A SAP30 complex inhibits IFN-beta expression in Rift Valley fever virus infected cells

Abstract

Rift Valley fever virus (RVFV) nonstructural protein NSs acts as the major determinant of virulence by antagonizing interferon beta (IFN-beta) gene expression. We demonstrate here that NSs interacts with the host protein SAP30, which belongs to Sin3A/NCoR/HDACs repressor complexes and interacts with the transcription factor YY1 that regulates IFN-beta gene expression. Using confocal microscopy and chromatin immunoprecipitation, we show that SAP30, YY1, and Sin3A-associated corepressor factors strongly colocalize with nuclear NSs filaments and that NSs, SAP30 and Sin3A-associated factors are recruited on the IFN-beta promoter through YY1, inhibiting CBP recruitment, histone acetylation, and transcriptional activation. To ascertain the role of SAP30, we produced, by reverse genetics, a recombinant RVFV in which the interacting domain in NSs was deleted. The virus was unable to inhibit the IFN response and was avirulent for mice. We discuss here the strategy developed by the highly pathogenic RVFV to evade the host antiviral response, affecting nuclear organization and IFN-beta promoter chromatin structure.

Figure 1. ZH NSs Protein Inhibits IFN-β Promoter and Interacts with Host Protein SAP30

(A) L929 wt330 cells, carrying an integrated wild type muIFN-β promoter fused to CAT reporter gene, were mock infected or infected by RVFV ZH or C13 or with NDV. Total cell extracts were prepared at 4, 6 and 8 h p.i. and CAT actvity was measured. (B) Non-confocal conventional fluorescence microscopy was used to analyze the nuclear distribution of NSs filaments in murine L929 cells infected by C13 or ZH. Presence of NSs filament detected using rabbit polyclonal anti-NSs antibody (green) or total DNA distribution revealed with Hoechst 33258 are shown respectively, in left and middle panels. Merged images are shown in right panels. Scale bars, 10 μm. (C) For yeast two-hybrid screening, AH109 yeast were co-transformed by pACT2-SAP30_1–152 that expressed Gal4 transactivating domain fused to the open reading frames corresponding to the 152 first aa of SAP30 and pGBKT7, pGBKT7-NSs_ZH, pGBKT7-NSs_C13, pGBKT7-NSs_TOS, or pGBKT7-NSs_GER in which NSs from RVFV ZH or C13 or NSs proteins from Toscana (TOSV) and Germiston (GERV) bunyaviruses were fused to the Gal4 DNA-binding domain. The values of β galactosidase activity represent at least four independent experiments with SD bars. (D) Two-hybrid system using full length wild type NSs_ZH or the deleted forms. The numbers indicate the amino acid position in the reference sequence. The sequence lacking amino acids 16–198 correspond to C13. (E) GST-NSs (left panel) or GST-SAP30 (right panel) was incubated with an extract from 293 cells transfected with the HA tagged-SAP30 expressing plasmid (left panel) or from ZH infected L929 cells (right panel). After extensive washing, the proteins bound to the beads were analysed by western blots using antibodies against HA (left panel) or NSs (right panel). The Coomassie blue staining showing that equivalent amounts of GST fusion proteins were loaded on the beads is not shown. (F) HEK 293 cells were transfected with either pCS2-Myc (lanes 1,2) or pCS2-Myc-SAP30 (lane 3) and either not infected (lane 1) or infected with ZH (lanes 2,3). Cell lysates were precipitated with anti-myc (9E10) antibody. Crude lysates (input) and the precipitated proteins (IP) were detected with anti-myc and anti-NSs antibodies.

Figure 2. Endogenous SAP30 and YY1 Colocalize with NSs Filaments in the Nuclei of ZH Infected Cells

Colocalization of endogenous SAP30 (A, C, and E) and YY1 proteins (B, D, and F) with NSs filament was analyzed by confocal microscopy in L929 wt330 cells uninfected (NI) or infected with C13 or ZH at m.o.i. 5 collected at 18 h p.i. (A and B), 5h (C and D) or 7 h p.i. (E and F). Each row represents a single optical section of the same nucleus. A, C, and E) Left panels (a, d, g) correspond to SAP30 distribution revealed with goat polyclonal anti-SAP30 antibodies. Middle panels (b, e, h) show subnuclear NSs distribution detected with anti-NSs rabbit polyclonal antibodies. Merged images of SAP30 and NSs are shown on right panels (c, f, i). (B, D, and F) Left panels (a, d, g) correspond to YY1 distribution revealed with mouse monoclonal anti-YY1 antibody. Middle panels (b, e, h) show subnuclear NSs distribution detected with anti-NSs rabbit polyclonal antibody. Merged images of YY1 and NSs are shown on right panels (c, f, i). Scale bar, 10 μm.

