Bayesian Semiparametric Inference in LongitudinalMetabolomics Data: The EarlyBird Study

The article is motivated by an application to the EarlyBird cohort study aiming to explore how anthropometrics and clinicaland metabolic processes are associated with obesity and glucose control during childhood. There is interest in inferring therelationship between dynamically changing and high-dimensional metabolites and a longitudinal response. Important aspects ofthe analysis include the selection of the important set of metabolites and the accommodation of missing data in both responseand covariate values. With this motivation, we propose a flexible but parsimonious Bayesian semiparametric joint model for theoutcome and the covariate generating processes, making novel use of nonparametric mean processes, latent factor models,and different classes of continuous shrinkage priors. The proposed approach efficiently addresses daunting dimensionalitychallenges, simplifies imputation tasks, and automates the selection of important predictors. Implementation via an efficientMarkov chain Monte Carlo algorithm appropriately accounts for uncertainty in various aspects of the analysis. Simulationexperiments illustrate the efficacy of the proposed methodology. The application to the EarlyBird cohort study illustrates itspractical utility in enabling statistical integration of different molecular processes involved in glucose production and metabolism.From this study, we were able to show that glucose levels from 5 to 16 years of age is associated with different circulating levelsof metabolites in the blood serum and can be fitted over time for a wide range of shapes of trajectories. Among the metabolitesthat contributed the most to explain the glucose trajectories are involved in different central energy metabolic pathways as wellas other metabolites, which could be used as a tool to generate new hypotheses in understanding obesity and glucose controlduring childhood and adolescence.