MDITRE: scalable and interpretable machine learning for predicting host status from temporal microbiome dynamics

Abstract

Longitudinal microbiome datasets are being generated with increasing regularity, and there is broad recognition that these studies are critical for unlocking the mechanisms through which the microbiome impacts human health and disease. Yet, there is a dearth of computational tools for analyzing microbiome time-series data. To address this gap, we developed an open-source software package, MDITRE, which implements a new highly efficient method leveraging deep-learning technologies to derive human-interpretable rules that predict host status from longitudinal microbiome data. Using semi-synthetic and a large compendium of publicly available 16S rRNA amplicon and metagenomics sequencing datasets, we demonstrate that in almost all cases, MDITRE performs on par or better than popular uninterpretable machine learning methods, and orders-of-magnitude faster than the prior interpretable technique. MDITRE also provides a graphical user interface, which we show through use cases can readily derive biologically meaningful interpretations linking patterns of microbiome changes over time with host phenotypes.