Title :
Biomarker identification by knowledge-driven multi-scale independent component analysis
Author :
Chen, Li ; Xuan, Jianhua ; Clarke, Robert ; Wang, Yue
Author_Institution :
Virginia Tech., Arlington
Abstract :
Many statistical methods have been proposed to identify biomarkers from gene expression profiles. However, from expression data alone, statistical methods often fail to identify biologically meaningful biomarkers related to a specific biological process or disease under study. In this paper, we develop a novel strategy, namely knowledge-driven multi-scale independent component analysis (ICA), to infer regulatory signals and identify biologically relevant biomarkers from microarray data. Specifically, based on partial prior knowledge and clustering results, we apply ICA to find the most knowledge relevant linear regulatory mode in each subset of genes and then extract associated biomarkers according to their weighted loading factors. We have applied our method to a yeast cell cycle microarray dataset to find cell cycle regulated biomarkers. The experimental results indicate that our knowledge-driven multi-scale ICA method outperforms both baseline ICA method and correlation method significantly.
Keywords :
cellular biophysics; correlation methods; diseases; genetics; independent component analysis; medical computing; biomarker identification; clustering method; correlation method; disease; gene expression profiles; knowledge-driven multi-scale independent component analysis; partial prior knowledge; yeast cell cycle microarray dataset; Biological processes; Biomarkers; Correlation; Data mining; Diseases; Fungi; Gene expression; Independent component analysis; Signal processing; Statistical analysis;
Conference_Titel :
Life Science Systems and Applications Workshop, 2007. LISA 2007. IEEE/NIH
Conference_Location :
Bethesda, MD
Print_ISBN :
978-1-4244-1813-8
Electronic_ISBN :
978-1-4244-1813-8
DOI :
10.1109/LSSA.2007.4400934