Should We Abandon the t-Test in the Analysis of Gene Expression Microarray Data: A Comparison of Variance Modeling Strategies

High-throughput post-genomic studies are now routinely and promisingly investigated in biological and biomedical research. The main statistical approach to select genes differentially expressed between two groups is to apply a t-test, which is subject of criticism in the literature. Numerous alternatives have been developed based on different and innovative variance modeling strategies. However, a critical issue is that selecting a different test usually leads to a different gene list. In this context and given the current tendency to apply the t-test, identifying the most efficient approach in practice remains crucial. To provide elements to answer, we conduct a comparison of eight tests representative of variance modeling strategies in gene expression data: Welch's t-test, ANOVA [1], Wilcoxon's test, SAM [2], RVM [3], limma [4], VarMixt [5] and SMVar [6]. Our comparison process relies on four steps (gene list analysis, simulations, spike-in data and re-sampling) to formulate comprehensive and robust conclusions about test performance, in terms of statistical power, false-positive rate, execution time and ease of use. Our results raise concerns about the ability of some methods to control the expected number of false positives at a desirable level. Besides, two tests (limma and VarMixt) show significant improvement compared to the t-test, in particular to deal with small sample sizes. In addition limma presents several practical advantages, so we advocate its application to analyze gene expression data.

• Publication year

  2010

• Venue

  PLoS ONE

• Publication date

  2010-09-03

• Fields of study

  Biology, Medicine, Computer Science

• Identifiers
  DOI 10.1371/journal.pone.0012336PMID 20838429PMCID 2933223
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Moderated effect size and P-value combinations for microarray meta-analyses

  2009cited by this paper
• Comparison of small n statistical tests of differential expression applied to microarrays

  2009influential reference
• Prediction of future metastasis and molecular characterization of head and neck squamous-cell carcinoma based on transcriptome and genome analysis by microarrays

  2008cited by this paper
• A comparative study of different machine learning methods on microarray gene expression data

  2008cited by this paper
• Consolidated strategy for the analysis of microarray spike-in data

  2008cited by this paper
• Review of the literature examining the correlation among DNA microarray technologies

  2007cited by this paper
• A comprehensive evaluation of SAM, the SAM R-package and a simple modification to improve its performance

  2007cited by this paper
• A structural mixed model for variances in differential gene expression studies.

  2007cited by this paper
• Gene-expression profiling of systemic anaplastic large-cell lymphoma reveals differences based on ALK status and two distinct morphologic ALK+ subtypes.

  2007cited by this paper
• Transcriptome classification of HCC is related to gene alterations and to new therapeutic targets

  2007cited by this paper
• Exquisite Sensitivity of TP53 Mutant and Basal Breast Cancers to a Dose-Dense Epirubicin−Cyclophosphamide Regimen

  2007cited by this paper
• Microarray data analysis: from disarray to consolidation and consensus

  2006cited by this paper
• Significance testing for small microarray experiments

  2005cited by this paper
• Differential gene expression detection using penalized linear regression models: the improved SAM statistics

  2005cited by this paper
• An expression index for Affymetrix GeneChips based on the generalized logarithm

  2005cited by this paper
• VarMixt: efficient variance modelling for the differential analysis of replicated gene expression data

  2005cited by this paper
• HOXA genes are included in genetic and biologic networks defining human acute T-cell leukemia (T-ALL).

  2005cited by this paper
• Linear Models and Empirical Bayes Methods for Assessing Differential Expression in Microarray Experiments

  2004cited by this paper
• The ade4 package - I : One-table methods

  2004cited by this paper
• Multiple Hypothesis Testing in Microarray Experiments

  2003cited by this paper
• Selecting Differentially Expressed Genes from Microarray Experiments

  2003cited by this paper
• Pitfalls in the use of DNA microarray data for diagnostic and prognostic classification.

