Distinct cis-acting regions control six6 expression during eye field and optic cup stages of eye formation

Abstract

The eye field transcription factor, Six6, is essential for both the early (specification and proliferative growth) phase of eye formation, as well as for normal retinal progenitor cell differentiation. While genomic regions driving six6 optic cup expression have been described, the sequences controlling eye field and optic vesicle expression are unknown. Two evolutionary conserved regions 5' and a third 3' to the six6 coding region were identified, and together they faithfully replicate the endogenous X. laevis six6 expression pattern. Transgenic lines were generated and used to determine the onset and expression patterns controlled by the regulatory regions. The conserved 3' region was necessary and sufficient for eye field and optic vesicle expression. In contrast, the two conserved enhancer regions located 5' of the coding sequence were required together for normal optic cup and mature retinal expression. Gain-of-function experiments indicate endogenous six6 and GFP expression in F₁ transgenic embryos are similarly regulated in response to candidate trans-acting factors. Importantly, CRISPR/CAS9-mediated deletion of the 3' eye field/optic vesicle enhancer in X. laevis, resulted in a reduction in optic vesicle size. These results identify the cis-acting regions, demonstrate the modular nature of the elements controlling early versus late retinal expression, and identify potential regulators of six6 expression during the early stages of eye formation.

Figure 1

Alignment of the six6 gene from X. laevis and X. tropicalis reveals major differences in the 5′ flanking region. (A) Two evolutionary conserved regions, R2 and R1 (golden boxes) were detected 5′ to the six6 open reading frame. Both regions were identified in human, dog, opossum, mouse, chicken, coelacanth and spotted gar with the percent identity indicated. The numbers below the golden boxes indicated the base position upstream from the X. tropicalis ATG (A=0). Purple boxes indicate exon 1; CDS, coding DNA sequence; white boxes indicate sequences not identified by ECR Browser, but located by manual alignment. (B) Mauve alignment of X. tropicalis six6, Xenopus laevis six6.L and six6.S identified a 979 bp insertion (orange arrow) in six6.S R1 domain, which is not present in X. laevis six6.L or in X.tropicalis. Green indicates similarities, while gray indicates gaps in alignment.

Figure 2

F₁ transgenic X. laevis carrying the 5′ flanking region of six6 only express GFP in the differentiated optic cup. (A–E) Expression pattern of endogenous six6 by whole-mount in situ hybridization (WISH). (A) At stage 12.5, six6 is undetectable, but by stage 15 (B) six6 transcript is detected in the eye field. (C) Strong six6 expression persists in stage 24 optic vesicles, but no expression is seen in the forebrain. (D) At stage 28, six6 is expressed in the pineal (arrowhead) and the presumptive pituitary/hypothalamic area (arrow), as well as the optic cups. (E) At stage 32, strong expression continues to be detected in the eyes. (F–J) Whole mount in situ hybridization of embryos carrying the Xt six6 R2R1→GFP transgene shows (F–G) no detectable expression of GFP RNA at eye field or (H) optic vesicle stages. (I–J) GFP transcripts were first detected at stage 28 in the optic cup (black arrow, eye), pineal (a) and ventral forebrain (b). (K–L) GFP fluorescence was first detected at stage 33/34 in eye and pineal; (L) brightfield image of embryo in panel K. (M) Stage 40 animals expressing GFP in eye (arrowhead) and brain (tectum and midbrain). (N) Bright field image of transgenic tadpole shown in (O) expressing GFP brightly in eyes, optic stalk (os) and synapsing on the tectum; weak fluorescence was also sometimes observed in the hindbrain. Yolk autofluorescence is also observed (K,M,O).

Figure 3

Alignment of vertebrate six6 genes reveals an evolutionary conserved region 3′ of the six6 coding region. PIP analysis was used to compare vertebrate genomic DNA sequences from mammalian (human, mouse), marsupial (tazmanian devil), aves (chicken), reptile (green sea turtle), lobe-finned fish (coelacanth) and fish (medaka). Golden boxes show evolutionarily conserved regions (R); purple boxes indicate exons; white box, intron; dark and light blue lines, 5′ and 3′ flanking genomic regions, respectively. The line at the bottom of the PIP analysis indicates distance in kilobases from the translation start site. The percent identity of X. tropicalis R3 to each species is included. Exon 1 contains 146 bp of 5′ untranslated region, while exon 2 contains 964 bp of 3′ untranslated region, both depicted in light purple.

