Structural and functional ramifications of antigenic drift in recent SARS-CoV-2 variants

Abstract

Neutralizing antibodies (nAbs) elicited against the receptor binding site (RBS) of the spike protein of wild-type severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are generally less effective against recent variants of concern. RBS residues Glu⁴⁸⁴, Lys⁴¹⁷, and Asn⁵⁰¹ are mutated in variants first described in South Africa (B.1.351) and Brazil (P.1). We analyzed their effects on angiotensin-converting enzyme 2 binding, as well as the effects of two of these mutations (K417N and E484K) on nAbs isolated from COVID-19 patients. Binding and neutralization of the two most frequently elicited antibody families (IGHV3-53/3-66 and IGHV1-2), which can both bind the RBS in alternative binding modes, are abrogated by K417N, E484K, or both. These effects can be structurally explained by their extensive interactions with RBS nAbs. However, nAbs to the more conserved, cross-neutralizing CR3022 and S309 sites were largely unaffected. The results have implications for next-generation vaccines and antibody therapies.

Fig. 1. Emergent SARS-CoV-2 variants escape two major classes of neutralizing antibodies.

(A) Emergent mutations (spheres) in the RBS of B.1.351 and P.1 lineages are mapped onto a structure of SARS-CoV-2 RBD (white) in complex with ACE2 (green) (PDB ID: 6M0J) (90). Binding affinities of Fc-tagged human ACE2 against SARS-CoV-2 RBD wild type and mutants were assayed by biolayer interferometry (BLI) experiments. Detailed sensorgrams are shown in fig. S1. (B) Distribution of IGHV gene usage. Numbers of RBD-targeting antibodies encoded by each IGHV gene are shown as solid bars. The frequently used IGHV3-53 and IGHV3-66 genes are highlighted in blue, and IGHV1-2 in orange. The IGHV gene usage in 1,593 SARS-CoV-2 RBD-targeting antibodies (, –44) compared to healthy individuals (baseline) (76) (fold-enrichment) is shown as black lines. ^#: IGHV gene frequencies in healthy individuals that were not reported in (76) are shown with hashtags (^#). *: IGHV genes that are significantly enriched over the baseline repertoire (76) (p < 0.05, one-sample proportion test with Bonferroni correction) are shown with an asterisk (*). A fold-enrichment of one (red dashed line) represents no difference over baseline. (C) Effects of single mutations on the neutralization activity and binding affinity of each neutralizing antibody. IC₅₀ or K_D increase that are less than 10-fold are represented by “–”, between 10- and 100-fold as “+”, and greater than 100-fold as “++”. Results in red with “✕” indicate no neutralization activity or binding was detected at the highest amount of IgG used. N.C.: not categorized in the original studies. N.S.: No structure available. (D) Neutralization of pseudotyped SARS-CoV-2 virus and variants carrying K417N or E484K mutations. A panel of 17 neutralizing antibodies were tested, including four mode-1 IGHV3-53 antibodies (blue), two mode-2 IGHV3-53 antibodies (purple), and two IGHV1-2 antibodies (orange). The discrepancy between CV05-163 neutralizing SARS-CoV-2 pseudotyped virus (IC₅₀ = 0.47 μg/ml) and authentic virus (IC₅₀ = 0.02 μg/ml) reported in our previous study (17) is possibly due to different systems (pseudovirus vs. authentic virus) and host cells (Hela cells vs. Vero E6 cells) used in these experiments.

Fig. 2. Antibody binding and structures to the wild-type SARS-CoV-2 RBS.

(A) Antibodies making contact with RBD residues K417, E484 and N501 are represented by blue, red and yellow boxes, respectively (cutoff distance = 4 Å). Antibodies encoded by the most frequently elicited IGHV3-53/3-66 and IGHV1-2 in convalescent patients are shown in green and orange boxes, respectively. Antibodies are ordered by epitopes originally classified in (9) with an additional epitope RBS-D that maps to a region in the RBS above or slightly overlapping with the S309 site. Details of the epitope classifications are shown in fig. S3A. Structures of RBD-targeting antibodies that were isolated from patients are analyzed (91). (B and C) Residues that are mutated in recently circulating variants are integral to the binding sites of IGHV3-53 antibodies. Representative structures are shown for (B) IGHV3-53 binding mode 1 [CC12.1 (PDB 6XC3), CC12.3 (PDB 6XC4) (13), and COVA2-04 (PDB 7JMO) (75)] and (C) binding mode 2 [COVA2-39 (PDB 7JMP) (75)]. The SARS-CoV-2 RBD is in white and Fabs in different colors. Residues K417 and E484 are represented by blue and red spheres, respectively. Hydrogen bonds and salt bridges are represented by black dashed lines.

Fig. 3. E484 is critical for RBD recognition of IGHV1-2 antibodies.

Heavy and light chains of antibody 2-4 (PDB 6XEY) (27) are shown in pink and light pink, respectively, S2M11 (PDB 7K43) (30) in orange and yellow, and C121 (PDB 7K8X) (10) in dark and light green, and CV05-163 in cyan and light cyan. The RBD is shown in white. E484 and K417 are highlighted as red and blue spheres, respectively. Hydrogen bonds are represented by dashed lines. Hydrogen bonds are not shown in the panel of C121 due to the limited resolution (3.9 Å).

Fig. 4. Antibodies targeting other major antigenic sites are differentially affected by mutations in recent variants.

(A) Interactions between RBS-C antibodies and SARS-CoV-2 RBD. The RBD is shown in white with E484, K417 represented as red and blue spheres, respectively. The various antibodies illustrated are in different colors. Only the variable domains are shown for clarity. Hydrogen bonds and salt bridges to E484 are represented by dashed lines. Published structures with PDB IDs 6XKP (17), 7CHF (38), 7BWJ (18), 7K8U (10), and 7CWN (78) are used to depict structures of SARS-CoV-2 RBD with CV07-270, BD-368-2, P2B-2F6, C104, and P17, respectively. The electron density for the full side chain of V_H N52 was not well resolved in the 3.8-Å structure of C104 in complex with SARS-CoV-2 S. The full side chain is modeled here and shown as transparent sticks to illustrate a possible interaction with E484. (B) Cross-neutralizing antibodies to the RBD are not affected by E484 and K417 mutations. COVA1-16 targets the CR3022 cryptic site (yellow) (80) and CV38-142 targets the S309 proteoglycan site (blue) (81) to the RBD. Glycans at the N343 glycosylation site are represented by sticks. The RBS surface is shown in green. E484 and K417 are highlighted as red and blue spheres, respectively. (C) Neutralization of CV38-142 and COVA1-16 against SARS-CoV-2 wild type, K417N or E484K pseudoviruses.