Multi-omic machine learning predictor of breast cancer therapy response
Stephen-John Sammut1,2,3, Mireia Crispin-Ortuzar1, Suet-Feung Chin1
1Cancer Research UK Cambridge Institute, University of Cambridge, Li Ka Shing Centre, Cambridge, UK.
Nature
|December 7, 2021
Summary
Breast cancer treatment response depends on the tumor microenvironment. Machine learning models integrating multi-omic data predict treatment outcomes, aiding personalized therapy development.
Area of Science:
- Oncology
- Computational Biology
- Genomics
Background:
- Breast cancers are complex ecosystems involving malignant cells and the tumor microenvironment.
- Tumor ecosystem composition influences response to cytotoxic therapy.
- Existing response predictors lack integration of this knowledge.
Purpose of the Study:
- To investigate the role of the pre-treatment tumor ecosystem in breast cancer treatment response.
- To develop predictive models for treatment outcomes using multi-omic data.
- To correlate pre-therapy multi-omic features with pathological response endpoints.
Main Methods:
- Collected clinical, digital pathology, genomic, and transcriptomic profiles from 168 pre-treatment breast tumor biopsies.
- Correlated multi-omic features with pathological response (complete response or residual disease) post-therapy.
- Developed and validated a multi-omic machine learning model.
Main Results:
- Treatment response is modulated by the pre-treated tumor ecosystem.
- Residual disease correlates with pre-therapy features like tumor mutational landscape, proliferation, and immune infiltration.
- A multi-omic machine learning model achieved an AUC of 0.87 in predicting pathological complete response in an external cohort.
Conclusions:
- Treatment response is determined by baseline tumor ecosystem characteristics.
- Data integration and machine learning can capture these characteristics for predictive modeling.
- This approach holds potential for developing predictors in other cancer types.
Related Concept Videos
02:50Combination Therapies and Personalized Medicine
5.2K
Combining two or more treatment methods increases the life span of cancer patients while reducing damage to vital organs or tissue from the overuse of a single treatment. Combination therapy also targets different cancer-inducing pathways, thus reducing the chances of developing resistance to treatment.
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...
5.2K
01:21Cancer Survival Analysis
478
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
478
02:53Adaptive Mechanisms in Cancer Cells
6.0K
Cancer cells accumulate genetic changes at an abnormally rapid rate due to the defects in the DNA repair mechanisms. From an evolutionary perspective, such genetic instability is advantageous for cancer development. Mutant cell lines accumulate a series of beneficial mutations that contribute to their progression into cancer.
Some of the advantages that cancer cells have on normal cells include - enhanced ability to divide without terminally differentiating, induce new blood vessel formation,...
Some of the advantages that cancer cells have on normal cells include - enhanced ability to divide without terminally differentiating, induce new blood vessel formation,...
6.0K