CD164 is a host factor for lymphocytic choriomeningitis virus entry

Abstract

Lymphocytic choriomeningitis virus (LCMV) is a rodent-borne zoonotic arenavirus that causes congenital abnormalities and can be fatal for transplant recipients. Using a genome-wide loss-of-function screen, we identify host factors required for LCMV entry into cells. We identify the lysosomal mucin CD164, glycosylation factors, the heparan sulfate biosynthesis machinery, and the known receptor alpha-dystroglycan (α-DG). Biochemical analysis revealed that the LCMV glycoprotein binds CD164 at acidic pH and requires a sialylated glycan at residue N104. We demonstrate that LCMV entry proceeds by the virus switching binding from heparan sulfate or α-DG at the plasma membrane to CD164 prior to membrane fusion, thus identifying additional potential targets for therapeutic intervention.

Keywords: CD164; arenavirus; lymphocytic choriomeningitis virus; virus entry.

Fig. 1.

A genome-wide screen to identify host genes required for LCMV entry. (A) WT and ΔDAG1 A549 cells were infected with VSV, VSV-LASV, or VSV-LCMV at an MOI of 2. At 1 h postinfection, cells were washed to remove unbound virus and were subsequently replenished with fresh media. At 6 h postinfection, cells were fixed and subjected to flow cytometry to quantify infected cells by eGFP expression. Infectivity levels were normalized to WT A549 infectivity. A representative of three experimental replicates is shown. (B) Schematic of the CRISPR-Cas9 loss-of-function screen. Briefly, A549-Cas9 cells were transduced with the lentiviral Brunello sgRNA library and subjected to puromycin selection. The resulting mutagenized library was then infected with VSV-LCMV with a pool of the library taken to prior to use as a reference library. The resulting surviving cells were allowed to expand and then subjected to deep sequencing and MAGeCK analysis. (C) Results of the CRISPR-Cas9 genetic screen. The y-axis represents the significance score of each of the hits. The size of the circles represents the fold enrichment of each gene compared to the reference library. The number in parenthesis represents the number of guides that were enriched in the screen. Significant and relevant hits are grouped and colored by function.

Fig. 2.

CRISPR-Cas9 significant hits are important LCMV entry factors. (A) WT, ΔCD164, ΔSLC35A1, and ΔST3GAL4 A549 cells were infected with VSV or VSV-LCMV at an MOI of 2. At 1 h postinfection, cells were washed to remove unbound virus and incubated for 6 h following infection. Cells were then fixed and subjected to flow cytometry to quantify infected cells by eGFP expression. Infectivity levels were normalized to WT A549 infectivity (n = 3 experimental replicates). (B) WT, ΔCD164, ΔSLC35A1, and ΔST3GAL4 A549 cells were infected with LCMV-2A-GFP at an MOI of 2. At 1 h postinfection, cells were washed to remove unbound virus and incubated for 24 h following infection. Cells were then fixed and subjected to flow cytometry to quantify infected cells by eGFP expression. Infectivity levels were normalized to WT A549 infectivity (n = 3 experimental replicates). (C) Phylogenetic tree based on GPC sequences of selected representative arenaviruses used in Fig. 2D using MEGA sequence alignment software. The scale bar indicates the number of amino acid substitutions per position. (D) WT and ΔCD164 A549 cells were infected with VSV or VSV recombinants bearing the representative arenavirus GPC at an MOI of 2. At 1 h postinfection, cells were washed, medium was added, and the cells were incubated for 6 h prior to flow cytometric analysis as described in the legend for Fig. 2A. Infectivity levels were normalized to WT A549 infectivity (n = 3 experimental replicates).

Fig. 3.

The CRD of CD164 is critical for its function as a host factor for LCMV. (A) WT and ΔCD164 HeLa cells were transduced by lentiviral vectors express null, human CD164, or mouse CD164. Cells were infected at an MOI of 2 with VSV-LCMV. At 1 h postinfection, cells were washed, medium was added, and the cells were incubated for 6 h prior to flow cytometric analysis as above. Infectivity levels were normalized to WT HeLa infectivity (n = 3 experimental replicates). (B) Truncation mutants used in infectivity studies within Fig. 3C. (C) WT, ΔCD164, and ΔCD164 HeLa cells expressing CD164 truncation mutants by lentiviral transduction were infected with VSV-LCMV at an MOI of 2. At 1 h postinfection, cells were washed, medium was added, and the cells were incubated for 6 h prior to flow cytometric analysis as above. Infectivity levels were normalized to WT HeLa infectivity (n = 3 experimental replicates).

Fig. 4.

Effect of CD164 glycosylation on LCMV infection. (A) WT, ΔCD164, ΔSLC35A1, and ΔCD164/ΔSLC35A1 HeLa cells were infected with VSV-LCMV or VSV-PIV5 at an MOI of 2. At 1 h postinfection, cells were washed, medium was added, and the cells were incubated for 6 h prior to flow cytometric analysis as above. Infectivity levels were normalized to WT HeLa infectivity (n = 3 experimental replicates). (B) Topology of CD164. Predicted N-linked glycans are depicted in red, and predicted O-linked glycans are depicted in green. SP = signal peptide; TM = transmembrane Domain; CT = cytoplasmic tail. (C) WT, ΔCD164, and ΔCD164 HeLa cells expressing CD164 N-linked glycan mutants were infected with VSV-LCMV at an MOI of 2. At 1 h postinfection, cells were washed, medium was added, and the cells were incubated for 6 h prior to flow cytometric analysis as above. Infectivity levels were normalized to WT HeLa infectivity (n = 3 experimental replicates). (D) Schematic of CD164 CRD-LAMP1 chimeras used for infectivity studies within Fig. 3E. (E) WT, ΔCD164, and ΔCD164 HeLa cells expressing CD164 or the CD164 CRD-LAMP1 chimeras by lentiviral transduction were infected with VSV-LCMV at an MOI of 2. At 1 h postinfection, cells were washed, medium was added, and the cells were incubated for 6 h prior to flow cytometric analysis as above. Infectivity levels were normalized to WT HeLa infectivity (n = 3 experimental replicates). (F) WT, ΔCD164, and ΔCD164 HeLa cells expressing rCD164 or T102 rCD164 by lentiviral transduction were infected with VSV-LCMV at an MOI of 2. At 1 h postinfection, cells were washed, medium was added, and the cells incubated for 6 h prior to flow cytometric analysis as above. Infectivity levels were normalized to WT HeLa infectivity (n = 4 experimental replicates).

