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 Video

Updated: Jun 24, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Development of biomarker classifiers from high-dimensional data.

Songjoon Baek1, Chen-An Tsai, James J Chen

  • 1National Center for Toxicological Research, U.S. Food and Drug Administration, USA. jamesj.chen@fda.hhs.gov

Briefings in Bioinformatics
|April 7, 2009
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

Coordinated Temporal Dynamics of Glucocorticoid Receptor Binding and Chromatin Landscape Drive Transcriptional Regulation.

bioRxiv : the preprint server for biology·2026
Same author

Linker histone H1.5 contributes to centromere integrity.

Nucleic acids research·2026
Same author

Predictive prioritization of enhancers associated with pancreatic disease risk.

Cell genomics·2025
Same author

Oncogenic lncRNA transgene transcription modulates epigenetic memory at a naïve chromosomal locus.

Nucleus (Austin, Tex.)·2025
Same author

Linker Histone H1.5 Contributes to Centromere Integrity in Human Cells.

bioRxiv : the preprint server for biology·2025
Same author

Oncogenic lncRNA transgene transcription modulates epigenetic memory at a naïve chromosomal locus.

bioRxiv : the preprint server for biology·2025
Same journal

SA-MTP: a structure-aware framework for multifunctional therapeutic peptide annotation.

Briefings in bioinformatics·2026
Same journal

Genome assemblies and annotations are not static and need support for tracking their evolution.

Briefings in bioinformatics·2026
Same journal

A historical journey of metabolite-protein interaction discovery: from data harmonization to AI-driven prediction.

Briefings in bioinformatics·2026
Same journal

Bridging local-global transmembrane protein contexts with contrastive pretraining for alignment-free pathogenicity prediction.

Briefings in bioinformatics·2026
Same journal

Prediction of drug hypersensitivity by comprehensive modeling of HLA-peptidomes.

Briefings in bioinformatics·2026
Same journal

EssTFNet: integration of adaptive time-frequency and DNA language models for interpretable human essential gene prediction.

Briefings in bioinformatics·2026
See all related articles

This study introduces a "frequency" approach for selecting molecular biomarker features, enhancing classifier stability for high-throughput data. This method improves predictive accuracy and reliability in diagnostics and safety assessments.

Area of Science:

  • Biomarker discovery
  • Computational biology
  • Statistical genetics

Background:

  • High-throughput technologies generate vast molecular data, driving demand for robust biomarker classifiers.
  • Biomarker classifiers are crucial for safety assessment, disease diagnosis, prognosis, and personalized medicine.
  • Developing reliable biomarker classifiers requires careful consideration of model building and performance assessment.

Purpose of the Study:

  • To review and evaluate key aspects of biomarker classifier development using high-throughput data.
  • To present and compare a 'frequency' approach for feature selection against a 'conventional' approach.
  • To assess the predictive accuracy and stability of feature sets selected by both approaches.

Main Methods:

  • Focus on feature selection within model building and cross-validation for performance assessment.

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Related Experiment Videos

Last Updated: Jun 24, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

  • Implemented a 'frequency' approach for feature selection and compared it to a 'conventional' method.
  • Evaluated four biomarker classifiers, each using a different feature selection method and classification algorithm.

    • Main Results:

    • The 'frequency' approach yielded more stable feature predictor sets compared to the 'conventional' approach across all four classifiers.
    • The study demonstrates the superior stability of the frequency-based feature selection method.
    • Differences in predictive accuracy between the two approaches were also analyzed.

    Conclusions:

    • The 'frequency' approach offers enhanced stability for feature selection in biomarker classifier development.
    • This improved stability is critical for reliable molecular diagnostics and safety assessments.
    • The findings support the adoption of the frequency approach for high-throughput data analysis in biomarker discovery.