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

Entropy-based gene ranking without selection bias for the predictive classification of microarray data.

Cesare Furlanello1, Maria Serafini, Stefano Merler

  • 1ITC-irst, Trento, Italy. furlan@itc.it

BMC Bioinformatics
|November 8, 2003
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

The landscape of artificial intelligence in neurodegenerative diseases: a systematic review.

Communications medicine·2026
Same author

Effectiveness of screening protocols to reduce MRSA colonization in a pediatric hospital.

International journal of infectious diseases : IJID : official publication of the International Society for Infectious Diseases·2026
Same author

Why almost all ML models for medicine are wrong-and what we need for evidence-based medical AI.

International journal of medical informatics·2026
Same author

Scenario analysis for potential community spread of Andes virus (ANDV).

Euro surveillance : bulletin Europeen sur les maladies transmissibles = European communicable disease bulletin·2026
Same author

Assessing the annual burden of tick-borne encephalitis virus infections, north-east Italy, 2017 to 2024.

Euro surveillance : bulletin Europeen sur les maladies transmissibles = European communicable disease bulletin·2026
Same author

Barriers, Perceptions, and Predictors for Utilizing Health-Related Technology Among Individuals Receiving Radiation Oncology Care.

Cureus·2026
Same journal

SNPio: a Python interface for population genomic data processing.

BMC bioinformatics·2026
Same journal

SpaHNR: a spatial domain identification method via sparse attention-based hierarchical node representation and multi-view contrastive learning.

BMC bioinformatics·2026
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
See all related articles

The Enhanced Recursive Feature Elimination (E-RFE) method efficiently ranks genes for predictive classification, significantly speeding up analysis while preventing selection bias in gene marker identification.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning in Genomics

Background:

  • Gene ranking is crucial for identifying predictive markers in array data analysis.
  • Standard methods can suffer from selection bias, leading to overly optimistic error estimates.
  • A practical modeling scheme is needed to avoid issues with small gene subsets.

Purpose of the Study:

  • To introduce and evaluate the Enhanced Recursive Feature Elimination (E-RFE) method for gene ranking.
  • To accelerate the Recursive Feature Elimination (RFE) process using Support Vector Machine (SVM) classifiers.
  • To mitigate selection bias in the identification of gene markers for predictive classification.

Main Methods:

  • E-RFE accelerates SVM-based RFE by eliminating non-informative genes using SVM weight distribution entropy.

Related Experiment Videos

  • A two-strata model evaluation procedure selects optimal gene subsets, employing external stratified-partition resampling and internal K-fold cross-validation.
  • Zipf's law profile saturation is used to estimate the optimal number of genes.

    • Main Results:

    • E-RFE achieves a 100-fold speed-up compared to standard RFE without compromising classification accuracy.
    • The method demonstrates improved performance over alternative parametric RFE reduction strategies.
    • The E-RFE process provides practical gene selection and error estimation with controlled selection bias.

    Conclusions:

    • E-RFE offers a practical and efficient approach to gene selection and error estimation in array data analysis.
    • The method effectively controls selection bias and provides valuable diagnostic indicators of gene importance.
    • This technique enhances the feasibility of identifying reliable gene markers for predictive classification.