Experience-dependent glial pruning of synaptic glomeruli during the critical period

Abstract

Critical periods are temporally-restricted, early-life windows when sensory experience remodels synaptic connectivity to optimize environmental input. In the Drosophila juvenile brain, critical period experience drives synapse elimination, which is transiently reversible. Within olfactory sensory neuron (OSN) classes synapsing onto single projection neurons extending to brain learning/memory centers, we find glia mediate experience-dependent pruning of OSN synaptic glomeruli downstream of critical period odorant exposure. We find glial projections infiltrate brain neuropil in response to critical period experience, and use Draper (MEGF10) engulfment receptors to prune synaptic glomeruli. Downstream, we find antagonistic Basket (JNK) and Puckered (DUSP) signaling is required for the experience-dependent translocation of activated Basket into glial nuclei. Dependent on this signaling, we find critical period experience drives expression of the F-actin linking signaling scaffold Cheerio (FLNA), which is absolutely essential for the synaptic glomeruli pruning. We find Cheerio mediates experience-dependent regulation of the glial F-actin cytoskeleton for critical period remodeling. These results define a sequential pathway for experience-dependent brain synaptic glomeruli pruning in a strictly-defined critical period; input experience drives neuropil infiltration of glial projections, Draper/MEGF10 receptors activate a Basket/JNK signaling cascade for transcriptional activation, and Cheerio/FLNA induction regulates the glial actin cytoskeleton to mediate targeted synapse phagocytosis.

Keywords: Drosophila; Brain circuit remodeling; Filamin; Glia; JNK signaling.

Figure 1

Glial infiltration in experience-dependent synaptic glomeruli pruning. (A) Experience-dependent pruning of olfactory sensory neuron (OSN) innervation during the early-life critical period. Low magnification images of central brain antennal lobe (AL) with anti-Cadherin-N (CadN, magenta) synaptic glomeruli labeling and ethyl butyrate (EB) responsive Or42a receptor driving a membrane marker (mCD8::GFP, green) in the Or42a OSNs innervating VM7 glomeruli. Animals exposed to mineral oil vehicle control (left) or EB odorant (right) for 24 h from 0–1 days post-eclosion (dpe). EB experience causes temporally-restricted pruning only in the critical period (arrows), with axon retraction to the AL boundary (asterisks). Abbreviations: antennal lobe (AL), mushroom body (MB), lateral horn (LH), and suboesophageal ganglion (SOG). Scale bar: 25 µm. (B) Critical period innervation pruning is dose-dependent. High magnification images of Or42a OSNs innervating the VM7 glomeruli following 24-h critical period exposure to the oil vehicle alone (left), 15% EB (middle), and 25% EB (right), showing the dose-dependent pruning. Scale bar: 10 µm. (C) Glial projections infiltrate the EB-responsive VM7 glomerulus in response to 24-h (0–1 dpe) critical period experience. Very high magnification images of glia (repo-Gal4 driven UAS-mCD8::GFP, green) following critical period exposure to oil vehicle (left) or 25% EB (right), with experience-dependent infiltration of glial projections specifically into the VM7 glomerulus (dotted outline). Scale bar: 5 µm.

