MicroSIA: A Gut-Microbes Information-Extraction Method with Semantic Inverse Analysis for Discovering Unique Bacteria-Combinations in Nationality

Extraction of gut-microbes information is important for analyzing the effects on human gut microbiome from the difference of human attributes such as nationality, gender, age and so on. It is pointed out that human gut microbiome, a set of bacteria, has various pathological and biological impacts on a hosting human body system. However, analyzing and estimating such kinds of impact from biological data resources are difficult even for data analysts with biological background. This paper presents MicroSIA, a new analytical method for human gut microbiome's effect by extracting the unknown relations with other adjunct metadata such as human attributes with Semantic Inverse Analysis. The most important feature of our method is the inverse processes (Semantic Inverse Analysis, computing the selection of axes in inversed direction to clustering) to discover potentially existing bacteria-combinations for classifying nationalities in human attribute data. MicroSIA extracts unique bacteria-combination selected from all bacteria-combinations by our original criteria such as the purity of a data cluster and the range of target human attributes. This paper also presents experimental studies on gut-microbes information acquisition to show the feasibility and the effectiveness of our method.