Paper Info
Title
Comparative analysis of gene sets in the Gene Ontology space under the multiple hypothesis testing framework.
Abstract
The Gene Ontology (GO) resource can be used as a powerful tool to uncover the properties shared among, and specific to, a list of genes produced by high-throughput functional genomics studies, such as microarray studies. In the comparative analysis of several gene lists, researchers maybe interested in knowing which GO terms are enriched in one list of genes but relatively depleted in another. Statistical tests such as Fisher's exact test or Chi-square test can be performed to search for such GO terms. However, because multiple GO terms are tested simultaneously, individual p-values from individual tests do not serve as good indicators for picking GO terms. Furthermore, these multiple tests are highly correlated, usual multiple testing procedures that work under an independence assumption are not applicable. In this paper we introduce a procedure, based on False Discovery Rate (FDR), to treat this correlated multiple testing problem. This procedure calculates a moderately conserved estimator of q-value for every GO term. We identify the GO terms with q-values that satisfy a desired level as the significant GO terms. This procedure has been implemented into the GoSurfer software. GoSurfer is a windows based graphical data mining tool. It is freely available at http://www.gosurfer.org.
Year
DOI
Venue
2004
10.1109/CSB.2004.1332455
CSB
Keywords
Field
DocType
multiple test,multiple hypothesis testing,false discovery rate,chi-square test,statistical testing,multiple hypothesis testing framework,genetics,gene sets,exact test,comparative analysis,individual p-values,gene ontology space,biology computing,individual test,gosurfer software,windows based graphical data mining tool,gene ontology,gene list,graphical data mining tool,correlated multiple testing problem,data mining,functional genomics,usual multiple testing procedure,statistical tests,fisher exact test,statistical test,satisfiability,multiple testing,chi square test,visualization,microarray,high throughput
Data mining,Computer science,Exact test,Software,Artificial intelligence,Statistical hypothesis testing,False discovery rate,Visualization,Multiple comparisons problem,Functional genomics,Bioinformatics,Statistical assumption,Machine learning
Conference
Issue
ISSN
ISBN
155
1551-7497
0-7695-2194-0
Citations 
PageRank 
References 
12
2.35
5
Authors
5
Name
Order
Citations
PageRank
Sheng Zhong12019144.16
Lu Tian2122.35
Cheng Li311418.42
Kai-Florian Storch4122.35
Wing Hung Wong560796.45