CoMMiT: Co-informed inference of microbiome-metabolome interactions via transfer learning
Journal:
arXiv
Published Date:
Jun 30, 2025
Abstract
Recent multi-omic microbiome studies enable integrative analysis of microbes
and metabolites, uncovering their associations with various host conditions.
Such analyses require multivariate models capable of accounting for the complex
correlation structures between microbes and metabolites. However, existing
multivariate models often suffer from low statistical power for detecting
microbiome-metabolome interactions due to small sample sizes and weak
biological signals. To address these challenges, we introduce CoMMiT,
Co-informed inference of Microbiome-Metabolome Interactions via novel Transfer
learning models. Unlike conventional transfer-learning methods that borrow
information from external datasets, CoMMiT leverages similarities across
metabolites within a single cohort, reducing the risk of negative transfer
often caused by differences in sequencing platforms and bioinformatic pipelines
across studies. CoMMiT operates under the flexible assumption that auxiliary
metabolites are collectively informative for the target metabolite, without
requiring individual auxiliary metabolites to be informative. CoMMiT uses a
novel data-driven approach to selecting the optimal set of auxiliary
metabolites. Using this optimal set, CoMMiT employs a de-biasing framework to
enable efficient calculation of p-values, facilitating the identification of
statistically significant microbiome-metabolome interactions. Applying CoMMiT
to a feeding study reveals biologically meaningful microbiome-metabolome
interactions under a low glycemic load diet, demonstrating the diet-host link
through gut metabolism.
