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

Filter versus wrapper gene selection approaches in DNA microarray domains.

Iñaki Inza1, Pedro Larrañaga, Rosa Blanco

  • 1Department of Computer Science and Artificial Intelligence, University of the Basque Country, P.O. Box 649, E-20080 Donostia-San Sebastián, Basque Country, Spain. inza@si.ehu.es

Artificial Intelligence in Medicine
|June 29, 2004
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

CTCF Regulates Erythroid Differentiation Through Control of Core Erythroid Transcription Factors.

Biomolecules·2026
Same author

Discovering Genetic Variants in Hypertrophic Cardiomyopathy With Multiple Machine Learning Techniques.

IEEE transactions on computational biology and bioinformatics·2025
Same author

Repeat Expansions in PLIN4 Cause Autosomal Dominant Vacuolar Myopathy With Sarcolemmal Features.

Annals of clinical and translational neurology·2025
Same author

Adult-onset distal myopathy with predominant hand involvement as a rare phenotype of plectinopathy.

Journal of neuromuscular diseases·2025
Same author

A Homozygous ATP2A2 Variant Alters Sarcoendoplasmic Reticulum Ca<sup>2+</sup>-ATPase 2 Function in Skeletal Muscle and Causes a Novel Vacuolar Myopathy.

Neuropathology and applied neurobiology·2025
Same author

Absence of Pathogenic Mutations and Strong Association With HLA-DRB1*11:01 in Statin-Naïve Early-Onset Anti-HMGCR Necrotizing Myopathy.

Neurology(R) neuroimmunology & neuroinflammation·2024
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

Gene selection in DNA microarray data is crucial for accurate classification. This study compares filter and wrapper methods, finding both improve accuracy and reduce dimensionality, with wrappers offering higher accuracy at a greater computational cost.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning

Background:

  • DNA microarrays generate vast gene expression data, essential for disease diagnosis and tumor classification.
  • High dimensionality (more genes than samples) in microarray data necessitates dimensionality reduction for effective classification.
  • Supervised classifiers' accuracy degrades with irrelevant or redundant features, highlighting the need for gene selection.

Purpose of the Study:

  • To evaluate and compare the effectiveness of gene selection techniques in DNA microarray data analysis.
  • To investigate the performance of filter and wrapper methods for feature selection in high-dimensional gene expression datasets.
  • To identify informative genes for improved sample classification and reduced data dimensionality.

Main Methods:

Related Experiment Videos

  • Comparison of various filter metrics and a wrapper sequential search procedure for gene selection.
  • Application of four classic supervised classifiers on two well-known DNA microarray datasets.
  • Analysis of both continuous and discretized (three-interval) gene expression data.
  • Evaluation of gene selection on classification accuracy and dimensionality reduction.

Main Results:

  • Both filter and wrapper gene selection significantly improved classification accuracy compared to no selection.
  • Gene selection led to substantial dimensionality reduction in the analyzed datasets.
  • The wrapper approach generally yielded higher accuracy than filter metrics but required more computational resources.
  • Selected genes by both methods largely corresponded with previously identified informative genes.

Conclusions:

  • Gene selection is essential for enhancing classification performance and interpretability in DNA microarray studies.
  • Filter and wrapper methods offer viable strategies for dimensionality reduction and feature identification in gene expression data.
  • The choice between filter and wrapper methods involves a trade-off between accuracy and computational cost.