Neuron-glia interactions through the Heartless FGF receptor signaling pathway mediate morphogenesis of Drosophila astrocytes

Abstract

Astrocytes are critically important for neuronal circuit assembly and function. Mammalian protoplasmic astrocytes develop a dense ramified meshwork of cellular processes to form intimate contacts with neuronal cell bodies, neurites, and synapses. This close neuron-glia morphological relationship is essential for astrocyte function, but it remains unclear how astrocytes establish their intricate morphology, organize spatial domains, and associate with neurons and synapses in vivo. Here we characterize a Drosophila glial subtype that shows striking morphological and functional similarities to mammalian astrocytes. We demonstrate that the Fibroblast growth factor (FGF) receptor Heartless autonomously controls astrocyte membrane growth, and the FGFs Pyramus and Thisbe direct astrocyte processes to ramify specifically in CNS synaptic regions. We further show that the shape and size of individual astrocytes are dynamically sculpted through inhibitory or competitive astrocyte-astrocyte interactions and Heartless FGF signaling. Our data identify FGF signaling through Heartless as a key regulator of astrocyte morphological elaboration in vivo.

Figure 1. Drosophila astrocytes are morphologically similar to mammalian protoplasmic astrocytes

(A–I) Confocal analysis of L3 larval central nervous systems. (A, B) Colabeling of astrocytic nuclei using alrm-Gal4 UAS-lacZ-NLS (green) together with α-HRP for neuronal membranes (red) and α-Brp for the synaptic neuropil (blue). Projection of a confocal stack (A) and mid VNC orthogonal cross section (B) showing the nuclear positions of astrocytes around the neuropil. (C) alrm-Gal4 UAS-CD8-GFP expression (green) labels the dense meshwork of fine processes of astrocytes in the synaptic neuropil. Single confocal section in the VNC (C′) and mid VNC orthogonal cross section (C). (D–F) Z-projections of confocal stacks of CD8-GFP marked MARCM clones labeling astrocytes (green). All astrocytes are labeled with α-Gat antibody (red). Arrowhead in (F) shows a contralateral projection of an astrocyte. (G-I) Two color flip out strategy using alrm-Gal4 UAS-CD8>GFP>RFP repoFLP labeling astrocytes with GFP (green) or RFP (red) reveals their tiling behavior. (G′–I′) show higher magnification views of the boxed area in (G–H). Scale bars represent 50μm in (A) and 25μm in (B–I). See also Figure S1.

Figure 2. Astrocytes closely associate with synapses

(A, B, E, F) Confocal analysis of L3 larval VNCs. (A, B) Astrocytic membranes are labeled with α-Gat antibody (green), synaptic profiles with α-Brp (red). Higher magnification view of the boxed area in (A–A″) is shown in (B–B″), showing close apposition of astrocytic membranes and Brp⁺ synaptic puncta. (C, C′) TEM image of a section of the neuropil in the ventral nerve cord in a L3 larva. (C) Tracings of synapses (green) and putative astrocyte processes (red) of the original image (C′). (D) Quantification of the distance from a synapse to the next glial process. Scatterplot with mean and SD representing error bars are shown (N=498). (E) α-Gat (blue) colabels alrm-Gal4 UAS-CD8-GFP (green) positive astrocytes and the synaptic neuropil is labeled by α-Brp (red). (F) Knockdown of Gat in astrocytes with alrm-Gal4 UAS-CD8-GFP UAS-gat^RNAi shows the specificity of the α-Gat antibody. (G) Western blot analysis of Gat knockdown with alrm-Gal4 by RNAi in L3 larval CNS extracts. GD: UAS-gat-RNAi^GD13359, KK: UAS-gat-RNAi^KK106638, JF: UAS-gat-RNAi^JF03358 (H) Quantification of Gat levels in western blots normalized to LaminC signal and to the control lane (N=3). (I) Quantification of locomotion defects in alrm-Gal4 UAS-CD8-GFP UAS-gat^RNAi animals compared to control animals (alrm-Gal4 UAS-CD8-GFP/+). control: N=11, gat^RNAi: GD: N=20, KK: N=10, JF: N=10, ***p<0.0001. Scale bars represent 25μm in (A, E), 2μm in (B) and 1μm in (C). See also Figure S2, Movies 1–4, and Movie 8.

