Gene ranking and biomarker discovery under correlation Export

@article{citeulike:5334116, abstract = {Motivation: Biomarker discovery and gene ranking is a standard task in genomic high-throughput analysis. Typically, the ordering of markers is based on a stabilized variant of the t-score, such as the moderated t or the SAM statistic. However, these procedures ignore gene-gene correlations, which may have a profound impact on the gene orderings and on the power of the subsequent tests. Results: We propose a simple procedure that adjusts gene-wise t-statistics to take account of correlations among genes. The resulting correlation-adjusted t-scores ( cat' scores) are derived from a predictive perspective, i.e. as a score for variable selection to discriminate group membership in two-class linear discriminant analysis. In the absence of correlation the cat score reduces to the standard t-score. Moreover, using the cat score it is straightforward to evaluate groups of features (i.e. gene sets). For computation of the cat score from small sample data, we propose a shrinkage procedure. In a comparative study comprising six different synthetic and empirical correlation structures, we show that the cat score improves estimation of gene orderings and leads to higher power for fixed true discovery rate, and vice versa. Finally, we also illustrate the cat score by analyzing metabolomic data. Availability: The shrinkage cat score is implemented in the R package st', which is freely available under the terms of the GNU General Public License (version 3 or later) from CRAN (http://cran.r-project.org/web/packages/st/). Contact: strimmer@uni-leipzig.de 10.1093/bioinformatics/btp460}, author = {Zuber, Verena and Strimmer, Korbinian}, citeulike-article-id = {5334116}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btp460}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/25/20/2700.abstract}, citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/25/20/2700.full.pdf}, citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/19648135}, citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=19648135}, day = {15}, doi = {10.1093/bioinformatics/btp460}, issn = {1460-2059}, journal = {Bioinformatics}, keywords = {biomarker, classification, correlation, marker, microarray, prediction, ranking, shrinkage, t-test}, month = {October}, number = {20}, pages = {2700--2707}, posted-at = {2009-10-09 10:42:56}, priority = {2}, title = {Gene ranking and biomarker discovery under correlation}, url = {http://dx.doi.org/10.1093/bioinformatics/btp460}, volume = {25}, year = {2009} }

TY - JOUR ID - citeulike:5334116 L3 - citeulike-article-id:5334116 N2 - Motivation: Biomarker discovery and gene ranking is a standard task in genomic high-throughput analysis. Typically, the ordering of markers is based on a stabilized variant of the t-score, such as the moderated t or the SAM statistic. However, these procedures ignore gene-gene correlations, which may have a profound impact on the gene orderings and on the power of the subsequent tests. Results: We propose a simple procedure that adjusts gene-wise t-statistics to take account of correlations among genes. The resulting correlation-adjusted t-scores ( cat' scores) are derived from a predictive perspective, i.e. as a score for variable selection to discriminate group membership in two-class linear discriminant analysis. In the absence of correlation the cat score reduces to the standard t-score. Moreover, using the cat score it is straightforward to evaluate groups of features (i.e. gene sets). For computation of the cat score from small sample data, we propose a shrinkage procedure. In a comparative study comprising six different synthetic and empirical correlation structures, we show that the cat score improves estimation of gene orderings and leads to higher power for fixed true discovery rate, and vice versa. Finally, we also illustrate the cat score by analyzing metabolomic data. Availability: The shrinkage cat score is implemented in the R package st', which is freely available under the terms of the GNU General Public License (version 3 or later) from CRAN (http://cran.r-project.org/web/packages/st/). Contact: strimmer@uni-leipzig.de 10.1093/bioinformatics/btp460 IS - 20 JF - Bioinformatics SN - 1460-2059 EP - 2707 TI - Gene ranking and biomarker discovery under correlation VL - 25 SP - 2700 KW - biomarker KW - classification KW - correlation KW - marker KW - microarray KW - prediction KW - ranking KW - shrinkage KW - t-test AU - Zuber, Verena AU - Strimmer, Korbinian PY - 2009/10/15/ UR - http://dx.doi.org/10.1093/bioinformatics/btp460 ER -