Multi-omic machine learning predictor of breast cancer therapy response.
Multi-omic machine learning predictor of breast cancer therapy response.
复制标题
乳腺癌治疗反应的多组体机器学习预测因子。
DOI：
10.1038/s41586-021-04278-5
复制
发表时间：
2022-01
期刊：
影响因子：
64.8
通讯作者：
Caldas C
中科院分区：
文献类型：
--
作者：
Sammut SJ;Crispin-Ortuzar M;Chin SF;Provenzano E;Bardwell HA;Ma W;Cope W;Dariush A;Dawson SJ;Abraham JE;Dunn J;Hiller L;Thomas J;Cameron DA;Bartlett JMS;Hayward L;Pharoah PD;Markowetz F;Rueda OM;Earl HM;Caldas C
乳腺癌是恶性细胞和肿瘤微环境的复杂生态系统。这些肿瘤生态系统的组成及其相互作用有助于对细胞毒性治疗的反应。建立反应预测指标的努力没有纳入这方面的知识。我们收集了168例乳腺肿瘤患者治疗前活检的临床、数字病理学、基因组和转录组学特征，这些患者在手术前接受了联合或不联合HER2（由ERBB2编码）靶向治疗的化疗。然后将手术时的病理学终点（完全缓解或残留疾病）与这些诊断性活检中的多组学特征相关联。在这里，我们表明，对治疗的反应是由预治疗的肿瘤生态系统调节的，其多组学景观可以使用机器学习整合到预测模型中。治疗后残留疾病的程度与治疗前特征单调相关，包括肿瘤突变和拷贝数景观、肿瘤增殖、免疫浸润和T细胞功能障碍和排斥。将这些特征结合到多组学机器学习模型中，预测了外部验证队列（75名患者）的病理完全缓解，曲线下面积为0.87。总之，对治疗的反应是由通过数据集成和机器学习捕获的肿瘤生态系统整体的基线特征决定的。这种方法可用于开发其他癌症的预测因子。使用机器学习将治疗前肿瘤特征整合到预测模型中可以为治疗反应提供信息。
Breast cancers are complex ecosystems of malignant cells and the tumour microenvironment. The composition of these tumour ecosystems and interactions within them contribute to responses to cytotoxic therapy. Efforts to build response predictors have not incorporated this knowledge. We collected clinical, digital pathology, genomic and transcriptomic profiles of pre-treatment biopsies of breast tumours from 168 patients treated with chemotherapy with or without HER2 (encoded by ERBB2)-targeted therapy before surgery. Pathology end points (complete response or residual disease) at surgery were then correlated with multi-omic features in these diagnostic biopsies. Here we show that response to treatment is modulated by the pre-treated tumour ecosystem, and its multi-omics landscape can be integrated in predictive models using machine learning. The degree of residual disease following therapy is monotonically associated with pre-therapy features, including tumour mutational and copy number landscapes, tumour proliferation, immune infiltration and T cell dysfunction and exclusion. Combining these features into a multi-omic machine learning model predicted a pathological complete response in an external validation cohort (75 patients) with an area under the curve of 0.87. In conclusion, response to therapy is determined by the baseline characteristics of the totality of the tumour ecosystem captured through data integration and machine learning. This approach could be used to develop predictors for other cancers. Integration of pre-treatment tumour features in predictive models using machine learning could inform on response to therapy.