Functional evolution of a cis-regulatory module

Abstract

Lack of knowledge about how regulatory regions evolve in relation to their structure-function may limit the utility of comparative sequence analysis in deciphering cis-regulatory sequences. To address this we applied reverse genetics to carry out a functional genetic complementation analysis of a eukaryotic cis-regulatory module-the even-skipped stripe 2 enhancer-from four Drosophila species. The evolution of this enhancer is non-clock-like, with important functional differences between closely related species and functional convergence between distantly related species. Functional divergence is attributable to differences in activation levels rather than spatiotemporal control of gene expression. Our findings have implications for understanding enhancer structure-function, mechanisms of speciation and computational identification of regulatory modules.

Figure 1. Expression of eve

(A–D) Embryos of four Drosophila species at early cellular blastoderm stage. EVE stained with immunoperoxidase DAB reaction enhanced by nickel. (E–H) Df(eve) D. melanogaster embryos with two copies of transgenes containing eve S2E from four species fused to D. melanogaster eve coding region (−0.9 to +1.85 kb) at blastoderm stage. Immunofluorescence-labeled EVE. The S2E_ere-EVE (G) produces consistently weaker stripes than lines carrying S2Es from the other three species. (A and E) D. melanogaster, (B and F) D. yakuba, (C and G) D. erecta, and (D and H) D. pseudoobscura.

Figure 2. Genetic Constructs and Rescue Scheme

(A) Summary map of the eve locus and eve S2E deletion transgene (EVEΔS2E). Adam and Apple are adjacent open reading frames [40]. The late element (Auto) and early stripe enhancers are shown. (B) S2E-EVE transgenes used to rescue eve function. The rescue EVE locus used is the D. melanogaster eve flanked by 0.9 kb of 5′ and approximately 0.6 kb of 3′ of endogenous sequence. The S2E _o -EVE does not have any S2E sequences and is a negative control. The known trans-factor-binding sites in the S2E from D. melanogaster: five bicoid (circles), three hunchback (ovals), six Kruppel (squares), three giant (rectangles), and one sloppy-paired (triangle) binding site. Symbols representing sites 100% conserved compared to D. melanogaster are open, while those diverged are shaded gray. Note the evolutionary gain of novel but functionally necessary [6] activator (bicoid and hunchback) binding sites (red) in D. melanogaster lineage. Full sequences are shown in Figures S1 and S2. (C) Example of a cross between independent rescue lines and relevant offspring genotypes for the viability assay (see Materials and Methods for details). Genetic notation b: mutant black; yellow box: native eve; R13 and X'd out yellow box: eve^R13 lethal mutant; P(S2EΔEVE): eve −6.4 to 8.4 kb without S2E; P(S2E _A1 -EVE) and P(S2E _A2 -EVE) are two independent rescue-transgene inserts with S2E from species A.

Figure 3. Developmental Series of EVE Abundance

(A–E) Immunofluorescence labeling of time-staged early EVEΔS2E homozygous embryos. This developmental sequence, which corresponds roughly from the initialization of cellularization (A) to its completion (E), takes approximately 45 min at 25 ^oC in wild-type flies [41]. (F) Expression of en in same genotype at stage 10. Arrows mark third and fourth en stripes. Note the short interval between en stripes 3 and 4 (parasegment 3) and the reduced fourth stripe. (G) EVE expression in stripe 2 during the developmental series around cellularization, where times 1–5 correspond to pictures in A–E. Stage 1 is early cellularization, while the process has been completed for embryos in class 5. The series is comparable to time classes 4–8 on the FlyEx Web site (http://flyex.ams.sunysb.edu/flyex/) [34]. Estimated least square means (± SE) for EVEΔS2E/Cy stock and wild-type line w1118; note the Cy/Cy homozygote is essentially wild-type. Early eve pair-rule expression is not known to be autoregulated (as occurs in postcellularization stages), and we observe a 2-fold difference in early stripe expression, with an additive component (a) of 0.62 and negligible dominance deviation (d/a) = 0.01, for the first two stages. This dosage dependency is lost after the cellularization stage (3), presumably because all embryos carry two copies of the autoregulatory element.

Figure 4. Rescue to Adulthood of eve Null Mutants

Rescue percentages to adulthood of EVEΔS2E homozygotes with one or two copies of rescue construct from the four species, and the negative control, denoted on x-axis. Each bar represents percentages summarized over sexes and reciprocal crosses (full data in Table S1).

Figure 5. Effects on en Expression

(A, C–I) The en pattern in homozygous EVEΔS2E and (B) wild-type (w1118) specimens at stages 9–11. All strains (except [B]) are homozygous for Df(eve) P(EVEΔS2E) second chromosomes, with the third chromosome differing only by rescue transgenes: (A) no rescue transgenes; (C) P(mel 36)/P(mel 36) is a S2E_mel-EVE stock; (D) P(yak 74)/TM3 Sb and (E) P(yak 74)/P(yak 74) are S2E _yak -EVE stocks; (F) P(S2E_o-EVE)/P(S2E_o-EVE) has no S2E; both (G) P(ere 41)/P(ere 41) and (H) P(ere 21)/P(ere 21) are S2E_ere-EVE transgenic stocks; and (I) P(pse 91)/P(pse 91) is a S2E_pse-EVE stock. Note the variation in distance between third and forth en stripes (arrows) and relative level of en expression in the fourth stripe. Only the first seven parasegments of the en pattern are show (except in [A]). The en protein was visualized by an immunoperoxidase DAB reaction enhanced by nickel. mel: D. melanogaster; yak: D. yakuba; ere: D. erecta; pse: D. pseudoobscura. S2E_o-EVE lacks a S2E.

Figure 6. Diverged S2Es Contribute Differentially to EVE Abundance

Fluorescence-labeled antibody staining of EVE in embryos with zero (A, C, and E) or two (B, D, and F) copies of rescue transgene. A dose effect is seen in D. pseudoobscura line 91, (A and B), while none is observed in D. erecta line 41 (C and D) or 21 (E and F). (G) These effects are significant when comparing EVE protein quantity (least square means ± SE) in stripe 2 (Dose × Species, F = 4.69_{(2, 100.44)}, p = 0.01; see Tables 1 and S2) D. pseudoobscura (black circles, n = 59) and D. erecta embryos (open circles, n = 71). For D. pseudoobscura the estimated additive component (a) = 0.37 and dominance deviation(d/a) = 0.17.

Figure 7. Predicted Binding-Site Composition and Sequence Conservation in the eve 5′ Noncoding Region

(A) D. melanogaster predicted binding-site composition. (B) D. yakuba predicted binding-site composition and sequence conservation with D. melanogaster. (C) D. erecta predicted binding-site composition and sequence conservation with D. melanogaster. (D) D. pseudoobscura predicted binding-site composition and sequence conservation with D. melanogaster. Coordinates of functionally characterized enhancer sequences are shown in light blue, and unannotated conserved noncoding sequences are shown in pink. The coordinates of the homologous stripe 2 sequences correspond to the constructs in Figure S1, while the coordinates of the AR and stripe 3 enhancers have been estimated based on sequence conservation. Note that the scale of the genomic intervals plotted differs between panels (black bar = 500 bp). Binding sites are indicated by color; bicoid (blue), hunchback (red), and Kruppel (green).