High-Throughput GoMiner, an 'industrial-strength' integrative gene ontology tool for interpretation of multiple-microarray experiments, with application to studies of Common Variable Immune Deficiency (CVID)

Abstract

Background: We previously developed GoMiner, an application that organizes lists of 'interesting' genes (for example, under-and overexpressed genes from a microarray experiment) for biological interpretation in the context of the Gene Ontology. The original version of GoMiner was oriented toward visualization and interpretation of the results from a single microarray (or other high-throughput experimental platform), using a graphical user interface. Although that version can be used to examine the results from a number of microarrays one at a time, that is a rather tedious task, and original GoMiner includes no apparatus for obtaining a global picture of results from an experiment that consists of multiple microarrays. We wanted to provide a computational resource that automates the analysis of multiple microarrays and then integrates the results across all of them in useful exportable output files and visualizations.

Results: We now introduce a new tool, High-Throughput GoMiner, that has those capabilities and a number of others: It (i) efficiently performs the computationally-intensive task of automated batch processing of an arbitrary number of microarrays, (ii) produces a human-or computer-readable report that rank-orders the multiple microarray results according to the number of significant GO categories, (iii) integrates the multiple microarray results by providing organized, global clustered image map visualizations of the relationships of significant GO categories, (iv) provides a fast form of 'false discovery rate' multiple comparisons calculation, and (v) provides annotations and visualizations for relating transcription factor binding sites to genes and GO categories.

Conclusion: High-Throughput GoMiner achieves the desired goal of providing a computational resource that automates the analysis of multiple microarrays and integrates results across all of the microarrays. For illustration, we show an application of this new tool to the interpretation of altered gene expression patterns in Common Variable Immune Deficiency (CVID). High-Throughput GoMiner will be useful in a wide range of applications, including the study of time-courses, evaluation of multiple drug treatments, comparison of multiple gene knock-outs or knock-downs, and screening of large numbers of chemical derivatives generated from a promising lead compound.

Figure 1

Schematic of stand-alone and web versions of High-Throughput GoMiner architecture and data flow.

Figure 2

Screen shot of High-Throughput GoMiner results in Excel for GO categories enriched in genes with altered expression. The 30 GO categories with FDR = 0.10 are color-coded red; the other GO categories are color-coded blue.

Figure 3

Clustered image map (CIM) [5,6] showing GO categories versus genes for genes with altered expression in a patient with CVID. Yellow indicates absence of the gene from the GO category. Red and green indicate over-and underexpressed genes, respectively. Clustering was performed with the Pearson correlation metric and average linkage algorithm. Instructions for using CIMminer to generate the CIMs in this paper are given in Supplementary Materials [see Additional file 5].

Figure 4

Clustered image map (CIM) 5,6 showing transcription factor binding sites versus GO categories in a patient with CVID. Red indicate FDR = 0.0, and yellow indicates FDR > 1.0 or a missing value. Clustering was performed with the Pearson correlation metric and average linkage algorithm. The inset is a blow-up of the first few transcription factor binding site names. A full-size version in which all the transcription factor binding site names are readable is available in Supplementary Materials [see Additional file 8]. There are 35 rather than 30 GO categories because this result was computed with a more recent version of the GO Consortium database.

Figure 5

Time series for GO categories with low FDR for overexpressed genes. The data were obtained from a study of schistosomiasis in a murine model [37-40] over the course of 20 weeks after infection. 3D bar graph visualization in Excel. (Elnekave et al, in preparation).

Figure 6

CIM [5,6] with hierarchically clustered categories (Pearson correlation, average linkage clustering) versus time (Elnekave et al., in preparation).