Figure 2

Glial Draper required for experience-dependent critical period pruning. (A) Representative images of Or42a OSNs innervating the paired VM7 synaptic glomeruli with Or42a-Gal4 driving the membrane marker UAS-mCD8::GFP (Or42a > GFP, green) following 24-h critical period exposure to oil vehicle control (top) or 25% EB (bottom). Robust pruning of VM7 innervation occurs in the genetic background control (left, arrows) following 0–1 dpe EB odorant experience, but no pruning happens in the draper null mutant (draper^∆5, right). Scale bar: 10 µm. (B) Quantification of the innervation volume of Or42a OSNs in the VM7 glomeruli in all four genotypes, normalized to the oil vehicle control. Scatterplots show all data points and the mean ± SEM. Significance is indicated as not significant (NS; p > 0.05), or significant at p ≤ 0.0001 (****). (C) Glial-targeted draper RNAi prevents critical period experience-dependent pruning. Representative images of Or42a OSNs innervating VM7 synaptic glomeruli in glial attp2 TRiP transgenic driver controls (repo-Gal4/attP2; left) or glial draper RNAi (right) following 24-h critical period exposure to the oil vehicle (top) or 25% EB odorant (bottom). The robust pruning apparent in the controls (left, arrows) is prevented by glial-targeted draper RNAi. Scale bar: 10 µm. (D) Quantification of normalized innervation volume of Or42a OSNs in VM7 glomeruli in all four genotypes. Scatterplots show all data points and mean ± SEM. The significance is indicated as not significant (NS; p > 0.05), or significant at p ≤ 0.0001 (****).

Figure 3

Ensheathing glia mediate experience-dependent critical period pruning. (A) Representative images of the Or42a OSN innervation of the VM7 synaptic glomeruli (Or42a > GFP, green) with 24-h critical period exposure to oil vehicle (left) or EB (right). Robust innervation pruning occurs in Gal4 driver control (R56F03-Gal4/+), with oil vehicle (top left) and following EB experience (top right, arrows). Similar pruning occurs with both cortex glia (R54H02-Gal4) and astrocyte-like glia (R86E01-Gal4) draper RNAi (middle). In contrast, ensheathing glia (R56F03-Gal4) draper RNAi blocks experience-dependent pruning, with normal innervation in the oil vehicle (bottom left) and indistinguishable maintained innervation following 0–1 dpe EB odorant experience (bottom right). Scale bar: 10 µm. (B) Quantification of Or42a OSN innervation volume in VM7 glomeruli in all four genotypes, normalized to the driver oil vehicle control. For each glial class driver, paired 24-h critical period exposure from 0–1 dpe to oil vehicle (left) and 25% EB (right) is shown. Scatterplots show all the data points and mean ± SEM. The significance is indicated as not significant (NS; p > 0.05), or significant at p ≤ 0.0001 (****).

Figure 4

Glial JNK signaling drives experience-dependent critical period pruning. (A) Representative images of Or42a OSNs innervating VM7 olfactory synaptic glomeruli (Or42a > GFP, green) following 24-h critical period exposure to the oil vehicle control (top) or EB odorant (bottom) from 0–1 dpe. Striking experience-dependent pruning of the VM7 innervation occurs in the glial TRiP driver control (repo-Gal4/attP2) following critical period EB exposure (left; arrows), which is completely blocked by glial-targeted basket knockdown (repo-Gal4 driven basket RNAi, right). Scale bar: 10 µm. (B) Quantification of Or42a OSN innervation volume in the VM7 glomerulus in all four genotypes, normalized to the oil vehicle control. Scatterplots show all the data points and mean ± SEM. The significance is indicated as not significant (NS; p > 0.05), or significant at p ≤ 0.0001 (****). (C) Glial-targeted puckered phosphatase (puc) to block basket/JNK signaling prevents critical period experience-dependent pruning. The glial driver control (repo-Gal4/attP2, left) compared to glial-targeted puc overexpression (puc^OE, right) with the oil vehicle (top) and EB experience (bottom). Or42a OSN pruning in the VM7 glomeruli (left, arrows) is prevented by glial-targeted puc^OE to block glial basket/JNK signaling. Scale bar: 10 µm. (D) Normalized quantification of Or42a OSN innervation volume in VM7 glomeruli in all four genotypes. Scatterplots show all data points and the mean ± SEM. The significance is indicated as either not significant (NS; p > 0.05), or significant at p ≤ 0.0001 (****).

