Shuffling of cis-regulatory elements is a pervasive feature of the vertebrate lineage

Abstract

Background: All vertebrates share a remarkable degree of similarity in their development as well as in the basic functions of their cells. Despite this, attempts at unearthing genome-wide regulatory elements conserved throughout the vertebrate lineage using BLAST-like approaches have thus far detected noncoding conservation in only a few hundred genes, mostly associated with regulation of transcription and development.

Results: We used a unique combination of tools to obtain regional global-local alignments of orthologous loci. This approach takes into account shuffling of regulatory regions that are likely to occur over evolutionary distances greater than those separating mammalian genomes. This approach revealed one order of magnitude more vertebrate conserved elements than was previously reported in over 2,000 genes, including a high number of genes found in the membrane and extracellular regions. Our analysis revealed that 72% of the elements identified have undergone shuffling. We tested the ability of the elements identified to enhance transcription in zebrafish embryos and compared their activity with a set of control fragments. We found that more than 80% of the elements tested were able to enhance transcription significantly, prevalently in a tissue-restricted manner corresponding to the expression domain of the neighboring gene.

Conclusion: Our work elucidates the importance of shuffling in the detection of cis-regulatory elements. It also elucidates how similarities across the vertebrate lineage, which go well beyond development, can be explained not only within the realm of coding genes but also in that of the sequences that ultimately govern their expression.

Figure 1

Number of conserved gene loci versus number of rCNEs identified in the mouse, rat, human, and dog genomes. Graph showing the number of rCNEs found conserved in the dog, rat, mouse and human genomes versus the number of genes found conserved across the same genomes. Although almost 90% of the genes can be found in all four genomes, most rCNEs can be found only in three out of four genomes. rCNE, regionally conserved element.

Figure 2

Distribution of length, percentage identity and shuffling categories of SCEs. SCEs were categorized based on their change in location and orientation in Fugu rubripes with respect to their location and orientation in the mouse locus. The entire locus, comprising the entire flanking sequence up to the next upstream and downstream gene was taken into consideration. Definitions of specific classes: (a) collinear SCEs (elements that have not undergone any change in location or orientation within the entire gene locus); (b) reversed SCEs (elements that have changed their orientation in the fish locus with respect to the mouse locus, but have remained in the same portion of the locus); (c) moved SCEs (elements that have moved between the pre-gene, post-gene and intronic portions of the locus); (d) Moved-reversed (elements that have undergone both of the above changes). (e) Frequency distribution of SCE length in base pairs. (f) Frequency distribution of percentage identity of SCE hits in fugu. SCE, shuffled conserved region.

Figure 3

Examples of loci containing shuffled conserved elements. (a) The Sema6d (sema domain, transmembrane domain, and cytoplasmic domain, semaphorin 6D; MGI:2387661) locus contains a post-genic moved-reversed conserved element. The SCE is found downstream from the gene in mammalian loci and upstream of the gene in fish genomes, and in reverse orientation only in the genomes of fugu and tetraodon. (b) the Ptprg (protein tyrosine phosphatase, receptor type G; MGI:97814) locus contains an intronic moved-reversed conserved element. The SCE is found in the first intron of the Ptprg gene in mammalian genomes, downstream of the gene in reverse orientation in fugu and tetraodon, and in the second intron in reverse orientation in zebrafish. Boxes represent the multiple alignments of the SCEs identified. SCE, shuffled conserved region.

Figure 4

GO Classification of genes harboring CNEs versus genes harboring SCEs. All genes containing CNEs and/or SCEs were analyzed for GO term classification. Genes containing CNEs are shown in red and genes containing SCEs are shown in gray. Plots show differences in absolute numbers as well as relative percentages. Classification is shown for (a) cellular component and (b) biological process categories. CNE, conserved noncoding element; GO, Gene Ontology; SCE, shuffled conserved region.

Figure 5

Analysis of SCE shuffling in 1000 bp windows. Each column in the figure shows the analysis of a locus portion (pre-gene, intron-start, intron-end and post-gene) divided into 1000 bp windows. In each column the first graph indicates the number of collinear SCEs identified, the second graph the number of noncollinear SCEs identified, and the third graph the χ² test used to identify windows that show a significant deviation from the expected proportion of collinear to noncollinear SCEs. The P value is shown for the only window (1000 bp upstream of the transcription start site) that exhibits significant deviation from the expected proportion. bp, base pairs; SCE, shuffled conserved region.

Figure 6

Overlap of known mouse enhancers with conserved elements. All mouse enhancers deposited in GenBank (94) were mapped to the genome and compared with previously published conserved elements (UCEs and CNEs) as well as our own dataset of SCEs to verify their overlap. Only one known mouse enhancer is overlapped by a CNE and two by a UCE, whereas our dataset of SCEs identifies 18 known mouse enhancers as being conserved within fish genomes. CNE, conserved noncoding element; SCE, shuffled conserved region; UCE, ultraconserved element.

Figure 7

Expression profiles of X-Gal stained embryos. (a-f) Expression profiles of 1-day-old X-Gal stained zebrafish embryos. Each expression map represents a composite overview of the LacZ-positive cells of 65-175 embryos. Gene names and fragment/SCE id are shown. Detailed distribution of X-Gal stained cells in different tissues as well as data for all other fragments are shown in Table 3. Side view of head region of LacZ-stained embryos are shown with anterior to the left. (panel a) HSP-lacZ injected embryo. (d) Embryo co-injected with SCE 3121 associated with Jag1b gene. (f) Embryo co-injected with SCE 4939 associated with Mab21l2 gene. SCE, shuffled conserved region.