  2003cited by this paper
• Local-pooled-error test for identifying differentially expressed genes with a small number of replicated microarrays

  2003cited by this paper
• Statistical significance for genomewide studies

  2003cited by this paper
• Repeated observation of breast tumor subtypes in independent gene expression data sets

  2003cited by this paper
• A random variance model for detection of differential gene expression in small microarray experiments

  2003cited by this paper
• Comparing three methods for variance estimation with duplicated high density oligonucleotide arrays

  2002cited by this paper
• Gene expression profiling predicts clinical outcome of breast cancer

  2002cited by this paper
• Analysis of Variance for Gene Expression Microarray Data

  2000cited by this paper
• Controlling the false discovery rate: a practical and powerful approach to multiple testing

  1995cited by this paper
• September

  1869cited by this paper

• Identification and stress-responsive expression analysis of two Hsp70 genes in Epicauta impressicornis under temperature and diapause conditions

  2026cites this paper
• Exploration of real-time fluorescence quantitative PCR by analyzing effective reference genes in Galleria mellonella (Lepidoptera: Pyralidae)

  2025cites this paper
• PLS-based gene subset augmentation and tumor-specific gene identification

  2024cites this paper
• Differential Anti-Inflammatory Effects of Electrostimulation in a Standardized Setting

  2024cites this paper
• Chronic arsenic exposure induces malignant transformation of human HaCaT cells through both deterministic and stochastic changes in transcriptome expression.

  2024cites this paper
• A pilot investigation of differential hydroxymethylation levels in patient-derived neural stem cells implicates altered cortical development in bipolar disorder

  2023cites this paper
• Comparison Between Next-Generation Sequencing and Microarrays for miRNA Expression in Cancer Samples

  2023cites this paper
• Genetic Meta-Analysis of Expression and Signaling Pathways and Analysis of Interaction Networks of Some Genes with Different Expression from The Results of Several Microwave Studies in Patients with Autism Using R Software

  2023cites this paper
• The hitchhikers' guide to RNA sequencing and functional analysis

  2023cites this paper
• Hybridization of Data-driven Threshold Algorithm with Fuzzy Particle Swarm Optimization Technique for Gene Selection in Microarray Data

  2023cites this paper
• KLB and NOX4 expression levels as potential blood-based transcriptional biomarkers of physical activity in children

  2023cites this paper
• Advances in proteomics: characterization of the innate immune system after birth and during inflammation

  2023cites this paper
• Methodology to identify a gene expression signature by merging microarray datasets

  2023cites this paper
• Combinational Drug Repurposing from Genetic Networks Applied to Alzheimer’s Disease

  2022cites this paper
• SEQENS: An ensemble method for relevant gene identification in microarray data

  2022cites this paper
• A Clinical Outcome of the Anti-PD-1 Therapy of Melanoma in Polish Patients Is Mediated by Population-Specific Gut Microbiome Composition

  2022cites this paper
• Nitrogen Signalling in Arabidopsis thaliana roots

  2022influential citation
• Integration of differential expression and network structure for 'omics data analysis

  2022cites this paper
• A feature selection-based framework to identify biomarkers for cancer diagnosis: A focus on lung adenocarcinoma

  2022cites this paper
• MIDGET: Detecting differential gene expression on microarray data

  2021cites this paper
• Comparative untargeted metabolomic profiling of induced mitochondrial

  2021cites this paper
• The horizontal transfer of Pseudomonas aeruginosa PA14 ICE PAPI-1 is controlled by a transcriptional triad between TprA, NdpA2 and MvaT

  2021cites this paper
• Contrastive analysis for scatter plot-based representations of dimensionality reduction

  2021cites this paper
• Gene Expression Microarray: Technical Fundamentals and Data Analysis

  2021cites this paper
• Comparative Untargeted Metabolomic Profiling of Induced Mitochondrial Fusion in Pancreatic Cancer

  2021cites this paper
• Construction of Reduced PPI Network for Breast and Lung Cancer Using Random Walk with Restart

  2021cites this paper
• Intrinsic Electrical Remodeling Underlies Atrioventricular Block in Athletes

  2021cites this paper
• Finding associations in a heterogeneous setting: statistical test for aberration enrichment

  2020cites this paper
• Future Computing and Informatics Journal Future Computing and Informatics Journal

  2020cites this paper
• Statistical characterization and classification of colon microarray gene expression data using multiple machine learning paradigms

