CisMols Analyzer: identification of compositionally similar cis-element clusters in ortholog conserved regions of coordinately expressed genes

Abstract

Combinatorial interactions of sequence-specific trans-acting factors with localized genomic cis-element clusters are the principal mechanism for regulating tissue-specific and developmental gene expression. With the emergence of expanding numbers of genome-wide expression analyses, the identification of the cis-elements responsible for specific patterns of transcriptional regulation represents a critical area of investigation. Computational methods for the identification of functional cis-regulatory modules are difficult to devise, principally because of the short length and degenerate nature of individual cis-element binding sites and the inherent complexity that is generated by combinatorial interactions within cis-clusters. Filtering candidate cis-element clusters based on phylogenetic conservation is helpful for an individual ortholog gene pair, but combining data from cis-conservation and coordinate expression across multiple genes is a more difficult problem. To approach this, we have extended an ortholog gene-pair database with additional analytical architecture to allow for the analysis and identification of maximal numbers of compositionally similar and phylogenetically conserved cis-regulatory element clusters from a list of user-selected genes. The system has been successfully tested with a series of functionally related and microarray profile-based co-expressed ortholog pairs of promoters and genes using known regulatory regions as training sets and co-expressed genes in the olfactory and immunohematologic systems as test sets. CisMols Analyzer is accessible via a Web interface at http://cismols.cchmc.org/.

Figure 1

Detection and visualization of compositionally similar cis-regulatory modules shared by multiples genes. (A) CisMolGram provides a depiction of cis-element modules that are shared across two or more genes and contain two or more binding sites. Each module is represented by variously colored boxes located relative to the promoter of each gene in the analyzed group. Genes gathered from the GenomeTrafac database generally have their first exon locations at position 40 000. Most of the locations of cis-module clusters contain multiple modules. The locations of the clusters can be selected to be shown over either set of gene orthologs. By clicking on a cluster module (circled), a link is given to view either (B) the density of conserved elements over the regions (regulogram) or (C) the conserved cis-element arrangement at that location (Trafac image). The Regulogram shows the two sequences, mouse and human, represented as horizontal bars. The red-colored segments on these bars are exons. The green-colored bars shown parallel to the genomic sequences represent the repeat regions. The regions of sequence alignment are represented as differently colored quadrilaterals that relate one sequence to another. Within each shaded block, the percentage sequence similarity and the number of TFBSs are represented as two separate line graphs in the lower half. The frequencies of individual binding sites occurring in each of the sequences separately are shown as two running graphs in the top half of the pane. The percentage similarity is the average sequence conservation as determined by the BlastZ algorithm and the shared cis-element hits are determined by an algorithm that uses a 200 bp moving window to look through the cis-elements present within the conserved sequence block. Numbers are nucleotide positions. The regulogram can be clicked to zoom in or to view the TFBSs that are common to the two sequences at the click-point coordinate. In the Trafac image, the two gray vertical bars are the two genes (human and mouse) compared. The numbers represent the nucleotide positions with respect to the sequences used. The TFBSs occurring in both the genes are highlighted as variously colored bars drawn across the two genes. (D) The table view or the CisMolGram legend displays a summary of the results. It indicates the details of each cluster (the constituent individual cis-elements and their total frequency) and the frequency of the clusters occurring in each of the genes compared and involved in cluster analysis.