Severe acute respiratory syndrome coronavirus papain-like protease ubiquitin-like domain and catalytic domain regulate antagonism of IRF3 and NF-kappaB signaling

Abstract

The outcome of a viral infection is regulated in part by the complex coordination of viral and host interactions that compete for the control and optimization of virus replication. Severe acute respiratory syndrome coronavirus (SARS-CoV) intimately engages and regulates the host innate immune responses during infection. Using a novel interferon (IFN) antagonism screen, we show that the SARS-CoV proteome contains several replicase, structural, and accessory proteins that antagonize the IFN pathway. In this study, we focus on the SARS-CoV papain-like protease (PLP), which engages and antagonizes the IFN induction and NF-kappaB signaling pathways. PLP blocks these pathways by affecting activation of the important signaling proteins in each pathway, IRF3 and NF-kappaB. We also show that the ubiquitin-like domain of PLP is necessary for pathway antagonism but not sufficient by itself to block these pathways regardless of the enzymatic activity of the protease. The potential mechanism of PLP antagonism and its role in pathogenesis are discussed.

FIG. 1.

VRP-based screen for IFN antagonists. (A) MA104 cells were infected with VRPs expressing the identified ORFs at an MOI of 5 for 24 h. Type I IFN was quantified from supernatant of the infections using a type I IFN bioassay. Shown is the average of three experiments, each in triplicate. (B) RNA was isolated from the same infections as in panel A and used for RT-PCR of IFN-β and GAPDH expression. (C) MEFs from wild-type (WT) 129 mice and IFNAR^−/− mice were infected with the identified VRPs and analyzed by bioassay (C) and RT-PCR for IFN-β and GAPDH expression (D).

FIG. 2.

SARS PLP is an IFN antagonist. (A) HA- and GFP-tagged PLP expression plasmids were transfected into 293T cells with an IFN-β/luciferase construct. At 24 h posttransfection, cells were infected with SeV for 6 h and then luciferase was assayed to quantitate the level of induction of IFN-β transcription. (B) Using the same assay as in panel A, poly(I-C) was used as the inducer of IFN-β transcript. (C) To analyze whether PLP affected JAK/STAT signaling, PLP was transfected into cells with an ISRE/luciferase plasmid and incubated for 24 h. At 24 h, cells were treated with IFN-β protein for 6 h and then assayed for the induction of the ISRE promoter. We do not see a block in Jak/STAT signaling. (D) To identify where in the IFN-β induction pathway PLP is acting, cells were transfected with the IFN-β/luciferase reporter and plasmids containing either GFP, N-RIG, MAVS, IKKi or IRF3. The level of induction of each was set at 100%. Each plasmid was also transfected with HA-tagged PLP. Note that PLP blocked induction by each plasmid, signifying that PLP is not inhibiting signaling events upstream of IRF3. On the right, PLPΔUBL was used instead of PLP in the same experiments. Note that PLPΔUBL does not inhibit any of the inducers. (E) The UBL of PLP was used by itself to see if it blocked IFN induction via Ν-RIG, MAVS, IKKi, or IRF3. The UBL of PLP does not block the induction of IFN-β by these proteins. (F) Using the previously published (13) PLP construct, we find that it does block induction of IFN-β when each of the IRF3 signaling pathway proteins is expressed.

FIG. 3.

