Sepsid even-skipped enhancers are functionally conserved in Drosophila despite lack of sequence conservation

Abstract

The gene expression pattern specified by an animal regulatory sequence is generally viewed as arising from the particular arrangement of transcription factor binding sites it contains. However, we demonstrate here that regulatory sequences whose binding sites have been almost completely rearranged can still produce identical outputs. We sequenced the even-skipped locus from six species of scavenger flies (Sepsidae) that are highly diverged from the model species Drosophila melanogaster, but share its basic patterns of developmental gene expression. Although there is little sequence similarity between the sepsid eve enhancers and their well-characterized D. melanogaster counterparts, the sepsid and Drosophila enhancers drive nearly identical expression patterns in transgenic D. melanogaster embryos. We conclude that the molecular machinery that connects regulatory sequences to the transcription apparatus is more flexible than previously appreciated. In exploring this diverse collection of sequences to identify the shared features that account for their similar functions, we found a small number of short (20-30 bp) sequences nearly perfectly conserved among the species. These highly conserved sequences are strongly enriched for pairs of overlapping or adjacent binding sites. Together, these observations suggest that the local arrangement of binding sites relative to each other is more important than their overall arrangement into larger units of cis-regulatory function.

Figure 1. Binding site conservation and turnover in Drosophila even-skipped stripe 2 enhancer.

Predicted binding sites for the five factors known to regulate expression from the eve stripe 2 enhancer in the twelve sequenced Drosophila species . Sites were predicted independently in each species using PATSER and mapped onto an MLAGAN multiple alignment of the eve stripe 2 enhancer sequences. The height of the box representing each binding site is scaled by its PATSER p-value (taller boxes represent sites with higher predicted affinities). The top panel (grey shading) shows the positions of biochemically-verified (in vitro footprinting) binding sites . The indicated coordinates are for the multiple-alignment, which is longer than individual enhancers due to the high frequency of alignment gaps.

Figure 2. Conservation within and between sepsids and Drosophila.

The eve locus (20 kb flanking the eve protein-coding gene) is shown for two Drosophila (D. melanogaster and D. virilis) and two sepsid species (S. cynipsea and T. putris), centered on the eve homeodomain. Black lines represent significant BLASTZ hits on the plus strand, red lines on the minus strand (BLASTZ parameters: K = 1800, with chaining). Verified D. melanogaster enhancers are shown in green and predicted sepsid enhancers in black. Note that only a subset of D. melanogaster eve enhancers are shown here; all BLASTZ matches between D. melanogaster and S. cynipsea fall within known enhancers with the exception of those falling within 500 bp of the transcription start site in D. melanogaster.

Figure 3. Coding and non-coding trees of sepsids and Drosophila.

(A) Maximum likelihood tree of protein-coding genes inferred from seven genes using CODEML module of PAML . Branch lengths are in substitutions per codon using the [F3×4] model. (B) Maximum likelihood non-coding trees of six Drosophila and six sepsids computed using the BASEML module of PAML . Branch lengths are in substitutions per site using the HKY model.

Figure 4. Expression of eve and its upstream transcriptional regulators is conserved between Drosophila melanogaster and the sepsid Themira minor.

Expression patterns were visualized by in situ hybridization with species-specific digoxigenin-labeled antisense RNA probes. The gap transcription factors hb, gt and Kr are expressed in similar domains during stage 5 in D. melanogaster (A–C) and T. minor (E–G). eve is expressed in seven transverse stripes during cellularization in both species (D, H). Embryos are oriented with anterior to the left and dorsal up.

Figure 5. Sepsid eve enhancers drive conserved expression patterns in Drosophila melanogaster embryos.

Expression patterns of eve stripe 2, stripe 3+7, stripe 4+6 and muscle-heart enhancers from sepsids S. cynipsea, T. putris and T. superba were compared to their D. melanogaster counterparts in transgenic D. melanogaster embryos by RNA in situ hybridization with digoxigenin-labeled antisense RNA probes against the reporter genes lacZ (A, D, G) and CFP (B,C,E,F,H,I,K,L), or staining with βGal antibodies (J). (A–C) Sepsid stripe 2 enhancers drive strong expression in an anterior stripe corresponding to D. melanogaster stripe 2. (D–F) Sepsid stripe 3+7 enhancers drive expression within the limits of D. melanogaster stripe 3 and 7, with additional expression in the posterior. (G–I) Sepsid stripe 4+6 enhancers drive expression within the limits of D. melanogaster stripes 4 and 6. (J–L) Sepsid MHE enhancers are expressed in metameric clusters in the dorsal mesoderm in stage, as in D. melanogaster. Embryos were imaged during cellularization and are oriented with anterior to the left and dorsal up.

Figure 6. Extensive reorganization of binding sites between Drosophila and sepsid eve stripe 2 enhancers.

Predicted binding sites for the five factors known to regulate expression from the eve stripe 2 enhancer in six Drosophila species and six sepsid species. Sites were predicted independently in each species using PATSER and mapped onto an MLAGAN multiple alignment of the eve stripe 2 enhancer sequences. The height of the box representing each binding site is scaled by its PATSER p-value (taller boxes represent sites with higher predicted affinities). The top panel (grey shading) shows the positions of biochemically-verified (in vitro footprinting) binding sites . Binding sites conserved within families are indicated by solid boxes. A BCD-KR site pair conserved across families is indicated by a dashed box. Alignment coordinates are indicated.

Figure 7. Evolutionary fate of binding sites is dependent on their proximity to other sites.

Binding sites in the stripe 2, stripe 3+7, and MHE enhancers were classified as “overlapping” if they shared at least one base pair with a site for a different factor, “close” if the nearest base of another site (for a different factor) is within 10 bp, and “isolated” if neither condition is met. Binding sites in D. melanogaster were classified as non-conserved, minimally conserved (only within melanogaster subgroup), highly conserved (within 12 sequenced Drosophila species) and extremely conserved (12 Drosophila and 6 sepsids). (A) The distribution of conservation scores as a function of binding-site proximity shows overlapping and close sites are more likely to be highly or extremely conserved than isolated sites. (B) The fraction of each conservation category in different proximity groups again shows that extremely and highly conserved sites are strongly enriched for overlapping and close binding sites.