Understanding microbiome dynamics via interpretable graph representation learning

TL;DR

This paper introduces an interpretable graph learning method to model and analyze the complex, dynamic interactions within microbiomes, aiding in understanding their role in health and disease.

Contribution

It develops a novel low-dimensional representation of time-evolving microbiome graphs that preserves dynamics and highlights key microbial interactions related to clinical conditions.

Findings

Effective extraction of impactful microbial clusters

Identification of microbe interactions linked to diseases

Validated on synthetic and real microbiome data

Abstract

Large-scale perturbations in the microbiome constitution are strongly correlated, whether as a driver or a consequence, with the health and functioning of human physiology. However, understanding the difference in the microbiome profiles of healthy and ill individuals can be complicated due to the large number of complex interactions among microbes. We propose to model these interactions as a time-evolving graph whose nodes are microbes and edges are interactions among them. Motivated by the need to analyse such complex interactions, we develop a method that learns a low-dimensional representation of the time-evolving graph and maintains the dynamics occurring in the high-dimensional space. Through our experiments, we show that we can extract graph features such as clusters of nodes or edges that have the highest impact on the model to learn the low-dimensional representation. This information can be crucial to identify microbes and interactions among them that are strongly correlated with clinical diseases. We conduct our experiments on both synthetic and real-world microbiome datasets.