Robust hyperparameter estimation protects against hypervariable genes and improves power to detect differential expression

DOI10.1214/16-AOAS920zbMATH Open1400.62281arXiv1602.08678WikidataQ37730548 ScholiaQ37730548MaRDI QIDQ312950FDOQ312950

Authors: Belinda Phipson, Ian J. Majewski, Warren S. Alexander, Gordon K. Smyth, Stanley Lee 

Publication date: 9 September 2016

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Abstract: One of the most common analysis tasks in genomic research is to identify genes that are differentially expressed (DE) between experimental conditions. Empirical Bayes (EB) statistical tests using moderated genewise variances have been very effective for this purpose, especially when the number of biological replicate samples is small. The EB procedures can however be heavily influenced by a small number of genes with very large or very small variances. This article improves the differential expression tests by robustifying the hyperparameter estimation procedure. The robust procedure has the effect of decreasing the informativeness of the prior distribution for outlier genes while increasing its informativeness for other genes. This effect has the double benefit of reducing the chance that hypervariable genes will be spuriously identified as DE while increasing statistical power for the main body of genes. The robust EB algorithm is fast and numerically stable. The procedure allows exact small-sample null distributions for the test statistics and reduces exactly to the original EB procedure when no outlier genes are present. Simulations show that the robustified tests have similar performance to the original tests in the absence of outlier genes but have greater power and robustness when outliers are present. The article includes case studies for which the robust method correctly identifies and downweights genes associated with hidden covariates and detects more genes likely to be scientifically relevant to the experimental conditions. The new procedure is implemented in the limma software package freely available from the Bioconductor repository.

Full work available at URL: https://arxiv.org/abs/1602.08678

Recommendations

• Bayesian Robust Inference for Differential Gene Expression in Microarrays with Multiple Samples
• Linear Models and Empirical Bayes Methods for Assessing Differential Expression in Microarray Experiments
• Improved statistical tests for differential gene expression by shrinking variance components estimates
• A robust sequential Bayesian method for identification of differentially expressed genes
• Robust semiparametric mixing for detecting differentially expressed genes in microarray experiments

zbMATH Keywords

outliersrobustnessempirical Bayesgene expressionmicroarrays

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10) Protein sequences, DNA sequences (92D20) Empirical decision procedures; empirical Bayes procedures (62C12) Robustness and adaptive procedures (parametric inference) (62F35)

Cites Work

• Robust Empirical Bayes Analyses of Event Rates
• Robust Locally Weighted Regression and Smoothing Scatterplots
• Title not available (Why is that?)
• The Future of Data Analysis
• Parametric Empirical Bayes Inference: Theory and Applications
• Title not available (Why is that?)
• Robust Bayesian analysis
• Robust Bayesian analysis: sensitivity to the prior
• Limiting the Risk of Bayes and Empirical Bayes Estimators--Part II: The Empirical Bayes Case
• Stein's Estimation Rule and Its Competitors--An Empirical Bayes Approach
• Title not available (Why is that?)
• Robust hyperparameter estimation protects against hypervariable genes and improves power to detect differential expression
• Linear Models and Empirical Bayes Methods for Assessing Differential Expression in Microarray Experiments
• Bayesian Robust Inference for Differential Gene Expression in Microarrays with Multiple Samples

Cited In (6)

• Robust depth-based tools for the analysis of gene expression data
• Regularized t$$ t $$ distribution: definition, properties, and applications
• Continuous readout versus titer-based assays of influenza vaccine trials: sensitivity, specificity, and false discovery rates
• Robust hyperparameter estimation protects against hypervariable genes and improves power to detect differential expression
• Robust estimation of mean-variance relation
• No counts, no variance: allowing for loss of degrees of freedom when assessing biological variability from RNA-seq data

Uses Software

• Bioconductor
• edgeR
• limma
• Voom
• BRENT
• Rsubread
• csaw
• diffHic

This page was built for publication: Robust hyperparameter estimation protects against hypervariable genes and improves power to detect differential expression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q312950)