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 Selection of Predictive Genes via a Simple Classifier.

Veronica Vinciotti1, Allan Tucker, Paul Kellam

  • 1School of Information Systems, Computing and Mathematics, Brunel University, Uxbridge, UK. veronica.vinciotti@brunel.ac.uk

Applied Bioinformatics
|March 17, 2006
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 genetic architecture of HIV-1 virulence.

Virus evolution·2025
Same author

HIV-phyloTSI: subtype-independent estimation of time since HIV-1 infection for cross-sectional measures of population incidence using deep sequence data.

BMC bioinformatics·2025
Same author

Racial disparity in microvascular function among women with newly diagnosed breast cancer.

American journal of physiology. Heart and circulatory physiology·2025
Same author

Intranasal delivery of mRNA expressing newly identified Acinetobacter baumannii antigens protects against bacterial lung disease.

NPJ vaccines·2025
Same author

Optimal Set of Features for Leukaemia Images with Extracted Areas of Interest.

Studies in health technology and informatics·2025
Same author

Extracting Regions of Interest and Selective Feature Application in Leukaemia Image Classification.

Studies in health technology and informatics·2025

This study introduces a robust framework for identifying disease-related genes from gene expression data, even with limited samples. The method enhances diagnostic capabilities and aids in discovering potential cures for diseases like cancer.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Identifying disease-driving genes from gene expression data is crucial for understanding disease mechanisms, improving diagnostics, and developing cures.
  • High-dimensional data with few samples, common in gene expression studies, presents significant challenges for accurate gene identification.

Purpose of the Study:

  • To present a general framework for robustly identifying predictive features (genes) from high-dimensional, small-sample gene expression data.
  • To enhance the accuracy and reliability of gene identification methods in complex biological datasets.

Main Methods:

  • Developed a general framework emphasizing simplicity and data perturbation for robust feature identification.
  • Proposed a selective naive Bayes classifier discovered via a global search technique.

Related Experiment Videos

  • Combined the classifier with data perturbation to improve robustness, especially for small sample sizes.

    • Main Results:

    • The proposed method demonstrated capability in selecting genes associated with specific diseases.
    • Validated using microarray and simulated datasets, confirming effectiveness in high-dimensional, small-sample scenarios.
    • Successfully identified genes linked to prostate cancer and viral infections.

    Conclusions:

    • The presented framework offers a simple yet robust approach for gene identification in challenging expression datasets.
    • The method's effectiveness in identifying disease-relevant genes holds promise for advancing disease diagnosis and treatment strategies.
    • Data perturbation combined with a selective naive Bayes classifier improves gene discovery in genomics research.