Multi-View Learning to Unravel the Different Levels Underlying Hepatitis B Vaccine Response

The immune system acts as an intricate apparatus that is dedicated to mounting a defense and ensures host survival from microbial threats. To engage this faceted response provide protection against infectious diseases, vaccinations are critical tool be developed. However, vaccine responses governed by levels that, when interrogated, separately only explain fraction of the reaction. address knowledge gap, we conducted feasibility study determine if multi-view modeling could aid in gaining actionable insights on markers shared across populations, capture system’s diversity, disentangle confounders. We thus sought assess capacity responsiveness Hepatitis B virus (HBV) vaccination. Seroconversion vaccine-induced antibodies HBV surface antigen (anti-HBs) early converters (n = 21; <2 months) late 9; <6 was defined based anti-HBs titers (>10IU/L). data encompassed bulk RNA-seq, CD4+ T-cell parameters (including receptor data), flow cytometry data, clinical metadata age gender). included testing single-view joint dimensionality reductions. Multi-view reduction outperformed methods terms area under curve balanced accuracy, confirming increase predictive power gained. interpretation these findings showed age, gender, inflammation-related gene sets, pre-existing vaccine-specific T-cells associated with vaccination responsiveness. This approach complements seroconversion all single modalities. Importantly, identify what features predict response. methodology extended other trials key regulating