Decreased expression of synapse-related genes and loss of synapses in major depressive disorder

Abstract

Previous imaging and postmortem studies have reported a lower brain volume and a smaller size and density of neurons in the dorsolateral prefrontal cortex (dlPFC) of subjects with major depressive disorder (MDD). These findings suggest that synapse number and function are decreased in the dlPFC of patients with MDD. However, there has been no direct evidence reported for synapse loss in MDD, and the gene expression alterations underlying these effects have not been identified. Here we use microarray gene profiling and electron microscopic stereology to reveal lower expression of synaptic-function–related genes (CALM2, SYN1, RAB3A, RAB4B and TUBB4) in the dlPFC of subjects with MDD and a corresponding lower number of synapses. We also identify a transcriptional repressor, GATA1, expression of which is higher in MDD and that, when expressed in PFC neurons, is sufficient to decrease the expression of synapse-related genes, cause loss of dendritic spines and dendrites, and produce depressive behavior in rat models of depression.

Figure 1

Synaptic function-related genes, the number of spine synapses and MAP2 expression are decreased in dlPFC of MDD subjects. In situ hybridization analysis of five of the dysregulated genes that were confirmed by PCR analysis, including (a) calmodulin 2, (b) synapsin I, (c) Rab3A, (d) Rab4B, and (e) beta-tubulin 4. Representative images of the control (top) and MDD (bottom) autoradiographs (scale bar, 5 mm), and quantitative analysis (bar graphs) are shown. Results represent means ± S.E.M.s (n = 5). *P < 0.05 compared to control (unpaired t-test). (f) Levels of MAP2 were quantified by western blot analysis. Representative blot and quantitative results are shown. Results represent the mean ± S.E.M. (n = 4). *P < 0.05 compared to control (unpaired t-test). (g) Representative images of immunohistochemistry of MAP2 in dlPFC of control (upper) and MDD subjects (lower) (scale bar, 2 mm). (h) High power representative electron micrograph. Arrowheads point to examples of spine synapses (scale bar, 500 nm). Synapses were quantified in layer II/III of dlPFC (PFC II/III), and the results represent the mean ± SD (n = 5), *P < 0.05 compared to control (unpaired t-test).

Figure 2

Identification of a transcriptional repressor of synapse-related genes. (a) Summary of transcription factor binding motif analysis. To determine the common promoter elements in the 5 synapse related genes confirmed by qPCR, overlapping binding motifs were identified by Transfac analysis. Eight elements including GATA1 are present in the promoter regions of all the synapse related genes of both human and rat. (b) Expression of GATA1 mRNA is increased in dlPFC of MDD subjects. Results from microarray and qPCR analysis of GATA1 are shown, and represent the mean fold change relative to matched controls (n = 5 microarray pairs, and n = 10 pairs for PCR). *P <0.05 compared to control (unpaired t-test). (c) Influence of chronic unpredictable stress (CUS, 35 d) on the expression of Gata1 in rat PFC was determined by in situ hybridization (representative image shown, scale bar, 1 mm). Increased expression of Gata1 was reversed by fluoxetine administration for the last 21 d of CUS (C+F). Fluoxetine (FLX) alone did not influence Gata1 expression. Results represent the mean ± S.E.M (n = 4); *P <0.05 compared to control (unpaired t-test). (d) Chromatin immunoprecipitation (ChIP) with GATA1 antiserum and PCR analysis of the putative GATA1 binding sites on the promoter regions of the synapse-related genes. Chromatin was immunoprecipitated using a GATA1 antibody and the presence of each gene was determined by PCR; lanes 1, no DNA; 2, horse serum ChIP (negative control); 3, GATA1 antibody ChIP; 4, total chromatin (positive control).

Figure 3

GATA1 over-expression in cortical neurons decreases Rab4b expression and reduces dendrite branching. (a) rAAV-GATA1-EGFP vector construction. ITR, inverted terminal repeats; CMV, cytomegalovirus promoter; hGH-polyA, human growth hormone polyA signal (b) Levels of Gata1 protein, determined by western blot, are increased in response to rAAV-GATA1 infection; note that the size is shifted due to expression of conjugated GATA1-EGFP. (c) rAAV-GATA1 expression decreases levels of Rab4bdetermined by qRT-PCR. Cells were transfected at DIV5 and extracted at DIV19. Results of qPCR analysis of Rab4b represent the mean ± S.E.M. (n = 4). *P <0.05 compared to vector alone (unpaired t-test). (d, e) Images of cortical neurons infected with control virus (left panels) or rAAV-GATA1-EGFP (right panels) and stained with antibodies to GFP (d, scale bar = 20 µm; e, scale bar = 10 µm). (f) Cells were infected with control virus (left panel) or rAAV-GATA1-EGFP (right panel) as described above but were stained for the dendritic marker MAP2 (scale bar = 20 µm), which was also examined by (g) western blot analysis (n = 3). *P <0.05 compared to vector alone (unpaired t-test). (h) Representative picture of Sholl analysis and quantitative results of the number of neuronal process intersections (scale bar = 20 µm). Results represent the mean ± S.E.M. (n = 7 for control vector, n = 4 for GATA1). *P <0.01 compared to vector alone (unpaired t-test).

Figure 4

Viral expression of GATA1 in rodent PFC causes depressive behavior. (a) Schematic diagram of the experimental schedule. (b) Representative low power (left panel) image of GFP immunohistochemistry (IHC) demonstrating the location of the viral infusion site in the medial PFC. The right panel shows the labeled neurons at higher magnification. (c,d) Influence of rAAV-control and rAAV-GATA1 on behavior in the forced swim test (FST, c) and learned helplessness (LH, d) paradigm. There was no effect on levels of locomotor activity (LA) (not shown). Results represent the mean ± S.E.M. (n = 9 for rAAV-control and n = 10 for rAAV-GATA1). * P < 0.05 compared to rAAV-control (t-test). (e) Schematic diagram of Gata1 shRNA knock down in the chronic unpredictable stress (CUS) paradigm. (f) Representative image of GFP immunohistochemistry demonstrating the location of viral infusion in the same region of the PFC as shown in b. (g) Influence of rAAV-ScrshRNA and rAAV-GATA1shRNA on sucrose preference in control and CUS exposed rats. Results represent the mean ± S.E.M. (Control: n = 6 for rAAV-ScrshRNA; n = 8 for rAAV-GATA1shRNA; CUS: n = 7 for rAAV-ScrshRNA; n = 8 for rAAV-GATA1shRNA). ** P < 0.05 compared to Control group (ANOVA and Fishers PLSD post-hoc analysis).