Capturing Heterogeneity in Gene Expression Studies by Surrogate Variable Analysis Export

@article{citeulike:1755861, abstract = {Author SummaryIn scientific and medical studies, great care must be taken when collecting data to understand the relationship between two variables, such as a drug and its effect on a disease. In any given study there will be many other variables at play, such as the effects of age and sex on the disease. We show that in studies where the expression levels of thousands of genes are measured at once, these issues become surprisingly critical. Due to the complexity of our genomes, environment, and demographic features, there are many sources of variation when analyzing gene expression levels. In any given study, it is impossible to measure every single variable that may be influencing how our genes are expressed. Despite this, we show that by considering all expression levels simultaneously, one can actually recover the effects of these important missed variables and essentially produce an analysis as if all relevant variables were included. As opposed to traditional studies, the massive amount of data available in this setting is what makes the method, called surrogate variable analysis, possible. We hypothesize that surrogate variable analysis will be useful in many large-scale gene expression studies.}, author = {Leek, Jeffrey T. and Storey, John D.}, citeulike-article-id = {1755861}, citeulike-linkout-0 = {http://dx.doi.org/10.1371/journal.pgen.0030161}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/17907809}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=17907809}, day = {28}, doi = {10.1371/journal.pgen.0030161}, journal = {PLoS Genet}, keywords = {microarray}, month = {September}, number = {9}, pages = {e161+}, posted-at = {2009-06-18 16:03:53}, priority = {2}, publisher = {Public Library of Science}, title = {Capturing Heterogeneity in Gene Expression Studies by Surrogate Variable Analysis}, url = {http://dx.doi.org/10.1371/journal.pgen.0030161}, volume = {3}, year = {2007} }

TY - JOUR ID - citeulike:1755861 L3 - citeulike-article-id:1755861 N2 - Author SummaryIn scientific and medical studies, great care must be taken when collecting data to understand the relationship between two variables, such as a drug and its effect on a disease. In any given study there will be many other variables at play, such as the effects of age and sex on the disease. We show that in studies where the expression levels of thousands of genes are measured at once, these issues become surprisingly critical. Due to the complexity of our genomes, environment, and demographic features, there are many sources of variation when analyzing gene expression levels. In any given study, it is impossible to measure every single variable that may be influencing how our genes are expressed. Despite this, we show that by considering all expression levels simultaneously, one can actually recover the effects of these important missed variables and essentially produce an analysis as if all relevant variables were included. As opposed to traditional studies, the massive amount of data available in this setting is what makes the method, called surrogate variable analysis, possible. We hypothesize that surrogate variable analysis will be useful in many large-scale gene expression studies. IS - 9 JF - PLoS Genet TI - Capturing Heterogeneity in Gene Expression Studies by Surrogate Variable Analysis PB - Public Library of Science VL - 3 SP - e161 KW - microarray AU - Leek, Jeffrey AU - Storey, John PY - 2007/09/28/ UR - http://dx.doi.org/10.1371/journal.pgen.0030161 ER -