Fig. 5.

CD164 is a binding partner of LCMV GP. (A) Soluble LCMV-GP was coated onto 96-well, high-protein binding plates. Wells were washed, blocked, and then incubated with soluble CD164-Fc at the respective pH. Wells were washed extensively then incubated with goat anti-human IgG-HRP at the respective pH. Wells were extensively washed, and then TMB substrate was added, followed by a 650-nm stop solution, upon which the plate was read by a spectrophotometer plate-reader. The experiment was performed twice in duplicate, and a representative ELISA experiment is shown. (B) Soluble LCMV-GP was coated onto 96-half-well, high-protein binding plates. Wells were washed, blocked, and then incubated with soluble WT or N104Q CD164-Fc or LAMP1distal-Fc at pH 5. Wells were washed extensively and then incubated with goat anti-human IgG-HRP at pH 5. Wells were extensively washed, and then TMB substrate was added, followed by a 650-nm stop solution, upon which the plate was read by a spectrophotometer plate-reader. The experiment was performed twice in duplicate, and a representative ELISA experiment is shown. (C) Soluble LASV-GP was coated onto 96-well, high-protein binding plates. Wells were washed, blocked, and then incubated with soluble CD164-Fc or LAMP1Distal-Fc at pH 5. Wells were washed extensively and then incubated with goat anti-human IgG-HRP at pH 5. Wells were extensively washed, and then TMB substrate was added, followed by a 650-nm stop solution, upon which the plate was read by a spectrophotometer plate-reader. The experiment was performed twice in duplicate, and a representative ELISA experiment is shown. (D) Soluble LCMV-GP was coated onto 96-half-well, high-protein binding plates. Wells were washed, blocked, and then incubated with soluble untreated CD164-Fc or CD164-Fc that was treated either with PNGaseF (New England Biolabs) or NeuraminidaseA (New England Biolabs) at pH 5. Wells were washed extensively and then incubated with goat anti-human IgG-HRP at pH 5. Wells were extensively washed, and then TMB substrate was added, followed by a 650-nm stop solution, upon which the plate was read by a spectrophotometer plate-reader. The experiment was performed twice in duplicate, and a representative ELISA experiment is shown. (E) Soluble LCMV-GP was coated onto 96-well, high-protein binding plates. Wells were washed, blocked, and then incubated with soluble WT or T102N rCD164-Fc at pH 5. Wells were washed extensively and then incubated with goat anti-human IgG-HRP at pH 5. Wells were extensively washed, and then TMB substrate was added, followed by a 650-nm stop solution, upon which the plate was read by a spectrophotometer plate-reader. The experiment was performed twice in duplicate, and a representative ELISA experiment is shown.

Fig. 6.

Effect of CD164 mutants on membrane fusion. (A) ΔCD164 HeLa cells expressing mCherry (magenta) by lentiviral transduction were designated as “effector” cells. WT, ΔCD164, or ΔCD164 expressing plasma membrane–localized CD164 mutants expressing eGFP (cyan) by lentiviral transduction were designated as “target” cells. Separately, effector and target cells were seeded on 6-well plates. Effector cells were transfected with pCAGGS LCMV-GP. At 4 h posttransfection, effector cells were washed. Both effector and target cells were trypsinized, resuspended, mixed, and seeded on poly-d-lysine–coated plates. At 24 h posttransfection, wells were imaged. Cells were washed, treated with media at pH 4.5 for 10 min, and then back neutralized with warm media. After 1 h, cells were imaged by fluorescence microscopy. A representative of three independent experiments is shown. (Scale bar, 500 µm.) (B) WT, ΔCD164, or ΔCD164 expressing plasma membrane–localized CD164 mutants were preincubated with 100 nM Bafilomycin A1 for 1 h. These cells were then infected with VSV-LCMV at an MOI of 30 on ice for 1 h. Cells were then washed to remove unbound virus and treated with media at pH 7.4 or 4.5 for 10 min, and then were back neutralized with media supplemented with 100 nM Bafilomycin A1. At 6 h post–acid pH treatment, cells were fixed and subjected to flow cytometry to quantify infected cells by eGFP expression (n = 3 experimental replicates).

Fig. 7.

Heparan sulfate is an entry factor for LCMV. (A) Gene ontology analysis of the top 250 genes identified in the generic screen, showing the top seven pathways that were enriched. (B) VSV-LASV or VSV-LCMV at an MOI of 1 was incubated with soluble heparin at the indicated concentration for 45 min at room temperature. The medium on A549-Cas9 cells was aspirated and was replaced with the virus inoculum containing soluble heparin. At 1 h postinfection, cells were washed, fresh medium was added, and the cells were incubated for 6 h prior to flow cytometric analysis as described in Materials and Methods. Infectivity levels were normalized to 0 μg/mL soluble heparin. (n = 3 experimental replicates).