DENV up-regulates the HMG-CoA reductase activity through the impairment of AMPK phosphorylation: A potential antiviral target

Abstract

Dengue is the most common mosquito-borne viral disease in humans. Changes of lipid-related metabolites in endoplasmic reticulum of dengue virus (DENV) infected cells have been associated with replicative complexes formation. Previously, we reported that DENV infection inhibits HMGCR phosphorylation generating a cholesterol-enriched cellular environment in order to favor viral replication. In this work, using enzymatic assays, ELISA, and WB we found a significant higher activity of HMGCR in DENV infected cells, associated with the inactivation of AMPK. AMPK activation by metformin declined the HMGCR activity suggesting that AMPK inactivation mediates the enhanced activity of HMGCR. A reduction on AMPK phosphorylation activity was observed in DENV infected cells at 12 and 24 hpi. HMGCR and cholesterol co-localized with viral proteins NS3, NS4A and E, suggesting a role for HMGCR and AMPK activity in the formation of DENV replicative complexes. Furthermore, metformin and lovastatin (HMGCR inhibitor) altered this co-localization as well as replicative complexes formation supporting that active HMGCR is required for replicative complexes formation. In agreement, metformin prompted a significant dose-dependent antiviral effect in DENV infected cells, while compound C (AMPK inhibitor) augmented the viral genome copies and the percentage of infected cells. The PP2A activity, the main modulating phosphatase of HMGCR, was not affected by DENV infection. These data demonstrate that the elevated activity of HMGCR observed in DENV infected cells is mediated through AMPK inhibition and not by increase in PP2A activity. Interestingly, the inhibition of this phosphatase showed an antiviral effect in an HMGCR-independent manner. These results suggest that DENV infection increases HMGCR activity through AMPK inactivation leading to higher cholesterol levels in endoplasmic reticulum necessary for replicative complexes formation. This work provides new information about the mechanisms involved in host lipid metabolism during DENV replicative cycle and identifies new potential antiviral targets for DENV replication.

Fig 1. DENV infection down-regulates AMPK activity.

In A, The AMPK activity, depicted as phosphorylation levels at Thr-172, was evaluated in Huh7 cells infected with DENV 2/4 (MOI 3) at 1, 12, and 24 hpi by ELISA, and NS3 viral protein levels (A, lower panel) were determined as infection test. AMPK activity was expressed as U/mL. *p<0.05 compared to mock infected cells (0 hpi). Data are means ± standard error (S.E) of n = 3 independent experiments realized by duplicate. (B) The levels of AMPK phosphorylated, AMPK total, and NS3 viral protein were analyzed by western blot in whole cell lysates obtained from Huh7 cells infected with DENV2 (MOI 0.1, 1 and 3) for 24 h. Graph represents the relative quantification of pAMPK respect to AMPK total protein. The pAMPK and total AMPK densitometry values were normalized with β-actin and pAMPK/AMPK ratios were calculated, Ratios are represented with respect to the indicated control. *p<0.05 compared to mock infected cells. Data are means ± standard error (S.E) of n = 4 independent experiments. (C) The AMPK activity and NS3 viral protein levels (C, lower panel) were determined in Mock or DENV 2/4 infected Huh7 cells treated with DMSO 0.5% (vehicle, VEH), 10 mM Metformin (MET, AMPK activator) or 10 μM Compound C (CC, AMPK inhibitor) for 24 h. * p<0.05 compared to mock VEH-treated cells, ^ab p<0.05 compared to mock MET-treated cells. Data are means ± standard error (S.E) of n = 3 independent experiments realized by duplicate. (D) The levels of AMPK phosphorylated, AMPK total, and prM viral protein were analyzed by western blot in whole cell lysates obtained from Mock or DENV2 Huh7 infected cells (MOI 1 and 3) in the presence or absence of 10 mM metformin (MET) for 24h. Graph represents pAMPK/AMPK ratios normalized with respect to Mock infected cells with no MET treatment. pAMPK/AMPK ratios were obtained adjusting each protein with β-actin.

