Statistics Colloquium

 Hypothesis testing of the human microbiome decomposition using evolutionary trees

Thanks to next-generation sequencing technologies, researchers can gain access to millions of DNA sequences from a single experiment. A major area of interest has been the analysis of the human micro biome, which represents the total genome of the microorganisms living in the human body. The human body contains about 10^13 human cells and 10^14 bacterial cells, so the microbiome is frequently perceived as an extended human genome. Different parts of the body have distinct bacterial compositions, that are closely related to the presence of diseases, such as inflammatory bowel disease, peripheral vascular disease, asthma and hypertension. That is why, developing statistical procedures for comparison and identification of microbial diversity can be essential in the early diagnosis or curing of these and many other diseases.

 In this project, we develop a two-sample test statistic to test the hypothesis that the overall microbial compositions of two samples are different. We also establish its theoretical properties and nice asymptotic F-distribution. None of the existing methods establish exact distributions and rely only on permutation algorithms (PERMANOVA). We demonstrate through simulations and real data example the superiority of the type 1 error and computational efficiency of our method over the rest of them.