Multi-omic machine learning predictor of breast cancer therapy response.
Authors
Crispin-Ortuzar, Mireia
Bardwell, Helen A
Ma, Wenxin
Cope, Wei
Dariush, Ali
Abraham, Jean E
Dunn, Janet
Hiller, Louise
Cameron, David A
Bartlett, John MS
Hayward, Larry
Earl, Helena M
Publication Date
2022-01Journal Title
Nature
ISSN
0028-0836
Publisher
Springer Science and Business Media LLC
Volume
601
Issue
7894
Pages
623-629
Language
en
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Sammut, S., Crispin-Ortuzar, M., Chin, S., Provenzano, E., Bardwell, H. A., Ma, W., Cope, W., et al. (2022). Multi-omic machine learning predictor of breast cancer therapy response.. Nature, 601 (7894), 623-629. https://doi.org/10.1038/s41586-021-04278-5
Abstract
Breast cancers are complex ecosystems of malignant cells and the tumour microenvironment1. The composition of these tumour ecosystems and interactions within them contribute to responses to cytotoxic therapy2. 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 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 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.
Keywords
Article, /631/67/1347, /631/67/1059/99, /631/67/1857, /631/114/2401, /692/308/575, /45/23, /45/91, /38/39, article
Sponsorship
Wellcome Trust (106566/Z/14/Z)
European Research Council (694620)
Cancer Research UK (A27657)
Cancer Research UK (A19274)
National Institute for Health Research (IS-BRC-1215-20014)
Identifiers
s41586-021-04278-5, 4278
External DOI: https://doi.org/10.1038/s41586-021-04278-5
This record's URL: https://www.repository.cam.ac.uk/handle/1810/333351
Rights
Licence:
http://creativecommons.org/licenses/by/4.0/
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.