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

Diagnostic pattern recognition on gene-expression profile data by using one-class classification.

Yun Xu1, Richard G Brereton

  • 1School of Chemistry, University of Bristol, Cantock's Close, Bristol BS8 1TS, United Kingdom.

Journal of Chemical Information and Modeling
|September 27, 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

Tapping the Full Potential of Infrared Spectroscopy for the Analysis of Technical Lignins.

ChemSusChem·2024
Same author

Chemometrics in analytical chemistry-part II: modeling, validation, and applications.

Analytical and bioanalytical chemistry·2018
Same author

XPO1-mediated nuclear export of RNF146 protects from angiotensin II-induced endothelial cellular injury.

Biochemical and biophysical research communications·2018
Same author

The associated volumes of sub-cortical structures and cognitive domain in patients of Mild Cognitive Impairment.

Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia·2018
Same author

pH plays a role in the mode of action of trimethoprim on Escherichia coli.

PloS one·2018
Same author

Tube Feeding with a Diabetes-Specific Enteral Formula Improves Glycemic Control in Severe Acute Ischemic Stroke Patients.

JPEN. Journal of parenteral and enteral nutrition·2018
Same journal

PSDTA: An Approach to Drug-Target Binding Affinity Prediction by Integrating Physicochemical and Structural Information to Reduce Feature Redundancy.

Journal of chemical information and modeling·2026
Same journal

M-JEPA: Predictive Self-Supervised Learning for Molecular Graphs with Scaffold-Shift Evaluation on Tox21.

Journal of chemical information and modeling·2026
Same journal

Advancing Biochemical Molecule Registration, Representation and Search for New Drug Modalities.

Journal of chemical information and modeling·2026
Same journal

A Unified Molecular Graph and Protein Language Model Framework for Predicting Human Drug-Hormone Receptor Interactions with Structure-Aware Validation.

Journal of chemical information and modeling·2026
Same journal

Intricate Role of Cholesterol in Membrane Fusion.

Journal of chemical information and modeling·2026
Same journal

tmGNN-XAI: An Explainable Graph Neural Network Tool for Predicting Electronic Properties of Transition Metal Complexes from SMILES.

Journal of chemical information and modeling·2026
See all related articles

One-class classification effectively identifies diagnostic patterns in gene expression data. Performance depends on data splitting and feature selection, with most methods yielding high-quality results.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning

Background:

  • Gene expression profiling generates high-dimensional data for disease classification.
  • Conventional multiclass classifiers require labeled data from all classes.
  • One-class (OC) classification offers an alternative for identifying patterns within a single class.

Purpose of the Study:

  • To evaluate the performance of six OC classifiers for diagnostic pattern recognition in gene expression data.
  • To compare the effectiveness of different OC classification methods on distinct biological datasets.

Main Methods:

  • Evaluated Gaussian model, Parzen windows, support vector data description (with inner product and Gaussian kernels), nearest neighbor data description, K-means, and PCA.
  • Applied classifiers to SRBCT, Colon, and Leukemia gene expression profile datasets.

Related Experiment Videos

  • Focused on the impact of training/test sample splitting and feature selection.

    • Main Results:

    • Most OC classifiers achieved high-quality results with appropriate data splitting and feature selection.
    • Parzen windows and support vector data description were often 'over-strict'.
    • Nearest neighbor data description tended to be 'over-loose', with other methods falling in between.

    Conclusions:

    • OC classification is a viable approach for diagnostic pattern recognition in gene expression data.
    • Classifier behavior varies, with some being too strict or too loose.
    • Optimizing decision thresholds is challenging with limited training samples.