The PP4R1 sub-unit of protein phosphatase PP4 is essential for inhibition of NF-κB by merkel polyomavirus small tumour antigen

Abstract

Merkel cell carcinoma (MCC) is a highly aggressive skin cancer with a high metastatic potential. The majority of MCC cases are caused by the Merkel cell polyomavirus (MCPyV), through expression of the virus-encoded tumour antigens. Whilst mechanisms attributing tumour antigen expression to transformation are being uncovered, little is known of the mechanisms by which MCPyV persists in the host. We previously identified the MCPyV small T antigen (tAg) as a novel inhibitor of nuclear factor kappa B (NF-kB) signalling and a modulator of the host anti-viral response. Here we demonstrate that regulation of NF-kB activation involves a previously undocumented interaction between tAg and regulatory sub-unit 1 of protein phosphatase 4 (PP4R1). Formation of a complex with PP4R1 and PP4c is required to bridge MCPyV tAg to the NEMO adaptor protein, allowing deactivation of the NF-kB pathway. Mutations in MCPyV tAg that fail to interact with components of this complex, or siRNA depletion of PP4R1, prevents tAg-mediated inhibition of NF-kB and pro-inflammatory cytokine production. Comparison of tAg binding partners from other human polyomavirus demonstrates that interactions with NEMO and PP4R1 are unique to MCPyV. Collectively, these data identify PP4R1 as a novel target for virus subversion of the host anti-viral response.

Keywords: NF-κB; immune evasion; phosphatase; skin cancer; virus.

Figure 1. The NEMO UBAN domain is necessary for tAg binding in cells

(A) Schematic representation of the FLAG-tagged NEMO truncations and internal deletions. (B) MCC13 cells were transfected with plasmids encoding GFP fusion proteins and a panel of FLAG-tagged NEMO truncations. GFP-TRAP co-immunoprecipitations were performed on the transfected lysates, and both input lysates and precipitations were probed with antibodies against GFP and FLAG. Lysates probed with an antibody detecting GAPDH served as a loading control. (C) GFP-TRAP co-immunoprecipitations were performed with a GFP control or GFP MCPyV tAg and two FLAG-tagged internal deletions of NEMO. Precipitations and lysates were analyzed as above. (D) MCC13 cells were transfected with plasmids encoding GFP fusion proteins and GST-tagged NEMO point mutants. GFP-TRAP co-immunoprecipitations were performed on the transfected lysates, and both lysate and precipitation were probed with antibodies against GFP and GST. GAPDH served as a loading control. Western blots shown are representative from at least three independent experimental repeats.

Figure 2. MCPyV tAg interacts with PP4c but not NEMO in vitro

(A) Equal amounts of bacterially expressed GST and GST-tAg were bound to glutathione-agarose beads and incubated with ITT produced FLAG-tagged PP4c and NEMO alone or in combination. Following washes, bound proteins were separated by SDS PAGE and probed with antibodies against GST and FLAG. A sample of the ITT input was analyzed to confirm appropriate expression of the FLAG-tagged proteins. (B) Equal amounts of bacterially expressed GST and GST-NEMO were bound to glutathione-agarose beads and incubated with ITT produced FLAG-tagged PP4c and tAg alone or in combination. Following washes, bound proteins were separated by SDS PAGE and probed with antibodies against GST and FLAG. A sample of the ITT input was analyzed to confirm appropriate expression of the FLAG-tagged proteins. Western blots are representative of at least three independent repeats.

Figure 3. PP4R1 interacts with PP4c and NEMO in MCC13 cells

MCC13 cells were transfected with empty plasmid or FLAG-tagged (A) PP4c or (B) NEMO. Immunoprecipitations were performed using FLAG-agarose beads and analyzed by western blot with antibodies against FLAG or endogenous PP4R1. Total cell lysates served as a positive control for expression. Western blots shown are representative of at least three independent experiments.

