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

Joint classifier and feature optimization for comprehensive cancer diagnosis using gene expression data.

Balaji Krishnapuram1, Lawrence Carin, Alexander J Hartemink

  • 1Department of Electrical Engineering, Duke University, Durham, NC 27708-0291, USA.

Journal of Computational Biology : a Journal of Computational Molecular Cell Biology
|August 3, 2004
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

Gradient Importance Learning for Incomplete Observations.

... International Conference on Learning Representations·2026
Same author

Comprehensive profiling of chromatin occupancy dynamics through the cell cycle.

Nucleic acids research·2026
Same author

Genome-wide nucleosome and transcription factor responses to genetic perturbations reveal chromatin-mediated mechanisms of transcriptional regulation.

Genome research·2025
Same author

Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations.

Proceedings of machine learning research·2025
Same author

Enabling Counterfactual Survival Analysis with Balanced Representations.

ACM CHIL 2021 : proceedings of the 2021 ACM Conference on Health, Inference, and Learning : April 8-9, 2021, Virtual Event. ACM Conference on Health, Inference, and Learning (2021 : Online)·2025
Same author

Inferring differential protein binding from time-series chromatin accessibility data.

Bioinformatics advances·2025

This study introduces the Joint Classifier and Feature Optimization (JCFO) algorithm for accurate cancer diagnosis using gene expression profiles. JCFO identifies optimal gene sets and classifiers, outperforming current methods and potentially enabling inexpensive diagnostic assays.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Accurate cancer diagnosis relies on comparing gene expression profiles.
  • Existing methods for cancer classification using gene expression data have limitations.
  • Identifying key genes for diagnosis is crucial for developing effective classifiers.

Purpose of the Study:

  • To introduce a novel algorithm, Joint Classifier and Feature Optimization (JCFO), for cancer diagnosis.
  • To jointly identify an optimal nonlinear classifier and a minimal set of diagnostic genes.
  • To demonstrate the superior diagnostic accuracy of JCFO compared to state-of-the-art methods.

Main Methods:

  • Development of the JCFO algorithm utilizing a sparse Bayesian approach.
  • Joint optimization of a nonlinear classifier and a subset of informative genes.

Related Experiment Videos

  • Validation using a leave-one-out cross-validation on five benchmark gene expression datasets.

    • Main Results:

    • JCFO achieved superior diagnostic classification accuracy compared to existing methods.
    • The algorithm identified a small subset of genes (typically around twenty) for diagnosis.
    • Identified genes included known clinical markers and potential new candidates for investigation.

    Conclusions:

    • The JCFO algorithm offers a powerful and accurate approach to cancer diagnosis via gene expression profiling.
    • Identifying a small set of discriminatory genes enhances classifier generalization and may reveal disease mechanisms.
    • The findings support the potential for developing inexpensive, widely deployable gene-based cancer diagnostic assays.