Figure 3. Htl FGF signaling controls infiltration of astrocyte processes into the neuropil

(A) Schematic view of the embryonic CNS showing the approximate positions of confocal images shown in (B-J) with longitudinal plane of section shown in (A, B–J, B′–J′) and a cross section in (A′, B″–J″, B‴–J‴). (B–J) Astrocytes are labeled by α-Gat antibody (red) and the neuropil by α-Brp (green). (B–E) Wild type progression of astrocyte infiltration of the neuropil during the last hours of embryogenesis. Wild type embryos hatch at ~21h of development. Control (F), htl^AB42 (G), Df(2R)BSC25 (H), pyr^S0439/ pyr^S3547 (I) and Df(2R)ths²³⁸ mutant embryos at the end of embryogenesis. Scale bars represent 10μm. (K) Quantification of the infiltration phenotype using an infiltration score (IF) from 0–5. (L) Quantification of the number of ventral astrocytes (VC) per segment. control: N=25, htl^AB42: N=36, Df(2R)BSC25: N=34, pyr^S0439/ pyr^S3547: N=13, pyr¹⁸: N=13, ths⁷⁵⁹: N=13 and Df(2R)ths²³⁸: N=19. See also Movies 5–7.

Figure 4. The FGFR Htl acts cell autonomously in astrocytes to control infiltration behavior and domain size

(A–D) confocal images of late embryonic VNCs in single longitudinal sections (A–D, A′–D′) and orthogonal cross sections (A″–D″, A‴–D‴) with astrocytes labeled with α-Gat antibody (red) and the neuropil with α-Brp (green). (B) Expression P35 in astrocytes does not rescue astrocyte infiltration defects in htl^AB42 mutant embryos. Expression of wild type Htl (C) or constitutive active λ-Htl (D) in an htl^AB42 mutant background is able to rescue astrocytic infiltration. Scale bar represents 10μm (A–D). (E) Quantification of infiltration scores (IF). (F) Quantification of the number of ventral astrocytic cells (VC) per segment. control: N=25, htl^AB42: N=36, htl^AB42 alrm-Gal4 UAS-P35: N=16, htl^AB42 alrm-Gal4 UAS-htl: N=13, alrm-Gal4 UAS-λ-htl: N=35. ***p<0.001, ns: not significant with p>0.05. (G–I) MARCM analysis of htl and dof function in the L3 larval VNC. Cross sectional 3D projections are shown. Clones are labeled with CD8-GFP (green) and all astrocytes with α-Gat antibody (red). While control clones show normal infiltration behavior (G) Astrocytes mutant for htl^AB42 (H) or the FGFR adapter dof¹ (I) show severely reduced infiltration and cell domain size. Scale bar represents 25μm (G–I). (J) Quantification of infiltration/ cell size defects shown in (G–I). control: N=84, htl^AB42: N=24, dof¹: N=12, ***p<0.001. Clones in thoracic and abdominal segments of the VNC were analyzed. (K) Quantification of astrocyte cell domain volume after clonal manipulation of Htl signaling strength using the alrm>QF>Gal4 repoFLP system driving clonal expression of either UAS-htl^RNAi or UAS-λ-htl. control: N=20, htl^RNAi: N=22, λ-htl: N=27, ***p<0.001. See also Figure S4. Note that in (K) only clones in abdominal segments were analyzed and that average domain size in wild type is smaller in abdominal segments compared to thoracic segments (Figure S1B).

