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

Empirical study of supervised gene screening.

Shuangge Ma1

  • 1Department of Epidemiology and Public Health, Yale University, New Haven, CT 06520, USA. shuangge.ma@yale.edu

BMC Bioinformatics
|December 21, 2006
PubMed
Summary

Different supervised gene screening methods yield varying results in microarray analysis. Gene discovery is impacted by these differences, with moderate reproducibility observed across methods.

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

Heterogeneity-aware Clustered Distributed Learning for Multi-source Data Analysis.

Journal of machine learning research : JMLR·2026
Same author

Medicare Insurance Type and Broad Genomic Profiling in Metastatic Cancer.

JAMA network open·2026
Same author

Doubly Robust Estimators of the Restricted Mean Time in Favor Estimands in Individual- and Cluster-Randomized Trials.

Statistics in medicine·2026
Same author

JOINT IDENTIFICATION OF SPATIALLY VARIABLE GENES VIA A NETWORK-ASSISTED BAYESIAN REGULARIZATION APPROACH.

The annals of applied statistics·2026
Same author

Subgroup Analysis of Differential Networks with Latent Variables.

Statistics and computing·2026
Same author

Robust Heterogeneity Adjustment for Gaussian Graphical Model With Latent Variables.

Statistics in medicine·2026

Area of Science:

  • Genomics
  • Bioinformatics
  • Statistical Genetics

Background:

  • Microarray studies link phenotypic variations to genetic causes.
  • Predictive model construction involves unsupervised screening, supervised screening, and model building.
  • Supervised gene screening using marginal gene ranking is crucial for reducing gene numbers in high-dimensional data.

Purpose of the Study:

  • To investigate the concordance and reproducibility of supervised gene screening using various marginal statistics.
  • To assess the impact of different supervised gene screening methods on gene discovery outcomes.
  • To introduce and evaluate a Bootstrap Reproducibility Index for gene screening reproducibility.

Main Methods:

  • Investigated concordance via gene overlap fractions between different marginal statistics.
  • Proposed and applied a Bootstrap Reproducibility Index to measure individual gene reproducibility.
  • Conducted empirical studies on four public microarray datasets, analyzing top 20%, 40%, and 60% gene selections.

Main Results:

  • Significant differences observed in genes selected by various supervised gene screening methods.
  • Concordance levels varied based on data structure and gene selection percentage.
  • Genes passing supervised screening showed only moderate reproducibility when assessed by the Bootstrap Reproducibility Index.

Conclusions:

  • The choice of marginal statistics in supervised gene screening substantially impacts gene discovery.
  • Supervised screening does not inherently improve concordance by focusing on reproducibility.
  • Findings highlight the need for careful consideration of screening methods in microarray data analysis.

Related Experiment Videos