Title: Module-based breast cancer classification

Authors: Yuji Zhang; Jianhua Xuan; Robert Clarke; Habtom W. Ressom

Addresses: Division of Biomedical Statistics and Informatics, Department of Health Sciences Research, Mayo Clinic College of Medicine, Rochester, Minnesota, 55905, USA ' Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, Arlington, Virginia, 22203, USA ' Lombardi Comprehensive Cancer Center, Georgetown University Medical Center, Washington, District of Columbia, 20057, USA ' Lombardi Comprehensive Cancer Center, Georgetown University Medical Center, Washington, District of Columbia, 20057, USA

Abstract: The reliability and reproducibility of gene biomarkers for classification of cancer patients has been challenged due to measurement noise and biological heterogeneity among patients. In this paper, we propose a novel module-based feature selection framework, which integrates biological network information and gene expression data to identify biomarkers not as individual genes but as functional modules. Results from four breast cancer studies demonstrate that the identified module biomarkers 1) achieve higher classification accuracy in independent validation datasets; 2) are more reproducible than individual gene markers; 3) improve the biological interpretability of results; 4) are enriched in cancer 'disease drivers'.

Keywords: cancer biomarkers; systems biology; feature selection; disease classification; breast cancer; bioinformatics; gene biomarkers; biological network information; gene expression data; functional modules; module biomarkers.

DOI: 10.1504/IJDMB.2013.053309

International Journal of Data Mining and Bioinformatics, 2013 Vol.7 No.3, pp.284 - 302

Received: 26 Sep 2011
Accepted: 03 Oct 2011
Published online: 07 Jun 2013 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article