Influenza A virus inhibits type I IFN signaling via NF-kappaB-dependent induction of SOCS-3 expression

Abstract

The type I interferon (IFN) system is a first line of defense against viral infections. Viruses have developed various mechanisms to counteract this response. So far, the interferon antagonistic activity of influenza A viruses was mainly observed on the level of IFNbeta gene induction via action of the viral non-structural protein 1 (NS1). Here we present data indicating that influenza A viruses not only suppress IFNbeta gene induction but also inhibit type I IFN signaling through a mechanism involving induction of the suppressor of cytokine signaling-3 (SOCS-3) protein. Our study was based on the observation that in cells that were infected with influenza A virus and subsequently stimulated with IFNalpha/beta, phosphorylation of the signal transducer and activator of transcription protein 1 (STAT1) was strongly reduced. This impaired STAT1 activation was not due to the action of viral proteins but rather appeared to be induced by accumulation of viral 5' triphosphate RNA in the cell. SOCS proteins are potent endogenous inhibitors of Janus kinase (JAK)/STAT signaling. Closer examination revealed that SOCS-3 but not SOCS-1 mRNA levels increase in an RNA- and nuclear factor kappa B (NF-kappaB)-dependent but type I IFN-independent manner early in the viral replication cycle. This direct viral induction of SOCS-3 mRNA and protein expression appears to be relevant for suppression of the antiviral response since in SOCS-3 deficient cells a sustained phosphorylation of STAT1 correlated with elevated expression of type I IFN-dependent genes. As a consequence, progeny virus titers were reduced in SOCS-3 deficient cells or in cells were SOCS-3 expression was knocked-down by siRNA. These data provide the first evidence that influenza A viruses suppress type I IFN signaling on the level of JAK/STAT activation. The inhibitory effect is at least in part due to the induction of SOCS-3 gene expression, which results in an impaired antiviral response.

Figure 1. Influenza virus infection results in impaired IFNβ-induced STAT1 and STAT2 phosphorylation.

A549 (A, C) or Vero cells (E) were infected with the human influenza virus PR8 (H1N1) (MOI = 5) for the indicated time points and were subsequently stimulated for 15 min with either human IFNβ at a concentration of 100 U/ml (A) or 500 U/ml (E) or human IFNγ 500 U/ml (C). Cells were lysed and cell extracts were separated by SDS-PAGE and blotted onto nitrocellulose membranes. Membranes were incubated with anti-phospho-STAT1, anti-STAT1, anti-phospho-STAT2 and anti-PB1 antibodies in Western blots. (B, D, F) Quantification of relative pSTAT1 and pSTAT2 band intensities in A, C and E using AIDA software and 2D densitometry (Fuji).

Figure 2. Forced expression of influenza viral proteins does not result in impaired IFNβ-induced STAT1 and STAT2 phosphorylation.

HEK293 cells were transfected with 500 ng plasmid DNA for expression of viral NP, M, NS, (A) PA, PB1 and PB2 (C) genes (see Table 1 for accession numbers of viral genes) using L2000 according to manufacturer's instructions. Note that the Pol II constructs in use also give rise to expression of second reading frames in the NS, M and PB1 genes (NS2, M2, PB1-F2). 48 h post transfection cells were stimulated with human IFNβ (500 U/ml) for 15 minutes. Total protein lysates were subjected to Western blot analysis using anti-phospho-STAT1, anti-phospho-STAT2, anti-STAT1 antibodies. Expression of influenza viral proteins was monitored with antibodies against NP, M1, NS1, PA, PB1 or PB2. (E) HEK293 cells were infected with the human influenza virus PR8 (H1N1) (MOI = 5) for the indicated time points and were subsequently stimulated for 15 min with either human IFNβ at a concentration of 100 U/ml. Cell lysates were subjected to Western blots as described. (B, D, F) Quantification of relative pSTAT1 and pSTAT2 band intensities in A, C and E using AIDA software and 2D densitometry (Fuji).

