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

Evaluation of gene importance in microarray data based upon probability of selection.

Li M Fu1, Casey S Fu-Liu

  • 1Pacific Tuberculosis and Cancer Research Organization, Pasadena, California, USA. lifu@patcar.org

BMC Bioinformatics
|March 24, 2005
PubMed
Summary

This study introduces a probability analysis model to identify important genes from microarray data. The method effectively selects a minimal gene set for accurate disease classification, reducing data-fitting errors.

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

Analysis of Parkinson's disease pathophysiology using an integrated genomics-bioinformatics approach.

Pathophysiology : the official journal of the International Society for Pathophysiology·2014
Same author

Machine learning and tubercular drug target recognition.

Current pharmaceutical design·2013
Same author

The Differential Gene Expression Pattern of Mycobacterium tuberculosis in Response to Capreomycin and PA-824 versus First-Line TB Drugs Reveals Stress- and PE/PPE-Related Drug Targets.

International journal of microbiology·2009
Same author

Genome-wide analysis of intergenic regions of Mycobacterium tuberculosis H37Rv using Affymetrix GeneChips.

EURASIP journal on bioinformatics & systems biology·2008
Same author

The gene expression data of Mycobacterium tuberculosis based on Affymetrix gene chips provide insight into regulatory and hypothetical genes.

BMC microbiology·2007
Same author

Understanding the action of INH on a highly INH-resistant Mycobacterium tuberculosis strain using Genechips.

Tuberculosis (Edinburgh, Scotland)·2006

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Microarray technology enables genome-scale gene function evaluation, accelerating biomedical research.
  • Identifying gene expression patterns linked to metabolic characteristics is crucial for understanding disease development.
  • High dimensionality in microarray data presents challenges in recognizing disease-related gene patterns for classifier design.

Purpose of the Study:

  • To develop a probability analysis model for assessing gene importance in microarray data.
  • To address the challenge of selecting a minimal, biologically significant gene set for classifier design.
  • To improve the reliability and accuracy of gene selection in high-dimensional datasets.

Main Methods:

  • A novel model for probability analysis of selected genes was developed.

Related Experiment Videos

  • P-values were derived for each gene across multiple gene selection trials using varying data sample combinations.
  • Reliability analysis was conducted based on the derived P-values.

    • Main Results:

    • Gene importance is indicated by P-values, with smaller values signifying higher information content.
    • The method identified a minimal set of 19 genes for optimal classification performance on small round blue cell tumor data.
    • This approach demonstrated superior classification accuracy compared to existing literature results.

    Conclusions:

    • Probability values derived from multi-sample gene selection enhance classifier design using microarray data.
    • This method effectively reduces the tendency to fit local data particularities, improving generalizability.
    • The approach provides a robust mechanism for reliable gene selection in complex genomic studies.