Sulfatide regulates caspase-3-independent apoptosis of influenza A virus through viral PB1-F2 protein

Abstract

Influenza A virus (IAV) generally causes caspase-dependent apoptosis based on caspase-3 activation, resulting in nuclear export of newly synthesized viral nucleoprotein (NP) and elevated virus replication. Sulfatide, a sulfated galactosylsphingolipid, enhances IAV replication through promoting newly synthesized viral NP export induced by association of sulfatide with hemagglutinin delivered to the cell surface. Here, we demonstrated that sulfatide is involved in caspase-3-independent apoptosis initiated by the PB1-F2 protein of IAV by using genetically sulfatide-produced cells and PB1-F2-deficient IAVs. Sulfatide-deficient COS7 cells showed no virus-induced apoptosis, whereas SulCOS1 cells, sulfatide-enriched COS7 cells that genetically expressed the two transferases required for sulfatide synthesis from ceramide, showed an increase in IAV replication and were susceptible to caspase-3-independent apoptosis. Additionally, PB1-F2-deficient IAVs, which were generated by using a plasmid-based reverse genetics system from a genetic background of A/WSN/33 (H1N1), demonstrated that PB1-F2 contributed to caspase-3-independent apoptosis in IAV-infected SulCOS1 cells. Our results show that sulfatide plays a critical role in efficient IAV propagation via caspase-3-independent apoptosis initiated by the PB1-F2 protein.

Figure 1. Inhibitory effects of CycA and GS-5 treatment on virus-induced apoptosis.

Virus-infected SulCOS1 cells were incubated at 34°C for 24 h. A, Inhibitory effects of CycA and GS-5 on virus-induced apoptosis at 24 h postinfection. CyA and VAD were used at 20 µM and 50 µM, respectively. B, Detection of active caspase-3 in virus-infected cells. MDCK cells were used as a positive control of caspase-3 activation. Gray-painted histograms and lined histograms were results of non-infected cells and infected cells, respectively. The results shown in (A) and (B) are representative data of two repeated experiments. C, Inhibitory effects of CycA and GS-5 on mitochondrial membrane potential loss in virus-infected cells. The JC-1 ratio of each cell was calculated as red value per green subtracted by respective fluorescent values of no cells and is shown as a relative percentage of non-infected cells. The results (± standard deviation) shown are average values of three experiments. Student's t-test was used for statistical analysis compared to no virus in (C). *. p<0.05; **, p<0.01.

Figure 2. Effects of GS-5 and CyA on AIF and viral NP localization and on virus replication.

A–B, Effects of GS-5 and CycA on nuclear translocation of AIF and nuclear export of viral NP in IAV-infected cells. Virus-infected SulCOS1 cells were maintained in a medium without (Con) or with GS-5, TU-1, CycA (50 µM), or VAD (100 µM) at 37°C for 7 h. After fixation of cells, AIF and viral NP were immunostained in green and red, respectively. Nuclei were stained in blue. C and D, Inhibitory effects of CycA treatment (C) and VAD treatment (D) on virus replication of SulCOS1 cells at 28 h postinfection. The virus titers (± standard deviation) in supernatants are expressed as a relative percentage of those with no CycA or VAD treatment and are average values of three experiments. Student's t-test was used for statistical analysis compared to no CycA or VAD treatment in (C) and (D). **, p<0.01.

Figure 3. PB1-F2 mediates induction of caspase-3-independent apoptosis in SulCOS1 cells.

SulCOS1 cells were infected with two recombinant PB1-F2-deficient mutant viruses (PB1 G144A and PB1 T120C) and wild-type virus. A, Fluorescent staining of AIF, NP, and nuclei at 7 h postinfection as described in the legend of Figure 2. B–D, SulCOS1 cells were infected with the respective virus as described in the Materials and Methods section. Inhibition of virus-induced apoptosis (B), mitochondrial membrane potential loss (C), and progeny virus production (D) in cells infected with PB1-F2-deficient viruses at 24 h postinfection. The progeny virus titers (± standard deviation) in supernatants are expressed as a relative percentage of those of wild-type virus and are average values of three experiments. Student's t-test was used for statistical analysis compared to no virus in (C) and compared to wild-type virus in (D). **, p<0.01.

Figure 4. Inhibition of virus-induced apoptosis and progeny virus production in SulCOS1 cells by siRNA against AIF.

SulCOS1 cells were transfected with efficient small interfering RNA (siRNA) against AIF (AIF1) or inefficient siRNA (AIF2 and GFP1) as a control. Mock means transfection without siRNA into infected cells. A, AIF and GAPDH were immunoblotted at 48 h posttransfection. B–D, After transfection with siRNA for 48 h, the cells were infected with the virus as described in the Material and Methods section. B, Fluorescent staining of AIF, NP, and nuclei at 7 h postinfection as described in the legend of Figure 2. C, Inhibitory effect of AIF1 on progeny virus production at 24 h postinfection. The progeny virus titers (± standard deviation) in supernatants are expressed as a relative percentage of those of mock treatment and are average values of three experiments. Student's t-test was used for statistical analysis compared to mock treatment in (C). **, p<0.01. D, Inhibitory effect of AIF1 on virus-induced apoptosis at 24 h postinfection. The results shown in (D) are representative data of two repeated experiments.

Figure 5. Putative scheme of nuclear export of vRNP invoked by sulfatide-associated apoptosis.

Once sulfatide binds with the newly synthesized HA transferred to the cell surface membrane, mitochondrial membrane potential loss is invoked in mitochondria localized with PB1-F2. AIF translocates from mitochondria to the nucleus, followed by induction of apoptosis. Apoptosis enhances nuclear export of vRNP from the nucleus, resulting in promotion of progeny virus production. Since activation of the Raf/MEK/ERK pathway is linked to both surface membrane translocation of the newly synthesized HA and apoptosis induction , this pathway is possible between sulfatide binding of HA and mitochondria membrane potential loss. A dotted line is a putative pathway.