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

Predicting gene function from gene expressions and ontologies.

T R Hvidsten1, J Komorowski, A K Sandvik

  • 1Knowledge Systems Group, Department of Information and Computer Science, Norwegian University of Science and Technology, 7491 Trondheim, Norway.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|March 27, 2001
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

A non-coding cancer mutation disrupting an HNF4α binding motif affects an enhancer regulating genes associated to the progression of liver cancer.

Experimental oncology·2021
Same author

Integration of absolute multi-omics reveals dynamic protein-to-RNA ratios and metabolic interplay within mixed-domain microbiomes.

Nature communications·2020
Same author

CausalTAB: the PSI-MITAB 2.8 updated format for signalling data representation and dissemination.

Bioinformatics (Oxford, England)·2019
Same author

Photoperiodic control of seasonal growth is mediated by ABA acting on cell-cell communication.

Science (New York, N.Y.)·2018
Same author

Recurrent attacks of acute hepatic porphyria: major role of the chronic inflammatory response in the liver.

Journal of internal medicine·2018
Same author

BRAF V600E mutation in early-stage multiple myeloma: good response to broad acting drugs and no relation to prognosis.

Blood cancer journal·2015

This study presents a new method for classifying gene expression using predictive rule models and background knowledge. This approach aids in understanding gene function and generating hypotheses for unknown genes.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Gene Expression Analysis

Background:

  • Microarray hybridisation experiments generate large gene expression datasets.
  • Functional classification of genes is crucial for understanding biological processes.
  • Existing unsupervised clustering methods may not fully leverage biological background knowledge.

Purpose of the Study:

  • To introduce a supervised methodology for inducing predictive rule models for gene expression functional classification.
  • To utilize background knowledge of gene function in a supervised learning framework.
  • To improve the accuracy and interpretability of gene function prediction.

Main Methods:

  • Employing the rough set framework for rule induction.
  • Annotating genes using Ashburner's Gene Ontology for functional class mining.

Related Experiment Videos

  • Extracting biologically meaningful features from gene expression data.
  • Supervised learning using background knowledge and extracted features.
  • Cross-validation for fine-tuning predictive quality before classifying unknown genes.

    • Main Results:

    • Demonstrated predictive and descriptive quality of the rule model on fibroblast serum response data.
    • The induced rule models effectively represent complex relationships between gene expressions and function.
    • Successfully classified unknown genes with high-quality hypotheses generation.

    Conclusions:

    • The proposed methodology offers a powerful alternative to unsupervised clustering for gene function classification.
    • Supervised learning with background knowledge enhances the predictive accuracy of gene function models.
    • This approach facilitates the generation of testable hypotheses regarding the function of novel genes.