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

Applications of beta-mixture models in bioinformatics.

Yuan Ji1, Chunlei Wu, Ping Liu

  • 1Department of Biostatistics, The University of Texas M.D. Anderson Cancer Center, Houston, 77030, USA.

Bioinformatics (Oxford, England)
|February 17, 2005
PubMed
Summary

This study introduces a beta-mixture model to identify significant gene-expression correlations in meta-analyses and find co-expressed genes. The ICL-BIC criterion is recommended for model selection, outperforming traditional methods like AIC and BIC.

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

Letter regarding "Testosterone and abdominal aortic aneurysm".

Journal of vascular surgery·2026
Same author

NT-proBNP and Sarcopenia: Marker, Mediator, or Misclassification?

Geriatrics & gerontology international·2026
Same author

Desiderata for a biomedical knowledge network: opportunities, challenges and future directions.

Bioinformatics advances·2026
Same author

Elevated Peripheral White Blood Cell Count and Lower Urinary Tract Symptom Risk: A Population-Based Cross-Sectional Study of Chinese Men.

Research and reports in urology·2026
Same author

S2SWCLIP: semantic-optimized prompts with spatial-wavelet synergy for zero-shot anomaly detection.

Scientific reports·2026
Same author

Electrocardiogram P-Wave Dispersion and New-Onset Atrial Fibrillation: A Nested Case-Control Study.

Reviews in cardiovascular medicine·2026

Area of Science:

  • Bioinformatics
  • Statistical Genetics
  • Computational Biology

Background:

  • Gene-expression correlation analysis is crucial for understanding biological pathways.
  • Meta-analyses of microarray data often rely on arbitrary correlation thresholds.
  • Identifying co-expressed genes requires robust statistical methods.

Purpose of the Study:

  • To propose a beta-mixture model for analyzing gene-expression correlations.
  • To develop a method for identifying significant correlations in meta-analyses.
  • To find co-expressed genes more effectively.

Main Methods:

  • Utilized a beta-mixture model to segment correlation coefficients into distinct populations.
  • Applied the model to identify high correlation coefficients in gene-expression datasets.

Related Experiment Videos

  • Evaluated model selection criteria, including AIC, BIC, and ICL-BIC.

    • Main Results:

    • The beta-mixture model successfully identifies significant gene-expression correlations.
    • The proposed method aids in identifying co-expressed genes.
    • ICL-BIC demonstrated superior performance in selecting the appropriate number of mixture components compared to AIC and BIC.

    Conclusions:

    • A beta-mixture model offers a robust approach for gene-expression correlation analysis.
    • The ICL-BIC criterion is recommended for determining mixture model complexity.
    • This method enhances the identification of biologically relevant gene correlations.