MAVS-mediated apoptosis and its inhibition by viral proteins

Abstract

Background: Host responses to viral infection include both immune activation and programmed cell death. The mitochondrial antiviral signaling adaptor, MAVS (IPS-1, VISA or Cardif) is critical for host defenses to viral infection by inducing type-1 interferons (IFN-I), however its role in virus-induced apoptotic responses has not been elucidated.

Principal findings: We show that MAVS causes apoptosis independent of its function in initiating IFN-I production. MAVS-induced cell death requires mitochondrial localization, is caspase dependent, and displays hallmarks of apoptosis. Furthermore, MAVS(-/-) fibroblasts are resistant to Sendai virus-induced apoptosis. A functional screen identifies the hepatitis C virus NS3/4A and the Severe Acute Respiratory Syndrome coronavirus (SARS-CoV) nonstructural protein (NSP15) as inhibitors of MAVS-induced apoptosis, possibly as a method of immune evasion.

Significance: This study describes a novel role for MAVS in controlling viral infections through the induction of apoptosis, and identifies viral proteins which inhibit this host response.

Figure 1. MAVS induces cell death.

(A) MAVS overexpression in HEK293T cells results in cell death. (B) MAVS-induced cell death displays dose dependency determined by Trypan blue exclusion cell counting. Cells were harvested for Trypan Blue counting 48 h post-transfection. (C) In the XTT cell viability assay, 1.0×10⁴ HEK293T were plated in 96-well plate, and increasing doses of MAVS from 0 ng/well to 200 ng/well were transfected and total amount of plasmids for each well was maintained at 400 ng by mixing pcDNA3 and MAVS plasmids together. XTT assays were performed 48 hours post-transfection. Error bar represents standard deviation of triplicates of biological samples and each graph represents three individual experiments.

Figure 2. MAVS expression leads to apoptosis.

(A) MAVS-induced cell death is caspase-dependent. HEK293T cells were treated with a pan-caspase inhibitor z-VAD-FMK before transfection with a titration doses of MAVS, and cell viability was measured by XTT assay. (B) MAVS triggers PARP cleavage as well as the activation of caspase-3 and caspase-9. One million HEK293T cells were transfected with 1 µg or 3 µg of MAVS-expressing plasmids and harvested 24 h or 48 h post-transfection. Cell extracts were immunoblotted for PARP, caspase-3 and caspase-9. (C) Densitometry analysis on the Western blot shown in (B). (D) Apoptotic morphological features of MAVS-induced cell death. Three micrograms of MAVS plasmids were transfected into 5×10⁵ HEK-293T cells. Transmission electron microscopy (TEM) analysis was carried out 48 hours post-transfection. Arrows: (I) intact plasma membrane; (II) marginated and condensed chromatin; (III) large vacuole; (IV) swollen mitochondria. Each graph represents two individual experiments.

Figure 3. MAVS mediates SeV-induced apoptosis in primary fibroblasts.

(A) MAVS is critical for SeV-induced apoptosis. MAVS wild type and knockout MEFs were infected with recombinant Sendai virus expressing GFP at a MOI of 0.5. Forty-eight hours post-infection, GFP-positive cells were gated (top graph) and then subjected to Annexin V binding analysis (bottom graph) by flow cytometry. (B) MAVS wild type and knockout MEFs were infected with rSeV-GFP at the MOI of 0.5. Forty-eight hours post-infection, cells were stained with Hoechst blue and Propidium Iodide (PI). (C) Morphological features of MAVS wild type and knock out MEFs infected by SeV. TEM pictures were taken 48 h post-infection. While SeV infected wildtype cells displayed morphology typical of apoptotic cells, SeV infected MAVS^−/− cells did not exhibit such morphology. Each graph represents two separate experiments.

Figure 4. Distinct MAVS domains are required for apoptosis.

(A) The domain structure of MAVS. MAVS contains a N-terminal CARD-like domain, a C-terminal transmembrane domain (TM) and a central proline-rich region. The cartoon shows the structure of the three truncation mutants we used in the study. (B) The TM and CARD-like domains are not dispensable for the pro-apoptotic function of MAVS. 1 µg of wildtype MAVS and its three mutants depicted in (A) were introduced in HEK293T cells; and apoptosis was assessed by flow cytometry 48 h post-transfection using 7-AAD and Annexin V as markers of dead and apoptotic cells respectively. (C) The mitochondrial localization of MAVS is critical for its pro-apoptotic function. Cell viability was determined by XTT assay. (D) MAVS induces mitochondrial membrane potential collapse in HEK293T cells as quantified by TMRE staining. Each graph represents two separate experiments.

