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

ROBUST HYPERPARAMETER ESTIMATION PROTECTS AGAINST HYPERVARIABLE GENES AND IMPROVES POWER TO DETECT DIFFERENTIAL

Belinda Phipson1, Stanley Lee2, Ian J Majewski2

  • 1Murdoch Childrens Research Institute.

The Annals of Applied Statistics
|April 4, 2017
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

The roles of the acetyltransferase domains of the chromatin regulators KAT6A and KAT6B in vivo.

Development (Cambridge, England)·2026
Same author

KAT6A is essential for developmental control gene expression in neural stem and progenitor cells.

PLoS genetics·2026
Same author

Acetyl-carnitine improves hyperactivity and learning deficits in <i>KAT6A</i> haploinsufficient mice.

Life science alliance·2026
Same author

TNF-⍺-mediated myeloid-instructed CD14<sup>+</sup>CD4<sup>+</sup> T cells are associated with poor survival in lung adenocarcinoma.

Cell reports. Medicine·2026
Same author

Mbd4 and MutSα protect cells from spontaneous deamination of 5-methylcytosine.

Nucleic acids research·2026
Same author

Interleukin 4 selectively expands functional type 1 conventional dendritic cells from bone marrow progenitors.

Cell reports·2025
Same journal

Inference on summaries of a model-agnostic longitudinal variable importance trajectory with application to suicide prevention.

The annals of applied statistics·2026
Same journal

A NOVEL BAYESIAN FRAMEWORK UNCOVERING BRAIN CONNECTIVITY-TO-SHAPE RELATIONSHIP IN PRECLINICAL ALZHEIMER'S DISEASE.

The annals of applied statistics·2026
Same journal

EVALUATING MULTIPLEX DIAGNOSTIC TEST USING PARTIALLY ORDERED BAYES CLASSIFIER.

The annals of applied statistics·2026
Same journal

BRIDGING THE GAP: ENHANCING THE GENERALIZABILITY OF EPIGENETIC CLOCKS THROUGH TRANSFER LEARNING.

The annals of applied statistics·2026
Same journal

TREATMENT EFFECT HETEROGENEITY AND IMPORTANCE MEASURES FOR MULTIVARIATE CONTINUOUS TREATMENTS.

The annals of applied statistics·2026
Same journal

FEDERATED LEARNING OF ROBUST INDIVIDUALIZED DECISION RULES WITH APPLICATION TO HETEROGENEOUS MULTIHOSPITAL SEPSIS POPULATION.

The annals of applied statistics·2026
See all related articles

This study introduces a robust Empirical Bayes (EB) method to improve differential gene expression analysis. The new approach enhances statistical power and reliability, especially in genomic research with small sample sizes.

Area of Science:

  • Genomics
  • Statistical genetics
  • Bioinformatics

Background:

  • Differential gene expression (DE) analysis is crucial in genomics.
  • Empirical Bayes (EB) methods with moderated variances are effective for DE analysis, particularly with small sample sizes.
  • Standard EB methods can be sensitive to outlier genes with extreme variances.

Purpose of the Study:

  • To enhance differential gene expression testing by robustifying the hyperparameter estimation in Empirical Bayes procedures.
  • To improve the reliability and statistical power of DE analysis, especially in the presence of outlier genes.

Main Methods:

  • Developed a robust hyperparameter estimation procedure for Empirical Bayes statistical tests.
  • Modified the prior distribution informativeness for outlier genes.
Keywords:
Empirical BayesRNA-seqgene expressionmicroarraysoutliersrobustness

Related Experiment Videos

  • Ensured the robust algorithm is fast, numerically stable, and allows exact small-sample null distributions.

    • Main Results:

    • The robust EB method reduces spurious identification of DE genes due to hypervariable genes.
    • It increases statistical power for the majority of genes.
    • Simulations demonstrate comparable performance to standard EB without outliers, but superior power and robustness with outliers.
    • Case studies show successful identification and downweighting of genes linked to hidden covariates.

    Conclusions:

    • The robust EB method provides a more powerful and reliable approach for differential gene expression analysis.
    • It effectively handles outlier genes, improving the detection of biologically relevant DE genes.
    • The procedure is implemented in the widely used limma software package.