Mechanism of PLP inhibition. (A) The effect of PLP on the phosphorylation of IRF3 was assayed by Western blotting. 293T cells were transfected with a plasmid expressing IKKi and either GFP, PLP, or PLPΔUBL for 24 h. Protein was analyzed by Western blotting with either anti-IRF3 antibody (αIRF3) or anti-phospho-IRF3 antibody (αP-IRF3). The arrows signify the specific bands in each lane, and the asterisk denotes a background band from the phospho-IRF3 antibody. (B) HA-tagged IRF3 and GFP-tagged IRF3 were either singly transfected or cotransfected into 293T cells to test for coimmunoprecipitation conditions. At 24 h posttransfection, 500 ng poly(I-C) was added for 6 h to induce IRF3 homodimerization and IFN-β. Lanes 2 and 3 show input extract blotted with anti-HA (αHA) or anti-GFP (αGFP) antibodies. The lysates from cotransfected cultures were used for immunoprecipitation with anti-HA antibody (αHA IP). The resulting immunoprecipitation is shown in lane 4. Note that HA- and GFP-tagged IRF3 was able to be immunoprecipitated with anti-HA antibody. (C) IRF3 and PLP were expressed either individually or together in 293T cells to identify if they bound each other in the cell. HA-tagged PLP and Flag-tagged IRF3 were transfected, and the extracts were used in immunoprecipitation experiments. In lanes 1 to 4, anti-HA antibody was used to immunoprecipitate the proteins. In lanes 5 to 8, anti-Flag antibody (αFLAG) was used for immunoprecipitation, and in the right section of the gel, 5% of the input for the immunoprecipitation was run in lanes 9 to 12. The top panel was visualized with anti-Flag antibody for the Western blot, and the bottom panel used anti-HA for the Western blot. M, mock transfection; P, PLP transfections only; I, IRF3 transfections only; and I/P, IRF3 and PLP transfected together. (D) V5-tagged PLP from Devaraj et al. (13) was used in IRF3 immunoprecipitations. Identical conditions were used as in panel B, but anti-V5 antibodies (αV5) were used for the pull down of V5-tagged protein complexes. Lane 1 is mock-immunoprecipitated extract. Lane 2 is V5 PLP Sol alone, lane 3 is V5-PLP TM alone, lane 4 is V5-PLP Sol cotransfected with Flag-tagged IRF3, and lane 5 is V5-PLP TM cotransfected with Flag-tagged IRF3. The top panel shows a Western blot of the immunoprecipitated extracts with anti-V5 antibody (αV5 IP), and the bottom panel is an identical Western blot with anti-Flag antibody. (E) Interactions between purified PLP and IRF3_173-416 (E) or IRF3_1-426 (F) are shown as analyzed by 10% native-PAGE gels run at 4°C at pH 8.5. Proteins were incubated in different ratios, as indicated above the gels, for 10 min and then diluted with 2× sample buffer before being loaded onto the gels. Locations of the individual proteins are indicated by arrows to the left of the gels. (G) Cross-linking experiments with the cross-linking agent BS³ were performed between purified PLP and the two forms of purified IRF3. Following a 30-min incubation at room temperature in the presence of BS³, the protein mixtures were quenched and then analyzed by SDS-PAGE. Arrows to the right of the gel indicate the locations of the three individual proteins incubated without other proteins. Molecular mass marker (M) sizes are shown to the left of the gel in kDa.

FIG. 4.

PLP does not inhibit the in vitro phosphorylation of IRF3. Purified IRF3_173-416 was incubated with IKKi (A) and TBK1 (B) and ATP to induce phosphorylation and then analyzed by SDS-PAGE. The same reactions were carried out in the presence of PLP to determine if PLP interferes with IRF3 phosphorylation. Locations of nonphosphorylated IRF3, phosphorylated IRF3 (p-IRF3), PLP, IKKi, and TBK1 are indicated by arrows or brackets to the right of the gels. Molecular mass marker (M) sizes are shown to the left of the gels in kDa.

FIG. 5.

PLP inhibits the NF-κB signaling pathway. (A) 293T cells were transfected with a 3xκB/luciferase reporter plasmid that reports NF-κB-mediated gene induction. The reporter was transfected with PLP, PLPΔUBL, or PLP-Sol-expressing plasmids (13). At 24 h after transfection, cells were treated wither either SeV (MOI of 5) (A), poly(I-C) (2 μg) (B), or TNF-α (10 ng) (C). Note that both PLP and PLP-Sol block NF-κB-mediated gene induction, while PLPΔUBL does not. (D) The effect of PLP on NF-κB signaling was assayed by Western blotting. 293T cells were transfected with GFP, PLP, PLPΔUBL, or UBL alone for 24 h. At 24 h posttransfection, cells were treated with 10 ng of TNF-α for 0, 15, 30, or 45 min and proteins were extracted at those time points. Western blots were analyzed for either total IKb or phospho-IKb. Below the blot is the numerical ratio of total IKb to phospho-IKb as quantified by IPLAB.

FIG. 6.

Analysis of the effect of PLP on IκBα kinase activity and of PLP interactions with various NF-κB pathway proteins. (A) IκBα was incubated with IKKβ and ATP to induce phosphorylation and then analyzed by SDS-PAGE. The same reactions were carried out in the presence of PLP to determine if PLP interferes with kinase activity. Locations of nonphosphorylated and phosphorylated IκBα, PLP, and IKKβ are indicated by arrows. Molecular mass marker (M) sizes are shown to the right of the gel in kDa. (B) Native gel analysis of PLP interactions with NF-κB pathway proteins. Proteins were mixed, as indicated above the gels, and incubated in 50 mM HEPES (pH 7.5) for 10 min at 4°C and then diluted with 2× sample buffer before being loaded onto the gels. Locations of the individual proteins are indicated by arrows to the left and right of the gels.

FIG. 7.

