Academic

Abstract

The quantification of microbiome using next-generation sequencing technologies has sparked intense interest in the study of the human microbiome and its relation with human health. In this talk, I will introduce my work on statistical methods tailored to the complex characteristics of microbiome data. I will first introduce Functional Tensor SVD, a method for the dimension reduction of longitudinal microbiome data with varying time points across subjects. The new method can extract key components in the trajectories of bacterial abundance, identify representative bacterial taxa for these key trajectories, and group subjects based on the change of bacteria abundance over time. I will then introduce my series of work on the association analysis of microbiome data, including regression of high-dimensional compositional covariates and two-sample testing of taxonomic tree-based count data.