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

Improved binary PSO for feature selection using gene expression data.

Li-Yeh Chuang1, Hsueh-Wei Chang, Chung-Jui Tu

  • 1Department of Chemical Engineering, I-Shou University, Kaohsiung 840, Taiwan. chuang@isu.edu.tw

Computational Biology and Chemistry
|November 21, 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

Plumbagin sensitizes leukemia cells to cisplatin by promoting oxidative stress, apoptosis, and DNA damage.

International journal of medical sciences·2026
Same author

Genome-wide association and MaODR-based multi-locus interaction analyses reveal a susceptibility gene network for newly identified metabolic syndrome.

Genome biology·2026
Same author

Santamarine Synergizes With Cisplatin via ROS/JNK Axis to Selectively Induce Apoptosis and DNA Damage in Oral Cancer Cells In Vitro.

Drug development research·2026
Same author

Cryptocaryone Exhibits ROS/MAPK-Dependent Antiproliferative and Apoptosis-Inducing Effects on Triple-Negative Breast Cancer Cells and Proof-of-Concept Breast Cancer Mouse Model.

Drug development research·2026
Same author

PM<sub>2.5</sub>-modulated targets and miRNAs associated with lung cancer and injury are protected by natural products.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Machine Learning for Establishing the Precision Prediction of Sarcopenia.

Gerontology·2026
Same journal

Protein dynamic simulations: From early inception to clinical translation over half a century.

Computational biology and chemistry·2026
Same journal

Integrated omics and virtual screening predict Tabularin as a dual inhibitor of the prognostic microRNAs mir-19a and mir-32 in colorectal cancer.

Computational biology and chemistry·2026
Same journal

In silico characterization of acetyl-CoA carboxylase from Staphylococcus aureus and Escherichia coli: A comparative analysis.

Computational biology and chemistry·2026
Same journal

An optimized cascaded transformer with progressive attention for lung and colon cancer diagnosis from histopathological images.

Computational biology and chemistry·2026
Same journal

From cross cancer transcriptomics to therapeutics: WGX-50 target hub genes in breast cancer and non-small cell lung carcinoma.

Computational biology and chemistry·2026
Same journal

Blood-based biomarker discovery through integrative transcriptomic and miRNA network analyses in schizophrenia, major depressive disorder, and bipolar disorder.

Computational biology and chemistry·2026
See all related articles

This study introduces an improved binary particle swarm optimization (IBPSO) for gene selection in cancer classification. The method enhances accuracy and reduces features, proving effective for small gene expression datasets.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Medical Diagnosis

Background:

  • Gene expression profiles offer potential for molecular-level cell state analysis and medical diagnosis.
  • Cancer type classification using gene expression data faces challenges due to small sample sizes relative to the number of genes.
  • Efficient gene selection is crucial for improving classification speed, reducing errors, and managing high-dimensional data.

Purpose of the Study:

  • To develop and evaluate a gene selection method for cancer type classification using limited gene expression data.
  • To enhance the efficiency and accuracy of classification by reducing the number of relevant genes.
  • To address the limitations of small training datasets in high-dimensional gene expression analysis.

Main Methods:

Related Experiment Videos

  • Utilized Improved Binary Particle Swarm Optimization (IBPSO) for effective feature selection.
  • Employed the K-nearest neighbor (K-NN) method as an evaluator for the IBPSO algorithm.
  • Tested the proposed method on 11 gene expression datasets for cancer classification problems.

    • Main Results:

    • The IBPSO method significantly simplified feature selection and reduced the total number of genes required.
    • Achieved the highest classification accuracy in 9 out of 11 gene expression data test problems.
    • Demonstrated comparative classification accuracy on the remaining two test problems against published results.

    Conclusions:

    • The proposed IBPSO-based gene selection method is effective for cancer classification with limited gene expression data.
    • This approach offers a reliable solution for speeding up processing, decreasing predictive error rates, and simplifying complex datasets.
    • The method provides a robust strategy for handling high-dimensional gene expression data in medical diagnosis applications.