英国剑桥大学 Carlos Caldas 团队近日取得一项新成果。他们开发了乳腺癌治疗反应的多组学机器学习预测器。这一研究工作在2021年12月7日在线发表在《自然》杂志上。

科研人员收集了168例手术前接受 +/- HER2 靶向化学药物治疗的乳腺癌患者的相关资料，包括乳腺癌治疗前活检的临床学、数字病理学、基因组学和转录组学数据。然后将手术病理终点（完全缓解或残留疾病）与这些活检诊断中的多组学特征相关联

在这里，研究人员表明，肿瘤治疗的应答反应会受到肿瘤治疗前微环境系统的调控，肿瘤治疗前微环境的多组学特征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肿瘤的多组学特征呈单调相关性，包括肿瘤突变和复制数景观、肿瘤增殖、免疫浸润和T细胞功能障碍及排斥。将这些特征整合到多组学机器学习模型中，用这一模型来预测外部验证组（75例患者）的病理完全缓解（pathological complete response，PCR），其AUC为0.87。总的来说，对肿瘤治疗反应的预测是通过数据集成和机器学习捕获整个肿瘤生态系统的总体基本特征来实现的。这种方法也可以用于开发其它类型肿瘤治疗反应的预测器。

据悉，乳腺癌是由恶性细胞和肿瘤微环境组成的复杂生态系统。这些肿瘤生态系统的组成及其内部的相互作用会导致肿瘤治疗的细胞毒性反应。目前领域内还没有建立能够预测肿瘤治疗反应的预测器。

附：英文原文

Title: Multi-omic machine learning predictor of breast cancer therapy response

Author: Sammut, Stephen-John, Crispin-Ortuzar, Mireia, Chin, Suet-Feung, Provenzano, Elena, Bardwell, Helen A., Ma, Wenxin, Cope, Wei, Dariush, Ali, Dawson, Sarah-Jane, Abraham, Jean E., Dunn, Janet, Hiller, Louise, Thomas, Jeremy, Cameron, David A., Bartlett, John M. S., Hayward, Larry, Pharoah, Paul D., Markowetz, Florian, Rueda, Oscar M., Earl, Helena M., Caldas, Carlos

Issue&Volume: 2021-12-07

Abstract: Breast cancers are complex ecosystems of malignant cells and tumour microenvironment1. The composition of these tumour ecosystems and interactions within them contribute to cytotoxic therapy response2. 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 +/- HER2-targeted therapy prior to surgery. Pathology endpoints (complete response or residual disease) at surgery3 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 pathological complete response in an external validation cohort (75 patients) with an AUC 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.

DOI: 10.1038/s41586-021-04278-5

Source: https://www.nature.com/articles/s41586-021-04278-5