Figure 4

Early embryonic (eye field and optic vesicle) expression of GFP transcript and protein in F₁ animals with the addition of R3. (A) GFP transcript was detected by whole mount in situ hybridization (WISH) as early as eye field stages (stg 15). (B–E) At stage 23, GFP transcript was detected in developing optic vesicles; no signal was detected using a sense probe (E). (F–H) GFP fluorescence was detected by stage 22 in the optic vesicle of transgenic animals. (I–M) GFP fluorescence was weak in the midbrain (J, arrow), while strong in both the ventral forebrain (J,M, arrowhead) and in the optic cup (M). (N, O) Dorsal views of stage 39 and 45 tadpoles expressing GFP in the eye, forebrain, optic stalk (os), retinal ganglion cells projecting to the tectum and brain.

Figure 5

Deletion constructs indicate R3 is sufficient for early eye expression. (A) Schematic diagram of Xenopus tropicalis six6 gene. Location of exons (purple) and intron (white) are indicated. The flanking non-conserved (blue, NC) and evolutionarily conserved regions (yellow, R) are also shown; non-conserved regions at the 5′ end are depicted in dark blue, while those at the 3′ end are light blue. Numbering is based on the ‘A’ of the start codon marked as +1. (B) Percent of animals expressing GFP transcript (GFP detected by WISH/total analyzed) at the indicated stages of eye development. ND, not determined.

Figure 6

Pax6 expands, while FoxD1 and Onecut1 repress, endogenous six6 expression. (A–F) Whole mount in situ hybridization for six6 was performed on embryos injected in one dorsal blastomere at the four-cell stage with β-gal RNA (200 pg) alone (A, D), or with the indicated amount of transcription factor. The dorsoventral six6 expression domain was measured as indicated (brackets), and the change in expression on the injected side was determined relative to the control, uninjected side (G). Statistical significance was determined using an ordinary one-way ANOVA test with multiple comparisons to β-gal measurements. Statistically significant change indicated by ** (P ≤ 0.01), *** (P ≤ 0.001), **** (P≤0.0001) and ns (not significant); number of embryos analyzed is shown inside each histogram bar; error bars, s.e.m.

Figure 7

Pax6 induces, while FoxD1, Onecut1 and CA-Smad1 repress GFP expression under the control of Xt six6 R3R2R1→GFP in transgenic animals. (A–O) Four cell stage F₁ Xt six6 R3R2R1→GFP embryos were injected in one dorsal blastomere with mCherry alone (A–C), or with the indicated transcription factor (D–O). Embryos were sorted at optic vesicle stage for unilateral expression of mCherry (column one). The relative change in GFP fluorescence was determined by comparing the injected and uninjected side (column two, dashed line indicates midline) of embryos (P). Statistical significance was determined by using an unpaired, two-tailed Student’s t-test, comparing each sample to mCherry measurements. Statistically significant change indicated by *, P ≤ 0.05 and **, P<0.01; error bars are s.e.m.

Figure 8

Deletion of Region 3 from the X. laevis genome reduces optic vesicle size. (A) Schematic illustrating location of target regions in X. laevis six6.L and six6.S genes. Boxed region indicates location of region magnified in panel B. (B) Schematic showing location of small guide RNAs (red arrows) used to target R3 of the L and S six6 homeologs. Numbering is based on the ‘A’ of ATG start codon marked as +1. The red line is the expected deletion fragment. (C–F) The expression domain of six6 was determined by in situ hybridization on stage 24/25 heads. (C) Wild-type and (D) Cas9-injected embryos have measurably larger optic vesicles than embryos in which R3 has been deleted; (E) six6.L^ΔR3, or (F) six6.S ^ΔR3. (F) The optic vesicle area was determined as a function of overall head size. A one-way ANOVA test with multiple comparisons was used to determine statistical significance: *, P<0.05; **, P<0.01, ****, P<0.0001; error bars are s.e.m.; n = number of eyes measured.