Capturing the dynamics of microbiomes using individual-specific networks

Abstract

Background: Longitudinal analysis of multivariate individual-specific microbiome profiles over time or across conditions remains a daunting task. The vast majority of statistical tools and methods available to study the microbiota are based upon cross-sectional data. Over the past few years, several attempts have been made to model the dynamics of bacterial species over time or across conditions. However, the field needs novel views on how to incorporate individual-specific microbial associations in temporal analyses when the focus lies on microbial interactions. Results: Here, we propose a novel data analysis framework, called MNDA, to uncover taxon neighbourhood dynamics that combines representation learning and individual-specific microbiome co-occurrence networks. We show that tracking local neighbourhood dynamics in microbiome interaction or co-occurrence networks can yield complementary information to standard approaches that only use microbial abundances or pairwise microbial interactions. We use cohort data on infants for whom microbiome data was available at 6 and 9 months after birth, as well as information on mode of delivery and diet changes over time. In particular, MNDA-based prediction models outperform traditional prediction models based on individual-specific abundances, and enable the detection of microbes whose neighbourhood dynamics are informative of clinical variables. We further show that similarity analyses of individuals based on microbial neighbourhood dynamics can be used to find subpopulations of individuals with potential relevance to clinical practice. The annotated source code for the MNDA framework can be downloaded from: https://github.com/H2020TranSYS/microbiome\_dynamics Conclusions: MNDA extracts information from matched microbiome profiles and opens new avenues to personalized prediction or stratified medicine with temporal microbiome data.

Consensus Clustering for Robust Bioinformatics Analysis

“…Method perturbation consensus clustering (MPCC) is based on the idea of generating different equally plausible base clusterings by varying the clustering algorithm [23][24][25][26], hyperparameters [27][28][29][30][31], algorithm initializations [27,32], preprocessing methods [33,34] or combinations of these aspects [9,28,35].…”

“…Starting from distinct, often random, initial conditions, these methods often converge to a distinct local minima. To make these methods stable against the randomness of the initial conditions, the clusterings generated from different initial conditions can be used as input for CC [32].…”