  2020cites this paper
• Preparing for Life: Plasma Proteome Changes and Immune System Development During the First Week of Human Life

  2020cites this paper
• Patient Empowerment and Electronic Health Record Systems Sharing: A Design Perspective

  2020cites this paper
• Merging microarray studies to identify a common gene expression signature to several structural heart diseases

  2020cites this paper
• Using a supervised principal components analysis for variable selection in high-dimensional datasets reduces false discovery rates

  2020cites this paper
• Modeling Species Specific Gene Expression Across Multiple Regions in the Brain

  2020cites this paper
• Transcriptomic features of tumour-infiltrating CD4lowCD8high double positive αβ T cells in melanoma

  2020cites this paper
• Boolean Association Rule Mining on Microarray Gene Expression Data

  2020cites this paper
• LFQ-Analyst: An easy-to-use interactive web-platform to analyze and visualize label-free proteomics data preprocessed with MaxQuant.

  2020cites this paper
• MetaOmGraph: a workbench for interactive exploratory data analysis of large expression datasets

  2019cites this paper
• Newly identified LMO3-BORCS5 fusion oncogene in Ewing sarcoma at relapse is a driver of tumor progression

  2019cites this paper
• Gene shaving using a sensitivity analysis of kernel based machine learning approach, with applications to cancer data

  2019cites this paper
• Performance Improvement of Gene Selection Methods using Outlier Modification Rule

  2019cites this paper
• Statistical characterization and classification of colon microarray gene expression data using multiple machine learning paradigms

  2019cites this paper
• Boolean Rule Based Classification for Microarray Gene Expression Data

  2019influential citation
• Gene selection using hybrid binary black hole algorithm and modified binary particle swarm optimization.

  2019cites this paper
• Significance tests for analyzing gene expression data with small sample sizes

  2019cites this paper
• Detection and Characterization of a Mycobacterial L-Arabinofuranose ABC Transporter Identified with a Rapid Lipoproteomics Protocol.

  2019cites this paper
• Statistical Analysis of Microarray Data.

  2019cites this paper
• Characterization of Top Hub Genes in Breast and Lung Cancer Using Functional Association

  2019cites this paper
• Molecular effects of obesity and related metabolic risk factors : a transcriptomics and metabolomics approach

  2018cites this paper
• Identification of genes with universally upregulated or downregulated expressions in colorectal cancer

  2018cites this paper
• Differential Expression Analysis Based on Expression Data of Multiple Platforms

  2018cites this paper
• Fold change based approach for identification of significant network markers in breast, lung and prostate cancer

  2018cites this paper
• Impact of diet-induced obesity on the mouse brain phosphoproteome.

  2018cites this paper
• Microbial succession and metabolite changes during traditional serofluid dish fermentation

  2017cites this paper
• Targeting miR-423-5p Reverses Exercise Training–Induced HCN4 Channel Remodeling and Sinus Bradycardia

  2017influential citation
• Muscle transcriptome analysis reveals molecular pathways and biomarkers involved in extreme ultimate pH and meat defect occurrence in chicken

  2017cites this paper
• Single subject transcriptome analysis to identify functionally signed gene set or pathway activity

  2017cites this paper
• NFκB pathway analysis: An approach to analyze gene co-expression networks employing feedback cycles

  2017cites this paper
• DE-kupl: exhaustive capture of biological variation in RNA-seq data through k-mer decomposition

  2017cites this paper
• An improved analysis methodology for translational profiling by microarray

  2017influential citation
• Deciphering the genetic control of gene expression following Mycobacterium leprae antigen stimulation

  2017cites this paper
• DoEstRare: A statistical test to identify local enrichments in rare genomic variants associated with disease

  2017cites this paper
• Identification of Novel Signal Transduction, Immune Function, and Oxidative Stress Genes and Pathways by Topiramate for Treatment of Methamphetamine Dependence Based on Secondary Outcomes

  2017cites this paper
• Identification of common key genes in breast, lung and prostate cancer and exploration of their heterogeneous expression

  2017cites this paper
• RHCG and TCAF 1 promoter hypermethylation predicts biochemical recurrence in prostate cancer patients treated by radical prostatectomy

