Broadly neutralizing antibodies target the coronavirus fusion peptide

Abstract

The potential for future coronavirus outbreaks highlights the need to develop strategies and tools to broadly target this group of pathogens. Here, using an epitope-agnostic approach, we identified six monoclonal antibodies that bound to spike proteins from all seven human-infecting coronaviruses. Epitope mapping revealed that all six antibodies target the conserved fusion peptide region adjacent to the S2' cleavage site. Two antibodies, COV44-62 and COV44-79, broadly neutralize a range of alpha and beta coronaviruses, including SARS-CoV-2 Omicron subvariants BA.1 and BA.2, albeit with lower potency than RBD-specific antibodies. In crystal structures of Fabs COV44-62 and COV44-79 with the SARS-CoV-2 fusion peptide, the fusion peptide epitope adopts a helical structure and includes the arginine at the S2' cleavage site. Importantly, COV44-79 limited disease caused by SARS-CoV-2 in a Syrian hamster model. These findings identify the fusion peptide as the target of the broadest neutralizing antibodies in an epitope-agnostic screen, highlighting this site as a candidate for next-generation coronavirus vaccine development.

One-sentence summary: Rare monoclonal antibodies from COVID-19 convalescent individuals broadly neutralize coronaviruses by targeting the fusion peptide.

Figure 1.. Broadly neutralizing antibodies target coronaviruses associated with human disease.

(A) Analysis of the frequency of MBCs expressing broadly reactive antibodies from n = 19 donors. Values in parentheses represent the percentage of SARS-CoV-2 reactive supernatants that also bind the specified subsets of non-SARS coronavirus spikes. A total of 10,356 MBC culture supernatants (50–100 B cells/well) was screened. (B) Phylogenetic relationships across the coronavirus spike proteins targeted by the broadly reactive mAbs were inferred by the Neighbor-Joining method in MEGA11 using full-length amino-acid sequences of CoV spike proteins. Bootstrap values from 500 samplings are shown on the branches. (C) Heat map representing the binding of broadly reactive mAbs to spike proteins from coronaviruses across the alpha, beta and deltacoronavirus genera. H1 hemagglutinin was included as a negative control for mAb binding experiments and area under the curve (AUC) values for each antigen are shown after subtraction with values for the negative control antigen CD4. (D) Values represent antibody titer at 50% neutralization (NT₅₀) against SARS-CoV-2 Wuhan Hu-1, SARS-CoV-1, MERS-CoV, HCoV-NL63 and HCoV-229E envelope-pseudotyped lentivirus, as well as authentic HCoV-OC43. NT50 values were calculated using the dose-response-inhibition model with 5-parameter Hill slope equation in GraphPad Prism 9. (E) Neutralization of SARS-CoV-2 variants of concern (pseudovirus) by COV44-62 and COV44-79.

Figure 2.. Broadly reactive mAbs target the same region within the SARS-CoV-2 S2 subunit.

(A) Titration curves for mAb binding to selected regions within the SARS-CoV-2 spike protein: the receptor binding domain (RBD), N-terminal domain (NTD) and the S2 subunit. Interconnected data points are shown without curve fitting. (B) On-rates, off-rates and dissociation constants of the six fusion peptide Fabs for binding to SARS-CoV-2 pre-fusion stabilized spike (2P) with an unmodified furin cleavage site and the non-stabilized S2 subunit. (C) Fusion peptide mAb binding (AUC) to wild-type SARS-CoV-2 S2 subunit and S2 subunit constructs modified with two (2P) or six (HexaPro) stabilizing proline mutations. (D) Epitope binning of broadly reactive antibodies versus the S2 stem-helix targeting mAb S2P6. All included antibodies were tested as both ligands and analytes. Solid lines indicate two-way competition while hashed lines indicate one-way competition. Red boxes indicate competing antibody pairs, green boxes indicate non-competing antibody pairs and hashed filling indicates self-competition.

Figure 3.. Broadly neutralizing antibodies target the conserved fusion peptide.

