Bayesian Sparse Regression for Microbiome-Metabolite Data Integration

2026-05-18

AI Summary

Integrating microbiome and metabolome data is challenged by extensive missing metabolite values and the compositional nature of microbial data, rendering conventional variable selection methods inadequate. This work proposes a novel Bayesian sparse regression approach that, for the first time, jointly models the two distinct missingness mechanisms of metabolites within a unified framework while incorporating a compositionally appropriate Bayesian prior. The method simultaneously achieves accurate variable selection and imputation of missing values. In simulation studies, it successfully recovers true metabolite signals and identifies key microbial predictors. Applied to real colorectal cancer data, it effectively uncovers latent associations between the microbiome and metabolome, substantially enhancing the reliability of integrative inference.

Abstract

Numerous studies have shown that microbial metabolites, which represent the products of bacteria in the human gut, play a key role in shaping cancer risk and response to treatment. However, metabolite data typically contain a large proportion of missing values, which may result from either low abundance or technical challenges in data processing. Moreover, given the compositionality of microbiome data, where the observed abundances can only be interpreted on a relative scale, standard variable selection methods are not applicable. In this project, we propose a novel Bayesian regression method to address these challenges in the integration of metabolite and microbiome data. Key features of our proposed model include modeling the two different mechanisms of missingness for the metabolite data and adopting a Bayesian prior designed to address the compositional characteristics of microbiome data. We demonstrate on simulated data that our proposed model can accurately impute the unobserved true metabolite values and correctly select the relevant microbiome predictors. We further illustrate our method using real data from a study focused on understanding the interplay between the microbiome and metabolome in colorectal cancer.

Problem

• microbiome-metabolite integration
• missing data
• compositional data
• variable selection
• Bayesian regression

Innovation

• Bayesian sparse regression
• microbiome-metabolite integration
• compositional data
• missing data mechanisms
• variable selection