Ribeiro, A. A. | bioRxiv Science

bioRxiv2025

Deep-learning-based interpolation of longitudinal microbiome data powers biologically informative discovery

The human microbiome is a foundational and dynamic foundation for several health-related functions and disease processes. Advances in microbiome sequencing have enabled the characterization of microbial communities in several niches. Longitudinal microbiome studies further strive to discover clinically informative microbial community trajectories. However, these data are fraught with dropout events, high noise, and irregular sampling that limit and prevent the use of many available longitudinal analysis tools. To address these challenges, we introduce Bidirectional GRU-ODE-Bayes (BGOB), a deep learning framework developed for longitudinal microbiome interpolation. BGOB combines bidirectional information flow and ODE-based continuous modeling to jointly interpolate and smoothen trends across individual participants, providing uniform, denoised time intervals across patients. BGOB enables vastly improved performance in differential abundance testing and time-to-event analysis, and makes possible longitudinal analyses requiring uniformity, such as lead-lag detection and temporal clustering. After interpolation, previously low-powered datasets are able to broadly recapitulate known microbiology and elucidate interacting microbial communities. We highlight several associations between microbial taxa and disease, including novel species associated with Early Childhood Caries and disruption of key healthy gut microbiota in Inflammatory Bowel Disease. The BGOB package is publicly available at https://github.com/Rachel-Lyu/BGOB_n_test.

microbiology↗

bioRxiv2023

BZINB model-based pathway analysis and module identification facilitates integration of microbiome and metabolome data

Integration of multi-omics data is a challenging but necessary step to advance our understanding of the biology underlying human health and disease processes. To date, investigations seeking to integrate multi-omics (e.g., microbiome and metabolome) employ simple correlation-based network analyses; however, these methods are not always well-suited for microbiome analyses because they do not accommodate the excess zeros typically present in these data. In this paper, we introduce a bivariate zero-inflated negative binomial (BZINB) model-based network and module analysis method that addresses this limitation and improves microbiome-metabolome correlation-based model fitting by accommodating excess zeros. We use real and simulated data based on a multi-omics study of childhood oral health (ZOE 2.0; investigating early childhood dental disease, ECC) and find that the accuracy of the BZINB model-based correlation method is superior compared to Spearmans rank and Pearson correlations in terms of approximating the underlying relationships between microbial taxa and metabolites. The new method, BZINB-iMMPath facilitates the construction of metabolite-species and species-species correlation networks using BZINB and identifies modules of (i.e., correlated) species by combining BZINB and similarity-based clustering. Perturbations in correlation networks and modules can be efficiently tested between groups (i.e., healthy and diseased study participants). Upon application of the new method in the ZOE 2.0 study microbiome-metabolome data, we identify that several biologically-relevant correlations of ECC-associated microbial taxa with carbohydrate metabolites differ between healthy and dental caries-affected participants. In sum, we find that the BZINB model is a useful alternative to Spearman or Pearson correlations for estimating the underlying correlation of zero-inflated bivariate count data and thus is suitable for integrative analyses of multi-omics data such as those encountered in microbiome and metabolome studies.

bioinformatics↗