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

Applications of support vector machines to cancer classification with microarray data.

Feng Chu1, Lipo Wang

  • 1School of Electrical and Electronic Engineering, Nanyang Technological University, Block S1, Nanyang Avenue, Singapore 639798.

International Journal of Neural Systems
|December 31, 2005
PubMed
Summary

This study applies support vector machines (SVM) and dimensionality reduction techniques to cancer classification using microarray gene expression data. The methods achieved high accuracy with significantly fewer genes, improving efficiency in cancer diagnosis.

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

Morphology-guided deep learning for nanoparticle agglomeration diagnostic assays.

Scientific reports·2026
Same author

Gaps between medical biology and AI drug discovery.

Drug discovery today·2025
Same author

Discriminating single-molecule binding events from diffraction-limited fluorescence.

Nature communications·2025
Same author

Fyn kinase mediates the development of rats with chronic obstructive pulmonary disease by modulating the activation of p38 MAPK and NF-κB.

Iranian journal of basic medical sciences·2025
Same author

Local-Peak Scale-Invariant Feature Transform for Fast and Random Image Stitching.

Sensors (Basel, Switzerland)·2024
Same author

Ultra-highly efficient enrichment of uranium from seawater via studtite nanodots growth-elution cycle.

Nature communications·2024

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Microarray gene expression datasets are high-dimensional with numerous genes and few samples.
  • Accurate cancer classification is crucial for effective treatment strategies.

Purpose of the Study:

  • To develop an efficient cancer classification method using microarray data.
  • To reduce the number of genes required for accurate classification.

Main Methods:

  • Utilized Support Vector Machine (SVM) for cancer classification.
  • Applied dimensionality reduction techniques including Principal Component Analysis (PCA), class-separability measure, Fisher ratio, and t-test for gene selection.
  • Implemented a voting scheme with multiple binary SVMs for multi-group classification.

Related Experiment Videos

Main Results:

  • Achieved classification accuracy comparable to existing methods.
  • Significantly reduced the number of features (genes) needed for classification.
  • Demonstrated the effectiveness of SVM and dimensionality reduction in high-dimensional genomic data analysis.

Conclusions:

  • The proposed approach offers an efficient and accurate method for cancer classification from microarray data.
  • Feature selection is vital for managing high-dimensional gene expression data.
  • SVM provides a robust framework for complex biological data analysis.