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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Agentic artificial intelligence in inflammatory bowel disease: toward autonomous and adaptive care.

Crohn's & colitis 360·2026
Same author

Correction to: Global 30-Day Morbidity and Mortality of Primary Bariatric Surgery Combined with Another Procedure: The BLEND Study.

Obesity surgery·2026
Same author

Early risk stratification of late-onset sepsis in very preterm infants by intestinal microbiota profiling: a multicenter case-control validation study.

Gut microbes·2026
Same author

SPOTTER: Automated Tissue-Barcoding Platform for Spatial Proteomics and Phosphoproteomics.

bioRxiv : the preprint server for biology·2026
Same author

Hybrid Cardiac <sup>68</sup>Ga-FAPI-4 PET/MRI in Dilated Cardiomyopathy: A Feasibility and Pilot Study.

Radiology·2026
Same author

Integrated proteogenomic and metabolomic profiling of acute myeloid leukemias to identify molecular subtypes and associated therapy targets.

Nature cancer·2026

Related Experiment Video

Updated: Nov 29, 2025

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

7.8K

A random forest based biomarker discovery and power analysis framework for diagnostics research.

Animesh Acharjee1,2,3, Joseph Larkman4,5, Yuanwei Xu4,5

  • 1College of Medical and Dental Sciences, Institute of Cancer and Genomic Sciences, Centre for Computational Biology, University of Birmingham, Birmingham, B15 2TT, UK. a.acharjee@bham.ac.uk.

BMC Medical Genomics
|November 24, 2020
PubMed
Summary

We developed a stable Random Forest-based biomarker discovery framework. The Boruta method proved most stable, while Permutation (Raw) identified more features, aiding future translational medicine study design.

Keywords:
BiomarkerFeature selectionPower studyRandom forest

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

16.0K
Assisted Selection of Biomarkers by Linear Discriminant Analysis Effect Size LEfSe in Microbiome Data
04:57

Assisted Selection of Biomarkers by Linear Discriminant Analysis Effect Size LEfSe in Microbiome Data

Published on: May 16, 2022

16.8K

Related Experiment Videos

Last Updated: Nov 29, 2025

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

7.8K
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

16.0K
Assisted Selection of Biomarkers by Linear Discriminant Analysis Effect Size LEfSe in Microbiome Data
04:57

Assisted Selection of Biomarkers by Linear Discriminant Analysis Effect Size LEfSe in Microbiome Data

Published on: May 16, 2022

16.8K

Area of Science:

  • Genomics and Translational Medicine
  • Computational Biology
  • Biostatistics

Background:

  • Biomarker identification is crucial for early disease diagnosis and patient stratification in functional genomics and translational medicine.
  • Large-scale omics data offer potential for biomarker discovery, but require unbiased and stable methodologies.
  • Integrating biomarker discovery with future experimental design remains a challenge.

Purpose of the Study:

  • To assess the performance of various Random Forest (RF)-based feature selection methods for biomarker discovery.
  • To compare the stability and feature identification capabilities of different RF-based approaches.
  • To develop a tool for power calculations to aid in the design of future omics studies.

Main Methods:

  • Evaluated Boruta, permutation-based feature selection (with and without correction), and backward elimination using RF.
  • Utilized both simulated and published experimentally derived datasets for performance assessment.
  • Conducted power analysis to estimate sample size requirements for future studies.

Main Results:

  • The Boruta method demonstrated the highest stability across all tested scenarios.
  • The Permutation (Raw) approach identified the largest number of relevant features after stabilization.
  • A web interface, PowerTools, was developed to facilitate power calculations for future study design.

Conclusions:

  • A robust RF-based framework for biomarker discovery has been developed.
  • The PowerTools web interface supports the design of cost-effective future omics studies.
  • This framework enhances biomarker discovery and experimental planning in translational medicine.