BRIDGE框架:基于肿瘤转录组与组织病理学预测乳腺癌新辅助治疗反应
BRIDGE是一种计算框架,通过解卷积治疗前肿瘤转录组估计分子亚型组成并预测新辅助治疗病理完全缓解,在10个转录组数据集训练、24个独立数据集测试。在ER阳性/HER2阴性、HER2阳性和TNBC中AUC分别为0.84、0.77和0.73,优于现有商业签名替代实现。BRIDGE-Slide通过深度学习推断转录组实现组织病理学预测,表现优于直接切片-反应模型。
要点
- BRIDGE在ER阳性/HER2阴性乳腺癌中预测pCR的AUC为0.84(OR=8)。
- BRIDGE-Slide基于治疗前H&E切片预测反应,优于直接切片-反应模型。
- 空间转录组显示BRIDGE亚型分配形成空间连贯区域,具生物学可解释性。
核心结论
- BRIDGE是有生物学基础的新辅助乳腺癌反应预测框架,在多个独立队列中验证。
- BRIDGE-Slide作为快速低成本生物标志物具有潜力,尚需前瞻性测试验证。
研究设计与样本
- 计算框架BRIDGE在10个转录组数据集训练,在24个独立数据集测试,涵盖不同亚型。
- 额外6个含治疗前H&E切片和反应数据的数据集用于评估组织学预测。
主要发现
- 在ER阳性/HER2阴性肿瘤中,BRIDGE优于Oncotype DX、MammaPrint、ROR-S的替代实现,AUC为0.84(OR=8)。
- 在HER2阳性乳腺癌中AUC为0.77(OR=8.3),在TNBC中AUC为0.73(OR=3.1)。
- BRIDGE-Slide通过深度学习推断转录组,表现优于直接切片-反应模型。
- 探索性留一数据集分析提示对免疫检查点阻断治疗的ER阳性/HER2阴性肿瘤可能具有泛化性,待更大队列验证。
- 空间转录组显示BRIDGE推导的亚型分配形成与经典分子特征一致的空间连贯区域。
临床怎么用
- BRIDGE可用于治疗前预测新辅助治疗病理完全缓解,辅助治疗决策。
- BRIDGE-Slide有望基于常规H&E切片实现快速低成本反应预测。
局限性
- 对免疫检查点阻断治疗的泛化性仅来自探索性分析,需更大队列验证。
- BRIDGE-Slide需进一步前瞻性测试和验证。
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
BACKGROUND: While expression-based signatures inform adjuvant therapy in breast cancer (BC), no approved molecular biomarkers exist for the neoadjuvant setting, where early response prediction could inform treatment decisions. This challenge is compounded by intratumoral heterogeneity, as multiple malignant subtypes may coexist within a tumor and influence therapy sensitivity. METHODS: We developed BRIDGE (BReast Intra-tumoral Deconvolution of Gene Expression), a computational framework that deconvolves the pretreatment bulk tumor transcriptome to estimate molecular subtype composition and predict pathological complete response to neoadjuvant therapy. BRIDGE was trained on 10 transcriptomics datasets and tested on 24 independent ones spanning different subtypes. Six additional datasets with pretreatment hematoxylin and eosin slides and response data were analyzed to evaluate histology-based predictions. RESULTS: Analyzing measured transcriptomics, BRIDGE outperformed surrogate implementations of established commercial signatures (Oncotype DX, MammaPrint, ROR-S) in estrogen receptor (ER)-positive/human epidermal growth factor receptor 2 (HER2)-negative tumors and exceeded other transcriptomic predictors in HER2-positive and triple-negative breast cancer (TNBC) disease. In ER-positive/HER2-negative patients, it yields an receiver operating characteristic-area under the curve (AUC) of 0.84 with a high odds ratio (OR = 8); in HER2-positive disease, an AUC of 0.77 (OR = 8.3); and in TNBC, an AUC of 0.73 (OR = 3.1). We further developed BRIDGE-Slide, which applies BRIDGE to pretreatment histopathology slides via deep learning-inferred transcriptomics. BRIDGE-Slide outperforms direct slide-to-response models, underscoring its potential as a first-of-its-kind, fast, low-cost biomarker. Exploratory leave-one-dataset-out analyses across datasets treated with alternative neoadjuvant regimens suggest generalizability to immune checkpoint blockade-treated ER-positive/HER2-negative tumors, pending validation in larger cohorts. Finally, spatial transcriptomics shows that BRIDGE-derived subtype assignments form spatially cohesive regions aligned with canonical molecular features, reinforcing its biological interpretability. CONCLUSIONS: BRIDGE is a biologically grounded framework for neoadjuvant BC response prediction, validated on a rich set of different patients' cohorts. Its histopathology-based version opens the door for fast and low-cost prediction in the neoadjuvant setting, upon further prospective testing and validation.
引用
- Cantore T, Hoang DT, Pal LR, et al. Predicting neoadjuvant breast cancer therapy response using BRIDGE from tumor transcriptomics and histopathology. Ann Oncol. 2026. PMID: 42203036. doi:10.1016/j.annonc.2026.05.700
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。