Fig 2. HMGCR activity is increased during DENV infection through down-regulation of AMPK.

In A, The enzymatic activity of HMGCR was evaluated in Huh7 cells infected with Mock or DENV 2/4 (serotype 2 or 4, MOI 3) at 24 hours post-infection (hpi). HMGCR activity was expressed as U/mg protein. *p<0.05 compared to mock infected cells. From same cell lysates, levels of NS3 viral protein (A, lower panel) were determined by WB as infection test. (B) DENV4 infected Huh7 cells treated with DMSO 0.5% (vehicle, VEH), 10 mM metformin (MET, AMPK activator), 50 μM lovastatin or 10 nM Okadaic acid (O.A, PP2A inhibitor) for 24 hpi were assayed for HMGCR activity and NS3 viral protein levels (B, lower panel). *p<0.05 compared to mock infected cells, ^a p<0.05 compared to DENV4 VEH-treated cells. Relative quantification of NS3 levels (numbers in italics) was normalized to β-actin and represented with respect to the indicated control. (C) The levels of NS3, E (envelope), and prM viral proteins were analyzed by western blot in whole cell lysates obtained from Mock or DENV2 Huh7 infected cells (MOI 3) treated with DMSO 0.5% (vehicle, VEH), 10 mM metformin (MET, AMPK activator), 10 nM Okadaic acid (O.A, PP2A inhibitor), and 50 μM Lovastatin (LOV, HMGCR inhibitor) for 24 h. Graph represents the relative quantification each protein normalized to β-actin and represented with respect to the indicated control (VEH). All data are means ± standard error (S.E) of n = 3 independent experiments.

Fig 3. Intracellular distribution of HMGCR and NS4A viral protein during DENV infection.

(A)The distribution of the NS4A (green), a viral protein present at DENV-replication complexes, and the HMGCR (red), a cellular ER-resident protein, was evaluated by confocal microscopy in Huh7 cells infected (MOI 3) with DENV2 and DENV4 at 24 hpi. Nuclei were stained with Hoechst (blue). Scale bar 10 μm. White dashed boxes are depicting the zoom area. (B) Histograms represent the fluorescence intensity for NS4A and HMGCR in determined area (white continuous line) demonstrating the correlation between two signals. In all infected cells, HMGCR colocalized with NS4A, however, the optical cut does not allow us to clearly observed this colocalization. (C)The table indicates HMGCR/NS4A colocalization values for region of interest (ROI, white dashed boxes) and colocalization per infected cell expressed as mean ± S.E. of 52 DENV2 infected cells and 47 DENV4 infected cells from three independent images.

Fig 4. Activated HMGCR is required for the formation of DENV-replication complexes and the maintenance of its architecture.

The distribution of HMGCR and components of viral replication complexes (NS4A and E viral proteins) was evaluated by confocal microscopy in Huh7 cells infected with DENV2 (MOI 3) and treated with DMSO 0.5% (vehicle), 10 mM Metformin or 50 μM lovastatin (HMGCR inhibitor) for 24h. The integrity of replication complexes is depicted as the co-localization between NS4A and E proteins. In A is indicated the distribution of HMGCR (red), NS4A (light blue), and E protein (green) as well as the colocalization per infected cell of NS4A/HMGCR (B) and NS4A/E (C) represented by mean ± S.E of the colocalization of 60 infected cells per condition. D and E represent the mean fluorescence intensity of NS4A protein (D) and HMGCR (E) analyzed by flow cytometry. Graphs represent the mean fluorescence intensity ± S.E of three independent experiments, the histograms indicate the fluorescence intensity of a representative experiment.

Fig 5. DENV infection stimulates the intracellular cholesterol accumulation at replicative complexes through the activation of HMGCR.

