SARS-CoV-2 spike glycoprotein vaccine candidate NVX-CoV2373 immunogenicity in baboons and protection in mice

Abstract

The COVID-19 pandemic continues to spread throughout the world with an urgent need for a safe and protective vaccine to effectuate herd protection and control the spread of SARS-CoV-2. Here, we report the development of a SARS-CoV-2 subunit vaccine (NVX-CoV2373) from the full-length spike (S) protein that is stable in the prefusion conformation. NVX-CoV2373 S form 27.2-nm nanoparticles that are thermostable and bind with high affinity to the human angiotensin-converting enzyme 2 (hACE2) receptor. In mice, low-dose NVX-CoV2373 with saponin-based Matrix-M adjuvant elicit high titer anti-S IgG that blocks hACE2 receptor binding, neutralize virus, and protects against SARS-CoV-2 challenge with no evidence of vaccine-associated enhanced respiratory disease. NVX-CoV2373 also elicits multifunctional CD4⁺ and CD8⁺ T cells, CD4⁺ follicular helper T cells (Tfh), and antigen-specific germinal center (GC) B cells in the spleen. In baboons, low-dose levels of NVX-CoV2373 with Matrix-M was also highly immunogenic and elicited high titer anti-S antibodies and functional antibodies that block S-protein binding to hACE2 and neutralize virus infection and antigen-specific T cells. These results support the ongoing phase 1/2 clinical evaluation of the safety and immunogenicity of NVX-CoV2373 with Matrix-M (NCT04368988).

Fig. 1. SARS-CoV-2 spike glycoprotein constructs.

a Linear diagram of the full-length SARS-CoV-2 spike (S) protein showing the S1 and S2 subunits. Structural elements include a cleavable signal sequence (SS, white), N-terminal domain (NTD, dark blue), receptor binding domain (RBD, green), subdomains 1 and 2 (SD1/SD2, light blue), fusion peptide (FP, red), heptad repeat 1 (HR1, yellow), central helix (CH, light green), heptad repeat 2 (HR2, purple), transmembrane domain (TM, black), and cytoplasmic tail (CT, white). The native furin cleavage site was mutated (RRAR→QQAQ) to be protease resistant to generate the full-length BV2365 variant. BV2365 was further stabilized by introducing two proline (2P) substitutions at positions K986P and V987P to produce the double mutant NVX-CoV2373. b Reduced SDS-PAGE gel of purified full-length wild-type (WT), BV2365, and NVX-CoV2373 (representative of 3 to 10 lots). WT spike is produced as a mixture of cleaved and uncleaved proteins. Figure shows purified uncleaved WT spike protein. c Transmission electron microscopy and 2D class averaging of NVX-CoV2373. 2D images were constructed from 28,623 NVX-CoV2373 particles followed by two rounds of 2D averaging. 2D images of NVX-CoV2373 S-trimers showing well-defined triangle-shaped particles with a length of 15 nm and a width of 12.8 nm. The S1 apical surface with the N-terminal receptor and receptor-binding domain (NTD/RBD) is indicated by green arrows. Faint protrusions (orange arrow) extending from the tip of the trimers were evident and appear to correspond to the S2 HR2 domain. Class average images showing a good fit of NVX-CoV2373 S-trimer with cryoEM solved structure of the SARS-CoV-2 trimeric spike protein ectodomain (EMD ID: 21374) overlaid on the 2D image. 2D class averaging using a larger box size showing 2D class average image with the less well-defined HR2 (orange arrow) anchoring the S-trimer to polysorbate 80 (PS80) micelle by the C-terminal TM. Source data are provided as a Source Data file.

Fig. 2. Kinetics and specificity of SARS-CoV-2 S protein binding to hACE2 receptor determined by bio-layer interferometry (BLI) and ELISA.

BLI sensorgram showing the binding of a wild-type (WT) SARS-CoV-2 S, b BV2365, and c NVX-CoV2373 spike proteins to histidine-tagged hACE2 receptor immobilized on a Ni-NTA biosensor tip. Data are shown as colored lines at different concentrations of spike protein. Red lines are the best fit of the data. d WT-SARS-CoV-2 S, e BV2365, and f NVX-CoV2373 demonstrated binding to hACE2 receptor but failed to bind hDPP4 as determined by ELISA. Source data are provided as a Source Data file.

Fig. 3. Stability of SARS-CoV-2 variants under stress conditions.