Figure 3. Phosphatases do not mediate inhibition of IFNβ-induced STAT1 phosphorylation in infected cells.

(A) Vero cells were infected for 10 h with PR8 (MOI = 5) or left uninfected. Prior stimulation with human IFNβ (500 U/ml for 15 min), cells were treated for 10 min with sodium vanadate at concentrations indicated. Cells were harvested and protein lysates were subjected to Western blot analysis using anti-phospho-STAT1 and anti-STAT1 antibody. H₂O₂: was used as a control for solvent conditions. (B) Quantification of band intensities in (A). To visualize the effect of sodium vanadate on the STAT1 phosphorylation in infected and uninfected cells, band intensities of IFNβ stimulated samples were determined relative to background. Linear regression was calculated using the Excel software (Microsoft) (s = slope of the regression line). (C) Phosphatase activity in A549 cells infected wit PR8 (MOI = 5) was determined using tyrosine phosphatase assay (Promega) according to manufacturers instructions. For measurement of newly generated free phosphate two different phosphorylated pseudosubstrates (peptide 1 and peptide 2) were used.

Figure 4. Influenza A virus results in early SOCS-3 gene induction in an IFNβ-independent manner.

A549 cells were infected with PR8 (MOI = 5) (A, B, C) or stimulated with 100 U/ml human IFNβ (D) for the indicated time points. (F) A549 cells stably expressing IFNAR II-1 mRNA specific shRNA or control empty vector were infected with PR8 (MOI = 5) for 3 hours. Cells were lysed and RNA was subjected to reverse transcription. cDNA was analyzed in quantitative real time PCR to assess mRNA amounts of IFNβ (B), SOCS-1 (A), SOCS-3, (A, D, F), OAS1 (D) or MxA (D). Equivalent mRNA amounts were normalized to GAPDH mRNA levels and calculated as n-fold of the levels of untreated cells that were arbitrarily set as 1. To detect SOCS-3 protein expression (C) cells were infected for time points indicated or left uninfected. Total cell lysate was subjected to Western blot analysis using anti-SOCS-3 antibody. To allow better comparison of SOCS-3 protein expression and STAT1 phosphorylation phospho-STAT1 and STAT1 Western blots from figure 1A are shown again here. (E) To functionally test effective knock down of the IFNAR, A459 wild type, A549 vector control cells or A549 cells stably expressing IFNAR II-1specific shRNA were stimulated with human IFNβ (100 U/ml) for 15 min. Subsequently cells were lysed and levels of phospho-STAT1 were determined by Western blotting using specific antibodies. In addition, the relative pSTAT1 band intensities were quantified.

Figure 5. Viral 5′ triphosphate RNA efficiently induces SOCS-3 expression.

Total RNA from infected or uninfected A549 cells was isolated and used for transfection of native A549 cells with L2000 according to manufacturer's instructions (A–G). Transfection of RNA from infected cells (“viral RNA”) serves as a mimic for vRNA accumulation in infected cells while total cellular RNA from uninfected cells (“cellular RNA”) was used as a control. In (E and F) different amounts of poly (I:C) or RNA from infected or uninfected cells treated with phosphatase (CIAP) as indicated were transfected using L2000. In (G) viral RNA transfected cells were additionally treated with DMSO (solvent) or the protein synthesis inhibitor anisomycin (aniso.) at the concentrations indicated. (A, B, E, F, G) Cells were lysed 3 h post transfection and total RNA was reverse transcribed. cDNA was analyzed in quantitative real time PCR to assess amounts of SOCS-1 (A), SOCS-3 (A, E, G) and IFNβ (B, F) mRNA levels. Equivalent amounts of mRNA were normalized to GAPDH mRNA levels and calculated as n-fold of untreated cells, arbitrarily set as 1. In (C) cells were treated as in (A) and (B) and monitored for phospho-STAT1 and phospho-STAT2 levels in Western blot analysis. (D) Quantification of relative phospho-STAT1 and phospho-STAT2 band intensities in (C).

