Ancient origin of the rod bipolar cell pathway in the vertebrate retina

Abstract

Vertebrates rely on rod photoreceptors for vision in low-light conditions¹. Mammals have a specialized downstream circuit for rod signaling called the primary rod pathway, which comprises specific cell types and wiring patterns that are thought to be unique to this lineage^2-6. Thus, it has been long assumed that the primary rod pathway evolved in mammals^3,5-7. Here, we challenge this view by demonstrating that the mammalian primary rod pathway is conserved in zebrafish, which diverged from extant mammals ~400 million years ago. Using single-cell RNA-sequencing, we identified two bipolar cell (BC) types in zebrafish that are related to mammalian rod BCs (RBCs) of the primary rod pathway. By combining electrophysiology, histology, and ultrastructural reconstruction of the zebrafish RBCs, we found that, like mammalian RBCs⁸, both zebrafish RBC types connect with all rods and red-cones in their dendritic territory, and provide output largely onto amacrine cells. The wiring pattern of the amacrine cells post-synaptic to one RBC type is strikingly similar to that of mammalian RBCs. This suggests that the cell types and circuit design of the primary rod pathway may have emerged before the divergence of teleost fish and amniotes (mammals, bird, reptiles). The second RBC type in zebrafish, which forms separate pathways from the first RBC type, is either lost in mammals or emerged in fish to serve yet unknown roles.

Keywords: Evolution; Retina; Rod; Rod bipolar cells.

Figure 1.. Comparison of single-cell gene expressions identified two possible rod bipolar cells in zebrafish

a, Schematic representation of retinal circuits (left) and an image of a retinal slice from Tg(vsx1:GFP)^nns5 transgenic adult zebrafish (right). GFP expression in all bipolar cells (BCs). Nuclei was stained by DAPI. PR: photoreceptor, HC: horizontal cell, AC: amacrine cell, RGC: retinal ganglion cell. b, 2D visualization of single-cell clusters using Uniform Manifold Approximation (UMAP). Individual points correspond to single cells colored according to cluster identity. c, Marker genes for each cluster. d, Agglomerative hierarchical clustering of average gene signatures of clusters using the correlation metric and complete linkage. BC subclasses (colors) were assigned based on the known marker expressions shown in e. e, Gene expression patterns of known BC subclass markers in BC clusters. The size of each circle depicts the percentage of cells in the cluster in which the marker was detected (≥1 UMI), and its contrast depicts the scaled average expression level of cells within the cluster in c,e. Data for mouse is from Shekhar K, et al., 2016, Cell.

Figure 2.. Transgenic labeling of cluster 14 and 19 revealed morphological features of these BCs

a,b, En face view of retinal flat mount at the inner nucleus layer level. Cerulean fluorescent expression (colored yellow) transgenic lines, Tg(vsx1:memCerulean)^q19 (vsx1:memCer) in a and Tg(vsx2:memCerulean)^wst01 (vsx2:memCer) in b. vsx1:memCer and vsx2:memCer BCs are positive for cluster specific genes, s100a10b and uts1, respectively, which are detected using in situ hybridization chain reaction . c,d, Side views of the labeled cells and the distribution patterns of their axon terminals in en face views of retinal flat mounts for RBC1 (c) and RBC2 (d) BCs. Immunolabeling for PKCα is in magenta. IPL: inner plexiform layer. Note that not all PKC-immunoreactive cells are apparent in this image of the vsx1:memCer line, due to the incomplete labeling of this line. e,f, Dendritic tiling of RBC1 (e) and RBC2 (f) in en face view of retinal flat mounts at the outer plexiform layer level. Dendritic territories are marked by the red boundaries. g-j, Mean cell densities of RBC1 (g, n=3 and 4 for D and VT, respectively) and RBC2 (I, n=3 for both D and VT) BCs in different regions of the retina. Box and violin plots of dendritic field sizes of RBC1 (h, n=37 and 33 or D and VT, respectively) and RBC2 (j, n=40 and 41 or D and VT, respectively) BCs. White filled circles are medians. Grey circles indicate individual cells. D: dorsal, VT: ventrotemporal.