Figure 5. Interactions among astrocytes shape their domain size.<

br>(A–D) Image projections of confocal stacks of L3 VNCs labeled with α-Brp (blue), α-Gat (red) and/or CD8-GFP (green). (A) Wild type and (B) control MARCM analysis animals show the full complement of Gat⁺ astrocytes (red). GFP⁺ MARCM clones (green) in (B) demonstrate the wild type morphology of astrocytes. Astrocytic Reaper expression (alrm-Gal4 UAS-CD8GFP UAS-reaper) induces widespread ablation of astrocytes (C, D). Surviving astrocytes can exhibit striking cell growth (C) while some survivors show less growth and clearly aberrant morphology potentially due to effects of Reaper still being expressed (D). Note that low level expression of alrm-Gal4 UAS-CD8-GFP in ensheathing and nerve root glia seems unaffected (asterisks (C, D)). Scale bar represents 25μm (A–D). (E) Quantification of projected area of astrocytes of control MARCM clones and surviving cells in alrm-Gal4 UAS-CD8-GFP UAS-reaper ablations. control: N=54, reaper N=29, ***p<0.001 and the associated locomotion defects in L3 larvae (F), control: N=22, reaper: N=33, ***p<0.001. See also Figure S5.

Figure 6. FGFs Pyr and Ths are likely secreted from neurons to control astrocytes infiltration

(A–C) Confocal images of late embryonic VNCs in single longitudinal sections (A–C, A′–C′, F–G) and cross sections (A″–C″, A‴–C‴). Gal4 expression patterns are highlighted by GFP expression (green), in (A) and (F–I), astrocytes are labeled with α-Gat (red) and the neuropil with α-Brp in green (B, C) or in blue (F, G). (A) Expression pattern of OK371-Gal4 (glutamateric neurons) in a Df(2R)BSC25 mutant background (green). (B, C) Expression of either Pyr or Ths in glutamateric neurons is able to rescue astrocytic infiltration in Df(2R)BSC25 mutants. (D) Quantification of infiltration phenotypes. (E) Quantification of the number of ventral astrocytes per segment. Control: N=25, Df(2R)BSC25: N=34, Df(2R)BSC25 elav-Gal4 UAS-pyr: N=13, Df(2R)BSC25 elav-Gal4 UAS-ths: N=10, Df(2R)BSC25 Ok371-Gal4 UAS-pyr: N=12, Df(2R)BSC25 Ok371-Gal4 UAS-ths: N=19, ***p<0.001, ns: not significant with p>0.05. (F–I) Expression of Pyr or Ths in an extremely small number of neurons using the clonal RN2-FLP system in a Df(2R)BSC25 mutant background (green). In (F, G) single section confocal images are shown for the red (Gat) and blue (Brp) channels while the green channel (RN2-FLP neurons) shows z-projections of the image stacks to demonstrate the position of expressing neurons. (H, I) cross sectional 3D projections. Scale bars represent 10μm. See also Figure S6.

Figure 7. Ectopic expression of Pyr and Ths<

br>(A–F) Confocal images of late embryonic VNCs in single longitudinal sections (A–D, A′–D′) and cross sections (A″–D″, B‴-D‴, E, F). Expression pattern of Mz97-Gal4 is highlighted by GFP expression (green in (A)), astrocytes are labeled with α-Gat (red) and the neuropil with α-Brp (green in B–F). (A) Expression of Mz97-Gal4 UAS-actin5c-GFP (green) in a Df(2R)BSC25 mutant background in subperineurial (arrowheads) and nerve root glia (asterisks). Ectopic expression of Pyr and Ths with Mz97-Gal4 can partially rescue astrocyte infiltration into the neuropil in Df(2R)BSC25 mutants (C, D, G); however, ectopic recruitment of astrocyte processes (arrowheads) or lateral displacements of cell bodies (asterisks) were also observed (E, F). Scale bars represent 10μm. (G) Quantification of infiltration phenotypes. (H) Quantification of the number of ventral astrocytes per segment. Control: N=25, Df(2R)BSC25: N=34, Df(2R)BSC25 Mz97-Gal4 UAS-pyr: N=18, Df(2R)BSC25 Mz97-Gal4 UAS-ths: N=17. Quantification of the number of all ectopic cell bodies (I) or the number of laterally (J) or dorsally (K) displaced cell bodies per segment upon ectopic expression of FGFs. Control: N=25, Df(2R)BSC25 Mz97-Gal4 UAS-pyr: N=13, Df(2R)BSC25 Mz97-Gal4 UAS-ths: N=17. ***p<0.001, ns: not significant with p>0.05. See also Figure S7.