Constructing Predictive Microbial Signatures at Multiple Taxonomic Levels

ABSTRACT

Recent advances in DNA sequencing technology have enabled rapid advances in our understanding of the contribution of the human microbiome to many aspects of normal human physiology and disease. A major goal of human microbiome studies is the identification of important groups of microbes that are predictive of host phenotypes. However, the large number of bacterial taxa and the compositional nature of the data make this goal difficult to achieve using traditional approaches. Furthermore, the microbiome data are structured in the sense that bacterial taxa are not independent of one another and are related evolutionarily by a phylogenetic tree. To deal with these challenges, we introduce the concept of variable fusion for high-dimensional compositional data and propose a novel tree-guided variable fusion method. Our method is based on the linear regression model with tree-guided penalty functions. It incorporates the tree information node-by-node and is capable of building predictive models comprised of bacterial taxa at different taxonomic levels. A gut microbiome data analysis and simulations are presented to illustrate the good performance of the proposed method. Supplementary materials for this article are available online.

KEYWORDS:

• Compositional data
• High-dimensional data
• Microbiome signatures
• Tree-structured regression

Supplementary Materials

The online supplementary materials include the following:

Section A: Additional tree information

Section B: Additional simulation results

Section C: Additional simulations

Section D: Impact of the tree structure

Section E: Issue of tree rooting

Acknowledgments

The authors gratefully acknowledge Hongzhe Li and Jun Chen for providing the data.

Funding

This work was supported by Natural Science Foundation of China (11601326), and NIH grant R01 GM59507.