Multicohort analysis reveals baseline transcriptional predictors of influenza vaccination responses

Abstract

Annual influenza vaccinations are currently recommended for all individuals 6 months and older. Antibodies induced by vaccination are an important mechanism of protection against infection. Despite the overall public health success of influenza vaccination, many individuals fail to induce a substantial antibody response. Systems-level immune profiling studies have discerned associations between transcriptional and cell subset signatures with the success of antibody responses. However, existing signatures have relied on small cohorts and have not been validated in large independent studies. We leveraged multiple influenza vaccination cohorts spanning distinct geographical locations and seasons from the Human Immunology Project Consortium (HIPC) and the Center for Human Immunology (CHI) to identify baseline (i.e., before vaccination) predictive transcriptional signatures of influenza vaccination responses. Our multicohort analysis of HIPC data identified nine genes (RAB24, GRB2, DPP3, ACTB, MVP, DPP7, ARPC4, PLEKHB2, and ARRB1) and three gene modules that were significantly associated with the magnitude of the antibody response, and these associations were validated in the independent CHI cohort. These signatures were specific to young individuals, suggesting that distinct mechanisms underlie the lower vaccine response in older individuals. We found an inverse correlation between the effect size of signatures in young and older individuals. Although the presence of an inflammatory gene signature, for example, was associated with better antibody responses in young individuals, it was associated with worse responses in older individuals. These results point to the prospect of predicting antibody responses before vaccination and provide insights into the biological mechanisms underlying successful vaccination responses.

Fig. 1. Overview of the data analysis strategy

The meta-analysis was carried out on young and older influenza vaccination cohorts. Individual gene and module signatures were validated using independent cohorts.

Fig. 2. Vaccination cohorts used to define and validate influenza vaccination response gene and module signatures

(A) The four discovery cohorts each included young and older participants. Age cutoffs are indicated by the dashed horizontal lines. In several studies, gene expression data were collected for a subset of individuals (filled circles) enriched for high and low responders, as previously described (5). Two cohorts were used to independently validate the young and older response signatures. (B) The discovery and validation cohorts spanned five vaccination seasons. Numbers indicate the total count of participants in each study. The number of participants who met the age range criteria used for the young and older groups and the subset used in the transcriptional profiling analysis are shown in fig. S1.

Fig. 3. The adjMFC end point is independent of baseline titers

An illustration of our approach for computing adjMFC. The relationship between baseline titers and (A) MFC or (B) adjMFC in SDY404. Vertical lines separate the bins used for standardization, and the inset table indicates the P value resulting from the test for correlation. Correlation strengths and P values shown were based on Spearman’s rank correlation. Note that in this example, an outlier with high day 0 titer was removed when computing the adjMFC (see Methods).

Fig. 4. Identification of individual genes that predict vaccination response in young individuals

The x axes correspond to standardized mean difference, referred to as effect size (ES), between high and low responders, computed as Hedges’ g, in log₂ scale. The size of the rectangles is inversely proportional to the standard error of mean (SEM) in the individual cohort. Whiskers represent the 95% confidence interval. The diamonds represent overall mean difference for a given gene with combined support across the discovery cohorts. The width of the diamonds represents the 95% confidence interval of overall mean difference.

Fig. 5. Identification of gene modules that predict vaccination response in young or older individuals

(A) The QuSAGE activity for all gene modules that were significantly different between low and high responders in the discovery cohorts. Red indicates increased average expression of genes in the module among high vaccine responders. (B) Individual genes that comprise the three gene modules that predict vaccination response and were validated in the validation cohort (FDR ≤ 10%) in young individuals. Colors indicate the log₂ gene expression fold changes comparing high responders versus low responders, with red indicating increased expression among high vaccine responders.

Fig. 6. Validation of gene expression signature as a baseline predictor of the influenza vaccination response in young individuals

(A) The geometric mean of GRB2, ACTB, MVP, DPP7, ARPC4, PLEKHB2, and ARRB1 z-scored expression values (response score) was calculated for low, moderate, and high responders in the validation cohort (SDY80). (B) ROC curve for classifiers designed to separate individual participants as high responders versus low responders or moderate responders versus low responders in the validation cohort (SDY80). CI, confidence interval. (C) Temporal behavior of response score in the validation cohort (SDY80) for low, moderate, and high responders. Each point depicts an individual participant, and each point group is summarized by a boxplot. Significant P values are indicated above the data for comparisons of low and high responders and below the data for comparison between baseline and day 1 after vaccination.

Fig. 7. Baseline activity of the BCR signaling gene module (M54) is associated with influenza vaccination responses in young individuals

QuSAGE was used to calculate the PDF for the gene module activity using baseline data in the (A) discovery cohorts (SDY63, SDY404, SDY400, SDY212, and the combination) and (B) validation cohort (SDY80). (C) Temporal behavior of gene module in the validation cohort (SDY80) for low, moderate, and high responders. Each point depicts an individual participant, and each point group is summarized by a boxplot. Significant P values are indicated above the data for comparisons of low and high responders and below the data for comparison between baseline and day 1 after vaccination.

Fig. 8. Inverse correlation of baseline differences between young and older participants

(A) Gene effect sizes and (B) module activities comparing high and low responders were calculated in young and older individuals. All values were calculated using data from the discovery cohorts. (A) Significant genes for young (squares) individuals in the discovery cohorts are highlighted in black. (B) Significant modules for young (squares) and older (triangles) individuals in the discovery cohorts are highlighted in black.