Identification of Differentially Expressed Gene Categories in Microarray Studies Using Nonparametric Multivariate Analysis.

@article{citeulike:2085990, abstract = {MOTIVATION: The field of microarray data analysis is shifting emphasis from methods for identifying differentially expressed genes to methods for identifying differentially expressed gene categories. The latter approaches utilize a priori information about genes to group genes into categories and enhance the interpretation of experiments aimed at identifying expression differences across treatments. While almost all of the existing approaches for identifying differentially expressed gene categories are practically useful, they suffer from a variety of drawbacks. Perhaps most notably, many popular tools are based exclusively on gene-specific statistics that cannot detect many types of multivariate expression change. RESULTS: We have developed a nonparametric multivariate method for identifying gene categories whose multivariate expression distribution differs across two or more conditions. We illustrate our approach and compare its performance to several existing procedures via the analysis of a real data set and a unique data-based simulation study designed to capture the challenges and complexities of practical data analysis. We show that our method has good power for differentiating between differentially expressed and non-differentially expressed gene categories, and we utilize a resampling based strategy for controlling the false discovery rate when testing multiple categories. AVAILABILITY: R code (www.r-project.org) for implementing our approach is available from the first author by request. CONTACT: dnett@iastate.edu.}, address = {Department of Statistics, Iowa State University, Ames, Iowa 50011-1210, USA, Eli Lilly and Company,Lilly Research Laboratories, P.O. Box 708, Greenfield, Indiana 46140 and Department of Animal Science, Iowa State University, Ames, Iowa 50011-3150, USA.}, author = {Nettleton, Dan and Recknor, Justin and Reecy, James M. }, citeulike-article-id = {2085990}, doi = {http://dx.doi.org/10.1093/bioinformatics/btm583}, editor = {Quackenbush, John }, issn = {1460-2059}, journal = {Bioinformatics}, keywords = {gene\_sets}, month = {November}, posted-at = {2008-02-19 11:27:59}, priority = {0}, title = {Identification of Differentially Expressed Gene Categories in Microarray Studies Using Nonparametric Multivariate Analysis.}, url = {http://dx.doi.org/10.1093/bioinformatics/btm583}, year = {2007} }

TY - JOUR ID - citeulike:2085990 L3 - citeulike-article-id:2085990 TI - Identification of Differentially Expressed Gene Categories in Microarray Studies Using Nonparametric Multivariate Analysis. JF - Bioinformatics AD - Department of Statistics, Iowa State University, Ames, Iowa 50011-1210, USA, Eli Lilly and Company,Lilly Research Laboratories, P.O. Box 708, Greenfield, Indiana 46140 and Department of Animal Science, Iowa State University, Ames, Iowa 50011-3150, USA. SN - 1460-2059 N2 - MOTIVATION: The field of microarray data analysis is shifting emphasis from methods for identifying differentially expressed genes to methods for identifying differentially expressed gene categories. The latter approaches utilize a priori information about genes to group genes into categories and enhance the interpretation of experiments aimed at identifying expression differences across treatments. While almost all of the existing approaches for identifying differentially expressed gene categories are practically useful, they suffer from a variety of drawbacks. Perhaps most notably, many popular tools are based exclusively on gene-specific statistics that cannot detect many types of multivariate expression change. RESULTS: We have developed a nonparametric multivariate method for identifying gene categories whose multivariate expression distribution differs across two or more conditions. We illustrate our approach and compare its performance to several existing procedures via the analysis of a real data set and a unique data-based simulation study designed to capture the challenges and complexities of practical data analysis. We show that our method has good power for differentiating between differentially expressed and non-differentially expressed gene categories, and we utilize a resampling based strategy for controlling the false discovery rate when testing multiple categories. AVAILABILITY: R code (www.r-project.org) for implementing our approach is available from the first author by request. CONTACT: dnett@iastate.edu. KW - gene_sets AU - Nettleton, Dan AU - Recknor, Justin AU - Reecy, James A2 - Quackenbush, John PY - 2007/11/27/ UR - http://dx.doi.org/10.1093/bioinformatics/btm583 ER -