Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Analyzing gene expression data in terms of gene sets: methodological issues.

Jelle J Goeman1, Peter Bühlmann

  • 1Department of Medical Statistics and Bioinformatics, Leiden University Medical Center, Leiden, The Netherlands. j.j.goeman@lumc.nl

Bioinformatics (Oxford, England)
|February 17, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Biochemical profiling and symptomatology of androgen deficiency in males with cluster headache: A prospective case-control study.

Headache·2026
Same author

Early Prediction Model for Retinopathy of Prematurity Using Placental and Neonatal Risk Factors.

Investigative ophthalmology & visual science·2026
Same author

An observational diagnostic accuracy study comparing the urine dipstick with a consensus-based reference standard for the diagnosis of urinary tract infections in older adults.

BMC geriatrics·2026
Same author

Ex vivo T2*-weighted MRI and quantitative susceptibility mapping reflect spatial iron accumulation observed on histology in frontotemporal lobar degeneration.

Neurobiology of disease·2026
Same author

[<sup>89</sup>Zr]bevacizumab PET/CT imaging of vestibular schwannomas for the prediction of bevacizumab treatment effect in patients with symptomatic <i>NF2</i>-related schwannomatosis: a study protocol for a phase II single centre, prospective, feasibility trial.

BMJ open·2026
Same author

Multiple Testing of Mix-and-Match Feature Sets in Multi-Omics.

Statistics in medicine·2026

Gene set testing methods for gene expression data have varied assumptions. This study clarifies these assumptions, highlighting that gene-centric models can yield misleading P-values, and recommends a preferred methodology for gene set analysis.

Area of Science:

  • Bioinformatics
  • Statistical Genetics
  • Computational Biology

Background:

  • Numerous statistical tests exist for gene set analysis of gene expression data, often utilizing Gene Ontology.
  • These methods differ significantly in their underlying assumptions regarding sampling units (genes vs. subjects) and testing strategies (competitive vs. self-contained).

Purpose of the Study:

  • To clarify the methodological assumptions of various gene set testing approaches.
  • To identify a preferred methodology for gene set enrichment analysis in gene expression studies.

Main Methods:

  • Comparative analysis of statistical assumptions across different gene set testing frameworks.
  • Simulation experiments to evaluate the impact of model assumptions on P-value validity.

Related Experiment Videos

Main Results:

  • P-values from gene-centric models are prone to misinterpretation due to unrealistic independence assumptions between genes.
  • Gene-centric models can produce anti-conservative P-values, potentially leading to false discoveries.
  • Competitive gene set testing approaches unnecessarily separate gene set analysis from single gene testing.

Conclusions:

  • Gene set testing methods relying on gene-centric models are statistically flawed and biologically unrealistic.
  • A unified approach that avoids the artificial dichotomy between single gene and gene set testing is preferable.
  • Careful consideration of statistical assumptions is crucial for reliable gene expression data analysis.