Role of the spike glycoprotein of human Middle East respiratory syndrome coronavirus (MERS-CoV) in virus entry and syncytia formation

Abstract

Little is known about the biology of the emerging human group c betacoronavirus, Middle East Respiratory Syndrome coronavirus (MERS-CoV). Because coronavirus spike glycoproteins (S) mediate virus entry, affect viral host range, and elicit neutralizing antibodies, analyzing the functions of MERS-CoV S protein is a high research priority. MERS-CoV S on lentivirus pseudovirions mediated entry into a variety of cell types including embryo cells from New World Eptesicus fuscus bats. Surprisingly, a polyclonal antibody to the S protein of MHV, a group a murine betacoronavirus, cross-reacted in immunoblots with the S2 domain of group c MERS-CoV spike protein. MERS pseudovirions released from 293T cells contained only uncleaved S, and pseudovirus entry was blocked by lysosomotropic reagents NH4Cl and bafilomycin and inhibitors of cathepsin L. However, when MERS pseudovirions with uncleaved S protein were adsorbed at 4°C to Vero E6 cells, brief trypsin treatment at neutral pH triggered virus entry at the plasma membrane and syncytia formation. When 293T cells producing MERS pseudotypes co-expressed serine proteases TMPRSS-2 or -4, large syncytia formed at neutral pH, and the pseudovirions produced were non-infectious and deficient in S protein. These experiments show that if S protein on MERS pseudovirions is uncleaved, then viruses enter by endocytosis in a cathepsin L-dependent manner, but if MERS-CoV S is cleaved, either during virus maturation by serine proteases or on pseudovirions by trypsin in extracellular fluids, then viruses enter at the plasma membrane at neutral pH and cause massive syncytia formation even in cells that express little or no MERS-CoV receptor. Thus, whether MERS-CoV enters cells within endosomes or at the plasma membrane depends upon the host cell type and tissue, and is determined by the location of host proteases that cleave the viral spike glycoprotein and activate membrane fusion.

Figure 1. Incorporation of MERS-CoV SΔ16 protein into pseudovirions (A) Diagram of full length MERS-CoV S protein and MERS-CoV S∆16 protein with the C-terminal 16 amino acids substituted with a linker and FLAG tag.

S1, virus attachment domain; S2, membrane fusion domain; TM, transmembrane domain. (B) Detection of uncleaved MERS-CoV SΔ16 protein in cells and pseudovirions. Lanes 1 and 5, control pseudovirions with no spike; lanes 2 and 6, MERS pseudovirions; lanes 3 and 7, lysate of 293T cells producing MERS pseudovirions; lanes 4 and 8, lysate of 293T cells producing control pseudovirions with no spike. Lanes 1 to 4 were blotted with anti-FLAG; and lanes 5 to 8, with polyclonal goat antibody AO4 to MHV-A59 S protein. * indicates possible trimer of MERS-CoV S protein in pseudovirions. In the pseudovirions made in 293T cells, the ~200 kDa S protein is uncleaved. (C) Identification of the domain of MERS-CoV S protein that is recognized by polyclonal antibody to MHV spike protein. Truncated MERS-CoV S proteins with c-terminal FLAG tags were harvested from the medium over transfected cells, analyzed by SDS-PAGE, and then blotted with anti-FLAG or AO4 antibody. A lysate of 293T cells expressing full length codon-optimized MERS SΔ16 is shown in Lane 1 as a positive control for recognition of MERS S by AO4.

Figure 2. Entry into human, monkey and bat cells of pseudovirions with SARS-CoV, VSV or MERS-CoV glycoproteins.

(A) Entry of SARS (blue), MERS-CoV (red) or no spike control (white) pseudovirions into 293/hACE2 (293 cells stably expressing hACE2, the SARS-CoV receptor), Vero E6, LLCMK2, Calu3, and A549 cell lines. Pseudovirus entry was quantitated by luciferase activity at 40 hrs post inoculation (pi). (B) Entry of MERS-CoV (red) or no spike control (white) pseudovirions into HeLa cells expressing 6 different human CEACAM proteins, Calu3, LLCMK2 and Vero E6 cells. (C) Entry of VSV (black), MERS-CoV (red) or no spike control (white) pseudovirions into different cell lines: 293T, NIH3T3, NIH3T3/Vector (transfected with empty vector), NIH3T3/hAPN (stably expressing human APN), bat EFF (embryo cells from Eptesicus fuscus), and bat TB1Lu (lung cells from Tadarida brasiliensis).

Figure 3. Inhibition of entry of MERS pseudovirions by lysosomotropic agents or cathepsin inhibitors.

(A) Entry into Vero E6 cells of pseudovirions with SARS S protein, uncleaved MERS-CoV S protein or no spike control in the presence of 20mM NH₄Cl (bars with rising stripes), 200nM bafilomycin A (bars with horizontal stripes), or medium alone (no inhibitor control, white bars). (B) Effects of cathepsin inhibitors on entry of pseudovirions with uncleaved MERS-CoV S protein, SARS S or VSV-g protein. Broad spectrum cathepsin inhibitor, E64D, or cathepsin L-specific inhibitor, cathepsin L inhibitor III (black bars) reduced entry of MERS and SARS pseudovirions, but did not inhibit entry of VSV pseudovirions relative to no inhibitor controls (white bars). Virus entry was quantitated by luciferase activity at 40hr pi.

Figure 4. Trypsin activation of entry of MERS pseudovirions at the plasma membrane at neutral pH and MERS-CoV S-mediated syncytia formation.

(A) MERS pseudovirions or no spike control pseudovirions were adsorbed on Vero E6 cells at 4°C, then briefly treated with trypsin or medium alone, followed by trypsin inhibitor in the presence or absence of NH₄Cl to inhibit acidification of endosomes. Pseudovirus entry was quantitated by luciferase activity at 40 hrs pi. (B) In the same experiment, addition of trypsin activated S-mediated formation of scattered syncytia (black arrows) in Vero E6 cells with adsorbed MERS pseudovirions both in the presence and absence of NH₄Cl at 40hr pi. (C) 293T cells stably transfected with plasmid encoding MERS-CoV SΔ16 protein or with no spike were briefly pre-treated with trypsin at 4°C, then with soybean trypsin inhibitor and then co-cultured with Vero E6 cells for 20 hr, or were co-cultured with Vero E6 cells for 20 hr in the continuous presence of trypsin. Syncytia formation required expression on the Vero E6 cells of the MERS-CoV receptor as well as trypsin cleavage of MERS-CoV S protein, but did not require acid pH.

Figure 5. Effects of TMPRSS-2 and TMPRSS-4 on MERS-CoV S-mediated syncytia formation in 293T cells and MERS pseudovirus entry into Vero E6 cells.

(A) Co-expression in 293T cells of the transmembrane serine proteases TMPRSS-2 or TMPRSS-4 as well as MERS pseudovirions induced syncytia formation in 293T cells expressing the GFP reporter gene, visualized 40hr after transfection. (B) MERS pseudovirions or no spike control pseudovirions released from the cells in Figure 5A were inoculated onto Vero E6 cells in the presence (striped bars) or absence (white bars) of 20mM NH₄Cl to inhibit acidification of endosomes.