The hACE2 receptor binding ELISA method was used to assess the structural integrity of BV2365 and NVXCoV2373 under stressed conditions. a NVXCoV2373 and b BV2365 were exposed to repeat freeze–thaw cycles, pH extremes, agitation, elevated temperatures, and oxidation for extended periods as indicated. Treated samples were immobilized on 96-well plates, then incubated with serially diluted (2–0.0001 μg mL⁻¹) histidine-tagged hACE2. Bound receptor was detected with HRP-conjugated rabbit anti-histidine IgG. Source data are provided as a Source Data file.

Fig. 4. Immunogenicity of NVX-CoV2373 vaccine and protection against SARS-CoV-2 infection in mice.

a Groups of mice (n = 10/group) were immunized with a single priming dose (study day 14) or a prime/boost spaced 14 days apart (study days 0 and 14) with a dose range of NVX-CoV2373 with Matrix-M adjuvant (5 μg). A control group received formulation buffer (placebo). b Anti-SARS-CoV-2 IgG titers. Bars indicate the geometric mean titer (GMT) and the error bars indicate the 95% CI for each immunization group (n = 10/group). Individual animal values are indicated by colored symbols. Comparison of anti-SARS-CoV2 S IgG titer between a group immunized with two doses of NVX-CoV2373 (10 μg) without adjuvant compared to groups receiving different dose levels (0.01, 0.1, 1, and 10 μg) of NVX-CoV2373 with adjuvant. Comparisons were performed by Student’s t-test (unpaired, two tail); *p = 5.6E−05, **p = 2.4E−11, ***p = 2.8E−11. c hACE2-receptor-blocking antibodies in pooled serum (n = 10/group) collected after the first immunization (study days 13, 21, and 28). Bars indicate the mean of replicate assays. d SARS-CoV-2 virus-neutralizing antibody titers in pooled serum (n = 10/group) collected from groups receiving a single dose or a prime/boost. Bars indicate the mean of replicate assays. Following the booster immunization (study day 52), mice were transduced intranasally with 2.5 × 10⁸ pfu Ad/CMVhACE2. At 4 days post transduction (study day 56), mice were challenged intranasal with 1.5 ×10⁵ pfu of SARS-CoV-2. Animals were monitored daily for up to 7 days post infection (D0–D7). e Infectious virus load in lung homogenates at 4 days post SARS-CoV-2 challenge (D4). Bars represent the mean virus load (n = 5/group). Individual animal values are indicated by colored symbols. Comparisons were performed by Student’s t-test (unpaired, two tail); *p = 0.02, **p ≤ 0.003, ***p ≤ 1.0E−05, ****p ≤ 4.0E−06. Weight change was determined for up to 7 days following nasal challenge with SARS-CoV-2 (study days 56–63). f Mice immunized with one dose. g, h Mice immunized with two doses. Results are plotted as the mean and the error bars indicate the ±SD (D0–D4 n = 10 mice/time point and D5–D7 n = 5 mice/time point). Two-way ANOVA was used to compare differences in weight change of vaccinated groups compared to the placebo control group; *p = 0.5 (not significant), **p = 0.001, ^***p ≤ 0.0001. Dashed black line indicates the limit of detection (LOD). Source data are provided as a Source Data file.

Fig. 5. Histopathological analysis of SARS-CoV-2 infection in NVX-CoV2373-immunized mice transduced with Ad/hACE2 and challenged with SARS-CoV-2.

Groups of mice (N = 10/group) were immunized with NVX-CoV2373 with or without Matrix-M (5 μg) with two doses spaced 14 days apart. Placebo group received formulation buffer. Following immunization, mice were intranasally transduced with Ad/CMV/hACE2, 52 days after the first priming dose. At 4 days post transduction, mice were challenged with 1 × 10⁵ pfu/mouse of SARS-CoV-2 (WA1 strain). Lungs were collected 4 and 7 days post infection. Representative placebo control animal at 4 days post infection showing denuding of bronchial epithelium with marked thickening of the alveolar septa surrounded by mixed inflammatory cells. Diffuse perivascular cuffing was observed throughout the lung, consisting of neutrophils and macrophages. At 7 days post infection, peribronchiolar inflammation and perivascular cuffing was markedly increased. Lungs from NVX-CoV2373-vaccinated animals had little or no epithelial cell sloughing or infection within large and small bronchi at days 4 and 7 post infection. There was no evidence of exacerbated lung inflammation in NVX-CoV2373-immunized animals. Images from age- and sex-matched BALB/c mice from a separate experiment that were transduced with Ad/hACE2 alone as a control are shown in the right panel at 7 days post transduction. Scale bar 100 μm.

