HuD promotes BDNF expression in brain neurons via selective stabilization of the BDNF long 3'UTR mRNA

Abstract

Complex regulation of brain-derived neurotrophic factor (BDNF) governs its intricate functions in brain development and neuronal plasticity. Besides tight transcriptional control from multiple distinct promoters, alternative 3'end processing of the BDNF transcripts generates either a long or a short 3'untranslated region (3'UTR). Previous reports indicate that distinct RNA sequence in the BDNF 3'UTRs differentially regulates BDNF production in the brain to accommodate neuronal activity changes, conceivably through differential interactions with undefined trans-acting factors that regulate stability and translation of these BDNF mRNA isoforms. In this study, we report that the neuronal RNA-binding protein (RBP) HuD interacts with a highly conserved AU-rich element (ARE) specifically located in the BDNF long 3'UTR. Such interaction is necessary and sufficient for selective stabilization of mRNAs that contain the BDNF long 3'UTR in vitro and in vivo. Moreover, in a HuD transgenic mouse model, the BDNF long 3'UTR mRNA is increased in the hippocampal dentate granule cells (DGCs), leading to elevated expression of BDNF protein that is transported and stored in the mossy fiber (MF) terminals. Our results identify HuD as the first trans-acting factor that enhances BDNF expression specifically through the long 3'UTR and a novel mechanism that regulates BDNF protein production in selected neuronal populations by HuD abundance.

Figure 1. HuD enhances luciferase reporter expression through an ARE in the BDNF long 3′UTR.

(A) A highly conserved cluster of Class I ARE in the BDNF long 3′UTR, with a consensus core sequence of AUUUA flanked by symmetric A or U (underlined). Triangles indicate alternative polyadenylation sites in the BDNF primary transcript. Primers used for RT-PCR to detect reporter mRNAs are illustrated underneath. (B) RT-PCR using multiple primers illustrated in (A) confirms expression of the expected RNA sequence from each transfected reporter construct. (C) Immunoblot (IB) showing expression of myc-HuD in the input (Inp) of transfected CAD cells and successful immunoprecipitation (IP) of myc-HuD. Two different anti-myc antibodies were used for IP and IB. (D) CLIP-qRT-PCR quantification of reporter mRNAs co-immunoprecipitated with HuD relative to the corresponding mRNA levels in the input. * indicates P<0.05 by Student's t-test (n = 3). Due to the presence of endogenous BDNF mRNA, primers specific for the luciferase coding region were used to detect reporter mRNAs. BDNF long 3′UTR reporter mRNA is preferentially enriched over short 3′UTR mRNA in immunoprecipitated HuD complex. Deletion of the ARE in the long 3′UTR significantly reduced the association or reporter mRNA with HuD.

Figure 2. HuD selectively enhances expression of the luciferase reporter that harbors the BDNF long 3′UTR in an ARE-dependent manner.

CAD cells were cotransfected by 200 ng of reporter construct together with either pcDNA-HuD (HuD) or the pcDNA parental vector (PC). 20 ng of pRL-CMV Renilla luciferase construct was included in each transfection. Twenty-four hours after transfection, cells were harvested and subjected to dual luciferase reporter assay or mRNA extraction followed by DNAase-treatment and RT-qPCR. (A) myc-HuD enhances expression of the luciferase reporter that carries the BDNF long 3′UTR but not the short 3′UTR. (B) myc-HuD reduces decay of the BDNF long 3′UTR reporter mRNA in co-transfected CAD cells in which transcription is inhibited by actinomycin D. (C) Loss of the ARE in the BDNF long 3′UTR abolished the repose to HuD-dependent enhancement of reporter expression. (D) HuD regulates reporter mRNA expression mediated by the ARE in the BDNF long 3′UTR. * indicates P<0.05 by Student's t-test (n = 3).

Figure 3. Binding of HuD to the ARE in the BDNF-long 3′UTR increases the stability of the mRNA.

(A) Specific binding of HuD to the ARE in BDNF-long 3′UTR was demonstrated by REMSA using recombinant proteins and radiolabeled RNA along with a 10-fold molar excess of cold ARE competitor. (B) In vitro decay assay of capped and polyadenylated RNA containing the BDNF-ARE with left lane showing RNA molecular weight markers. Analysis of the rate of decay in three independent experiment revealed that the mRNA is stabilized in the presence of HuD. Half-life for GST-treated mRNA is 7.0±0.90 min, and for GST-HuD-treated mRNA is 12.0±1.0 min. ** indicates p<0.05 by Two way ANOVA with a quantitative factor (n = 3 separate experiments).

Figure 4. HuD knockdown reduced the levels of endogenous BDNF long 3′UTR mRNA.

(A) siRNA knockdown of HuD in transfected CAD cells measured by qRT-PCR using a HuD-specific primer flanking the target site by the siRNA. (B) Reduction of endogenous BDNF long 3′UTR mRNA in CAD cells measured by qRT-PCR as a result of HuD knockdown. For (A) and (B), results were derived from 3 independent experiments (n = 3), * indicates P<0.05. (C) Representative confocal images of L-BDNF FISH (red) in E17 hippocampal neurons transfected with either pEGFP control vector or pEGFP-shHuD plasmid. The transfected cells was marked by the green fluorescence and the number of FISH grains were counted in the cell bodies and processes (n = 6 for each condition) and graphically displayed in (D). Arrows mark the FISH grains in the processes. Note that the number of ISH grains in the shHuD- treated cells decreased throughout the soma and neurite relative to control GFP-vector treated cells.

Figure 5. Forced expression of exogenous HuD selectively enhanced expression of BDNF long 3′UTR mRNA in primary cultured neurons.

E17 cortical neurons were cultured for 2 days and then infected with HSV-HuD or HSV-lacZ virus. Following 3 days in culture, the levels of long 3′UTR BDNF mRNA and pan BDNF mRNA were determined by qRT-PCR using primers specific in the long 3′UTR (A) and primers in the coding region that detects the pan BDNF mRNA (B). *p<0.05 (Student's t-test, n = 4).

Figure 6. A HuD transgene enhances expression of the BDNF long 3′UTR mRNA in hippocampal DGCs.

(A) Representative FISH images of fluorescent in situ hybridization of BDNF long 3′UTR mRNA in the neuronal soma layers of hippocampal DG, CA3 and CA1 of HuD-Tg and WT littermates (scale bar = 75 µm). (B) Quantification of FISH intensity in four pairs of HuD-Tg and WT controls. ** p<0.01 (Student's t-test, n = 4).

Figure 7. The HuD transgene enhances BDNF protein levels in the hippocampal MF pathway.

(A) Representative images of BDNF immunofluorescence (green) in the hippocampal hilus, CA3 and CA1 regions in HuD-Tg and WT littermates. DAPI stained nuclei (blue) mark the aforementioned principle neuron layers. Asterisks indicate enhanced BDNF signals in the long processes of adult neural stem cells in the SGZ. (B) Quantification of BDNF immunofluorescence in the hilus, CA3 strata lucidum (SL) and strata radiatum (SR) and CA1 stratum radiatum (SR) are graphically displayed. *p<0.05 (Student's t-test, n = 3).