Distance-Based Mutual Information Test of Multivariate Association in Microbiome Multiomics Studies

Thomas M. Menino Convention & Exhibition Center 

An increasing number of microbiome studies are simultaneously collecting host omics profiles to better understand microbe-host interplay. Although, there remain analytic challenges due to the dimensionality, heterogeneity, and sparsity of the data, as well as the complexity of interactions within and between modalities. We focus on measuring global multivariate associations between the microbiome and a host omics modality, as it is often the first step in multiomics analysis due to its ability to aggregate effects across all features. Additionally, in microbiome studies global analysis has biologically meaningful connections to ecological diversity. We propose a distance-based mutual information test of global association for microbiome multiomics integration. The use of mutual information is advantageous, as it is able to capture general forms of dependence. This includes linear, nonlinear, monotone, and nonmonotone associations, which most correlation metrics can fail to capture. We develop a k-nearest neighbor estimation procedure and corresponding permutation test for independence, as well as an ensemble distance metric. Simulation studies show that our distance-based mutual information test controls type I error and maintains good power under a variety of alternative dependence structures. We apply our method to a multiple sclerosis case-control study to elucidate the gut microbiome's association with stool and plasma short chain fatty acids.

Association test

Distance statistics

Microbiome

Multiomics integration

Multivariate

Mutual information