Figure 3.. RBC1 and RBC2 connect to rods and red cones but differ in dendritic and axonal synaptic arrangements

a,b, Dendritic tips invaginating the rod and red cone axon terminals, visualized in retinal slices from (a) Tg(vsx1:memCerulean:trb2:tdtomato)^q19,q22 and (b) Tg(vsx2:memCerulean:trb2:tdtomato)^wst01,q22 adult zebrafish. Rods were immunolabeled using 4C12 antibody. c,d, Doughnut and simple dendritic tip structures at rod terminals (arrow heads) in RBC1 and RBC2, respectively. e-h, Box and violin plots of RBC1 (e,f, n=7) and RBC2 (g,h, n=8) connectivity with photoreceptors. i,j, Distribution of ribbon synapses in the RBC1 (i) and 2 (j) axons. Ribbons were immunolabeled by anti-ribeye antibody. Ribeye signals outside the axons were digitally masked out in the right two images. RBC2 axon harbors a ribbon containing distal bouton in the OFF layer (arrow head).

Figure 4.. Rod input to RBC1 is mediated by mGluR6 receptors.

a,b, Colocalization of mGluR6 and RBC1 (a) and RBC2 (b) dendritic tips at rod terminals visualized by structured illumination microcopy. c, Whole-cell patch clamping of a RBC1 axon terminal, visualized by dye-filling Alexa Fluor 594). d, Voltage responses of RBC1 and RBC2 after a cone activating light flash (arrow heads). e, Population data of RBC1 responses to rod activating light flashes with and without the group III metabotropic glutamate receptor agonist, APB (6-(2-aminopropyl)benzofuran). Filled circles: mean; error bars, S.D.; open circles, individual cells. Traces on the right are an example of the cell's light evoked response before and during APB bath application. Inhibitory neurotransmitter receptors were blocked (inh lock) by a bath application of gabazine, strychnine, and TPMPA ((1,2,5,6-Tetrahydropyridin-4-yl)methylphosphinic acid).

Figure 5.. Identification of RBC1 and RBC2 in a SBFSEM volume.

a, Reconstructions of a RBC1 and a RBC2, and zoomed-in images of their dendritic tips at rod and cone terminals. Ribbons in the rod and cones are painted red. b, Ribbon synapse distributions in a RBC1 and a RBC2. The locations of ribbon synapses are marked in red. Arrow heads indicate the locations of example ribbon synapses (arrows) shown in the insets. c, Reconstruction of all RBC1s and RBC2s in the EM volume. Postsynaptic neurons of a centrally located RBC1 (open arrow head) and RBC2 (closed arrow head) were reconstructed in Fig. 6, 7, and S5–9.

Figure 6.. Identification RBC1 and RBC2 post-synaptic neuron types

a-d, Quantification of morphological parameters of neurons postsynaptic to one of the RBC1s in the EM volume (marked by an open arrow head in Fig. 5c). One postsynaptic neuron contained an exceptionally higher number of synapses (14) with the RBC1 (marked in red in b and c). Dendritic stratification is normalized to 0 and 1 at the lower and upper ends of the RBC1 axon terminals, respectively in d. e, Mono-stratifying ACs with (red) or without (blue) reciprocal synapses with RBC1s in the volume. The axon of the presynaptic RBC1 is also shown in the side view. Individual cells were color coded. f-i, Quantification of morphological parameters for neurons postsynaptic to one of the RBC2s in the EM volume (marked by a closed arrow head in Fig. 5c). AC: amacrine cells, RGC: retinal ganglion cells.

Figure 7.. Circuit diagram of RBC1 is similar to mammalian RBC pathway

a, An example monostratified amacrine cell (RS AC) classified in Fig. 6e that formed of reciprocal synapse with RBC1. b, A mouse A17 amacrine cells (taken from ) (b). c,d, A2-like ACs that are postsynaptic to two neighboring RBC1s. e,d, Locations and distributions of synaptic sites and non-synaptic contacts with BCs in zebrafish bi-stratifying AC (e) and in rabbit A2 ACs (taken from ) (f). Note that synapses or non-synaptic contacts with AC and RGC are not included in (e), and inputs from CBC are not included in (f). g,h, Schematic diagrams of zebrafish (g) and mammalian (h) RBC pathways. Mouse A17 and rabbit A2 images are from and , respectively, used with permissions. Data for the distributions of synaptic sites within mammalian A2 ACs across the inner plexiform layer (IPL) are taken from.