Abstract:
|
In human microbiome studies, it is essential to evaluate the association between microbial group (e.g., community or clade) and a host phenotype of interest. Many microbial group association tests have been proposed, taking into account the unique features of the microbiome data (e.g., high-dimensionality, compositionality, phylogenetic relationship). These tests generally fall in the class of aggregation tests which amplify the overall association by combining all the underlying microbial signals; as such, they are powerful when many species are associated (i.e., low sparsity). In practice, the microbial association signals can be highly sparse, a situation in which we have difficulty to discover the group association. Hence, here we introduce a powerful microbial group association test for sparse microbial association signals, namely, microbiome higher criticism analysis (MiHC). MiHC is a data-driven test taken in a search space by tailoring the higher criticism test to incorporate phylogenetic information and/or modulate sparsity levels. Our simulations show that MiHC maintains a high power at different phylogenetic relevance and sparsity levels with correct type I error control
|