乳腺癌是恶性肿瘤细胞与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，可影响乳腺癌治疗效果。不过，既往关于乳腺癌疗效预测的研究大多并未整合这些多组学大数据。机器学习既是人工智能的分支之一，也是实现人工智能的途径之一，可对多组学大数据自动分析获得规律，并利用规律对未知数据进行预测。
2021年12月7日，全球自然科学三大旗舰期刊之首、英国《自然》正刊在线发表欧洲癌症科学院院士、英国医学科学院院士、剑桥大学肿瘤医学系主任、阿登布鲁克医院肿瘤内科名誉顾问医师、剑桥乳腺癌研究中心主任、剑桥大学罗宾逊学院研究员、英国癌症研究基金会剑桥研究院乳腺癌功能基因组学资深学科带头人、第44届圣安东尼奥乳腺癌大会2021年度布林克基础科学杰出奖获得者卡洛斯·卡尔达斯等学者的研究报告：多组学人工智能机器学习预测乳腺癌疗效。
该研究对2013～2017年剑桥大学医院168例早期乳腺癌患者新辅助化疗±HER2靶向治疗前的乳腺肿瘤活检标本基因组和转录组特征、数字化病理学特征、临床特征进行分析，随后将手术时切除标本的病理学终点（完全缓解或残留病变）与治疗前诊断活检标本的多组学特征进行关联。
结果发现，治疗效果受到治疗前肿瘤生态系统的影响，其多组学特征可以采用机器学习整合于疗效预测模型。治疗后残留病变的程度与治疗前特征（包括肿瘤基因突变和拷贝数变化特征、肿瘤增殖、免疫浸润、T淋巴细胞功能障碍和排斥）成单调函数关系。将这些特征结合于多组学机器学习模型，对其他75例早期乳腺癌新辅助治疗患者进行外部验证，可预测病理完全缓解，曲线下面积达0.87。
因此，该研究结果表明，通过多组学大数据集成和机器学习综合分析乳腺癌治疗前整个肿瘤生态系统的特征，可预测乳腺癌治疗效果，有助于及时调整优化治疗方案，该方法还被可用于开发其他癌症的预测工具。
Nature. 2021 Dec 7. Online ahead of print.
Multi-omic machine learning predictor of breast cancer therapy response.
Stephen-John Sammut, Mireia Crispin-Ortuzar, Suet-Feung Chin, Elena Provenzano, Helen A. Bardwell, Wenxin Ma, Wei Cope, Ali Dariush, Sarah-Jane Dawson, Jean E. Abraham, Janet Dunn, Louise Hiller, Jeremy Thomas, David A. Cameron, John M. S. Bartlett, Larry Hayward, Paul D. Pharoah, Florian Markowetz, Oscar M. Rueda, Helena M. Earl, Carlos Caldas.
University of Cambridge, Cambridge, UK; University of Warwick, Coventry, UK; Edinburgh Cancer Research Centre, Western General Hospital, Edinburgh, UK; Q2 Laboratory Solutions, Alba Campus, Livingston, UK; Peter MacCallum Cancer Centre, Melbourne, Australia; The University of Melbourne, Melbourne, Australia; Ontario Institute for Cancer Research, Toronto, Ontario, Canada; University of Toronto, Toronto, Ontario, Canada.
Breast cancers are complex ecosystems of malignant cells and tumour microenvironment. The composition of these tumour ecosystems and interactions within them contribute to cytotoxic therapy response. 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 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 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
2021版CBCS指南与规范完整版
2021版CBCS指南与规范精编版
2021版CBCS指南与规范小程序
联系客服
