Fully moderated t-statistic in linear modeling of mixed effects for differential expression analysis

Abstract

BackgroundGene expression profiling experiments with few replicates lead to great variability in the estimates of gene variances. Toward this end, several moderated t-test methods have been developed to reduce this variability and to increase power for testing differential expression. Most of these moderated methods are based on linear models with fixed effects where residual variances are smoothed under a hierarchical Bayes framework. However, they are inadequate for designs with complex correlation structures, therefore application of moderated methods to linear models with mixed effects are needed for differential expression analysis.ResultsWe demonstrated the implementation of the fully moderated t-statistic method for linear models with mixed effects, where both residual variances and variance estimates of random effects are smoothed under a hierarchical Bayes framework. We compared the proposed method with two current moderated methods and show that the proposed method can control the expected number of false positives at the nominal level, while the two current moderated methods fail.ConclusionsWe proposed an approach for testing differential expression under complex correlation structures while providing variance shrinkage. The proposed method is able to improve power by moderation and controls the expected number of false positives properly at the nominal level.

The International Conference on Intelligent Biology and Medicine (ICIBM) 2019: bioinformatics methods and applications for human diseases

“…The next paper by Yu et al [8] proposed a fully moderated t-statistic in linear modeling of mixed effects for differential expression analysis. Typical gene expression profiling experiments with few replicates lead to great variability in the estimates of gene variances, and several moderated t-test methods based on linear models with mixed effects have been developed to reduce this variability and to increase power of tests of differential expression.…”

MPACT: An Advanced Informatics Tool for Metabolomics and Data Visualization of Specialized Metabolites from Complex Microbial Samples

“…5). 25,64,65 This was simplified for the calculation of effective sample size, 𝑛 !"" , from the component technical (𝜎 $ ) and biological standard deviations (𝜎 ' ) and samples sizes (𝑛 $ and 𝑛 ' , respectively) in Eq.…”

Principal component analysis revisited: fast multi-trait genetic evaluations with smooth convergence

“…For example, remote sensing techniques, such as LiDAR (Light Detection and Ranging), which can capture detailed 3D structural information about crops and trees including canopy height, width and architecture, disease status and condition to name a few [42]. Another high-throughput 1/24 example involves gene expression data, where linear mixed effect models (LMM) have been used to identify sources of variation in human medicine studies of HIV infection [85], identifying genotype-by-environment (GxE) interactions in body mass index [57] and human brain regions [77]. In a plant breeding application, [72] showed how to use LMM to jointly analyze grain yield and hyperspectral reflectance traits measured in wheat (Triticum aestivum) field trials.…”