Trends in Machine Learning and Feature Selection Stability for Human Gut Microbiome (Shotgun Metagenomics) and Metabolomics Matched Datasets

Microbiome research is often limited by methodological inconsistencies that reduce reproducibility and functional insight. Traditional taxonomy-based profiling is limited by sparse data, variable resolution, and reliance on gDNA sequencing which provides only indirect links to microbial function. Multi-omics integration offers a framework for linking community composition to functional outputs, but progress has been hindered by the lack of standardized frameworks and inconsistent use of machine learning. In particular, feature selection stability, which is central to biomarker discovery and experimental validation, remains underexplored. Here, we systematically benchmarked three widely used algorithms (Elastic Net, Random Forest, XGBoost) across seven multi-omics integration strategies and single-omics models. Additionally, we evaluated the impact of transforming metabolomics and taxonomic abundance data. Using human gut microbiome datasets that integrate metagenomic taxonomic profiles with metabolomics, we evaluated models for 9 binary and 8 continuous outcomes across 20 train/test splits per dataset. We further assessed the effect of feature reduction on both predictive accuracy and feature selection stability. Nonlinear learners were most consistently competitive: continuous outcomes favored metabolomics-dominant models, whereas binary outcomes favored stacked multi-omics models. Random Forest and XGBoost also yielded greater feature selection stability, particularly for full dimensional metabolomics data. Together, these findings demonstrate how integration strategy, algorithm choice, and data preprocessing jointly shape predictive performance and feature selection reproducibility in multi-omics microbiome modeling.