TY - GEN
T1 - Biomarker identification by knowledge-driven multi-level ICA and motif analysis
AU - Chen, Li
AU - Wang, Chen
AU - Shih, Ie Ming
AU - Wang, Tian Li
AU - Zhang, Zhen
AU - Wang, Yue
AU - Clarke, Robert
AU - Hoffman, Eric
AU - Xuan, Jianhua
PY - 2007
Y1 - 2007
N2 - Many statistical methods often fail to identify biologically meaningful biomarkers related to a specific disease under study from expression data alone. In this paper, we develop a novel strategy, namely knowledge-driven multi-level independent component analysis (ICA), to infer regulatory signals and identify biologically relevant biomarkers from microarray data. Specifically, based on multi-level clustering results and partial prior knowledge, we apply ICA to find stable disease specific linear regulatory modes and then extract associated biomarker genes. A statistical test is designed to evaluate the significance of transcription factor enrichment for extracted gene set based on motif information. The experimental results on an Rsf-1 induced microarray data set show that our knowledgedriven method can extract more biologically meaningful biomarkers with significant enrichment of transcription factors related to ovarian cancer compared to other gene selection methods with/without prior knowledge.
AB - Many statistical methods often fail to identify biologically meaningful biomarkers related to a specific disease under study from expression data alone. In this paper, we develop a novel strategy, namely knowledge-driven multi-level independent component analysis (ICA), to infer regulatory signals and identify biologically relevant biomarkers from microarray data. Specifically, based on multi-level clustering results and partial prior knowledge, we apply ICA to find stable disease specific linear regulatory modes and then extract associated biomarker genes. A statistical test is designed to evaluate the significance of transcription factor enrichment for extracted gene set based on motif information. The experimental results on an Rsf-1 induced microarray data set show that our knowledgedriven method can extract more biologically meaningful biomarkers with significant enrichment of transcription factors related to ovarian cancer compared to other gene selection methods with/without prior knowledge.
UR - http://www.scopus.com/inward/record.url?scp=47349121988&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=47349121988&partnerID=8YFLogxK
U2 - 10.1109/ICMLA.2007.24
DO - 10.1109/ICMLA.2007.24
M3 - Conference contribution
AN - SCOPUS:47349121988
SN - 0769530699
SN - 9780769530697
T3 - Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007
SP - 560
EP - 566
BT - Proceedings - 6th International Conference on Machine Learning and Applications, ICMLA 2007
T2 - 6th International Conference on Machine Learning and Applications, ICMLA 2007
Y2 - 13 December 2007 through 15 December 2007
ER -