  2017cites this paper
• Evaluation of Methods for Gene Selection in Melanoma Cell Lines

  2017cites this paper
• An Efficient Semiparametric Approach for Marker Gene Selection and Patient Classification

  2017cites this paper
• Effects of mutations in the eEF1A2 gene in mouse gene expression profiles and identification of potential markers for motor neuron degeneration

  2017cites this paper
• Mètodes estadístics per al refinament del diagnòstic dels síndromes limfoproliferatius de cèl.lula B

  2017cites this paper
• Towards the complete picture: combining modelling and experimental data in a systems biology approach

  2017cites this paper
• Informative gene selection using Adaptive Analytic Hierarchy Process (A2HP)

  2017cites this paper
• Heart Failure Leads to Prolongation of the PR Interval and Atrioventricular Junction Enlargement and Ion Channel Remodelling in the

  2017cites this paper
• Exhaustive capture of biological variation in RNA-seq data through k-mer decomposition

  2017cites this paper
• Analysis of the microbiome and host-transcriptome in psoriasis and atopic dermatitis

  2017cites this paper
• A novel method for integrative biological studies

  2016cites this paper
• Streamlining and standardizing transcriptomic analysis in Amgen process development

  2016cites this paper
• Repression of p63 and induction of EMT by mutant Ras in mammary epithelial cells

  2016cites this paper
• Identification of CD177 as the most dysregulated parameter in a microarray study of purified neutrophils from septic shock patients.

  2016cites this paper
• Gene Expression Profiling of Evening Fatigue in Women Undergoing Chemotherapy for Breast Cancer

  2016cites this paper
• A crowdsourcing approach for reusing and meta-analyzing gene expression data

  2016cites this paper
• A Statistical Framework for Classification of Tumor Type from microRNA Data

  2016influential citation
• Gene Expression Profile Regulated by CREB in K562 Cell Line.

  2016cites this paper
• ROBUST HYPERPARAMETER ESTIMATION PROTECTS AGAINST HYPERVARIABLE GENES AND IMPROVES POWER TO DETECT DIFFERENTIAL EXPRESSION.

  2016cites this paper
• RHCG and TCAF1 promoter hypermethylation predicts biochemical recurrence in prostate cancer patients treated by radical prostatectomy

  2016cites this paper
• Molecular characterization of atopic dermatitis: a meta-analysis

  2016cites this paper
• Identification of phenotype-relevant differentially expressed genes in breast cancer demonstrates enhanced quantile discretization protocol's utility in multi-platform microarray data integration

  2016cites this paper
• Streamlining and Standardizing Transcriptomic Analysis in Amgen Process Development

  2016influential citation
• Finding causative genes from high-dimensional data: an appraisal of statistical and machine learning approaches

  2016cites this paper
• Prediction of drugs having opposite effects on disease genes in a directed network

  2016cites this paper
• Integrating mean and variance heterogeneities to identify differentially expressed genes

  2016cites this paper
• Regression, classification and feature selection from survival data : modeling of hypoxia conditions for cancer prognosis

  2015cites this paper
• Getting the most out of RNA-seq data analysis

  2015cites this paper
• Transcription regulatory networks in medulloblastoma.

  2015cites this paper
• Nephron Toxicity Profiling via Untargeted Metabolome Analysis Employing a High Performance Liquid Chromatography-Mass Spectrometry-based Experimental and Computational Pipeline*

  2015cites this paper
• Quantitative Proteomic Approach for MicroRNA Target Prediction Based on 18O/16O Labeling

  2015cites this paper
• MEF2B mutations in non-Hodgkin lymphoma dysregulate cell migration by decreasing MEF2B target gene activation

  2015cites this paper
• A Regression-Based Differential Expression Detection Algorithm for Microarray Studies with Ultra-Low Sample Size

  2015cites this paper
• A Critical Survey of Deconvolution Methods for Separating Cell Types in Complex Tissues

  2015cites this paper
• The American University in Cairo School of Sciences and Engineering META-ANALYSIS OF MICROARRAY DATA TO ASSESS GENDER BIASED DIFFERENTIAL GENE EXPRESSION IN HEPATIC TISSUE

  2015cites this paper