(A) Heat map of SARS-CoV-2 S2 peptide array. Binding responses were assessed by SPR using a 15-mer peptide array with 12 aa overlay covering the entire S2 subunit. Each column within the map represents a single peptide. The white triangle shows the S1/S2 cleavage site and the black triangle shows the S2’ cleavage site. FP, fusion peptide; HR1, heptad repeat 1; C helix, central helix; CD, connector domain; SH, stem helix; HR2, heptad repeat 2. (B) Sequence alignment of the fusion peptide from 34 viral isolates representing a diverse group of coronaviruses across four genera. Performed using MAFFT v7.450 using a BLOSUM62 scoring matrix and the L-INS-I algorithm. (C) Sequence conservation of pre-fusion SARS-CoV-2 spike protein (PDB 6VSB) with the fusion peptide (aa 816–843) highlighted in black. Inset shows a magnified view of this region. (D) Alanine scan evaluating the binding of COV44-62 and COV44-79 to the SARS-CoV2 fusion peptide. Responses were normalized to the wild-type sequence. A cut-off of 20% (brown hashed line) was used to identify residues that were critical for binding. (E) Sequence logo plot of diversity within the fusion peptide region of coronaviruses from 35 isolates, built using WebLogo 3. Height is proportional to the probability of an amino acid at a given position and amino-acid residues are colored by charge. Narrow stacks (amino acids) indicate deletions or gaps in the sequences. Numbering is based on the SARS-CoV-2 Wuhan-Hu-1 sequence. The key residues in the epitope footprints of mAbs COV44-62 (red) and COV44-79 (blue), based on peptide alanine scanning, are highlighted above the logo plot. (F-G) Amino acids critical for the binding of COV44-62, COV44-79 and COV77-39 identified by shotgun alanine mutagenesis of all residues on the S2 subunit. Key residues were identified based on a <20% signal relative to wild-type spike (brown hashed line), with no corresponding loss of signal for a control mAb, which targets the spike protein but does not bind to this site (see Figure S3C). The error bars show half the range (max – min signal).

Figure 4.. Crystal structures of COV44-62, COV44-79, and COV91-27 in complex with SARS-CoV-2 fusion peptide.

(A-C) The overall interactions of (A) COV44-62, (B) COV44-79, and (C) COV91-27 with the fusion peptide. Fabs are shown in a molecular surface and the CDRs and peptides are represented as tubes. Cyan and yellow represent the heavy and light chains of the Fabs. Peptides are shown in green. H1, H2, H3, L1, and L3 denotes CDRs in the heavy (H) and light (L) chains. The resolution of the crystal structures are 1.46 Å, 2.8 Å, and 2.3 Å for the COV44-62, COV44-79, and COV91-27 complexes. Peptide residues observed in the crystal structure are in bold and residues involved in interaction with antibody (buried surface area >0 Ų) are in red. (D-F) Details of the interactions between (D) COV44-62, (E) COV44-79, and (F) COV91-27 with the fusion peptide. V_H and V_L indicate the variable domains of the heavy (H) and light (L) chains. Kabat numbering was used for the Fabs and numbering in the native spike protein for the fusion peptide. The colors for the heavy chain, light chain, and fusion peptide are as in (A). (G-I) Buried surface area (in gray) and accessible surface area (in white) of each residue of the fusion peptide in complex with antibody are shown in the stacked bar chart. Residues that form polar interactions with COV44-62, COV44-79, and COV91-27 are denoted with “H” if they form a hydrogen-bond or “S” for a salt bridge on top of the corresponding bar. Buried and accessible surface areas were calculated with PISA ((31)).

Figure 5.. COV44-62 and COV44-79 inhibit SARS-CoV-2 spike-mediated fusion and COV44-79 limits disease in a Syrian hamster model.

(A) Images of fusion between HeLa cells stably expressing SARS-CoV-2 spike (RFP) and HeLa cells stably expressing the ACE2 receptor (GFP) after counter-staining with Hoechst (blue). Cells were co-cultured in the presence of COV44-62, COV44-79 or without a mAb (control). Scale bar, 500 μm. (B) Weight change for SARS-CoV-2 naïve animals versus virus-exposed animals that were mock-treated or treated with 16 mg/kg of mAb. Statistical significance for average body weight was analyzed across the 7-day time-course using a mixed-effects repeated measures model with Dunnett’s post-test multiple comparison (n=12 animals from Day 0–6 and n=6 animals from Day 7–12). Error bars show mean ± SD. (C and D) Clinical scores (C) and pathology scores (D) for SARS-CoV-2 naïve animals versus virus-exposed animals that were mock-treated or treated with 16 mg/kg of mAb. Statistical analyses for clinical (Days 0–7) and pathology (Days 3 and 7) scores were analyzed by a Kruskal-Wallis test with Dunn’s post-test multiple comparison (n=6–12 animals per condition), between the mAb-treated and mock-treated groups on each day. In (C), lines connect the median values. In (D), error bars show the median ± interquartile range.