Show simple item record

dc.contributor.authorSammut, Stephen
dc.contributor.authorCrispin-Ortuzar, Mireia
dc.contributor.authorChin, Suet-Feung
dc.contributor.authorProvenzano, Elena
dc.contributor.authorBardwell, Helen A
dc.contributor.authorMa, Wenxin
dc.contributor.authorCope, Wei
dc.contributor.authorDariush, Ali
dc.contributor.authorDawson, Sarah-Jane
dc.contributor.authorAbraham, Jean E
dc.contributor.authorDunn, Janet
dc.contributor.authorHiller, Louise
dc.contributor.authorThomas, Jeremy
dc.contributor.authorCameron, David A
dc.contributor.authorBartlett, John MS
dc.contributor.authorHayward, Larry
dc.contributor.authorPharoah, Paul
dc.contributor.authorMarkowetz, Florian
dc.contributor.authorRueda Palacio, Oscar
dc.contributor.authorEarl, Helena
dc.contributor.authorCaldas, Carlos
dc.description.abstractBreast 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.
dc.publisherSpringer Science and Business Media LLC
dc.rightsAttribution 4.0 International (CC BY)
dc.titleMulti-omic machine learning predictor of breast cancer therapy response.
dc.publisher.departmentDepartment of Oncology
dc.publisher.departmentCancer Research Uk Cambridge Institute
dc.publisher.departmentDepartment of Public Health And Primary Care, Cancer Genetic Epidemiology
dc.publisher.departmentMrc Biostatistics Unit
dc.contributor.orcidSammut, Stephen [0000-0003-4472-904X]
dc.contributor.orcidChin, Suet-Feung [0000-0001-5697-1082]
dc.contributor.orcidProvenzano, Elena [0000-0003-3345-3965]
dc.contributor.orcidDawson, Sarah-Jane [0000-0002-8276-0374]
dc.contributor.orcidThomas, Jeremy [0000-0002-4652-610X]
dc.contributor.orcidPharoah, Paul [0000-0001-8494-732X]
dc.contributor.orcidMarkowetz, Florian [0000-0002-2784-5308]
dc.contributor.orcidRueda Palacio, Oscar [0000-0003-0008-4884]
dc.contributor.orcidEarl, Helena [0000-0003-1549-8094]
dc.contributor.orcidCaldas, Carlos [0000-0003-3547-1489]
rioxxterms.typeJournal Article/Review
pubs.funder-project-idWellcome Trust (106566/Z/14/Z)
cam.orpheus.success2021-12-20 - Embargo set during processing via Fast-track
cam.orpheus.successVoR added.
pubs.licence-display-nameApollo Repository Deposit Licence Agreement

Files in this item


This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International (CC BY)
Except where otherwise noted, this item's licence is described as Attribution 4.0 International (CC BY)