Deep Learning Tools for Human Microbiome Big Data

Deep Learning is a branch of Machine Learning, which focuses on a set of algorithms that model high-level abstractions in data by using a deep representation of multiple processing layers. The goal of Machine Learning is to map input patterns to output values. This paper will suggest a potential application of Deep Learning Algorithms for the analysis of large amounts of data produced by the research of the Human Microbiome. Humans have coevolved with microbes in the environment, and each body habitat has a unique set of microorganisms (microbiota). The most abundant and well-studied microbiota are found in the gut, where the bacterial density reaches 1011-1012 cells/g in the distal human colon. The number of bacteria in the human gut has been estimated to exceed the number of somatic cells in the body by an order of magnitude and that the biomass of the gut microbiota may reach up to 1.5 kg. This paper presents different methods that have been implemented and tested on a Human Microbiome Dataset. Besides the findings concerning accuracy and runtime, the results suggest that the Deep Learning algorithms could be successfully used to analyze large amounts of Microbiota data.