Figure 5

Critical period experience signals Basket/JNK glial nuclear translocation. (A) Odorant experience in the critical period drives the nuclear translocation of activated Basket/JNK in glia to modulate downstream transcriptional regulation. Representative high magnification images of glia immediately adjacent to the VM7 glomerulus, which are double-labeled for glial repo-Gal4 targeted UAS-basket::GFP (bsk::GFP, green; top) and anti-Repo to mark the glial nuclei (Repo, magenta; middle), with merged images shown below (white overlap, bottom). 24-h critical period exposure from 0–1 dpe to the oil vehicle alone (left column) and with the EB odorant (right). The signal colocalization in the glial nucleus (white; bottom) indicates bsk::GFP nuclear accumulation driven by EB experience in the critical period. Scale bar: 2 μm. (B) Quantification of the glial nuclear bsk::GFP fluorescence intensity normalized to the oil control, following 24-h critical period exposure from 0–1 dpe to the oil vehicle (left) or 25% EB (right). Scatterplots show all data points and mean ± SEM, with each data point representing the average from the 10 glial nuclei closest to the VM7 glomerulus. Significance is shown at p ≤ 0.0001 (****).

Figure 6

Glial JNK signaling upregulates the F-actin scaffold Cheerio/FLNA. (A) Critical period EB experience dramatically upregulates glial Cheerio/FLNA expression downstream of both Draper receptor and Basket signaling in glia. Representative high magnification images of a VM7 glomerulus (dotted outlines) labeled for anti-Cheerio (red) in the glial transgenic driver control (repo-Gal4/attP2, left), glial-targeted draper RNAi (middle), and glial-targeted basket RNAi (right) following the 24-h critical period exposure from 0–1 dpe to the oil vehicle alone (top) or with the EB odorant (bottom). Experience-dependent Cheerio expression upregulation within the VM7 synaptic glomerulus (arrows) completely depends on glial Draper and Basket signaling. Scale bar: 5 μm. (B) Normalized quantification of the Cheerio fluorescence intensity expression levels in the repo-Gal4/attP2 driver control (left) compared to glial-targeted draper RNAi (middle) and basket RNAi (right), with both oil vehicle control and EB odorant exposure from 0–1 dpe. Scatterplots show all data points and the mean ± SEM. The significance is indicated as not significant (NS; p > 0.05), or significant at p ≤ 0.0001 (****).

Figure 7

Cheerio remodels F-actin cytoskeleton for experience-dependent pruning. (A) Glial Cheerio is required for critical period experience-dependent pruning of olfactory sensory neuron innervation. Representative images of the Or42a OSNs innervating VM7 synaptic glomeruli (Or42a > GFP, green) following 24-h critical period exposure to the oil vehicle control (top) or EB odorant (bottom) from 0–1 dpe. Robust glial pruning of the VM7 innervation occurs in the glial transgenic driver control (repo-Gal4/attP2) following EB experience (left, arrows), which fails completely with repo-Gal4 glial-targeted cheerio RNAi (right). Scale bar: 10 μm. (B) Quantification of the Or42a OSN innervation volume in the VM7 glomeruli of all four genotypes, normalized to the oil vehicle control. Scatterplots show all data points and mean ± SEM. The significance is indicated as not significant (NS; p > 0.05), or significant at p ≤ 0.0001 (****). (C) High magnification images of glial repo-Gal4 driven F-actin marker LifeAct::GFP in VM7 glomeruli (dotted outline) following 24-h critical period exposure to oil vehicle (top left) or EB odorant (top right) from 0–1 dpe, showing the experience-dependent remodeling of the F-actin cytoskeleton. Glial-targeted draper and cheerio RNAi prevents experience-dependent F-actin induction in VM7 glomeruli (bottom images). Scale bar: 5 μm. (D) Normalized quantification of glial LifeAct::GFP fluorescence intensity levels in VM7 glomeruli with 24-h critical period exposure to the oil vehicle or 25% EB. Scatterplots show all data points and mean ± SEM. The significance following a one-way ANOVA is indicated at p ≤ 0.0001 (****).