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 stable gene selection in microarray data analysis.

Kun Yang1, Zhipeng Cai, Jianzhong Li

  • 1Department of Computer Science and Engineering, Harbin Institute of Technology, Harbin 150001, China. kunyang@hit.edu.cn

BMC Bioinformatics
|April 29, 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

Injectate spread following posterior hip pericapsular block: a preliminary single-case anatomical observation in a formalin-fixed cadaver.

Frontiers in pain research (Lausanne, Switzerland)·2026
Same author

Targeting NFS1-mediated ferroptosis mitigates alveolar injury in experimental idiopathic pulmonary fibrosis.

Toxicology and applied pharmacology·2026
Same author

Climatic Niche Dynamics and Potential Distribution of the Invasive Sweet Potato Weevil (<i>Cylas formicarius</i>) in China.

Biology·2026
Same author

Targeting myofibroblast copper vulnerability reverses pulmonary fibrosis via METTL3-directed STAT6 m6A driving cuproptosis.

Journal of advanced research·2026
Same author

Nationwide occurrence of p-phenylenediamine antioxidants and their derivatives in coastal sediments across China.

Marine pollution bulletin·2026
Same author

Effects of replacing dietary glucose with fructose on intestinal morphology, oxidative status, and epithelial responses in weaned pigs.

Journal of animal science·2026
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026
Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026
See all related articles

This study introduces two novel gene selection methods for microarray analysis that effectively handle unbalanced sample sizes. These methods improve classification accuracy, offering robust gene identification for biological research.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Microarray data analysis presents challenges due to a high gene-to-sample ratio.
  • Gene selection aims to identify significant differentially expressed genes, crucial for classification performance.
  • Unbalanced sample class sizes pose a significant difficulty in existing gene selection methods.

Purpose of the Study:

  • To propose novel gene selection methods robust to unbalanced sample class sizes.
  • To develop methods that do not rely on explicit statistical models for gene expression values.
  • To enhance classification performance in microarray data analysis.

Main Methods:

  • Developed two new gene selection algorithms.
  • Evaluated methods on eight public microarray datasets.

Related Experiment Videos

  • Utilized leave-one-out and 5-fold cross-validation for performance assessment.

    • Main Results:

    • Proposed methods are unaffected by unbalanced sample class sizes.
    • Classification accuracy was measured using top-ranked genes from training datasets.
    • Experimental results demonstrated the efficiency and effectiveness of the proposed methods.

    Conclusions:

    • The novel gene selection methods are efficient, effective, and robust.
    • Selected genes lead to more accurate classification with SVM and KNN classifiers, especially with unbalanced data.
    • These methods offer a significant improvement for gene selection in complex biological datasets.