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

Multiple SVM-RFE for gene selection in cancer classification with expression data.

Kai-Bo Duan1, Jagath C Rajapakse, Haiying Wang

  • 1BioInformatics Research Centre, School of Computer Engineering, Nanyang Technological University, Singapore 639798. askbduan@ntu.edu.sg

IEEE Transactions on Nanobioscience
|October 14, 2005
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

Where Medical Statistics Meets Artificial Intelligence.

The New England journal of medicine·2023
Same author

Correction: Machine learning for predicting neurodegenerative diseases in the general older population: a cohort study.

BMC medical research methodology·2023
Same author

Machine learning for predicting neurodegenerative diseases in the general older population: a cohort study.

BMC medical research methodology·2023
Same author

Allergic airway inflammation delays glioblastoma progression and reinvigorates systemic and local immunity in mice.

Allergy·2022
Same author

DrDimont: explainable drug response prediction from differential analysis of multi-omics networks.

Bioinformatics (Oxford, England)·2022
Same author

The Supervision and Management Mode of Disinfection Supply Center Improves the Standardization of Sterile Goods Management in Clinical Departments.

Computational and mathematical methods in medicine·2022
Same journal

A Transparent, Microfluidic Lab On A Chip For Multi-Modal Cell Culture Monitoring For Neurotoxicity Research.

IEEE transactions on nanobioscience·2026
Same journal

Investigating Effect of Dimensional Variance on Separation of Glomerular Ultrafiltrate in a Microfluidic Environment.

IEEE transactions on nanobioscience·2026
Same journal

Green synthesis of multifunctional ZnFe<sub>2</sub>O<sub>4</sub>-MWCNT-Cellulose acetate nanocomposite for peroxidase enzyme immobilization.

IEEE transactions on nanobioscience·2026
Same journal

IoT-Enabled SnO₂-Based Humidity Sensor for Real-Time Monitoring in Neonatal Incubators.

IEEE transactions on nanobioscience·2026
Same journal

Electrokinetic and Antibiofilm Effects of Silver Nanoparticles Combined with Imipenem Against multidrug-resistant of Klebsiella pneumoniae.

IEEE transactions on nanobioscience·2026
Same journal

Bio-inspired Optofluidic Molecular Communication with Photothermally Actuated Microrobot Swarms.

IEEE transactions on nanobioscience·2026
See all related articles

A novel feature selection method enhances cancer classification by identifying superior gene subsets compared to SVM-RFE. This approach improves accuracy and selects functionally diverse genes for better performance.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning in Genomics

Background:

  • Gene expression data is crucial for cancer classification.
  • Existing feature selection methods like Support Vector Machine-Recursive Feature Elimination (SVM-RFE) have limitations.
  • Improving the selection of relevant genes is key to enhancing classification accuracy.

Purpose of the Study:

  • To propose and validate a new feature selection method for cancer classification using gene expression data.
  • To compare the proposed method against the standard SVM-RFE.
  • To assess the functional diversity of selected gene subsets.

Main Methods:

  • A backward elimination procedure utilizing statistical analysis of weight vectors from multiple linear Support Vector Machines (SVMs) trained on data subsamples.

Related Experiment Videos

  • Application of the method to four distinct gene expression datasets for cancer classification.
  • Gene Ontology (GO)-based similarity assessment to evaluate the functional diversity of selected gene subsets.

    • Main Results:

    • The proposed feature selection method consistently selected superior gene subsets compared to the original SVM-RFE.
    • Improved classification accuracy was observed when using the gene subsets identified by the new method.
    • Functional diversity analysis using Gene Ontology confirmed the biological relevance of the selected genes.

    Conclusions:

    • The developed feature selection technique offers an improvement over SVM-RFE for gene expression-based cancer classification.
    • The method's ability to select functionally diverse gene subsets validates its effectiveness.
    • Recommends using average test error from multiple data partitions as a performance benchmark for gene expression-based cancer classification.