Figure 3. A NSs/SAP30/YY1 Complex Is Recruited on the Silent IFN-β Promoter through YY1 −90 Site

L929 cells (A) or L929 wt330 (B, C, and E), or L929 wt330, mut90, and mut122 (D) were infected with ZH or C13 at a m.o.i. of 5 and collected at 6 h p.i. or as indicated (C). Input and DNA immunoprecipitated (IP) with specific antibodies as indicated, were amplified with primers specific for the endogenous IFN-β promoter (A), for the integrated murine wild type wt330 IFN-β promoter (B-E), for the mutated integrated promoters (D) or for the murine β-actin gene (C). Schematic representation of murine IFN-β promoters either wild type (wt330) or mutated at the YY1 binding site present at position −90 (mut90) or −122 (mut122) is shown in D. Inputs are shown as controls except in E where they are the same as in D (wt330). Triangles indicate increasing amounts of DNA used during PCR reactions and corresponding in (B) to 1 μl, 2 μl, or 3 μl of 1:5 dilution of DNA immunoprecipitated with a-YY1 and a-SAP30 and of 1:50 dilution of DNA immunoprecipitated with a-NSs; (C) 1 μl and 2 μl of 1:50 dilution of DNA immunoprecipitated with a-NSs and 1 μl of 1:1,000 and 1:200 dilution of input DNA; (D) 1 μl of 1:5 and 1:1 dilution of DNA immunoprecipitated with a-YY1 and a-SAP30, 1 μl and 2 μl of 1:50 dilution of DNA immunoprecipitated with a-NSs and 1 μl of 1:1,000 and 1:200 dilution of input DNA.

Figure 4. Sin3A and N-CoR, but Not Co-Activator CBP, Interact with IFN-β Promoter in ZH Infected Cells

Colocalization of endogenous Sin3A (A), N-CoR (B) and CBP proteins (C) with NSs filament was analyzed by confocal microscopy in L929 wt330 cells uninfected (NI) or infected with ZH or C13 at m.o.i. 5 collected at 18 h p.i. Each row represents a single optical section of the same nucleus. (A) Left panels (a, d, g) correspond to Sin3A distribution revealed with rabbit anti-Sin3A polyclonal antibody. Middle panels (b, e, h) show subnuclear NSs distribution detected with mouse anti-NSs polyclonal antibody. Merged images of Sin3A and NSs are shown on right panels (c, f, i). (B and C) Left panel (a) corresponds to NCoR (B) or CBP (C) distribution revealed with goat anti-NCoR polyclonal antibody or rabbit anti-CBP polyclonal antibody. Middle panel (b) shows subnuclear NSs distribution detected with rabbit anti-NSs polyclonal antibody. Merged images are shown in right panels (c). Scale bar, 10 μm. (D) Inputs or DNA immunoprecipitated (IP) with anti-Sin3A and anti-NCoR antibodies collected from murine L929 wt330 cells either uninfected (NI) or 6 h after infection by ZH or C13 was amplified with specific primers.

Figure 5. Recruitment of HDAC-3 on the IFN-β Promoter

Colocalization of endogenous HDACs-1, 2, and 3 with NSs filament was analyzed by immunofluorescence technique and confocal microscopy in L929 wt330 cells uninfected (NI) or infected with ZH or C13 at m.o.i. 5 collected at 18 h p.i. Each row represents a single optical section of the same nucleus. (A) Left panels (a, d, g) correspond to HDAC-1, 2, or 3 subnuclear distribution revealed with mouse anti-HDAC1, 2, or 3 monoclonal antibodies. Middle panels (b, e, h) show subnuclear NSs distribution detected with rabbit polyclonal anti-NSs antibody. Merged images of HDACs-1, 2, or 3 and NSs are shown on right panels (c, f, i). Scale bar, 10 μm. (B) Inputs and DNA immunoprecipitated (IP) with anti-HDACs-1, 2, and 3 antibodies collected from murine L929 wt330 cells either uninfected (NI) or 6 h after infection by ZH was amplified with specific primers.

Figure 6. A Recombinant RVFV Which Does Not Interact with SAP30 Induces IFN-β and Is Avirulent

(A) Monolayers of Vero cells infected with RVFV rec-ZH or rec-ZHΔ210–230 were fixed and stained with crystal violet at 5 days p.i. (B) GST or GST-SAP30 was incubated with extracts from cells uninfected or infected with rec-ZH or rec-ZHΔ210–230. Proteins from the crude extracts (input) or after binding on GST or GST-NSs beads were analyzed by Western blotting using anti NSs antibodies. * denotes a cellular protein bound on GST-NSs which copurified with NSs. BF (C) or L929 wt 330 cells (D, E, F) uninfected or infected with C13, wt ZH, rec-ZH, or Δ210–230 were incubated for 8 h (C), 18 h (E) or for the indicated time (D and F). Extracts were prepared and analyzed by RT-PCR to detect C) IFN-β, GAPDH, or NSs mRNA as described in [26]. (D) CAT activity, (E) confocal microscopy, or (F) chip experiment using anti-NSs antibodies like in Figure 3; (G) percentage of animals surviving after i.p. inoculation of 10⁴ pfu.

Figure 7. Schematic Representation of IFN-β Promoter during RVFV Infection

In uninfected cells, a SAP30/Sin3A/NCoR/HDAC-3 corepressor complex, described here for the first time, to our knowledge, interacts with the constitutively repressed murine IFN-β promoter through its YY1 binding site present at position −90. After RVFV ZH infection, in the presence of NSs filaments, recruitment of corepressor complex SAP30/Sin3A/NCoR/HDAC-3 is reinforced whereas recruitment of co-activator CBP and of YY1 at its −122 site as well as acetylation of histone residues K8H4 and K14H3 is inhibited. Therefore, IFN-β promoter remains silent in spite of IRF3 nuclear translocation and binding to the promoter.