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

Abstract

We developed MicroKPNN, a prior-knowledge guided interpretable neural network for microbiomebased human host phenotype prediction. The prior-knowledge used in MicroKPNN includes the metabolic activities of different bacterial species, phylogenetic relationships, and bacterial community structure. Application of MicroKPNN to seven gut microbiome datasets (involving five different human diseases including inflammatory bowel disease, type 2 diabetes, liver cirrhosis, colorectal cancer, and obesity) shows that incorporation of the prior knowledge helped improve the microbiome-based host phenotype prediction. MicroKPNN outperformed fully-connected neural network based approaches in all seven cases, with the most improvement of accuracy in the prediction of type 2 diabetes. MicroKPNN outperformed a recently developed deep-learning based approach DeepMicro, which selects the best combination of autoencoder and machine learning approach to make predictions, in six out of the seven cases. More importantly, we showed that MicroKPNN provides a way for interpretation of the predictive models. Our results suggested that the metabolic potential of the bacterial species contributed more than the two other sources of prior knowledge. MicroKPNN is publicly available at https://github.com/mgtools/MicroKPNN.