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

A mixture model-based strategy for selecting sets of genes in multiclass response microarray experiments.

Philippe Broët1, Alex Lewin, Sylvia Richardson

  • 1INSERM U472, 16 Avenue Paul Vaillant Couturier, 94807 Villejuif Cedex, France. broet@vjf.inserm.fr

Bioinformatics (Oxford, England)
|May 1, 2004
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

Provincial variation and associated factors in adherence to cervical cancer screening in Canada: Evidence from the Canadian Partnership for Tomorrow's Health.

Journal of medical screening·2026
Same author

Borrowing from historical control data in a Bayesian time-to-event model with flexible baseline hazard function.

Biostatistics (Oxford, England)·2026
Same author

Priorities for the development of a new rapid diagnostic test for patients with fever: a cross-sectional online survey among hospital physicians across Europe.

BMJ open·2026
Same author

Ethnic differences in Long COVID diagnosed in primary care in England (2020-2022): an observational cohort study using OpenSAFELY.

The Lancet regional health. Europe·2026
Same author

A Bayesian life-course linear structural equations model (BLSEM) to explore the development of body mass index (BMI) from the prenatal stage until middle age.

International journal of obesity (2005)·2025
Same author

Analytical approaches to evaluate risk factors of multimorbidity: a systematic scoping review protocol.

BMJ open·2025

This study introduces a new gene selection strategy for multiclass response (MCR) experiments using a flexible mixture model. The method enhances the analysis of complex gene expression patterns and aids in identifying significant genes.

Area of Science:

  • Bioinformatics
  • Statistical Genetics
  • Genomics

Background:

  • Multiclass response (MCR) experiments involve comparing more than two classes, often presenting complex gene expression patterns.
  • Traditional methods struggle with the numerous alternative hypotheses in MCR experiments.
  • Accurate gene selection is crucial for understanding biological differences across multiple conditions.

Purpose of the Study:

  • To propose a novel gene selection strategy for MCR experiments.
  • To develop a method for estimating and controlling false positive and negative discovery rates.
  • To enable the calculation of these rates for any predefined gene subset.

Main Methods:

  • A flexible mixture model is proposed for the marginal distribution of a modified F-statistic.

Related Experiment Videos

  • This model allows for the estimation of false positive and negative discovery rates.
  • The method facilitates the creation of a rule for selecting relevant gene subsets.

    • Main Results:

    • The approach's performance is demonstrated using simulated datasets.
    • Application to a real breast cancer microarray dataset highlights its utility.
    • The study identifies significant differences across three distinct biological pathways.

    Conclusions:

    • The proposed mixture model offers a robust strategy for gene selection in MCR experiments.
    • This method provides a flexible framework for managing discovery rates.
    • It aids in uncovering biologically relevant gene expression patterns in complex datasets.