Combinatorial action of miRNAs regulates transcriptional and post-transcriptional gene silencing following in vivo PNS injury

Abstract

Injury response in the peripheral nervous system (PNS) is characterized by rapid alterations in the genetic program of Schwann cells. However, the epigenetic mechanisms modulating these changes remain elusive. Here we show that sciatic nerve injury in mice induces a cohort of 22 miRNAs, which coordinate Schwann cell differentiation and dedifferentiation through a combinatorial modulation of their positive and negative gene regulators. These miRNAs and their targeted mRNAs form functional complexes with the Argonaute-2 protein to mediate post-transcriptional gene silencing. MiR-138 and miR-709 show the highest affinity amongst the cohort, for binding and regulation of Egr2, Sox-2 and c-Jun expression following injury. Moreover, miR-709 participates in the formation of epigenetic silencing complexes with H3K27me3 and Argonaute-1 to induce transcriptional gene silencing of the Egr2 promoter. Collectively, we identified a discrete cohort of miRNAs as the central epigenetic regulators of the transition between differentiation and dedifferentiation during the acute phase of PNS injury.

Figure 1. Protein expression changes and miRNA expression profile following in vivo sciatic nerve injury.

Protein expression analysis reveals a robust reduction in pro-myelination and upregulation of anti-myelination factors. All experiments were repeated three times unless otherwise stated. (A). Uninjured and distal segments of axotomized sciatic nerves at 48 hours post injury (PI) (n = 4) were lysed in SDS buffer and western blots were performed for Egr2 (63 kDa), C-Jun (43 kDa), Sox-2 (35 kDa), ID-2 (15 kDa), Nanog (34–40 kDa), QKI-6 (38 kDa), P75^NTR (75 kDa), beta-actin (42 kDa) and Histone H3 (17 KDa). (B). Relative protein levels normalized to beta-actin were plotted to demonstrate the differential expression of the pro-myelination and anti-myelination factors in injury. Statistical significance was calculated with a Student’s t-test (**: p<0.001). (C). Microarray for miRNAs (version 9.2) was performed using total RNA from 15 control and 15 axotomized mouse sciatic nerves at 6 hours and 24 hours post-injury (PI), by Exiqon (Vedbaek, Denmark). The array was repeated twice and Log2 median ratios of the miRNAs expressed in 24h-injured nerve compared to the control were plotted and the standard error was calculated.

Figure 2. miRNA-mRNA target prediction and evaluation.

Putative miRNA binding sites detected by RNA 22 are represented on individual mRNAs (not to scale) as squares (repressed in injury) or circles (up regulated in injury) with the maximum folding energy shown below. Underlined areas indicate regions used in Luciferase assays.

Figure 3. miR-138 and miR-709 bind and regulate Sox-2, c-Jun and Egr2.

Sox-2, c-Jun and Egr2 transcripts containing multiple target sites for both miRNAs 138 and 709 were cloned into the 3′-UTR of luciferase gene in the pmiR-report vector. Cos-7 cells were co-transfected with miR-target vector and pmir-Report β-Gal vector as a control for transfection efficiency. Cell lysates were assayed 24 h post transfection for luciferase and β-Gal expression and β-Gal is used to normalize for differences in transfection efficiency. Sox-2, which lacks highly accessible sites for miR-138 and miR-709 show comparable expression to control (A & D, first two bars), while c-Jun (C, first two bars) and Egr2 (B & E, first two bars) that have multiple highly accessible sites for both miR-138 and 709 (Table 1 & Table S2) are highly de-repressed (c-Jun) or highly repressed (Egr2) by endogenous miRNAs. When miRNAs were overexpressed in molar excess through transfection, then Sox-2, c-Jun and Egr2 constructs were significantly repressed (A - E, last three bars). Luciferase assays with the available mouse anti-miRs for miR-138 and 709 again revealed significant derepression by individual anti-miRs for Sox-2 and Egr2 (D & E,). The combinatorial effect of both miRNAs is more significant for all three genes (A-E, last bar). ** denotes statistical significance (p<0.005) as calculated by Student’s t-test.

Figure 4. miRNAs induce post-transcriptional gene silencing through association with Ago-2 in functional complexes.

