Evidence of escape of SARS-CoV-2 variant B.1.351 from natural and vaccine-induced sera

Abstract

The race to produce vaccines against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) began when the first sequence was published, and this forms the basis for vaccines currently deployed globally. Independent lineages of SARS-CoV-2 have recently been reported: UK, B.1.1.7; South Africa, B.1.351; and Brazil, P.1. These variants have multiple changes in the immunodominant spike protein that facilitates viral cell entry via the angiotensin-converting enzyme-2 (ACE2) receptor. Mutations in the receptor recognition site on the spike are of great concern for their potential for immune escape. Here, we describe a structure-function analysis of B.1.351 using a large cohort of convalescent and vaccinee serum samples. The receptor-binding domain mutations provide tighter ACE2 binding and widespread escape from monoclonal antibody neutralization largely driven by E484K, although K417N and N501Y act together against some important antibody classes. In a number of cases, it would appear that convalescent and some vaccine serum offers limited protection against this variant.

Keywords: ACE2; B.1.351; SARS-CoV-2; South Africa; antibody; escape; neutralization; receptor-binding domain; vaccine; variant.

Graphical abstract

Figure 1

Evolution of B.1.351 variant (A and B) Sliding 7-day window depicting proportion of sequences with wild-type (gray), 501Y mutation only (green), NTD deletion only (purple), and double-mutation variant (black) for (A) sequences selected containing UK, NTD deletion 69–70 and (B) South Africa, NTD deletion 241–243. (C) Structure plot showing distribution of mutations of South African variant sequences as defined by N501Y and deletion 241–243; point mutations are marked in yellow and the deletions in dark gray. Structure plots use spike protein structure (original frame from PDB: 6ZWV) where modeled, and models were extended in Coot for missing loops. (D) Positions of major changes in the spike protein are highlighted in the NTD and RBD. (E) Positions of the K417N, E484K, and N501Y (yellow) mutations within the ACE2 interaction surface (dark green) of RBD. The view is chosen for clarity and is related to that shown in (C) by a 45° rotation around the axis coming out of the page (to make the RBD upright compared with C) and an almost 180° rotation around the long axis of the RBD domain. (F) A linear representation of B.1.351 spike with changes marked on. Note the strain used in this report does not have L18F and R246I mutations.

Figure 2

Neutralization of Victoria and B.1.351 viruses by convalescent plasma Plasma was collected in the UK before June 2020, during the first wave of SARS-CoV-2, in the early convalescent phase 4–9 weeks following admission to hospital. (A) FRNT assays comparing neutralization of Victoria (orange) and B.1.351 (green) (n = 34). (B) Neutralization assays of Victoria and B.1.351 with plasma obtained from patients suffering B.1.1.7 infection at the indicated times following infection. (C and D) Comparison of FRNT₅₀ titers between B.1.351 and Victoria strains for convalescent and B.1.1.7 plasma, respectively. The Wilcoxon matched-pairs signed rank sum test was used for the analysis and two-tailed p values were calculated; geometric mean values are indicated above each column. The data underpinning the Victoria neutralization curves have been previously reported (Supasa et al., 2021). Individual FRNT₅₀ values are shown in Table S1.

Figure 3

Neutralization of B.1.351 by vaccine serum (A and B) Neutralization FRNT curves for Victoria and B.1.351 strains by (A) 25 sera taken 7–17 days following the second dose of the Pfizer-BioNTech vaccine and (B) 25 sera taken 14 or 28 days following the second dose of the Oxford-AstraZeneca vaccine. (C and D) Comparison of FRNT₅₀ titers between B.1.351 and Victoria strains for the Pfizer-BioNTech and Oxford-AstraZeneca vaccines, respectively. The Wilcoxon matched-pairs signed rank sum test was used for the analysis and two-tailed p values were calculated; geometric mean values are indicated above each column. The data underpinning the Victoria neutralization curves have been previously reported (Supasa et al., 2021). Individual FRNT₅₀ values are shown in Table S2. See also Figure S1.

Figure S1

Neutralization of Victoria and B.1.351 by serum collected before vaccination, related to Figure 3 Neutralization for Victoria and B.1.351 strains by 50 sera taken at day zero before the first dose of AstraZeneca vaccine. All sera were assayed in three-fold dilutions at 1:20 and 1:60 for the final dilutions.

Figure 4

Neutralization by potent mAbs (A) Neutralization curves for Victoria and B.1.351 using 22 human monoclonal antibodies (mAbs). (B) Neutralization curves of Victoria and B.1.351 strains using mAb pairs from Regeneron and AstraZeneca. The data underpinning the Victoria neutralization curves have been previously reported (Supasa et al., 2021). Individual FRNT₅₀ values are shown in Table S3.

Figure 5

Interactions of mutation site residues with a selection of RBD-binding mAbs (A–D) Interactions of (A) Fab 88 with K417 and E484 of the RBD (PDB: 7BEL), (B) 150 with N501 and K417 (PDB: 7BEI), (C) 253 has no contact with any of the three mutation sites (PDB: 7BEN), and (D) Fab 384 with only E484 (PDB: 7BEP). (E) Structures of IGHV3-51 and IGHV3-66 Fabs by overlapping the Cα backbones of the RBD. (F) Interactions of K417 with CB6 Fab (PDB: 7C01 [Wajnberg et al., 2020]). (G) The K417N mutation is modeled in the RBD/CB6 complex. In (A) to (G), the Fab light chain, heavy chain, and RBD are in blue, salmon, and gray, respectively. Cα backbones are drawn in thinner sticks and side chains in thicker sticks. Contacts (≤4 Å) are shown as yellow dashed lines and hydrogen bonds and salt bridges as blue dashed lines. (H and I) Positions of mutations and the deletion in the spike NTD of the B.1.351 variant relative to the bound antibodies (H) 159 (PDB: 7NDC) and (I) 4A8 (PDB: 7C2L); the 242–244 deletion would be predicted to disrupt the interaction of 159 and 4A4. The heavy chain and light chain variable domains (Vh and Vl) of the Fabs are shown as salmon and blue surfaces, respectively, and the NTD as gray sticks. The mutation sites are drawn as green spheres and deletions as magenta spheres.

Figure 6

Antibody RBD interaction and structural modeling (A and B) BLI plots showing a titration series of binding to ACE2 (see STAR Methods) for (A) Wuhan RBD and (B) K417N, E484K, and N501Y B.1.351 RBD. Note the much slower off-rate for B.1.351. (C and D) K_D of RBD/mAb interaction measured by BLI for WT Wuhan RBD (left dots) and K417N, E484K, and N501Y B.1.351 RBD (right dots). (E) Epitopes as defined by the clustering of mAbs on the RBD (gray). (F) BLI data mapped onto the RBD using the method described in (Dejnirattisai et al., 2021). Front and back views of the RBD are depicted with the spheres representing the antibody binding sites colored according to the ratio (K_DB.1.351/K_DWuhan). For white, the ratio is 1; for red, it is <0.1 (i.e., at least 10-fold reduction). Black dots refer to mapped antibodies not included in this analysis; dark green to RBD ACE2-binding surface; and yellow to mutated K417N, E484K, and N501Y. (G) As for the left pair, but colored according to the ratio of neutralization titers (half-maximal inhibitory concentration [IC₅₀]B.1.351/[IC₅₀]Victoria). For white, the ratio is 1; for red, it is <0.01 (i.e., at least 100-fold reduction). Note the strong concordance between the two effects, with 269 being the most strongly affected. The nearby pink antibodies are mainly the IGHV3-53 and IGHV3-66 antibodies.