Incorporating metabolic activity, taxonomy and community structure to improve microbiome-based predictive models for host phenotype prediction.

Abstract excerpt

We developed MicroKPNN, a prior-knowledge guided interpretable neural network for microbiome-based human host phenotype prediction. The prior knowledge used in MicroKPNN includes the metabolic activities of different bacterial species, phylogenetic relationships, and bacterial community structure, all in a shallow neural network. Application of MicroKPNN to seven gut microbiome datasets (involving five different...

Topics

Share this publication in a Topic to start or enrich a Post.

• Share to Diabetes Mellitus, Type 2
• Share to Diet and metabolism studies