Figure 6. SOCS-3 mRNA transcription is induced in an NF-κB dependent manner.

A549 wt cells or A549 cells stably transduced with empty vector, dominant negative MKK6Ala or IKK2KD were either infected with PR8 for 3 hours (MOI = 5) (A and B) or with the influenza A virus mutant ΔNS1 and the corresponding isogenic wild type virus (G and H) or transfected for 3 hours with RNA from infected or uninfected A549 cells (C–F). (E and F) A549 cells were treated with 40 µM of the NF-κB inhibitor BAY 11-7085 30 minutes prior transfection of RNA from infected (“viral RNA”) or uninfected A549 wt cells (“cellular RNA”). In all experiments shown total RNA from target cells was isolated and reverse transcribed. cDNA was subjected to quantitative real time PCR. mRNA levels of SOCS3 (A, C, E, G) or IFNβ (B, D, F, H) were assed by specific primers.

Figure 7. Enhanced STAT1 phosphorylation in infected SOCS-3 deficient MEF correlates with elevated induction of IFNβ-stimulated genes.

Wild type MEF and SOCS-3 knock out MEF were infected with PR8 (MOI = 5) for the indicated times. Subsequently, cell lysates were analyzed for STAT1 phosphorylation (A). For control of productive virus replication, cell lysates were analyzed for viral protein PB1 expression. In (E, F, G) wild type and knock out cells were lysed at indicated time-points of infection. Subsequently RNA was subjected to reverse transcription. cDNA was analyzed in quantitative real time PCR to assess mRNA amounts of three prototype type I IFN-stimulated genes, SP110 (E), interferon regulatory factor-1 (IRF-1) (F) and OAS1 (G). Equivalent mRNA amounts were normalized to GAPDH mRNA levels and calculated as n-fold of the levels of untreated cells that were arbitrarily set as 1. In (C) wild type MEF and knock out MEF were infected with PR8 (MOI = 5) or left uninfected. Supernatants were taken 6 p.i. and used for stimulation of wild type MEF for 15 minutes. As control wild type MEF were stimulated with 500 U/ml mouse IFNβ for 15 minutes. Cells were harvested and analyzed for the amount of STAT1 and phospho-STAT1 in Western blot analysis by specific antibodies. In (B) and (D) the relative band intensities of phospho-STAT1 of the blots in (A) and (C) were quantified as described.

Figure 8. Efficiency of influenza A virus replication is dependent on SOCS3 expression levels.

Wild type MEF and SOCS-3 knock-out MEF were infected with PR8 (MOI = 0.01) (A) or A/Victoria/3/75 (MOI = 0.001) (B) for the indicated times. In (C) A549 wt cells were transfected for 48 h with 150 nM human SOCS3 siRNA using Hiperfect according to manufacturers protocol and infected with PR8 (MOI = 0.001) for 9 h. In (D) the highly susceptible cell line HEK293 was transfected with either pSUPER empty vector or pSUPER-mSOCS-3 for 48 h. Subsequently cells were infected with PR8 (MOI = 0.001) for 9 h. For (A), (B), (C) and (D) progeny virus titers were determined from the supernatants of infected cells by means of plaque assay. To determine the effect of over expressed SOCS-3 on STAT1 phosphorylation (E) A549 cells were treated as in (D) and infected with PR8 (MOI = 5) and/or stimulated with human IFNβ (100 U/ml). Cells were lysed and cell extracts were analyzed for levels of phosphorylated STAT1 and over expressed mSOCS-3 using anti phospho-STAT1 and anti flag-antibody in Western blots. Effective of SOCS-3 knock down was determined by Western blot (C, right). Cells were treated as in (C, left) and total cells lysates were analyzed for endogenous SOCS-3 protein levels using anti-SOCS-3 antibody in Western blot. (F) Quantification of relative pSTAT1 band intensities in (E).