Life course exposures continually shape antibody profiles and risk of seroconversion to influenza

Abstract

Complex exposure histories and immune mediated interactions between influenza strains contribute to the life course of human immunity to influenza. Antibody profiles can be generated by characterizing immune responses to multiple antigenically variant strains, but how these profiles vary across individuals and determine future responses is unclear. We used hemagglutination inhibition titers from 21 H3N2 strains to construct 777 paired antibody profiles from people aged 2 to 86, and developed novel metrics to capture features of these profiles. Total antibody titer per potential influenza exposure increases in early life, then decreases in middle age. Increased titers to one or more strains were seen in 97.8% of participants during a roughly four-year interval, suggesting widespread influenza exposure. While titer changes were seen to all strains, recently circulating strains exhibited the greatest titer rise. Higher pre-existing, homologous titers at baseline reduced the risk of seroconversion to recent strains. After adjusting for homologous titer, we also found an increased frequency of seroconversion against recent strains among those with higher immunity to older previously exposed strains. Including immunity to previously exposures also improved the deviance explained by the models. Our results suggest that a comprehensive quantitative description of immunity encompassing past exposures could lead to improved correlates of risk of influenza infection.

Fig 1. Representative individual profiles of HAI titer against H3N2 strains circulating over forty years.

(A-F): Antibody profile for each representative individual. Blue circles and red triangles represent the HAI titers against the tested strains at baseline and follow-up visit, respectively. Blue and red solid lines represent the smoothed HAI titers for serum collected from baseline and follow-up visit, respectively. Smooth splines of HAI titers on circulating years are shown in this figure for illustration purposes and not used in the subsequent analysis. Grey areas represent the baseline antibody profile. Purple and green areas indicate the increase and decrease of HAI titer at follow-up visit compared to baseline, respectively. Blue and red vertical blocks represent the duration for baseline and follow-up visit, respectively. Vertical dotted-dashed lines indicate the year of birth of the individual. Dashed and dotted lines represent the titer of 1:10 (detectable cutoff) and 1:40 (protective cutoff), respectively. Table below each panel shows the values of metrics calculated for each individual. We provided six additional profiles of HAI titers from people who were aged 40 to 60 years in S1 Fig.

Fig 2. HAI titers and differences in HAI titers between two visits against historical H3N2 strains.

(A) and (B): HAI titers against H3N2 strains from serum collected from baseline and follow-up visit, respectively. Participants are sorted by age at baseline sampling. (C): Fold of changes of HAI titers between two visits. Cell of row i and column j represents HAI titer or differences of HAI between two visits to strain i for person j. (D-F): Distribution of HAI titers from serum collected from baseline (D), follow-up visit (E), and fold of changes between two visits (F), respectively. Distributions were plotted after grouping titers across all participants and all tested H3N2 strains. (G) Variations of HAI titers at baseline with ages of participants and the year of isolation of tested strains. Dashed lines represent birth years of the participants (same for panel H and I). (H) Variations of HAI titers at follow-up with ages of participants and the year of isolation of tested strains. (I) Variation of changes in HAI titers between the two visits with ages of participants and the year of isolation of tested strains.

Fig 3. Age and HAI titer against individual H3N2 strain.

Lines are the predicted mean HAI titer fitted from general additive model (GAM) using age at sampling (panel A to C) and age at isolation (panel D to F) as predictor, respectively. We fitted separate GAMs for HAI titers measured for serum collected from baseline (panel A and D), serum collected in follow-up visit (panel B and E) and the differences between two visits (panel C and F).

Fig 4. The normalized area under the curve (nAUC), width above 1:40 (nW₄₀) and average titer years (nATY) varying with age.

Metrics were calculated using post-birth strains and normalized by the number of post-birth strains. Blue and red represent the metrics measured for serum collected from baseline and follow-up visit, respectively. Purple indicates the differences in metrics between the two visits. Solid lines are predictions from a generalized additive model and the colored dashed lines represent the corresponding 95% confidence intervals. (A) Demonstration of nAUC for one participant as an example. The same participant, who was aged 73 years old at baseline, is used for panel E and I. (B) Age and nAUC at baseline. (C) Age and nAUC at follow-up. (D) Age and changes in nAUC between the two visits. (E) Demonstration of nW₄₀ for one participant as an example. Solid points are the years that contributed to calculating width. (F) Age and nW₄₀ at baseline. (G) Age and nW₄₀ at follow-up. (H) Age and changes in nW₄₀ between the visits. (I) Demonstration of nATY for one participant as an example. (J) Age and nATY at baseline. The sloping black dotted lines indicate the year of birth of participants and the black dashed lines indicate the unweighted average isolation year of post-birth strains given age on x-axis (same for panel K and L). (K) Age and nATY at follow-up. (L) Age and changes in nATY between the visits.

Fig 5. Changes in antibody profiles between visits.

(A) Geometric mean titers (GMT) by strain. Blue and red points represent GMT at baseline and follow-up, respectively. (B) Distribution of changes in titers by strain. We divided the changes in titers into four categories, i.e. decrease (green), no change (grey), two-fold increase (light purple) and four-fold change (seroconversion, dark purple).