A training algorithm for optimal margin classifiers
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Ant algorithms for discrete optimization
Artificial Life
The MIPS mammalian protein--protein interaction database
Bioinformatics
FANMOD: a tool for fast network motif detection
Bioinformatics
Hi-index | 0.00 |
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'.