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

Finding genomic ontology terms in text using evidence content.

Francisco M Couto1, Mário J Silva, Pedro M Coutinho

  • 1Departamento de Informática, Faculdade de Ciências, Universidade de Lisboa, Portugal. fcouto@di.fc.ul.pt

BMC Bioinformatics
|June 18, 2005
PubMed
Summary

This study presents an unsupervised method for recognizing biological properties in scientific text. The approach effectively identifies Gene Ontology annotations and their evidence, aiding automatic annotation systems.

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

Predicting non-coding RNA function using Artificial Intelligence.

Journal of biomedical informatics·2026
Same author

Multimorbidity measurement strategies for predicting hospital visits.

BMC health services research·2025
Same author

The FUNG-GROWTH database: linking fungal phenotype to genome.

Microbiology resource announcements·2025
Same author

Zero-shot learning for clinical phenotyping: Comparing LLMs and rule-based methods.

Computers in biology and medicine·2025
Same author

Dividing the α-amylase family GH57 of starch hydrolases and related enzymes into subfamilies using evolutionary, clustering and functional criteria.

International journal of biological macromolecules·2025
Same author

The Federated European Genome-Phenome Archive as a global network for sharing human genomics data.

Nature genetics·2025

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Natural Language Processing

Background:

  • Automated annotation of biological entities and their properties from scientific literature is a key research area.
  • Text mining systems require accurate recognition of biological entities and properties, followed by validation of annotation pairs.

Purpose of the Study:

  • To introduce a novel unsupervised method for recognizing biological properties within unstructured scientific text.
  • To leverage the evidence content of biological entity names for property recognition.

Main Methods:

  • Development of an unsupervised machine learning approach for biological property identification.
  • Utilizing name evidence for enhanced recognition of biological properties in text.

Related Experiment Videos

Main Results:

  • The method was applied to BioCreative tasks 2.1 and 2.2.
  • Successfully identified Gene Ontology (GO) annotations and their supporting evidence in a corpus of scientific articles.

Conclusions:

  • The unsupervised method demonstrates effectiveness in identifying biological properties from unstructured text.
  • The approach is suitable for integration into automatic annotation systems, as validated by BioCreative performance.