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

Gene selection based on multi-class support vector machines and genetic algorithms.

Bruno Feres de Souza1, André Ponce de Leon F de Carvalho

  • 1Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo, v. Trabalhador São-Carlense, 400, 13560-970 São Carlos, SP, Brazil. bferes@icmc.usp.br

Genetics and Molecular Research : GMR
|December 13, 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

Beyond the crisis: Tracking chronic neuropathic pain in sickle cell disease using Douleur Neuropathique 4 and PainDETECT questionnaires.

Hematology, transfusion and cell therapy·2025
Same author

Global, regional, and national burden of high sugar-sweetened beverages consumption, 1990-2021, with projections up to 2050: a systematic analysis for the Global Burden of Disease Study 2021.

The American journal of clinical nutrition·2025
Same author

Factors associated with the dietary total antioxidant capacity of pregnant Brazilian women.

Revista brasileira de epidemiologia = Brazilian journal of epidemiology·2025
Same author

High free sugars, insulin resistance, and low socioeconomic indicators: the hubs in the complex network of non-communicable diseases in adolescents.

Diabetology & metabolic syndrome·2024
Same author

Behavioral and metabolic risk factors associated with periodontitis in Brazil, 1990-2019: a multidimensional analysis for the Global Burden of Disease Study 2019.

Clinical oral investigations·2023
Same author

Excess deaths from all causes and by COVID-19 in Brazil in 2020.

Revista de saude publica·2021

This study introduces a novel gene selection method combining support vector machines and genetic algorithms for multi-class cancer classification. The approach effectively identifies key genes, improving diagnostic accuracy with smaller gene subsets.

Area of Science:

  • Genomics and Bioinformatics
  • Computational Biology
  • Cancer Research

Background:

  • Microarray technology enables gene-level analysis of diverse pathological states.
  • Large-scale gene expression data present significant analytical challenges, especially in multi-class scenarios.
  • Automated analysis for diagnostic purposes is complicated by data volume and complexity.

Purpose of the Study:

  • To address the gene selection challenge in multi-class cancer classification using gene expression data.
  • To develop a novel computational approach for identifying relevant gene subsets.
  • To enhance classification accuracy in cancer diagnostics.

Main Methods:

  • A hybrid approach combining Support Vector Machines (SVM) and Genetic Algorithms (GA) was developed.

Related Experiment Videos

  • The method focuses on selecting minimal yet informative gene subsets from complex expression datasets.
  • The approach was applied to multi-class gene expression-based cancer classification problems.

    • Main Results:

    • The novel method successfully identified small, relevant gene subsets.
    • The proposed gene selection strategy led to improved classification accuracy.
    • This approach offers a more efficient way to analyze complex cancer gene expression data.

    Conclusions:

    • The combined SVM and GA approach is effective for gene selection in multi-class cancer classification.
    • This method enhances diagnostic accuracy by focusing on critical gene expression patterns.
    • The findings suggest a promising avenue for improving computational cancer diagnostics.