A Review and Tutorial of Machine Learning Methods for Microbiome Host Trait Prediction

Abstract

With the growing importance of microbiome research, there is increasing evidence that host variation in microbial communities is associated with overall host health. Advancement in genetic sequencing methods for microbiomes has coincided with improvements in machine learning, with important implications for disease risk prediction in humans. One aspect specific to microbiome prediction is the use of taxonomy-informed feature selection. In this review for non-experts, we explore the most commonly used machine learning methods, and evaluate their prediction accuracy as applied to microbiome host trait prediction. Methods are described at an introductory level, and R/Python code for the analyses is provided.

https://www.frontiersin.org/articles/10.3389/fgene.2019.00579/full

Disentangling Interactions in the Microbiome: A Network Perspective

Abstract

Microbiota are now widely recognized as being central players in the health of all organisms and ecosystems, and subsequently have been the subject of intense study. However, analyzing and converting microbiome data into meaningful biological insights remain very challenging. In this review, we highlight recent advances in network theory and their applicability to microbiome research. We discuss emerging graph theoretical concepts and approaches used in other research disciplines and demonstrate how they are well suited for enhancing our understanding of the higher-order interactions that occur within microbiomes. Network-based analytical approaches have the potential to help disentangle complex polymicrobial and microbe–host interactions, and thereby further the applicability of microbiome research to personalized medicine, public health, environmental and industrial applications, and agriculture.

https://www.sciencedirect.com/science/article/pii/S0966842X16301858