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.
This is a preview of subscription content
Access options
Subscribe to Journal
Get full journal access for 1 year
199,00 €
only 3,90 € per issue
Tax calculation will be finalised during checkout.
Rent or Buy article
Get time limited or full article access on ReadCube.
from$8.99
All prices are NET prices.
Author information
Affiliations
Corresponding author
Supplementary information
Supplementary Information
This file contains Supplementary Methods and Supplementary Tables 1 – 15.
Supplementary Tables 1 – 6
This file contains Supplementary Tables 1 – 6. See below for Supplementary Table legends Supplementary Table 1 Clinical metadata of 168 cases recruited to the TransNEO study. Supplementary Table 2 Mutations identified within the WES data. Supplementary Table 3 Tumour proliferation and immune metrics extracted from the RNA-seq data. Supplementary Table 4 Complete list of features used to train the models, their computation methods, and mean, minimum, and maximum values in the training dataset. Supplementary Table 5 Clinical, molecular, and digital pathology metadata of validation cohort. Supplementary Table 6 Ranked list of biological features including signed importance z-scores.
Rights and permissions
About this article
Cite this article
Sammut, SJ., Crispin-Ortuzar, M., Chin, SF. et al. Multi-omic machine learning predictor of breast cancer therapy response. Nature (2021). https://ift.tt/3ECUIm7
-
Received:
-
Accepted:
-
Published:
Comments
By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.
"breast" - Google News
December 07, 2021 at 11:28PM
https://ift.tt/3dzqgNL
Multi-omic machine learning predictor of breast cancer therapy response - Nature.com
"breast" - Google News
https://ift.tt/2ImtPYC
https://ift.tt/2Wle22m
Bagikan Berita Ini
0 Response to "Multi-omic machine learning predictor of breast cancer therapy response - Nature.com"
Post a Comment