Fig. 6. Multifunctional cytokine analysis of SARS-CoV-2 S-specific CD4⁺ and CD8⁺ T cells in immunized mice.

a Groups of mice (n = 6/group) were immunized with 10 μg NVX-CoV2373 with and without 5 μg Matrix-M adjuvant in two doses spaced 21 days apart. A negative control group (N = 3) was not immunized. Splenocytes were collected 7 days after the second immunization (study day 28) and stimulated with a peptide pool (PP) that covers the entire spike protein for 6 h. b The number of IFN-γ secreting cells per million splenocytes was determined by ELISpot (n = 6/group). c, d The frequency of CD4⁺ memory T cells and CD8⁺ memory T cells producing IFN-γ, TNF-α, and IL-2, or at least 2 of 3 cytokines was determined by intracellular cytokine staining (n = 6/group). Analyzed cells were gated on the CD44^hiCD62L⁻ effector memory population. Bars represent the mean and the error bars indicate ±SD of triplicate assays. Individual animal values are indicated by colored symbols. Comparisons between groups receiving NVX-CoV2373 with and without adjuvant was performed by Student’s t-test (unpaired, two tail). e Pie charts represent the relative proportion of CD4⁺ and CD8⁺ T cells producing one, two, or three cytokines (IFN-γ, TNF-α, and IL-2) in mice immunized with NVX-CoV2373 antigen with and without Matrix-M. Source data are provided as a Source Data file.

Fig. 7. Frequencies of follicular helper T cell (Tfh) and germinal center (GC) B cells generated by immunization with NVX-CoV2373 and Matrix-M adjuvant.

Mice were immunized with NVX-CoV2373 with and without Matrix-M adjuvant and splenocytes were collected 7 days after the second immunization. a The frequency of splenic Tfh cells (CXCR5⁺ PD-1⁺ CD4⁺) in the CD4 T population. b The frequency of splenic germinal center (GC) B cells (GL7⁺ CD95⁺ CD19⁺) in B cells. Bars represent the mean values and the error bars indicate ±SD of triplicate assays. Colored symbols indicate individual animal values. Comparisons between groups receiving NVX-CoV2373 with and without adjuvant was performed by Student’s t-test (unpaired, two tail). Source data are provided as a Source Data file.

Fig. 8. Humoral and cellular immune response to NVX-CoV2373 with and without Matrix-M adjuvant in baboons.

a Baboons were randomly assigned to groups (n = 2–3/group) and immunized by IM injection with 1, 5, or 25 μg of NVX-CoV2373 and 50 μg Matrix-M adjuvant in two doses spaced 21 days apart (D0 and D21). A separate group (n = 2) received two doses of 25 μg NVX-CoV2373 without adjuvant. For serologic analysis, serum was collected prior to immunization (D0) and 21, 28, and 35 days after the first immunization (red triangle). For cellular responses, peripheral blood mononuclear cells (PBMCs) were collected 7 days after the booster (blue triangle) and re-stimulated with purified NVX-CoV2373 spike protein. b Anti-SARS-CoV-2 S IgG titers were determined by ELISA. c hACE2-receptor-blocking antibodies were determined by ELISA. d SARS-CoV-2-neutralizing antibodies determined by in vitro inhibition of cytopathic effect (CPE). Sold bars indicate the group mean and the colored symbols are individual animal values. The horizontal dashed black line indicates the limit of detection (LOD) for each assay. e Correlation of anti-SARS-CoV-2 S IgG titers vs SARS-CoV-2-neutralizing antibodies. f IFN-γ-secreting PBMCs re-stimulated with NVX-CoV2373 protein were determined by ELISpot anaylsis. g Frequency of SARS-CoV-2 spike-specific CD4⁺ T cells producing single and multiple combinations of type 1 cytokines IFN-γ, TNF-α, and IL-2 determined by intracellular cytokine staining (ICCS). Solid bars represent the group mean and individual animal values are indicated by colored symbols. Source data are provided as a Source Data file.

Fig. 9. Comparison of COVID-19 human convalescent serum antibody levels to NVX-CoV2373-vaccinated baboon antibody levels.

Convalescent sera were collected from recovered COVID-19 patients 4–6 weeks after testing positive for SARS-CoV-2 (n = 33). Sera were analyzed for anti-SARS-CoV-2 S IgG and human ACE2 receptor inhibition antibody levels (50% RI) and antibody levels compared to levels in serum of NVX-CoV2373 with Matrix-M immunized baboons as described in Fig. 8 (n = 7). The bars represent the group mean and error bars indicate the 95% confidence interval. The horizontal black dashed line indicates the limit of detection. Source data are provided as a Source Data file.