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

Development of two-stage SVM-RFE gene selection strategy for microarray expression data analysis.

Yuchun Tang1, Yan-Qing Zhang, Zhen Huang

  • 1Secure Computing Corporation, GA 30022, USA. tyczjs@yahoo.com

IEEE/ACM Transactions on Computational Biology and Bioinformatics
|August 2, 2007
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

Precise diagnosis of Alzheimer's disease based on sex-specific gray matter characteristics.

Frontiers in neuroscience·2026
Same author

Tissue block-resolved developmental transcriptomic atlas of human fetal brainstem reveals gene modules with implications for neurological disorders.

Frontiers in cell and developmental biology·2025
Same author

Dendrobine and Erianin alleviate inflammation-induced depressive-like behaviors by targeting phosphodiesterase 4B in adolescent mice.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2025
Same author

Alterations in miR-151a-3p of plasma-derived exosomes and associated multimodal neuroimaging patterns in major depressive disorder.

Molecular psychiatry·2025
Same author

Machine learning-powered fluorescent sensor arrays for rapid detection of heavy metals and pesticides in complex environments.

Biosensors & bioelectronics·2025
Same author

Chiral Pesticides Selectively Influence the Dissemination of Antibiotic Resistance Genes: An Overlooked Environmental Risk.

Environmental science & technology·2025
Same journal

circ2DGNN: circRNA-Disease Association Prediction via Transformer-Based Graph Neural Network.

IEEE/ACM transactions on computational biology and bioinformatics·2024
Same journal

Hierarchical Hypergraph Learning in Association- Weighted Heterogeneous Network for miRNA- Disease Association Identification.

IEEE/ACM transactions on computational biology and bioinformatics·2024
Same journal

Discriminative Domain Adaption Network for Simultaneously Removing Batch Effects and Annotating Cell Types in Single-Cell RNA-Seq.

IEEE/ACM transactions on computational biology and bioinformatics·2024
Same journal

MLW-BFECF: A Multi-Weighted Dynamic Cascade Forest Based on Bilinear Feature Extraction for Predicting the Stage of Kidney Renal Clear Cell Carcinoma on Multi-Modal Gene Data.

IEEE/ACM transactions on computational biology and bioinformatics·2024
Same journal

An End-to-End Knowledge Graph Fused Graph Neural Network for Accurate Protein-Protein Interactions Prediction.

IEEE/ACM transactions on computational biology and bioinformatics·2024
Same journal

Generative Biomedical Event Extraction With Constrained Decoding Strategy.

IEEE/ACM transactions on computational biology and bioinformatics·2024
See all related articles

A new two-stage Support Vector Machine - Recursive Feature Elimination (SVM-RFE) algorithm improves gene selection for cancer classification. This method is more accurate and reliable than the original SVM-RFE, offering efficient and stable gene subset extraction.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Gene expression data analysis is crucial for cancer classification.
  • Support Vector Machine - Recursive Feature Elimination (SVM-RFE) is a common gene selection algorithm.
  • The original SVM-RFE algorithm can be unstable and sensitive to its 'filter-out' factor.

Purpose of the Study:

  • To develop a more stable and accurate gene selection algorithm.
  • To improve the reliability of gene subset extraction for cancer prediction.
  • To overcome the limitations of the standard SVM-RFE algorithm.

Main Methods:

  • A novel two-stage SVM-RFE algorithm was developed.
  • The first stage focuses on eliminating irrelevant, redundant, and noisy genes.

Related Experiment Videos

  • The second stage performs fine selection for the final gene subset.

    • Main Results:

    • The two-stage SVM-RFE demonstrated significantly higher accuracy and reliability compared to the standard SVM-RFE.
    • Performance was validated against three correlation-based methods using public microarray data.
    • The algorithm is computationally efficient with a time complexity of O(d*log(2)d).

    Conclusions:

    • The two-stage SVM-RFE algorithm effectively addresses the instability issues of the original SVM-RFE.
    • This enhanced algorithm provides a more robust approach for selecting informative gene subsets.
    • The method offers improved utility for reliable cancer subtype prediction and other biological analyses.