Predicting microbiome compositions through deep learning.

Abstract

Microbes can form complex communities that perform critical functions in maintaining the integrity of their environment or their hosts well-being. Rationally managing these microbial communities requires improving our ability to predict how different species assemblages affect the final species composition of the community. However, making such a prediction remains challenging because of our limited knowledge of the diverse physical, biochemical, and ecological processes governing microbial dynamics. To overcome this challenge, here we present a deep learning framework that automatically learns the map between species assemblages and community compositions from training data only, without knowledge of any of the above processes. First, we systematically validate our framework using synthetic data generated by classical population dynamics models. Then, we apply it to experimental data of both in vitro and in vivo communities, including ocean and soil microbial communities, Drosophila melanogaster gut microbiota, and human gut and oral microbiota. In particular, we show how our framework learns to perform accurate out-of-sample predictions of complex community compositions from a small number of training samples. Our results demonstrate how deep learning can enable us to understand better and potentially manage complex microbial communities.