Figure 4. PP4R1 is a novel tAg binding partner required for NEMO binding

(A) GFP-TRAP co-immunoprecipitations were performed on lysates from MCC13 cells transfected with plasmids expressing GFP or GFP-tAg and analyzed by western blot with antibodies against GFP and endogenous PP4R1. Total cell lysates served as a positive control for protein expression and GAPDH as a loading control. (B) MKL1 cell lysates were precipitated with an anti-PP4R1 antibody or a pre-immune IgG control and analyzed by western blot. Samples were probed with antibodies against PP4R1, tAg (2T2) and GAPDH served as a loading control. (C) Equal amounts of bacterially expressed GST and GST-tAg were bound to glutathione-agarose beads and incubated with ITT produced HA-PP4R1 and FLAG-PP4c/NEMO alone or in combination. Following washes, bound proteins were separated by SDS PAGE and probed with antibodies against GST, HA and FLAG. A sample of the ITT input was analyzed to confirm appropriate expression of the epitope-tagged proteins. (D) Equal amounts of bacterially expressed GST and GST-NEMO were bound to glutathione-agarose beads and incubated with ITT produced HA-PP4R1 and FLAG-PP4c/tAg alone or in combination. Following washes, bound proteins were separated by SDS PAGE and probed with antibodies against GST, HA and FLAG. A sample of the ITT input was analyzed to confirm appropriate expression of the epitope-tagged proteins. (E) MCC13 cells were transfected with plasmids expressing GST, GST-NEMO or GST-NEMO D311N in combination with GFP-tAg. Cell lysates were incubated with glutathione-agarose beads and precipitates probed with antibodies against GST, GFP, PP4c and PP4R1. Total cell lysates served as an expression control and GADPH as a loading control. Western blots shown are representative of at least three independent experimental repeats.

Figure 5. Mapping the residues in MCPyV tAg necessary for inhibition of NF-κB activation

GFP-TRAP co-immunoprecipitations were performed using MCC13 cells co-transfected with plasmids expressing GFP, GFP-tAg or a panel of tAg point mutants in the presence of (A) a Myc-NEMO expression plasmid, (B) FLAG-PP4c expression plasmid, (C) HA-PP4R1 expression plasmid or (D) EE-tagged PP2A Aβ expression plasmid. Transfected cell lysates were incubated with GFP-TRAP affinity beads and bound protein was western blotted with antibodies detecting GFP and the appropriate epitope tag. Total cell lysates served as a positive control for protein expression and GAPDH as a loading control. (E) MCC13 cells were transfected with plasmids encoding the GFP-fusion proteins described and a luciferase reporter plasmid encoding the MCPyV early promoter [10]. Cell lysates were harvested after 24 hours and used in luciferase assays. (F) MCC13 cells were transfected with plasmids expressing GFP-fusion proteins and a reporter plasmid driving firefly luciferase under the control of NF-κB elements from the Concanavalin A promoter. Cells were treated with 10 ng/mL TNFα for 8 hours and samples analyzed for luciferase activity. To normalize for differences in transfection efficiency cells were co-transfected with a renilla luciferase reporter plasmid, and values were normalized relative to renilla expression. (G) IL-8 and (H) CCL20 protein levels in TNFα stimulated cells. Cells were stimulated as in (F), and media collected at 24 hours post stimulation for analysis by ELISA for each cytokine. Data are presented as picograms of cytokine. Error bars are +/−SD. Significance was analyzed by student's t-test and is indicated by an asterix *p<0.05, **p<0.01, ***p<0.001. Data shown are representative of at least three independent experimental repeats.

Figure 6. PP4R1 is necessary for MCPyV tAg-mediated inhibition of NF-κB

(A) Plasmids expressing GFP or GFP-tAg were transfected into MCC13 cells pre-transfected with scrambled or PP4R1-specific siRNA and GFP-TRAP co-immunoprecipitations performed. Precipitated protein complexes were separated by SDS PAGE and western blot performed with antibodies against GFP and endogenous PP4R1, PP4c and NEMO. Total lysates served as positive controls for protein expression, and confirmed PP4R1 depletion, whilst GAPDH acted as a loading control. (B) MCC13 cells containing scrambled control or PP4R1-specific siRNA were transfected with plasmids expressing GFP or GFP-tAg and a reporter plasmid driving firefly luciferase under the control of NF-κB elements from the Concanavalin A promoter. Cells were treated with 10 ng/mL TNFα for 8 hours and samples analyzed for luciferase activity. To normalize for differences in transfection efficiency cells were co-transfected with a renilla luciferase reporter plasmid, and values were normalized relative to renilla expression. (C) IL-8 and (D) CCL20 protein levels in TNFα stimulated cells. Cells were stimulated as in (B), and media collected at 24 hours post stimulation for analysis by ELISA for each cytokine. Data are presented as picograms of cytokine. Error bars are +/−SD. Significance was analyzed by student's t-test and is indicated by an asterix *p<0.05, **p<0.01, ***p<0.001. Data shown are representative of at least three independent experimental repeats.

Figure 7. Binding to NEMO and PP4R1 is not conserved amongst PyV tAg

(A) Total lysates from MCC13 cells transfected with plasmids expressing GFP and GFP-tAg from MCPyV, SV40, BKPyV and JCPyV in the presence of FLAG-PP4c, HA-PP4R1, EE-PP2A Aα, EE-PP2A Aβ or Myc-NEMO expression plasmids. GAPDH served as a loading control. (B) GFP-TRAP co-immunoprecipitations performed from cell lysates and western blots probed with antibodies against GFP and the appropriate epitope tag. Western blots shown are representative of five independent experimental repeats.