PLP from NL63 but not MHV is an IFN antagonist. PLPs from NL63 and MHV were assayed for their ability to inhibit IFN-β, NF-κB, and STAT1 signaling in 293T cells. (A) In this assay, 293T cells were transfected with N-RIG and either GFP-, MHV PLP1-, MHV PLP2-, or NL63 PLP2-expressing plasmids and an IFN-β/luciferase reporter plasmid. At 24 h posttransfection, cells were assayed for luciferase expression. The value of induction in GFP plus N-RIG was set at 100%, with all other values in relation to it. Notice that MHV PLP1 and -2 do not block IFN-β induction, while NL63 and SARS-CoV PLP do. (B) 293T cells were transfected with GFP-, MHV PLP1-, MHV PLP2-, or NL63 PLP2-expressing plasmids and an NF-κB/luciferase reporter plasmid. At 24 h posttransfection, cells were treated with 100 ng of TNF-α; 6 h later, cells were assayed for luciferase expression. The value of induction in GFP plus TNF-α was set at 100%, with all other values in relation to it. Notice that MHV PLP1 and -2 do not block IFN-β induction, while NL63 and SARS-CoV PLP do. (C) 293T cells were transfected with either GFP-, MHV PLP1-, MHV PLP2-, or NL63 PLP2-expressing plasmids and an ISRE/luciferase reporter plasmid. At 24 h posttransfection, cells were treated with 100 ng of IFN-β; 6 h later, cells were assayed for luciferase expression. The value of induction in GFP plus IFNβ was set at 100%, with all other values in relation to it. Notice that none of the expressed proteins inhibits ISRE induction.

FIG. 8.

PLPΔUBL retains its protease and DUB functions. (A) A schematic of the SARS-CoV polyprotein cleavage assay is shown. The C terminal 100 aa of NSP2 through the N-terminal 80 aa of NSP3 were fused to GFP in an expression plasmid. PLP should cleave between NSP2 and -3 at the black arrowhead if the PLP protease is functional. The uncleaved product should be 46 kDa (46kD), and the cleaved product should be 35 kDa (35kD) when assayed on an SDS-PAGE gel. (B) 293T cells were transfected with either the cleavage reporter alone (mock) or the reporter and each plasmid noted above the Western blot. Proteins were extracted 24 h posttransfection and analyzed by Western blotting with an anti-GFP antibody to identify the cleaved or uncleaved cleavage reporter. The mock lane (lane 1) shows the full NSP2/3/GFP reporter. The PLP lane shows the cleaved product at ∼35 kDa. (C) PLPΔUBL retains its DUB activity. 293T cells were transfected with Flag-tagged ubiquitin and either GFP, PLP, or PLPΔUBL. Proteins were extracted 24 h posttransfection and analyzed by Western blotting (WB) with either an anti-HA antibody (αHA) (bottom panel) to visualize the PLP expression or anti-Flag antibody (αFLAG) to visualize Flag-tagged ubiquitin (top panel). (D) Vero cells were transfected with Flag-tagged ubiquitin and infected with icSARS-CoV at an MOI of 5 24 h posttransfection. Cells were lysed at 12 h postinfection and assayed for anti-Flag and antiactin (αACTIN) staining by Western blotting. (E) BHK cells were transfected with Flag-tagged ubiquitin and infected with MHV-A59 at an MOI of 5 24 h posttransfection. Cells were lysed at 6, 12, and 24 h postinfection and assayed for anti-Flag and antiactin staining by Western blotting.

FIG. 9.

PLP catalytic mutants play a role in IFN antagonism. (A) 293T cells were transfected with an IFN-β/luciferase plasmid that reports IRF3-mediated gene induction. The reporter was cotransfected with N-RIG and GFP, PLP, or the PLP W1633A, C1651A, or D1826A mutants. At 24 h after transfection, cells were lysed and assayed for luciferase expression. (B) 293T cells were transfected with a 3xκB/luciferase plasmid that reports NF-κB-mediated gene induction. The reporter was cotransfected with GFP, PLP, or the PLP W1633A, C1651A, or D1826A mutants. At 24 h after transfection, cells were treated with 10 ng of TNF-α, and 6 h after treatment, the cells were lysed and assayed for luciferase expression. (C) PLP mutants were tested for their cleavage activity using the construct and experimental design described in the legend to Fig. 8. The top panel is a Western blot for anti-GFP showing cleavage of the reporter protein, and the lower panel is a Western blot of the same extract probed with anti-HA antibody showing expression of the PLP mutants. (D) Deubiquitinase activities of the PLP mutants were assayed using the Flag-tagged ubiquitin assay described in the legend to Fig. 8. The top panel is a Western blot probed with anti-Flag antibody showing Flag-ubiquitin conjugation to cellular proteins. WT, wild type. The bottom panel is a Western blot with anti-HA antibody showing expression of the PLP variants.