The distribution of intracellular cholesterol levels stained with filipin III complex (blue), and its co-localization with the viral protein NS4A (green) were evaluated by confocal microscopy in Huh7 cells non-infected, infected with DENV4 and treated with DMSO 0.5% (vehicle), 10 mM metformin or 50 μM lovastatin (HMGCR inhibitor) for 24 h. DENV4 infected cells are marked with (+), and non-infected cells marked with (-). Nuclei were stained with propidium iodide (red). Numbers inserted in images indicate the co-localization index between cholesterol and NS4A for that specific infected cell. Graph represents NS4A and cholesterol colocalization values as mean ± S.E of 50 infected cells analyzed from 3 independent experiments. Scale bar 10 μm. Images correspond to one representative experiment.

Fig 6. Metformin induces an antiviral effect in DENV infected cells.

In A and B, The antiviral effect of metformin-treatment (0, 1 and 10 mM) against DENV infection was evaluated in supernatants from Huh7 cells infected (MOI 3) with DENV2 (A) and DENV4 (B) at 24 hpi through determination of viral yield by foci assay, and NS1 secretion by ELISA. Viral yield is expressed as Foci Forming Units (FFU) / mL. NS1 secretion was normalized respect to infected non-treated cells and expressed as fold change vs 0 mM. (C) The percentage of infected cells after 10 mM metformin-treatment was determined by flow cytometry using a mouse anti-E monoclonal antibody-4G2 to detect the E viral protein in mock or DENV 2/4 infected cells. Upper histograms show the fluorescence of infected cells at 24h (gray filled histograms) or 48h (dark filled histograms) respect to mock infected cells (non-filled histograms). Lower histograms display the fluorescence of DENV infected cells treated with metformin (gray filled histograms) respect to vehicle-treated infected cells (dark filled histograms). (D) The Mean Fluorescence intensity (MFI) is presented on Graphs. (E) DENV 2/4 infected cells treated with 10mM metformin (MET) were visualized at 24 hpi by confocal microscopy using a mouse anti-E monoclonal antibody-4G2 (green). Nuclei were stained with Hoechst (blue). Scale bar 50 μm. Images correspond to one experiment representative of n = 3. (F) The number of viral genome copies of DENV 2/4 infected cells treated with metformin (0, 1, 10 mM) for 24h was examined by qRT-PCR, and expressed as Log of No. Copies. DMSO 0.5% was used as vehicle for all cases (0 mM). Data are means ± S.E of n = 3 independent experiments realized by duplicated. * p<0.05 compared to non-treated cells.

Fig 7. PP2A activity is not altered by DENV, but its inhibition by Okadaic acid has an antiviral effect.

The PP2A activity was analyzed in Huh7 cells infected (MOI 3) with DENV 2/4 at 1, 12 and 24 hpi (A), and in Mock or DENV 2/4 infected cells treated with DMSO 0.05% (vehicle) or 10 nM Okadaic acid (O. A) for 24h (B). Activity is expressed as picomoles of phosphate (phosphates pmoles). From the same cell lysates, the levels of NS3 viral protein (lower panels) were determined by WB as infection test. * p<0.05 compared to mock vehicle-treated cells. The antiviral effect of O. A (0, 1 and 10 nM) against DENV infection was evaluated in supernatants from Huh7 cells infected (MOI 3) with DENV2 (C) and DENV4 (D) by viral yield and NS1 secretion at 24 hpi. Viral yield is expressed as Foci Forming Units (FFU) / mL. NS1 secretion was normalized respect to infected non-treated cells and expressed as fold change vs 0 mM. (E) The number of viral genome copies of DENV 2/4 infected cells treated with O. A (0, 5, 10 nM) for 24h was examined by qRT-PCR, and expressed as Log of No. Copies. * p<0.05 compared to non-treated cells. DMSO 0.05% was used as vehicle for all cases (0 nM). Data are means ± S.E of n = 3 independent experiments realized by duplicated.