(A). Protein expression of Ago-1, Ago-2 and Dicer in sciatic nerves before and after nerve injury to confirm the expression of the miRNA processing machinery proteins. Actin was used as a loading control. (B) Cytoplasmic lysates isolated from control sciatic nerves and injured distal segments (10 nerves each) were immunoprecipitated with Ago-2 antibody (Cell Signaling, USA) or IgG control. A portion (1/3^rd) of the sample was used for each of the analysis and the experiment was repeated twice. Input, No-Antibody (No AB) and Ago-2 immunoprecipitated protein was analyzed by western blotting with Ago-2 antibody, which shows enrichment of Ago-2 in the 24 hour post-injury samples. (C). For RNA-IPs (RIPs), mRNAs that were co-immunoprecipitated with Ago-2 in vivo, were reverse transcribed using oligo-dT primer and genes of interest were PCR amplified using gene-specific primers (Krox-20  =  1274 bp, C-Jun  =  689 bp, Nanog  =  753 bp, QKI-6  =  1345 bp, Sox-2  =  958 bp and ID-2  =  588 bp). (D). microRNAs that were co-immunoprecipitated with Ago-2 in complex with their targeted mRNAs, were reverse-transcribed with microRNA specific RT-primers using Multiscribe RT kit. Ago-2 associated microRNAs were detected by real time qPCR with miRNA specific Taqman probe/primer sets. Data were normalized to input and an internal control. Fold difference (2^-ΔΔCT) in the association of individual microRNAs with Ago-2 protein between injured and control nerves was plotted as log 2 median ratio and error is expressed as standard deviation.

Figure 5. miRNAs mediate transcriptional gene silencing of Egr2.

(A). Real-time qRT-PCR of Egr2 transcripts normalized to GAPDH control 6, 24 and 48 hours post-injury as compared to control uninjured nerves. Fold difference (2^-ΔΔCT) between injured and control nerves is plotted and error is expressed as standard deviation. Inset: Egr2 mRNA expression at 24 hours and 48 hours after injury as compared to Egr2 mRNA expression in uninjured nerves. Egr2 mRNA expression is completely inhibited 48 hours post-injury. Beta-actin was used to show equal loading and amplification. (B). Nuclear “run-on” experiment for nascent Egr2 mRNA transcription in rat Schwann cells transfected with control or miR-709 duplexes as measured by quantitative RT-PCR and normalized to GAPDH mRNA transcription levels. The experiment was repeated three times, the data were normalized to GAPDH and fold difference (2^-ΔΔCT), between injured and control nerves was plotted as a log-2 median ratio. Error is expressed as standard deviation, (**: p<0.005). (C). Egr2 protein expression in Schwann cells transfected with miR-709, antimiR-138 or non-targeting control miRNA and compared with non-transfected Schwann cells. (D). Methylation PCR analysis (SA Biosciences) of the CpG islands of the proximal Egr-2 promoter from control and injured sciatic nerves (24h-post injury). The relative percentages of hypermethylated (HM) and unmethylated (UM) fractions were calculated by comparing the amount in each digest with that of a mock (no enzyme added) digestion. (E). ChIP assays, using antibody to H3K27Me3 or no antibody (No Ab) controls were performed in sciatic nerves isolated from control and axotomized mice 48 hours post-injury. Western blot of input, no antibody control (No Ab) and H3K27Me3-ChIP was performed with antibodies against Ago-1 and H3K27Me3. This showed that Ago-1 is enriched in H3K27me3 silencing complexes following in vivo peripheral nerve injury. (F). Real-time quantitative PCR to assess the presence of the MSE region of the Egr2 promoter (left bars) and miR-709 (right bars) in the H3K27me3 immunoprecipitated chromatin. Lysates pre-treated with RNase H were immunoprecipitated to confirm RNA-DNA interaction. Values for the MSE and miR-709 were normalized to input DNA and miRNA respectively. The fold difference (2^-ΔΔCT) in the association of MSE and miR-709 with H3K27Me3 complex between injured and control nerves, was plotted as a log-2 median ratio and the error is expressed as standard deviation. (**: p<0.001). Note the significant increase in the association of miR-709 and MSE with H3K27me3 silencing complexes following in vivo nerve injury.

Figure 6. Schematic representation of our proposed model regarding the existence of a miRNA code, which regulates the transition between differentiation and dedifferentiation following in vivo PNS injury.

The synchronous and concerted binding of miRNAs generates a unique code, which is dynamically regulated and affects the expression of the genes that modulate injury response in the PNS (e.g. c-Jun, Sox-2, Egr2).