Classification of Breast Cancer Subtypes by combining Gene Expression and DNA Methylation Data

Markus List 1 , 2 , 3 , Anne-Christin Hauschild 4 , Qihua Tan 5 , 6 , Torben A. Kruse 1 , 3 , Jan Baumbach 7  and Richa Batra 7
  • 1 Lundbeckfonden Center of Excellence in Nanomedicine (NanoCAN), University of Southern Denmark, 5000, Odense, Denmark
  • 2 Institute of Molecular Medicine, University of Southern Denmark, 5000, Odense, Denmark
  • 3 Clinical Institute, University of Southern Denmark, 5000, Odense, Denmark
  • 4 Computational Systems Biology Group, Max Planck Institute for Informatics, 66123, Saarbrücken, Germany
  • 5 Clinical Institute, University of Southern Denmark, 5000, Odense, Denmark
  • 6 Epidemiology, Biostatistics and Biodemography, Institute of Public Health, University of Southern Denmark, 5000, Odense, Denmark
  • 7 Department of Mathematics and Computer Science (IMADA), University of Southern Denmark, 5000, Odense, Denmark


Selecting the most promising treatment strategy for breast cancer crucially depends on determining the correct subtype. In recent years, gene expression profiling has been investigated as an alternative to histochemical methods. Since databases like TCGA provide easy and unrestricted access to gene expression data for hundreds of patients, the challenge is to extract a minimal optimal set of genes with good prognostic properties from a large bulk of genes making a moderate contribution to classification. Several studies have successfully applied machine learning algorithms to solve this so-called gene selection problem. However, more diverse data from other OMICS technologies are available, including methylation. We hypothesize that combining methylation and gene expression data could already lead to a largely improved classification model, since the resulting model will reflect differences not only on the transcriptomic, but also on an epigenetic level. We compared so-called random forest derived classification models based on gene expression and methylation data alone, to a model based on the combined features and to a model based on the gold standard PAM50. We obtained bootstrap errors of 10-20% and classification error of 1-50%, depending on breast cancer subtype and model. The gene expression model was clearly superior to the methylation model, which was also reflected in the combined model, which mainly selected features from gene expression data. However, the methylation model was able to identify unique features not considered as relevant by the gene expression model, which might provide deeper insights into breast cancer subtype differentiation on an epigenetic level.

If the inline PDF is not rendering correctly, you can download the PDF file here.


Journal + Issues

The Journal of Integrative Bioinformatics is an international journal dedicated to methods and tools of computer science and electronic infrastructure applied to biotechnology. The journal covers mainly but not exclusively data/method integration, modeling, simulation and visualization in combination with applications of theoretical/computational tools and any other approach supporting an integrative view of complex biological systems.