Figure 5. MAVS-induced apoptosis is independent of type I IFNs production.

(A) Three molecules (ΔRIG-I, MDA5 and MAVS) that activate the production of type I IFNs were introduced into HEK293T cells; only MAVS is able to induce apoptosis. (B) Anti-IFN-β antibody was added to the medium at the final concentration of 200 neutralization units/ml to prevent secreted IFN-β binding to IFNAR, this neutralization process did not inhibit MAVS-induced apoptosis. (C) SeV-induced apoptosis is IFN-I-independent. MEFs from both C57BL/6 wild type and IFNAR^−/− mice were infected with rSeV-GFP. Cells were stained with Hoechst and PI 48 h post-infection. (D) The non-degradable form of IκB was co-expressed with different doses of MAVS, yet cell viability loss was not restored. (E) HEK293T cells were plated at both the lower chamber and upper chamber of the transwell plate separated by an insert filter membrane with 0.4 µm pore size. 1 µg of MAVS-containing plasmid was transfected into the cells in the lower chamber and all cells were harvested 48 h post-transfection for flow cytometry analysis.

Figure 6. MAVS-induced apoptosis does not depend on IRF3.

(A) 1.0×10⁴ HEK293T cells were plated in 96-well plates, a pool of four siRNA targeting IRF3 or control siRNA were added to each well, 24 hours later 200 ng MAVS or empty vector plasmids were transfected into the cell. XTT assay was performed 48 hours thereafter. Error bars shown in the plot represents three biological replicates. (B) The same IRF3-targeting and non-targeting siRNA transfection reagents used in (A) were applied to 5.0×10⁵ cells, and all cells were lysed in RIPA buffer 48 hours post-transfection and subjected to Western blotting to confirm knockdown. (C) 5.0×10⁵ HEK293T cells were plated in 6-well plates and treated with IRF3 or control siRNAs, 24 hours later 3 µg of MAVS expression plasmid or empty vector plasmids were introduced into the cells. Half of the cells from each well were harvested 48 hours thereafter and stained with Annexin V. The plot represents two separate experiments and the percentages of Annexin V positive cells were averaged for quantification. (D) The other half of the cells described in (C) were lysed in RIPA buffer and subjected to western blot analyses to confirm IRF3 knockdown.

Figure 7. The SARS-CoV NSP15 protein abrogates MAVS-induced apoptosis.

(A) Twelve of the SARS-CoV proteins were co-expressed with MAVS and NSP15 is the only one that exhibited a potent inhibitory effect on MAVS-induced apoptosis as assessed by XTT cell viability assay. (B) The inhibitory effect of NSP15 displays dose-dependency. Cell death was measured by an adenylate kinase activity assay. (C) The anti-apoptotic function of NSP15 does not extend to staurosporine-induced cell death. NSP15-expressing plasmid or empty vector were transfected in HEK293T cells seeded on 96-well plate, cells were treated with 500 nM staurosporin or PBS 24 h post-transfection, cell death fold change was evaluated by the adenylate kinase activity assay. (D) The inhibitory effects of NSP15 is unique to SARS-CoV. MAVS was co-expressed with NSP15 encoded by SARS-CoV, HKU1 and NL63. Flow cytometry analysis of 7-AAD/Annexin V stained cells was performed 48 h post-transfection. The results represent two separate experiments.

Figure 8. A proposed model for the dual functions of MAVS.

MAVS is engaged in two distinct host protective responses to viral infections. Upon activation by RNA viruses, MAVS initiates type 1 IFN signaling by activating the nuclear translocation of NF-κB and IRF3. In addition, host cells could mount apoptotic responses to viruses such as SeV via MAVS. Notably MAVS is targeted by viruses not only for abrogating IFN-I production but also inhibiting host apoptosis. For example, HCV NS3/4A and SARS-CoV NSP15 proteins abrogate MAVS-mediated apoptosis.