Biology subjects

Weaver, N. E.

Publications and source records attributed to Weaver, N. E..

2 recordsLinked to original sources

bioRxiv2024

SimMiL: Simulating Microbiome Longitudinal Data

0.Structured AbstractO_ST_ABSMotivationC_ST_ABSThe quantity of statistical tools designed for omics data analysis has grown rapidly with the ability to collect large sets of human health data, particularly longitudinal data sets. Most tools are assessed for performance using simulated datasets constructed to mimic a handful of relevant characteristics from real world data sets. Consequently, the simulated data sets, and their respective simulation frameworks, are too narrow in scope to qualify as a standard for assessment in longitudinal omics analyses. ResultsHere we present the flexible and accessible simulation framework and software package called SimMiL (Simulating Microbiome Longitudinal data) capturing three general components of longitudinal microbiome data: (i) absence/presence of microbes, (ii) individual microbe abundance, and (iii) microbiome community composition over time. The framework is assessed by replicating the Type I error and Power analyses of a broad range of statistical tools (MirKAT, repeated measures permANOVA, and a modified kernel association test). Software AvaliabilityThe simulation framework is at https://github.com/nweaver111/SimMiL

bioinformatics↗

bioRxiv2020

Accessible Analysis of Longitudinal Data with Linear Mixed Effects Models

Longitudinal mouse models are commonly used to study possible causal factors associated with human health and disease. However, the statistical models, such as two-way ANOVA, often applied in these studies do not appropriately model the experimental design, resulting in biased and imprecise results. Here, we describe the linear mixed effects (LME) model and how to use it for longitudinal mice studies. We re-analyze a dataset published by Blanton et al (Science 2016) that modeled mice growth trajectories after microbiome implantation from nourished or malnourished children. We compare the fit and stability of different parameterizations of ANOVA and LME models; most models found the nourished vs. malnourished growth trajectories differed significantly. We show through simulation that the results from the two-way ANOVA and LME models are not always consistent. Incorrectly modeling correlated data can result in increased rates of false positives or false negatives, supporting the need to model correlated data correctly. We provide an interactive Shiny App to enable accessible and appropriate analysis of longitudinal data using LME models.

bioinformatics↗