Interpretable machine learning framework reveals novel gut microbiome features in predicting type 2 diabetes

Gut microbiome targets for type 2 diabetes (T2D) prevention among human cohorts have been controversial. Using an interpretable machine learning-based analytic framework, we identified robust human gut microbiome features, with their optimal threshold, in predicting T2D. Based on the results, we constructed a microbiome risk score (MRS), which was consistently associated with T2D across 3 independent Chinese cohorts involving 9111 participants (926 T2D cases). The MRS could also predict future glucose increment, and was correlated with a variety of gut microbiota-derived blood metabolites. Faecal microbiota transplantation from humans to germ-free mice demonstrated a causal role of the identified combination of microbes in the T2D development. We further identified adiposity and dietary factors which could prospectively modulate the MRS, and found that body fat distribution may be the key factor modulating the gut microbiome-T2D relationship. Taken together, we proposed a new analytical framework for the investigation of microbiome-disease relationship. The identified microbiota may serve as potential drug targets for T2D in future.