Integrative mapping of preexisting influenza immune landscapes predicts vaccine response

Abstract

BACKGROUNDPredicting individual vaccine responses is a substantial public health challenge. We developed Immunaut, an open-source, data-driven framework for systems vaccinologists to analyze and predict immunological outcomes across diverse vaccination settings, beyond traditional assessments.METHODSUsing a comprehensive live attenuated influenza vaccine (LAIV) dataset from 244 Gambian children, Immunaut integrated prevaccination and postvaccination humoral, mucosal, cellular, and transcriptomic data. Through advanced modeling, our framework provided a holistic, systems-level view of LAIV-induced immunity.RESULTSThe analysis identified 3 distinct immunophenotypic profiles driven by baseline immunity: (a) CD8+ T cell responders with strong preexisting immunity boosting memory T cell responses; (b) mucosal responders with prior influenza A virus immunity developing robust mucosal IgA and subsequent influenza B virus seroconversion; and (c) systemic, broad influenza A virus responders starting from immune naivety who mounted broad systemic antibody responses. Pathway analysis revealed how preexisting immune landscapes and baseline features, such as mucosal preparedness and cellular support, quantitatively dictate vaccine outcomes.CONCLUSIONOur findings emphasize the power of integrative, predictive frameworks for advancing precision vaccinology. The Immunaut framework is a valuable resource for deciphering vaccine response heterogeneity and can be applied to optimize immunization strategies across diverse populations and vaccine platforms.FUNDINGWellcome Trust (110058/Z/15/Z); Bill & Melinda Gates Foundation (INV-004222); HIC-Vac Consortium; NIAID (R21 AI151917); NIAID CEIRR Network (75N93021C00045).

Keywords: Adaptive immunity; Clinical Research; Immunology; Influenza; Vaccines; Virology.

Figure 1. Immune response landscape mapping of LAIV reveals distinct immunophenotypic groups.

(A) Cohort overview depicting all features used for unsupervised machine learning analysis: 244 children (24–59 months of age) vaccinated with LAIV; mucosal and blood samples collected on day 0 (prevaccination) and day 21 (postvaccination). Vaccine-induced immune responses calculated as fold-change relative to prevaccination levels. (B) Workflow schematic for automated clustering pipeline applying t-SNE dimensionality reduction, KNN graph construction, and Louvain community detection to identify distinct immunophenotypic clusters. (C and D) Louvain resolution sweep results used to assess cluster stability and select optimal number of clusters. (C) Modularity score plotted against Louvain resolution parameter, colored by number of clusters identified (–6). High modularity indicates well-separated clusters. Red diamond indicates selected clustering parameters. (D) Number of clusters identified plotted against Louvain resolution parameter, colored by modularity score. Stability of 3-cluster solution (red diamond) is observed across range where modularity is maximal (Q ≈ 0.717). (E) Clustered t-SNE plot of fold-change data (post/pre-LAIV) revealing 3 distinct LAIV response phenotypes: group 1 (green, n = 82), group 2 (orange, n = 88), and group 3 (purple, n = 74). (t-SNE parameters: perplexity: 30; exaggeration factor: 4; max iterations: 10,000; theta: 0; eta: 500; K: 60 for KNN graph; final silhouette score: 0.40). (F and G) Clustering patterns overlaid with demographic factors on t-SNE map. (F) Clustering by sex (female, green; male, orange). (G) Clustering by study year (2017, green; 2018, orange). (H) Heatmap and hierarchical clustering display fold-change data for key immune features across 3 clusters (columns: groups 2, 1, and 3 from left to right). Rows represent immune features, clustered using Euclidean distance and Ward’s D2 method. Heatmap cells are colored based on scaled FC values from –1 (blue, low FC) to 1 (red, high FC). The top color bar indicates responder groups (group 1, green; group 2, orange; group 3, purple). Side color bars indicate qualitative response classifications derived from assays: HAI (purple: high, dark; low, light), IgA (orange: high, dark; low, light), CD4⁺ T cell (blue: high, dark; low, light), and CD8⁺ T cell (green: high, dark; low, light). Column cluster ordering optimized for visual clarity.

Figure 2. Vaccine response immune signatures defining LAIV responder types.

(A) Polar plot summarizing scaled median expression of key immune features in CD8⁺ T cell responders (group 1, green). CD8⁺ T cell responders are characterized by robust influenza B virus HA–specific CD8⁺ IFN-γ responses and limited humoral immunity, with median feature values represented in the polar plot and fold-change comparisons shown in the adjacent box plot. (B) Polar plot for mucosal responders (group 2, orange) illustrating strong mucosal IgA responses, particularly stalk-specific (cH7/3 IgA) and H3N2 virus HA–specific IgA antibodies and influenza B virus–specific responses. Box plots detail fold changes (shown as log₁₀) for various immune features, highlighting systemic (influenza B virus HAI) and mucosal immune activation (IgA). (C) Polar plot depicting systemic, broad influenza A virus responders (group 3, purple), showing elevated systemic antibody responses to multiple influenza A virus strains (e.g., H1, H3), as well as cross-reactive IgG and antibody-dependent cellular cytotoxicity activity. Box plots show fold-change values (log₁₀) for each immune marker across responder groups. (D) Integrated radar plot comparing scaled median immune expression profiles across all responder groups (CD8⁺ T cell responders in green, mucosal responders in orange, systemic broad influenza A virus responders in purple), emphasizing distinct immune feature distributions. This integrative visualization highlights the unique baseline and postvaccination immune landscapes that define each responder profile. Box plots denote minimum to maximum values, and points are all individuals within the group. *P < 0.05, **P < 0.01, ***P < 0.001, and ****P < 0.0001, by 1-way ANOVA Kruskal-Wallis test with Dunn’s multiple-comparison test to adjust for multiple testing.

