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 gene selection for classification of microarrays.

J Jaeger1, R Sengupta, W L Ruzzo

  • 1Department of Computer Science & Engineering, University of Washington, 114 Sieg Hall, Box 352350, Seattle, WA 98195, USA.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|February 27, 2003
PubMed
Summary

This study introduces novel pre-filter methods to select distinct, informative genes from microarray data, improving gene selection for better classification accuracy.

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

Evaluation of the current use of MRI to aid the diagnosis of axial spondyloarthritis in the UK: results from a freedom of information request.

Clinical radiology·2023
Same author

Longitudinal Cognitive Decline in Patients With Mild Cognitive Impairment or Dementia Due to Alzheimer's Disease.

The journal of prevention of Alzheimer's disease·2022
Same author

A Twist on Gastric Volvulus: Painless Presentation in a 97-Year-Old.

Journal of the American Medical Directors Association·2021
Same author

Delayed Onset Postsurgical Endophthalmitis.

Journal of the American Medical Directors Association·2021
Same author

Depression among Patients Presenting with Gastrointestinal Symptoms: Prevalence and Associated Factors.

Mymensingh medical journal : MMJ·2021
Same author

Risk-mitigating behaviours in people with inflammatory skin and joint disease during the COVID-19 pandemic differ by treatment type: a cross-sectional patient survey.

The British journal of dermatology·2020

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Microarray data analysis often involves selecting informative genes using statistical tests.
  • A common issue is the selection of highly correlated genes, which can be suboptimal for classification tasks.

Purpose of the Study:

  • To develop and evaluate methods for selecting distinct yet informative genes from microarray data.
  • To improve gene selection techniques for enhanced classification performance.

Main Methods:

  • Proposed three pre-filter methods: two clustering-based and one correlation-based.
  • Genes were grouped by similarity before applying a test-statistic for final selection.
  • Evaluated the effectiveness of the filtered gene sets in improving classifiers.

Related Experiment Videos

Main Results:

  • The proposed pre-filter methods successfully retrieved groups of similar genes.
  • The filtered gene sets led to significant improvements in existing classification algorithms.
  • Demonstrated the advantage of selecting distinct informative genes over highly correlated ones.

Conclusions:

  • The developed pre-filter methods offer an effective approach to refine gene selection from microarray data.
  • Selecting distinct informative genes enhances the performance of machine learning classifiers.
  • This work provides a valuable strategy for optimizing gene selection in bioinformatics.