Molecular-level analysis of the serum antibody repertoire in young adults before and after seasonal influenza vaccination

Abstract

Molecular understanding of serological immunity to influenza has been confounded by the complexity of the polyclonal antibody response in humans. Here we used high-resolution proteomics analysis of immunoglobulin (referred to as Ig-seq) coupled with high-throughput sequencing of transcripts encoding B cell receptors (BCR-seq) to quantitatively determine the antibody repertoire at the individual clonotype level in the sera of young adults before and after vaccination with trivalent seasonal influenza vaccine. The serum repertoire comprised between 40 and 147 clonotypes that were specific to each of the three monovalent components of the trivalent influenza vaccine, with boosted pre-existing clonotypes accounting for ∼60% of the response. An unexpectedly high fraction of serum antibodies recognized both the H1 and H3 monovalent vaccines. Recombinant versions of these H1 + H3 cross-reactive antibodies showed broad binding to hemagglutinins (HAs) from previously circulating virus strains; several of these antibodies, which were prevalent in the serum of multiple donors, recognized the same conserved epitope in the HA head domain. Although the HA-head-specific H1 + H3 antibodies did not show neutralization activity in vitro, they protected mice against infection with the H1N1 and H3N2 virus strains when administered before or after challenge. Collectively, our data reveal unanticipated insights regarding the serological response to influenza vaccination and raise questions about the added benefits of using a quadrivalent vaccine instead of a trivalent vaccine.

Figure 1

Delineation of the serological repertoire to IIV3. (a) Experimental design. For the sequencing of B cell receptor (BCR)-encoding transcripts (BCR-seq), we used peripheral B cells isolated 7 d after vaccination to sequence the V_H repertoires for constructing custom databases of each donor for heavy chain peptide identification and the paired heavy and light chain (V_H:V_L) repertoire for acquiring the endogenous light-chain information for the heavy chains. From sera of the donors, antibodies specific to each IIV1 were isolated through IIV1-immobilized column purification, and the purified immunoglobulins were subsequently analyzed proteomically (Ig-seq). Representative serum antibodies were recombinantly expressed for characterization. (b) Representative serological repertoire (rep.) (of n = 36 that we analyzed) (donor 1, day 28 anti–H1 A/CA09). Each bar represents a unique clonotype, and the y axis indicates the relative abundance (fraction), as determined by proteomic analysis. (c) Heat maps of the relative amounts of antibody clonotypes (each column indicates distinct clonotype) comprising the serological repertoire to each IIV1 at different time points for donor 1. The amount of each clonotype is determined by multiplying its relative abundance by the serum titer for that sample. Relative amounts are determined by normalizing the amounts to day 28 serum titers (Online Methods). Similar analyses were done for all of the donors (n = 4). (d) Predominance of pre-existing antibody clonotypes (Abs) in serum after vaccination. Each data point (see key) corresponds to the fraction of pre-existing Abs in the serological repertoire to an IIV1 for a specific donor. Averages are calculated as mean, with error-bars indicating s.e.m. (n = 12 for each group). Vic, Victoria. (e) Correlation between ELISA serum titer to IIV1 and the number of clonotypes in the respective serum repertoires. Each data point corresponds to titers and the number of clonotypes in the serological repertoire specific to an IIV1 for a donor at each time point (n = 36). (f) Inverse correlation between pre-vaccination ELISA serum titers and the frequency of vaccine-elicited clonotypes at day 28. Frequency is calculated as the number of vaccine-elicited clonotypes divided by the total number of unique clonotypes at day 28. For e,f, statistical analyses were performed using two-sided nonparametric Spearman rank correlation test.

Figure 2

Analysis of H1 + H3 cross-reactive serological repertoire. (a) Representative histogram from donor 1, day 28 anti–influenza A serological repertoire. The fraction of each antibody clonotype in the anti–H1 A/CA09 and anti–H3 A/VI09 repertoires are indicated. CR, cross-reactive. Similar analyses were done for all of the donors (n = 4) for two antigens at three time points (total n = 24 serological repertoires). (b) Relative abundance of H1 + H3 CR antibody clonotypes in the serum repertoires. Averages are calculated as the mean, with error bars indicating s.e.m. (n = 8 for each group). (c) Inverse correlation between pre-vaccination amount of H1 + H3 CR antibodies and the frequency of vaccine-elicited CR antibodies at day 28. y axis indicates the amount of H1 + H3 CR antibodies in sera at day 0, and x axis indicates the frequency of vaccine-elicited CR antibodies, calculated as the number of vaccine-elicited cross-reactive clonotypes divided by the total number of cross-reactive clonotypes at day 28. Amounts were calculated as described in Figure 1c, and statistical analyses were performed using a two-sided nonparametric Spearman rank correlation test. Symbols in b,c are defined in the key for Figure 1d–f. a.u., arbitrary units.

