文献速递乳腺癌放疗放疗物理与技术

整合基因组与非基因组数据分层放疗后对侧乳腺癌风险

Integrating Genomic and Nongenomic Data to Stratify the Risk of Contralateral Breast Cancer After Radiation Therapy.
PubMed 文献 · Int J Radiat Oncol Biol Phys · 2026-02-26

基于Women's Environmental Cancer and Radiation Epidemiology研究子集(633例对侧乳腺癌病例与1253例匹配的单侧乳腺癌对照,均接受放疗且有全基因组关联研究单核苷酸多态性数据),比较三种数据整合方法构建对侧乳腺癌风险分层模型。最佳方法为序贯迭代整合联合混合效应随机森林算法,测试集曲线下面积为0.64,预测与观察对侧乳腺癌发生的比值比均为3.27。基因集富集与蛋白互作分析提示高重要性评分基因与脂质和脂肪酸代谢及他莫昔芬敏感性相关。

要点

  • 序贯迭代整合联合混合效应随机森林为最佳建模方法,测试集AUC为0.64。
  • 测试集最低与最高风险分箱间,预测与观察对侧乳腺癌发生的比值比均为3.27。
  • 高重要性评分基因与脂质和脂肪酸代谢及乳腺癌对他莫昔芬敏感性通路相关。

核心结论

  • 混合效应随机森林方法可整合高维基因组与低维非基因组数据,用于对侧乳腺癌风险分层,具有中等预测能力。

研究设计与样本

  • 基于人群的Women's Environmental Cancer and Radiation Epidemiology研究子集,含633例对侧乳腺癌病例和1253例个体匹配的单侧乳腺癌对照,均接受放疗且具备全基因组关联研究单核苷酸多态性数据。
  • 研究人群划分为训练集、验证集和测试集,比较朴素整合、序贯整合与序贯迭代整合三种方法。
  • 对最终模型进行基因集富集分析和蛋白互作分析。

主要发现

  • 最佳整合方法为序贯迭代整合联合混合效应随机森林算法,测试集曲线下面积为0.64。
  • 校准分析显示测试集按预测值排序的最低与最高风险分箱间一致性良好,预测与观察对侧乳腺癌发生的比值比均为3.27。
  • 基因集富集与蛋白互作分析显示高重要性评分基因与脂质和脂肪酸代谢及乳腺癌对他莫昔芬敏感性相关通路有关。

临床怎么用

  • 该模型可辅助识别放疗后对侧乳腺癌高风险女性,但预测能力中等,尚需外部验证后再用于临床决策。

局限性

  • 测试集曲线下面积为0.64,预测能力仅为中等。
  • 研究基于特定人群子集,结论外推需谨慎。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

PURPOSE: Women treated with radiation therapy (RT) for breast cancer have an increased risk of developing radiation-associated contralateral breast cancer (CBC). Predicting CBC events is challenging because of the complex interplay of genomic, treatment, personal, and clinical factors. This study investigated computational methods that integrate genome-wide single-nucleotide polymorphisms and nongenomic data to develop a risk stratification model for developing CBC in women treated with RT for their first primary breast cancer. METHODS AND MATERIALS: This study used a subset of the population-based Women's Environmental Cancer and Radiation Epidemiology study that included 633 CBC cases and 1253 individually matched unilateral breast cancer controls who were treated with RT and had single-nucleotide polymorphism data available from a genome-wide association study. The study population was split into training, validation, and test sets for rigorous modeling and validation. Three data integration methods were compared in terms of their ability to stratify CBC risk: (1) naive integration; (2) sequential integration; and (3) sequential iterative integration. A biological analysis of the final model was performed using gene set enrichment analysis and protein-protein interaction analysis with gene annotation information informed by the model. RESULTS: The best-performing integration method was the sequential iterative integration equipped with the mixed-effect random forest algorithm. This approach achieved an area under the curve of 0.64 to stratify CBC risk in the test set, representing moderate predictive power. Calibration analysis showed good agreement between the lowest and highest risk bins stratified using sorted predicted values in the test set, resulting in an odds ratio of 3.27 for both predicted and observed CBC occurrence. Gene set enrichment analysis and protein-protein interaction analysis revealed that genes with high importance scores were associated with pathways relevant to lipid and fatty acid metabolism as well as breast cancer sensitivity to tamoxifen. CONCLUSIONS: The mixed-effect random forest approach demonstrated the potential for integrating high-dimensional genomic and low-dimensional nongenomic data to stratify CBC risk.

来源:Int J Radiat Oncol Biol Phys,查看原文。版权归原作者所有。

引用

  1. Lee S, Shu X, Derkach A, et al. Integrating Genomic and Nongenomic Data to Stratify the Risk of Contralateral Breast Cancer After Radiation Therapy. Int J Radiat Oncol Biol Phys. 2026. PMID: 41763494. doi:10.1016/j.ijrobp.2026.02.237

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。