Glass confers rhabdomeric photoreceptor identity in Drosophila, but not across all metazoans

Abstract

Across metazoans, visual systems employ different types of photoreceptor neurons (PRs) to detect light. These include rhabdomeric PRs, which exist in distantly related phyla and possess an evolutionarily conserved phototransduction cascade. While the development of rhabdomeric PRs has been thoroughly studied in the fruit fly Drosophila melanogaster, we still know very little about how they form in other species. To investigate this question, we tested whether the transcription factor Glass, which is crucial for instructing rhabdomeric PR formation in Drosophila, may play a similar role in other metazoans. Glass homologues exist throughout the animal kingdom, indicating that this protein evolved prior to the metazoan radiation. Interestingly, our work indicates that glass is not expressed in rhabdomeric photoreceptors in the planarian Schmidtea mediterranea nor in the annelid Platynereis dumerilii. Combined with a comparative analysis of the Glass DNA-binding domain, our data suggest that the fate of rhabdomeric PRs is controlled by Glass-dependent and Glass-independent mechanisms in different animal clades.

Keywords: Drosophila; Evolutionary conservation; Eye development; Glass; Photoreceptor development; Platynereis; Rhabdomeric photoreceptors; Schmidtea; Transcription factor.

Fig. 1

Glass phylogeny. To identify Glass homologues, we searched for Glass-like sequences with BLAST and obtained a cluster map by using all-against-all pairwise similarity. In this graph, those sequences that are most similar appear clustered together, and connected by a darker line (a). Based on these data, we built a maximum likelihood tree for Glass (b) (for further details, see the “Methods” section, the tree file and the sequences that we used for it are included in the Additional file 3)

Fig. 2

Glass homologues exist in most animal groups. Based on sequence comparison (Additional file 4, also see Fig. 3), we infer that glass appeared in the common ancestor of all metazoans, and that it has been transmitted to most present-day animals (shown in green on the phylogenetic tree [74]). However, we were not able to identify glass in vertebrates

Fig. 3

Analysis of the Glass zinc fingers. Generally, Glass homologues possess a cluster of five Cys₂His₂ zinc fingers, each of them containing the following motif: Cys-X_2,4-Cys-X₁₂-His-X_3,4,5-His. Of these, we compared the sequences of the fourth and the fifth zinc fingers, which are responsible for recognising the DNA Glass-binding motif in PRs in vivo [–37], from the following species: Amphimedon (Porifera), Schmidtea (Platyhelminthes), Platynereis (Annelida), Aplysia (Mollusca), Caenorhabditis (Nematoda), Drosophila (Arthropoda), Strongylocentrotus (Echinodermata) and Branchiostoma (Cephalochordata). In the table, those amino acids that match the Glass consensus sequence (deduced by aligning the homologues of different species, in the first column) appear on black background. The 3D structure of the DNA-bound Cys₂His₂ domain has been resolved [75], and it is expected that four amino acids per zinc finger directly recognise three base pairs. These amino acids are well evolutionarily conserved across different Glass homologues and, in the sequences that we show, they are no. 10 (D), 12 (S), 13 (T), and 16 (K) in the fourth zinc finger, and no. 38 (Q), 40 (G), 41 (N), and 44 (R) in the fifth zinc finger. Other residues and neighbouring zinc fingers are also expected to contribute to the DNA-binding specificity of Glass [76]. Similarly, we aligned Glass-like proteins from vertebrates (e.g. human) and choanoflagellates (e.g. Salpingoeca) with BLAST [24] and MUSCLE [28], but they showed little similarity to the Glass consensus sequence (shown in the second column). Furthermore, a ‘DNA-binding site predictor for Cys₂His₂ Zinc Finger Proteins’ has been developed and is available online [32, 33]. This software predicts that, based on their amino acid sequence, all Glass homologues (in the first column) can bind to the same DNA motif: GAAGCC, which was expected from experimental works in Drosophila and Caenorhabditis [34, 35]. By contrast, it appears that the Glass-like proteins of vertebrates and choanoflagellates (in the second column) would not be able to recognise this motif. All sequences are available in the Additional file 4

Fig. 4

glass is not expressed in rhabdomeric PRs in Schmidtea. These graphs were obtained from the Planarian Digiworm atlas, a single-cell transcriptome database for Schmidtea mediterranea [19, 25]. Each point corresponds to one single cell, and they are clustered according to the similarity of their transcriptome. One of the clusters shown, corresponding to non-ciliated neurons, is formed by 14 rhabdomeric PRs which can be identified because of the expression of the opsin gene (dd_Smed_v4_15036_0_1, a). However, these PRs do not appear to express the Schmidtea glass homologue (annotated as dd_Smed_v4_75162_0_1 in this website [19, 54], b)

Fig. 5

glass is not expressed in rhabdomeric PRs in Platynereis. a, b glass is present in all Drosophila rhabdomeric PRs, including those in the compound eye [12, 55]. This can be observed in head cryosections, either by using in situ hybridisation (magenta in a and greyscale in a′) or with glass > mCD8::RFP flies (magenta in b and greyscale in b′). In both cases, samples were counterstained with DAPI (green). c–e In contrast to Drosophila, double in situ hybridisation against the glass (red) and r-opsin1 (green) transcripts shows that glass is not present in Platynereis rhabdomeric PRs. Samples were counterstained with antibodies against acetylated Tubulin (ac-Tub, blue), which is a neuropil marker (c, transversal view of a whole-mounted, 5-day-old larva). To the right, close-ups of the dorsal (arrow in c; c′, c′′) and ventral eyes (arrowhead in c; c′′′, c′′′′) show that glass (in magenta/greyscale) is not expressed in either of these visual organs. Similarly, we found that a microinjected glass-Tomato reporter (magenta/greyscale) was not co-expressed with a stable r-opsin1-GFP insertion (green). Brightfield (BF, greyscale) was imaged as a reference (d–d′′, dorsal view of a whole-mounted, 8-day-old larva). The positions of the dorsal and ventral eyes are shown with an arrow and an arrowhead, respectively. Close-ups to the right show how the axons of Tomato, and GFP-positive neurons project into two different areas in the brain (d′, d′′; orthogonal views taken along the Z segment are shown below). As a control, we also imaged an 8-day-old, wild-type, uninjected larva to test its autofluorescence (using two excitation laser wavelengths: 552 nm, same as for Tomato; and 488 nm, same as for GFP). Scale bars: 10 μm in c′, c′′′; 20 μm in d–e; and 50 μm in a, b. Axes: D, dorsal; M, medial; P, posterior; V, ventral

Fig. 6

Glass-expressing cells in Platynereis include sensory neurons. When we injected our glass-Tomato reporter, we observed that many of the neurons that were appeared labelled in the Platynereis head were bipolar, located close to the surface, and they often possessed membranous specialisations resembling sensory dendrites (arrows) (a–d). Scale bars: 5 μm