Translational control of FOG-2 expression in cardiomyocytes by microRNA-130a

Abstract

MicroRNAs are increasingly being recognized as regulators of embryonic development; however, relatively few microRNAs have been identified to regulate cardiac development. FOG-2 (also known as zfpm2) is a transcriptional co-factor that we have previously shown is critical for cardiac development. In this report, we demonstrate that FOG-2 expression is controlled at the translational level by microRNA-130a. We identified a conserved region in the FOG-2 3' untranslated region predicted to be a target for miR-130a. To test the functional significance of this site, we generated an expression construct containing the luciferase coding region fused with the 3' untranslated region of FOG-2 or a mutant version lacking this microRNA binding site. When these constructs were transfected into NIH 3T3 fibroblasts (which are known to express miR-130a), we observed a 3.3-fold increase in translational efficiency when the microRNA target site was disrupted. Moreover, knockdown of miR-130a in fibroblasts resulted in a 3.6-fold increase in translational efficiency. We also demonstrate that cardiomyocytes express miR-130a and can attenuate translation of mRNAs with a FOG-2 3' untranslated region. Finally, we generated transgenic mice with cardiomyocyte over-expression of miR-130a. In the hearts of these mice, FOG-2 protein levels were reduced by as much as 80%. Histological analysis of transgenic embryos revealed ventricular wall hypoplasia and ventricular septal defects, similar to that seen in FOG-2 deficient hearts. These results demonstrate the importance of miR-130a for the regulation of FOG-2 protein expression and suggest that miR-130a may also play a role in the regulation of cardiac development.

Figure 1. MicroRNA-130a is expressed in the heart.

In (A), microarray analysis of microRNAs predicted to target the 3′ UTR of FOG-2. Signal intensity was taken as the mean of 8 probe sets and normalized to U6snRNP. In (B), an alignment of the predicted miR-130a target site in the FOG-2 3′ UTR from several different species as predicted by MicroRNA.org. Shaded boxes indicate bases pairing with miR-130a. In (C), northern analysis of 100 µg total RNA from different adult mouse tissues using a probe specific for miR-130a. Ribosomal RNA is shown as a loading control below. In (D), quantitative RT-PCR performed on RNA from pooled embryonic hearts at days 11.5, 13.5, 15.5, as well as neonatal and adult hearts. Results are normalized to GAPDH expression levels (n = 6). ‘*’ indicates a statistically significant difference (p<0.02) compared to adult. In (E), western analysis of embryonic hearts during development using an anti-FOG-2 antibody (top panel) or Lamin B (as a control for equal protein loading, bottom panel). In (F), graph of relative levels of miR-130a compared to FOG-2 protein levels during cardiac development.

Figure 2. The 3′ UTR of FOG-2 inhibits mRNA translation.

In (A), a schematic of the expression vector pRL and its derivative containing the FOG-2 3′UTR in place of the SV40 polyadenylation sequence. In (B), NIH 3T3 fibroblasts were transfected with the constructs shown above along with pVRβgal. Forty-eight hours post transfection, cell lysates were assayed for luciferase activity and normalized to β-galactosidase activity. Results reported are the mean±S.E.M. (n = 11). In (C), northern analysis of 20 µg total RNA from transfected fibroblasts from (B) using a probe specific to the luciferase coding region (above) or β-galactosidase (below). ‘*’ indicates a statistically significant difference (p<0.0001).

Figure 3. The miR-130a target site in the FOG-2 3′UTR is required for translational repression.

In (A), a schematic of the constructs used to evaluate the function of the conserved region of the FOG-2 3′ UTR. In (B), NIH 3T3 fibroblasts were transfected with the constructs shown above along with pVRβgal. Forty-eight hours post transfection, cell lysates were assayed for luciferase activity and normalized to β-galactosidase activity. Results reported are the mean±S.E.M. (n = 8). In (C), northern analysis of 10 µg total RNA from transfected fibroblasts from (B) using a probe specific to the luciferase coding region (above) or β-galactosidase (below). In (D), primary neonatal cardiomyocytes were transfected with pVRβgal and a luciferase reporter containing the 3′UTR of FOG-2 or the ΔA 3′UTR mutation. Forty-eight hours after transfection, cells were assayed for luciferase and β-galactosidase activity. Results are reported as the mean normalized luciferase activity±S.E.M. (n = 20). In (E), NIH 3T3 fibroblasts were transfected with a luciferase reporter containing the 3′ UTR of FOG-2 (columns 1–3) or the ΔA mutation (columns 4 & 5) in the absence (columns 1 & 4) or presence of increasing amounts of 2′-O-methyl oligonucleotide (columns 2, 3, 5). Forty-eight hours post transfection, cell lysates were assayed for luciferase activity and normalized to β-galactosidase activity. Results reported are the mean±S.E.M. (n = 7). ‘*’ indicates a statistically significant difference (p<0.01 )

Figure 4. Overexpression of miR-130a inhibits translation of mRNA containing the 3′UTR of FOG-2.

In (A), northern analysis using 20 µg total RNA from COS-7 or NIH 3T3 cell lines with a probe specific for miR-130a. Ribosomal RNA is shown below as a loading control. In (B), COS-7 fibroblasts were transfected with a luciferase reporter containing the 3′ UTR of FOG-2 (column 1) or the ΔA mutation (column 2) along with pVRβgal. Forty-eight hours post transfection, cells were assayed for luciferase and β-galactosidase activity. Results report the mean normalized luciferase activity±S.E.M. (n = 12). Shown in (C) is a schematic of the miR-130a expression construct. In (D), northern analysis using a probe specific for miR-130a and 20 µg total RNA from COS-7 fibroblasts transfected with increasing amounts of the miR-130a expression construct shown in (C). Ribosomal RNA is shown below as a loading control. In (E), COS-7 fibroblasts were transfected with a luciferase reporter containing the 3′ UTR of FOG-2 (columns 1 & 2) or the ΔA mutation (columns 3 & 4) in the absence (columns 1 & 3) or presence (columns 2 & 4) of the miR-130a expression construct. Forty-eight hours post transfection, cell were assayed for luciferase activity. Results reported are the mean±S.E.M. (n = 12); ‘*’ indicates statistically significant decrease in activity (p<0.001).

Figure 5. Cardiac overexpression of miR-130a results in decreased FOG-2 expression and a thin ventricular myocardial wall.

In (A), expression of miR-130a as determined by quantitative RT-PCR on four wild type (WT) and four transgenic hearts (TG-1 thru 4) at embryonic day 13.5. Results represent the mean±S.E.M. of three separate experiments performed in duplicate. ‘*’ indicates statistically significant difference from wild-type, p<0.002. In (B), western analysis of wild type (WT) and transgenic hearts (TG-5 thru 8) using an anti-FOG-2 antibody. Western analysis of Lamin B was used as a control for equal protein loading. Quantitation of this blot is shown in (C), with wild type levels of FOG-2 set to 100%. In (D - G), transverse sections of embryonic day 14.5 hearts from wild type (D, F) and β-MHC-miR-130a transgenics (E, G) stained with hematoxylin and eosin. Note the ventricular septal defect (arrow, E) and the thin compact zone of ventricular myocardium (arrowheads, F compared to G) seen in the transgenic embryos. In (H), echocardiographic determination of left ventricular fractional shortening (left panel) and left ventricular end diastolic diameter (right panel) in embryonic day 14.5 transgenic and non-transgenic embryos. ‘*’ indicates a statistically significant difference (p<0.0005).