF）和梯度提升生存（GBS）模型，随后进行五折交叉验证。锁定的最终RSF模型随后在METABRIC中进行外部测试，未重新训练或优化风险截断值。单变量筛选确定ADAM15、MMP15和ADAMTSL1为全局风险因素，而ADAMTS8和MMP7为保护性因素。预后信号具有亚型依赖性。整合多变量模型在内部测试中优于仅转录本方法。整合RSF获得最高留出区分度（C指数=0.797），优于仅基于年龄和分期训练的临床-only Cox基线（C指数=0.742，95% CI 0.636-0.826）。在METABRIC中，外部C指数为0.581（95% CI 0.562-0.598），训练定义的风险组间生存分离显著（log-rank < 0.0001）。ECM蛋白酶转录谱在TCGA-BRCA中提供补充预后信息，并显示出对METABRIC的部分可移植性。然而，适度的外部C指数表明跨平台个体水平区分能力有限，因此这些候选标志物应被解释为产生假设，在临床实施前需要进一步验证。
Abstract
: Traditional breast cancer prognostic tools relying on clinical staging often miss molecular heterogeneity, leading to divergent patient outcomes. Extracellular matrix (ECM) remodeling, driven by the Matrix Metalloproteinase (MMP), ADAM, and ADAMTS enzyme families, is critical to tumor progression. This study evaluates whether integrating ECM protease transcript abundance with standard clinical variables improves survival prediction accuracy and personalized risk stratification. : Clinical and transcriptomic data from The Cancer Genome Atlas (TCGA) breast cancer cohort were analyzed. We integrated the protein-coding transcripts per million (pTPM) of top-ranked protease genes with standard clinical covariates (age, ordinal stage). Cox Proportional Hazards (CoxPH), penalized Cox (CoxNet), Random Survival Forest (RSF), and Gradient Boosting Survival (GBS) models were evaluated under a stratified 70/30 train-test split, followed by five-fold cross-validation. The locked final RSF model was then externally tested in METABRIC without retraining or risk-cutoff optimization. : Univariate screening identified ADAM15, MMP15, and ADAMTSL1 as global risk factors, whereas ADAMTS8 and MMP7 were protective. Prognostic signals were subtype-dependent. Integrated multivariable models outperformed transcript-only approaches in internal testing. The integrative RSF achieved the highest held-out discrimination (C-index = 0.797), outperforming a clinical-only Cox baseline trained on age and stage alone (C-index = 0.742, 95% CI 0.636-0.826). In METABRIC, the external C-index was 0.581 (95% CI 0.562-0.598), with significant survival separation across training-defined risk groups (log-rank < 0.0001). : ECM protease transcript profiles provide complementary prognostic information in TCGA-BRCA and show partial transportability to METABRIC. However, the modest external C-index indicates limited individual-level discrimination across platforms, so these candidate markers should be interpreted as hypothesis-generating and require further validation before clinical implementation.
如何引用
AMA
Rami Babas, Demitrios H Vynios, Aristotelis Kompothrekas, Basilis Boutsinas, Nikos Karamanos. Integrative Survival Prediction in Breast Cancer Using Extracellular Matrix Protease Transcript Signatures and Clinical Variables: A Machine Learning Approach.. Cancers. 2026; doi:10.3390/cancers18101497.
APA
Rami Babas, Demitrios H Vynios, Aristotelis Kompothrekas, Basilis Boutsinas, Nikos Karamanos (2026). Integrative Survival Prediction in Breast Cancer Using Extracellular Matrix Protease Transcript Signatures and Clinical Variables: A Machine Learning Approach.. Cancers. https://doi.org/10.3390/cancers18101497
GB/T 7714
Rami Babas, Demitrios H Vynios, Aristotelis Kompothrekas, Basilis Boutsinas, Nikos Karamanos. Integrative Survival Prediction in Breast Cancer Using Extracellular Matrix Protease Transcript Signatures and Clinical Variables: A Machine Learning Approach.[J]. Cancers, 2026 doi:10.3390/cancers18101497.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出