Figure 3

Biochemical and functional analysis of the recombinantly expressed H1 + H3 CR serum antibodies. (a) Binding and functional characteristics. Recombinant monoclonal antibody ID (rmAb ID) indicates the donor information, as well as the abundance rankings of the antibody at day 28 in respective repertoire (i.e., D1 H1-1/H3-1 indicates that this antibody is from donor 1 and ranked first in abundance in the anti–H1 A/CA09 repertoire and first in the anti–H3 A/VI09 repertoire). EC₅₀ values, as determined by ELISA, for each recombinant antibody tested against IIV1s or rHAs as listed are shown according to the color scheme included. A/California/7/2009 (CA09) and A/Perth/16/2009 (PE09) strains were used for both the HAI and PVN assays. All assays were repeated in triplicate. (b) Binding of H1 + H3 CR antibodies to the HAs on the surface of the MDCKs infected with the 2009 pandemic H1N1 strain (A/Netherlands/602/09; NL09), as analyzed by FACS. 50,000 events/sample were collected using the gating scheme included in Supplementary Figure 6. (c) Survival data (Kaplan–Meier plots) (top) and weight loss data (bottom) for BALB/c mice (n = 5 per group) after passive immunization (5 mg/kg) with H1 + H3 CR antibodies followed by challenge with NL09. (d) Survival (top) and weight loss (bottom) data for BALB/c mice (n = 5 per group) after passive immunization (5 mg/kg) with the protective antibodies from c followed by challenge with H3N2 strain X-31 (A/Hong Kong/1/68 in the backbone of A/PR/8/34). (e) Survival (top) and weight loss (bottom) data for BALB/c mice (n = 10 per group) challenged with NL09, followed by therapeutic administration of antibodies (5 mg/kg) at 48 h.p.i. For c–e, averages were calculated as mean, with error bars indicating s.d.

Figure 4

Structural analysis of H1 + H3 CR antibodies. (a) Binding characteristics to head versus stem HA, as determined by biolayer interferometry, repeated in triplicate. H1 + H3 CR Abs bind to the RBS of the HA molecule. D1 H1-3/H3-3 and D1 H1-17/H3-14 antibodies bound with high affinity to full-length HA (A/Hong Kong/1/1968 H3) and the RBS domain (A/New Caledonia/20/1999 HA RBD H1), whereas minimal binding was observed to a stabilized stem HA (A/New Caledonia/20/1999 HA stem H1) construct or to a covalent HA trimer molecule (A/Hong Kong/1/1968 H3 (212Cys–216Cys). (b) Analysis of HA–Fab complexes by negative-stain EM shows that the antibody binds to a HA monomer. Scale bar, 100 Å. (c) EM structure of D1 H1-3/H3-3 in complex with HA, determined to 22 Å using the random conical-tilt method. (d) Combined electron-density map of a single HA protomer and antibody Fab that were docked separately. (e) The fitted HA protomer–Fab complex was overlaid with an intact HA trimer (colored red-to-white indicating influenza HA conservation for one protomer; light blue for the remaining two protomers) showing that major overlap occurs between the Fab and an adjacent protomer molecule, which precludes binding of the antibodies to intact trimers. A set of highly conserved residues is located in this region (inset), which likely forms part of this antibody epitope.

Figure 5

Analysis of H1- or H3-specific, and influenza B–specific, serological repertoire. (a) Quantification of H1- or H3-specific antibodies in the vaccine-elicited antibody repertoire at day 28. Averages were calculated as mean, with error bars indicating s.e.m. (n = 4 for each group). (b) HAI serum titers before and after vaccination as a function of the amount of H1- or H3-specific antibodies in serum before and after vaccination. Amounts were calculated as described in Figure 1c, and statistical analyses were performed using a two-sided nonparametric Spearman rank correlation test. a.u., arbitrary units. (c) Prevalence of Vic + Yama CR antibodies in serum. Average was calculated as the mean, with bars indicating s.e.m. (n = 3 for each group). Symbols in a–c are defined in the key for Figure 1d–f. (d) Binding and functional characteristics of recombinantly expressed influenza B–specific serum antibodies. EC₅₀ values, as determined by ELISA, for each recombinant antibody tested against IIV1s or rHAs is listed. HAI assays were performed with B/Brisbane/60/2008 (BR08). All assays were repeated in triplicate.