|
Abstract:
|
The importance of human microbiome is being increasingly recognized, and researchers are more than ever interested in studying associations between microbial features and human health. Microbiome data are high dimensional, and some or even most microbial taxa often might not be associated with the outcome of interest. Realizing the existing methods' susceptibility to the adverse effects of noise accumulation, we introduce Adaptive Microbiome Association Test (AMAT), a novel and powerful tool for multivariate microbiome association analysis, which unifies the blessings of feature selection and the robustness of adaptive tests. AMAT first alleviates the burden of noise accumulation via distance correlation learning, and then conducts a data-adaptive association test under the flexible generalized linear model framework. Extensive simulation studies and real data applications demonstrate that AMAT is highly robust and often more powerful than several existing methods, while preserving the correct type I error rate. Besides, applying AMAT to a high taxonomic rank can provide a useful preliminary screening, and facilitate more targeted downstream microbiome fine mapping.
|
