Date & Time
May 7, 2021, 11:00 am – 12:00 pm
Title: Phylogenetically informed Bayesian truncated copula graphical models for microbial association networks
Abstract: Microbes play a critical role in host health. The advancement of high-throughput sequencing technologies provides opportunities for a deeper understanding of microbe-microbe interaction. However, due to limited sequencing depth, quantitative microbiome data are zero-inflated. We propose a novel phylogenetically informed Bayesian truncated Gaussian copula graphical model that explicitly accounts for zero-inflation and incorporates microbes’ evolutionary information through a phylogenetic tree prior. Simulations suggest that the proposed phylogenetic tree prior substantially improves the estimation of microbial interaction networks. We illustrate our method by an analysis of a quantitative microbiome profiling dataset.