Metagenomic Analysis and Features Selection in Human Oral Microbiota Associated with Periodontal Disease

Metagenomic information provides deeper understanding of the ecological role, metabolism, and evolutionary history of microbes in a given ecosystem by analyzing environmental DNA directly without prior cultivation. In this paper, we propose methods and implement tools to facilitate the bioinformatics analysis of metagenomic data. The open-source metagenomic sequences data analysis softwares were integrated to construct accessible platforms for metagenomic data analysis. The functionality of the platform is examined by composition analysis of human oral microbiome. Furthermore, a feature selection algorithm was also proposed to choice more informative features among many variables. By using the algorithm, the support vector machine can get absolute accuracy with few features.