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

Automatic ontology construction from the literature.

Christian Blaschke1, Alfonso Valencia

  • 1Protein Design Group, CNB/CSIC, Campus Universidad Autónoma, 28049 Madrid, Spain. blaschke@cnb.uam.es

Genome Informatics. International Conference on Genome Informatics
|October 23, 2003
PubMed
Summary

This study introduces an automated method for classifying gene-product functions using literature. This approach aids human experts in ontology annotation, mirroring expert-constructed classifications.

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

Intelligent tool orchestration for rapid mechanistic model prototyping: MCP servers as AI-biology interfaces.

NPJ systems biology and applications·2026
Same author

IMPaCT-Data: A Federated Precision Medicine Infrastructure Associated with Science and Technology in Spain.

Studies in health technology and informatics·2026
Same author

Commonalities in frailty and psychopathology predict chronotype across severe mental disorders from a comorbidity perspective.

Psychological medicine·2026
Same author

Leveraging training expertise to build capacity in computational personalised medicine.

Bioinformatics advances·2026
Same author

Deep representation learning for temporal inference in cancer omics: a systematic literature review.

Briefings in bioinformatics·2026
Same author

Airway organoids reveal patterns of influenza A tropism and adaptation in wildlife species.

Emerging microbes & infections·2026

Area of Science:

  • Molecular Biology
  • Bioinformatics
  • Genomics
  • Proteomics

Background:

  • Controlled vocabularies and classifications are vital in science and technology.
  • Their recent adoption in molecular biology has driven progress in genomics and proteomics.
  • Manual ontology construction, including terminology and relations, is labor-intensive, requiring extensive literature analysis.

Purpose of the Study:

  • To propose and evaluate a method for automatically generating gene-product function classifications.
  • To create classification structures that resemble those built by human experts.
  • To assess the utility of automated classifications in assisting human experts with ontology annotation.

Main Methods:

  • Utilized bibliographic information to automatically derive gene-product function classifications.

Related Experiment Videos

  • Developed classification structures that mirror human-curated ontologies.
  • Analyzed a large-scale classification for yeast gene-products.

    • Main Results:

    • The automated method successfully generated classification structures comparable to expert-defined ones.
    • Analysis of yeast gene-products demonstrated encouraging properties of the generated classifications.
    • Comparison with the Gene Ontology (GO) revealed specific scenarios where the automated classification is beneficial.

    Conclusions:

    • Automated generation of gene-product function classifications from literature is feasible.
    • The proposed method provides a valuable tool for assisting human experts in ontology development and annotation.
    • This approach can complement existing ontologies like GO by offering alternative or supplementary classification perspectives.