Infectious entry of West Nile virus occurs through a clathrin-mediated endocytic pathway

Abstract

The pathway of West Nile flavivirus early internalization events was mapped in detail in this study. Overexpression of dominant-negative mutants of Eps15 strongly inhibits West Nile virus (WNV) internalization, and pharmacological drugs that blocks clathrin also caused a marked reduction in virus entry but not caveola-dependent endocytosis inhibitory agent, filipin. Using immunocryoelectron microscopy, WNV particles were seen within clathrin-coated pits after 2 min postinfection. Double-labeling immunofluorescence assays and immunoelectron microscopy performed with anti-WNV envelope or capsid proteins and cellular markers (EEA1 and LAMP1) revealed the trafficking pathway of internalized virus particles from early endosomes to lysosomes and finally the uncoating of the virus particles. Disruption of host cell cytoskeleton (actin filaments and microtubules) with cytochalasin D and nocodazole showed significant reduction in virus infectivity. Actin filaments are shown to be essential during the initial penetration of the virus across the plasma membrane, whereas microtubules are involved in the trafficking of internalized virus from early endosomes to lysosomes for uncoating. Cells treated with lysosomotropic agents were largely resistant to infection, indicating that a low-pH-dependent step is required for WNV infection. In situ hybridization of DNA probes specific for viral RNA demonstrated the trafficking of uncoated viral RNA genomes to the endoplasmic reticulum.

FIG. 1.

Localization study of WNV envelope protein in Vero cells during the infection cycle. At different times p.i. (a, 3 min; b, 10 min; c, 30 min; d, 4 h; e, 12 h), Vero cells were fixed and processed for immunofluorescence assay. WNV E protein was detected with polyclonal anti-WNV E protein and with anti-rabbit antibodies conjugated with FITC as the secondary antibody.

FIG. 2.

Ultrastructural analysis of WNV entry process by using immunocryoelectron microscopy. (a) Homogeneous population of negatively stained WNV particles. (b) Binding of WNV particle at the plasma membrane of Vero cells. (c) Uptake of WNV particle (arrow) by coated pit (arrowheads). (d) WNV particle (arrow) is internalized within a clathrin-coated pit as indicated by the 10-nm gold particles. (e) Localization of single WNV particle in endocytic vesicles. (f) Fusion of WNV (black arrows) containing endocytotic vesicles (white arrows) that formed multivirus-containing compartments. (g) Multivirus-containing endocytotic vesicles are found in close proximity to the ER compartments. Virus particles are indicated by arrows. (h) Fusion of the WNV particle (arrows) with the endocytotic vesicle membrane. (i) Expulsion of the nucleocapsid of WNV (arrows) after fusion of the viral envelope with the endocytotic membrane. (j) Immunodetection of WNV nucleocapsid particles in the cytoplasm with gold particles conjugated to anti-capsid serum. Bars represent 100 nm (a to d) 200 nm (f, g, and j), 50 nm (e and j, inset), or 100 nm (h).

FIG. 3.

The uncoated WNV RNA genome is associated with the ER. WNV RNA genome was detected by using immunogold labeling against DGdUTP (black arrows) that are incorporated into the DNA probes. Bar, 50 nm.

FIG.4.

Colocalization of WNV with early and late endocytic vesicles markers. (a) Anti-EEA1 was used to stain the early endosomes at 5 min p.i. Lysotracker (b) and anti-LAMP1 (c) were used to stain late endosomes and lysosomes at 12 and 15 min p.i., respectively. EEA1 and LAMP1 antibodies are conjugated with Texas Red (TR), and WNV E protein antibody is conjugated with FITC. (d) A WNV particle (arrow) is localized within early endosomes, as indicated by gold particles conjugated to anti-EEA1 antibodies. (e) LAMP1-positive lysosome (gold particles [arrowheads]) containing large number of WNV particles (arrows) can be seen in close association with the ER. The virus particles are decorated with gold particles conjugated with anti-WNV E protein. (f) Colocalization of WNV nucleocapsids with ER marker. Anti-BiP and anti-capsid sera are used to stain the ER and nucleocapsid, respectively. WNV nucleocapsids were localized to the ER. BiP marker is conjugated with TR, and capsid protein antibody is conjugated with FITC. Bars (d and e), 50 nm. NU, nucleus.

FIG. 5.

Effects of clathrin-mediated endocytosis-disrupting drugs on WNV entry into Vero cells. The percentage of viral antigen-positive cells was plotted against time. Cells treated with monodanslycadervine (a), chlorpromazine (b), or sucrose (c) showed marked reduction in WNV entry, whereas filipin (d) does not significantly inhibit virus entry. The average of three independent experiments is shown.

FIG. 6.

Inhibition of WNV entry into Vero cells expressing Eps15 dominant-negative mutant protein. (a) The entry of WNV was significantly inhibited in Vero cells transfected with GFP-EΔ95/295. The number of viral E antigen-positive cells in relation to the total cell population is expressed as a percentage of viral antigen-positive cells. (b) Binding of WNV (stained with TR [arrows]) on the plasma membrane of the GFP-EΔ95/295-expressing cell was observed but no internalization of the virus particles occurred. (c) Internalized WNV particles (arrows) are observed within cells expressing the negative control plasmid expressing GFP.

FIG. 7.

Cytochalasin D- and nocodazole-pretreated Vero cells inhibit entry of WNV. The percentage of viral antigen-positive cells is plotted against time. A dose-dependent inhibition of WNV internalization into cytochalasin D (a)- and nocodazole (b)-treated Vero cells is observed. The average of three independent experiments is shown.

FIG. 8.

Subcellular fractionations of cellular homogenates from WNV-infected cells in 20% Percoll gradients. (a) Standard plot of density distribution determined by density marker beads in the 20% Percoll gradient. (b) Vero cells are allowed to internalized radiolabeled WNV at an MOI of 10 for 30 min and subjected to cellular fractionation. (c and d) A procedure similar to that for panel b was carried out except that the Vero cells were pretreated (1 h) with nocodazole and cytochalasin D, respectively.

FIG. 9.

pH-dependent entry pathway of WNV into Vero cells. (a and b) Acridine orange staining of untreated Vero cells (a) and cells after incubation with 1.5 μM chloroquine (b). Acridine orange staining of acidic vesicles in chloroquine-treated cells (a) was abolished compared to the untreated cells (b). Inhibitory effect on the entry of WNV into pretreated Vero cells with bafilomycin A (c), chloroquine (d), and amantidine (e). A dose-response inhibition of WNV entry was observed for all three of the drugs used. The average of three independent experiments is shown.