Open Access Highly Accessed Open Badges Research article

Prediction of breast cancer prognosis using gene set statistics provides signature stability and biological context

Gad Abraham12, Adam Kowalczyk2, Sherene Loi34, Izhak Haviv567 and Justin Zobel12*

Author affiliations

1 Department of Computer Science and Software Engineering, The University of Melbourne, Parkville 3010, VIC, Australia

2 NICTA Victoria Laboratory, The University of Melbourne, Parkville 3010, VIC, Australia

3 Department of Translational Research and Functional Genomics Unit, Jules Bordet Institute, Brussels, Belgium

4 Department of Medical Oncology, Peter MacCallum Cancer Centre, East Melbourne, VIC 3002, Australia

5 Metastasis Research Laboratory, Peter MacCallum Cancer Centre, East Melbourne, VIC 3002, Australia

6 The Blood and DNA Profiling Facility, Baker IDI Institute, Prahran, VIC 3004, Australia

7 Department of Biochemistry, School of Medicine, University of Melbourne, VIC 3010, Australia

For all author emails, please log on.

Citation and License

BMC Bioinformatics 2010, 11:277  doi:10.1186/1471-2105-11-277

Published: 25 May 2010



Different microarray studies have compiled gene lists for predicting outcomes of a range of treatments and diseases. These have produced gene lists that have little overlap, indicating that the results from any one study are unstable. It has been suggested that the underlying pathways are essentially identical, and that the expression of gene sets, rather than that of individual genes, may be more informative with respect to prognosis and understanding of the underlying biological process.


We sought to examine the stability of prognostic signatures based on gene sets rather than individual genes. We classified breast cancer cases from five microarray studies according to the risk of metastasis, using features derived from predefined gene sets. The expression levels of genes in the sets are aggregated, using what we call a set statistic. The resulting prognostic gene sets were as predictive as the lists of individual genes, but displayed more consistent rankings via bootstrap replications within datasets, produced more stable classifiers across different datasets, and are potentially more interpretable in the biological context since they examine gene expression in the context of their neighbouring genes in the pathway. In addition, we performed this analysis in each breast cancer molecular subtype, based on ER/HER2 status. The prognostic gene sets found in each subtype were consistent with the biology based on previous analysis of individual genes.


To date, most analyses of gene expression data have focused at the level of the individual genes. We show that a complementary approach of examining the data using predefined gene sets can reduce the noise and could provide increased insight into the underlying biological pathways.