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

Simple decision rules for classifying human cancers from gene expression profiles.

Aik Choon Tan1, Daniel Q Naiman, Lei Xu

  • 1Center for Cardiovascular Bioinformatics and Modeling, Whitaker Biomedical Engineering Institute, Baltimore, MD 21218, USA. actan@jhu.edu

Bioinformatics (Oxford, England)
|August 18, 2005
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

irAE.AI: AI-powered exploration of real-world immune-related adverse events.

JAMIA open·2026
Same author

Targeting of MEK and Autophagy in Pancreatic Adenocarcinoma and Analysis of Treatment Sensitivity in Preclinical and Clinical Models: MEKiAUTO.

JCO precision oncology·2026
Same author

Clinico-genomic nomograms for estimation of survival risk in metastatic castrate-resistant prostate cancer.

JNCI cancer spectrum·2026
Same author

Associations Between Two-Year Immune-Related Adverse Events and Psychological Distress and Subsequent Survival Outcomes Among ICI-Treated Survivors Diagnosed With Advanced Cancers in the US.

Psycho-oncology·2026
Same author

Addressing Disparities: A Pragmatic Comparative Effectiveness Trial of School-Based Executive Functioning Interventions.

Evidence-based practice in child and adolescent mental health·2026
Same author

Impact of baseline medications on real-world overall survival in immune checkpoint inhibitor-treated patients with cancer in the RADIOHEAD cohort.

Med (New York, N.Y.)·2026
Same journal

3DICE: Interpretable 3D Cross-Modal Learning for Drug-Target Interaction Prediction and Large-Scale Drug Discovery.

Bioinformatics (Oxford, England)·2026
Same journal

KASSPer: Kinase Active Site Structure Prediction using Protein and Ligand Language Models and Its Application to Virtual Screening.

Bioinformatics (Oxford, England)·2026
Same journal

IDR searcher: a search engine solution for public image resources.

Bioinformatics (Oxford, England)·2026
Same journal

KCFtools: Rapid alignment-free method for introgression screening and GWAS using k-mer profiles.

Bioinformatics (Oxford, England)·2026
Same journal

Meta2DB: Curated shotgun metagenomic feature sets and metadata for health state prediction.

Bioinformatics (Oxford, England)·2026
Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

Bioinformatics (Oxford, England)·2026
See all related articles

A new machine learning method, k-Top Scoring Pairs (k-TSP), accurately classifies cancer gene expression data. This approach provides interpretable rules, aiding biological insight and follow-up studies.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Machine learning accurately detects and classifies cancer via gene expression patterns.
  • Interpreting these gene expression classifiers for biological insight remains a challenge.
  • Current methods often present a trade-off between accuracy and interpretability.

Purpose of the Study:

  • Introduce a novel classifier, k-Top Scoring Pairs (k-TSP), to address interpretability issues in cancer gene expression classification.
  • Develop a method based on 'relative expression reversals' for simpler, more accurate decision rules.
  • Facilitate biological insight through gene expression comparisons.

Main Methods:

  • The k-TSP classifier utilizes 'relative expression reversals' for gene expression comparisons.

Related Experiment Videos

  • It generates decision rules involving a small number of gene-to-gene comparisons.
  • The approach was compared against other machine learning techniques on 19 cancer datasets.

    • Main Results:

    • k-TSP demonstrates comparable efficiency to Prediction Analysis of Microarray and support vector machines.
    • It outperforms decision trees, k-nearest neighbor, and naïve Bayes classifiers.
    • The classifier provides easily interpretable rules using a limited set of informative genes.

    Conclusions:

    • k-TSP offers a valuable tool for cancer classification using gene expression data.
    • Its interpretability enhances biological understanding of classification mechanisms.
    • The method balances accuracy and comprehensibility for clinical applications.