A0561
Title: Bayesian structural learning with parametric marginals for count data: An application to microbiota systems
Authors: Veronica Vinciotti - University of Trento (Italy)
Reza Mohammadi - University of Amsterdam (Netherlands)
Pariya Behrouzi - Wageningen University and Research (Netherlands) [presenting]
Abstract: High-dimensional and heterogeneous count data are collected in various applied fields. The aim is to look closely at high-resolution sequencing data on the microbiome, which has enabled researchers to study the genomes of entire microbial communities. Revealing the underlying interactions between these communities is of vital importance to learn how microbes influence human health. To perform structural learning from multivariate count data such as these, a novel Gaussian copula graphical model is developed with two key elements. Firstly, parametric regression is employed to characterize the marginal distributions. This step is crucial for accommodating the impact of external covariates. Neglecting this adjustment could potentially introduce distortions in the inference of the underlying network of dependences. Secondly, a Bayesian structure learning framework is advanced, based on a computationally efficient search algorithm that is suited to high dimensionality. The approach returns simultaneous inference of the marginal effects and of the dependence structure, including graph uncertainty estimates. A simulation study and a real data analysis of microbiome data highlight the applicability of the proposed approach in inferring networks from multivariate count data in general and its relevance to microbiome analyses in particular. The proposed method is implemented in the R package BDgraph.