Figure 3. Automated machine learning framework for mapping and predicting LAIV immunogenicity response phenotypes.

(A) Overview of the automated machine learning framework developed to predict LAIV response phenotypes using baseline immune data from mucosal and blood samples, capturing multidimensional immune parameters such as transcriptomics, antibody titers, bacterial load, flu-specific T cell responses, and comprehensive immunophenotyping. (B) Step 1, balanced data partitioning: the dataset is split into training (80%) and testing (20%) sets, ensuring proportional representation of each immunophenotypic group (CD8⁺ T cell; mucosal; and systemic, broad influenza A responders) to maintain predictive accuracy across classes. Step 2, model optimization cycle: 10-fold cross-validation and hyperparameter tuning are applied across 141 machine learning models, each iteratively trained and validated to identify the best predictors of vaccine response. Step 3, model evaluation and scoring: predictive performance metrics, including specificity, sensitivity, and AUC, are calculated on the test set (20%) for model validation. Feature importance scores are computed for each baseline variable, providing a ranked analysis of each immune parameter’s contribution to LAIV response prediction. (C) Multiclass ROC plot of the gradient boosting machine model evaluated on the test set (20%), displaying predictive accuracy across all 3 classes: CD8⁺ T cell responders (green); mucosal responders (orange); and systemic, broad influenza A responders (purple) in a one-versus-all comparison. (D) Variable importance score table for the gradient boosting machine model, showcasing the cumulative importance of the selected baseline features across the 3 predicted classes, highlighting the most influential parameters in LAIV immunogenicity prediction.

Figure 4. Baseline immune landscape and viral shedding profiles predictive of LAIV response groups.

(A) Heatmap of baseline immune features predictive of LAIV response groups, organized by hierarchical clustering to show feature relationships and variations across groups (Euclidean distance, Ward’s D2 clustering method). Each cell reflects a scaled expression level, with red representing high expression and blue indicating low expression, revealing the distribution of immune features at baseline across the identified immunophenotypic clusters. (B) The proportion of seropositive children (HAI titer ≥10) at baseline (before vaccination) within each responder group and across all 3 LAIV-strains, pH1N1, H3N2, and influenza B virus. (C) The proportion of children that shed LAIV strains (pH1N1, H3N2, and B) on day 2 and day 7 after vaccination across all 3 responder groups. (D) Box plots showing baseline features, including H3N2 HAI geometric mean titer (gmt), titer of antibodies binding H3 HA from A/Switzerland/9715293/2013 analyzed by influenza virus protein microarray (H3 HA SWISS IVPM), titer of antibodies binding NA from group 2 (N2) and frequency of influenza B virus HA–specific CD8⁺ T cells producing IFN-γ across all 3 responder groups, CD8⁺ T cell responders (green); mucosal responders (orange); and systemic, broad influenza A virus responders (purple). Box plots denote minimum to maximum values, and points are all individuals within the group. *P < 0.05, **P < 0.01, ***P < 0.001, and ****P < 0.0001, by 1-way ANOVA Kruskal-Wallis test with Dunn’s multiple-comparison test to adjust for multiple testing. (E) Forest plots showing log-odds estimates from a logistic regression model. The plots illustrate the association of the mucosal responder (orange) and systemic, broad influenza A virus responder (purple) groups with the outcomes of viral shedding (day 2 and 7) and HAI seropositivity, relative to the CD8 T-cell responder group which serves as the reference category. The analysis is stratified by LAIV strain (H3N2, pH1N1, and B), and the error bars represent the confidence intervals for the log-odds estimates.

Figure 5. Baseline immune features and pathway-level determinants of LAIV responder profiles.

(A–C) Polar plots illustrating scaled median expression of immune pathways across 3 responder groups: (A) CD8⁺ T cell responders (group 1, green); (B) mucosal responders (group 2, orange); and (C) systemic, broad influenza A virus responders (group 3, purple). (D) Combined radar plot showing integrated immune pathway signatures across the 3 responder groups, highlighting intergroup differences in pathway activation. (E) SHAP (SHapley Additive exPlanations) summary plots showing the contribution of baseline features to model predictions for each responder group (CD8⁺ T cell responders, group 1, green; mucosal responders, group 2, orange; and systemic, broad influenza A virus responders, group 3, purple). The intercept represents the baseline prediction before feature contributions. All other factors include the combined effect of features not displayed in the top 10 contributors. Prediction (purple bar) is the final probability derived by summing the intercept, top 10 feature contributions, and all other factors. Feature impacts are color coded as follows: green (positive, 1) increases the likelihood of belonging to the group, and red (negative, –1) decreases it. The top 10 features are ranked by their contribution to the prediction, providing insights into key drivers of LAIV response profiles. (F) The decision tree depicts the splits made at each node based on immune feature thresholds. Splits are chosen to maximize class separation, with fitted class probabilities displayed as group 1 (CD8⁺ T cell responders, green), group 2 (mucosal responder, orange), and group 3 (systemic, broad influenza A virus responders, purple) for each terminal node. The coverage percentage represents the proportion of observations falling under each rule. Nodes are labeled with thresholds and the conditions that define group separation, with terminal nodes representing the predicted group and associated probabilities.