A personalized committee classification approach to improving prediction of breast cancer metastasis
Open Access
- 10 March 2014
- journal article
- research article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 30 (13), 1858-1866
- https://doi.org/10.1093/bioinformatics/btu128
Abstract
Motivation: Metastasis prediction is a well-known problem in breast cancer research. As breast cancer is a complex and heterogeneous disease with many molecular subtypes, predictive models trained for one cohort often perform poorly on other cohorts, and a combined model may be suboptimal for individual patients. Furthermore, attempting to develop subtype-specific models is hindered by the ambiguity and stereotypical definitions of subtypes. Results: Here, we propose a personalized approach by relaxing the definition of breast cancer subtypes. We assume that each patient belongs to a distinct subtype, defined implicitly by a set of patients with similar molecular characteristics, and construct a different predictive model for each patient, using as training data, only the patients defining the subtype. To increase robustness, we also develop a committee-based prediction method by pooling together multiple personalized models. Using both intra- and inter-dataset validations, we show that our approach can significantly improve the prediction accuracy of breast cancer metastasis compared with several popular approaches, especially on those hard-to-learn cases. Furthermore, we find that breast cancer patients belonging to different canonical subtypes tend to have different predictive models and gene signatures, suggesting that metastasis in different canonical subtypes are likely governed by different molecular mechanisms. Availability and implementation: Source code implemented in MATLAB and Java available at www.cs.utsa.edu/∼jruan/PCC/ . Contact:jianhua.ruan@utsa.edu Supplementary information: Supplementary data are available at Bioinformatics online .Keywords
This publication has 32 references indexed in Scilit:
- Comprehensive molecular portraits of human breast tumoursNature, 2012
- Subtype and pathway specific responses to anticancer compounds in breast cancerProceedings of the National Academy of Sciences of the United States of America, 2011
- ID genes mediate tumor reinitiation during breast cancer lung metastasisProceedings of the National Academy of Sciences of the United States of America, 2007
- Challenges in Projecting Clustering Results Across Gene Expression–Profiling DatasetsJNCI Journal of the National Cancer Institute, 2007
- The macrophage-stimulating protein pathway promotes metastasis in a mouse model for breast cancer and predicts poor prognosis in humansProceedings of the National Academy of Sciences of the United States of America, 2007
- Network‐based classification of breast cancer metastasisMolecular Systems Biology, 2007
- Repeated observation of breast tumor subtypes in independent gene expression data setsProceedings of the National Academy of Sciences of the United States of America, 2003
- A Gene-Expression Signature as a Predictor of Survival in Breast CancerNew England Journal of Medicine, 2002
- Gene expression profiling predicts clinical outcome of breast cancerNature, 2002
- Gene expression patterns of breast carcinomas distinguish tumor subclasses with clinical implicationsProceedings of the National Academy of Sciences of the United States of America, 2001