CRSD: a comprehensive web server for composite regulatory signature discovery

Abstract

Transcription factors (TFs) and microRNAs play important roles in the regulation of human gene expression, and the study of their combinatory regulations of gene expression is a new research field. We constructed a comprehensive web server, the composite regulatory signature database (CRSD), that can be applied in investigating complex regulatory behaviors involving gene expression signatures (GESs), microRNA regulatory signatures (MRSs) and TF regulatory signatures (TRSs). Six well-known and large-scale databases, including the human UniGene, mature microRNAs, putative promoter, TRANSFAC, pathway and Gene Ontology (GO) databases, were integrated to provide the comprehensive analysis in CRSD. Two new genome-wide databases, of MRSs and TRSs, were also constructed and further integrated into CRSD. To accomplish the microarray data analysis at one go, several methods, including microarray data pretreatment, statistical and clustering analysis, iterative enrichment analysis and motif discovery, were closely integrated in the web server, which has not been the case in previous studies. Our implementation showed that the published literature could demonstrate the results of genome-wide enrichment analysis. We conclude that CRSD is a powerful and useful bioinformatic web server and may provide new insights into gene regulation networks. CRSD and the online tutorial are publicly available at http://biochip.nchu.edu.tw/crsd1/.

Figure 1

The architecture of CRSD. (A) The high-level workflow for the four main functional components: (i) microarray data pretreatment, (ii) microarray data statistical and clustering analysis, (iii) iterative enrichment analysis and (iv) motif discovery. CRSD provides three initial procedures using microarray data pretreatment, enrichment analysis and motif discovery. (B) The MRS database integrating the microRNA and 3′-UTR databases is constructed by microRNA target prediction, and the TRS database is constructed by TF binding site prediction integrating promoter and TRANSFAC databases. The detailed data processing paths are shown in the flowchart, which represents the iterative enrichment analysis among GO, pathway, TRS and MRS.

Figure 2

Partial screenshots of the results page for the enrichment analysis. (A) The results page for significant enrichment MRSs showing the total number of target genes of microRNA hsa-miR-500, the retrieved set (intersection) of input genes, P-value, Q-value, microRNA targets and additional analysis buttons, including GO annotation, pathway, TRS and motif discovery of the interaction genes. (B) The results page for significant enrichment TRSs showing the total number of target genes, the retrieved set of input genes, P-value, Q-value, TF binding sites, and additional analysis buttons. (C) The results page for significant enrichment pathways showing the total number of pathway genes, the retrieved set of input genes, P-value, Q-value, the interaction genes, and additional analysis buttons. (D) The results page for significant enrichment GO annotations showing the total number of genes of the GO annotation, the retrieved set of input genes, P-value, Q-value, the interaction genes and additional analysis buttons.