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

Gene symbol disambiguation using knowledge-based profiles.

Hua Xu1, Jung-Wei Fan, George Hripcsak

  • 1Department of Biomedical Informatics, Columbia University, New York City, New York, USA.

Bioinformatics (Oxford, England)
|February 23, 2007
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

Characterizing Documented Psychosocial Stressors in Pediatric Psychiatric Emergencies with an Open-Weight Large Language Model.

medRxiv : the preprint server for health sciences·2026
Same author

Integrating Entrustable Professional Activities in Simulation-Based Health Care Education: A Systematic Literature Review.

Simulation in healthcare : journal of the Society for Simulation in Healthcare·2026
Same author

Association between nocturnal asthma, symptom severity, and clinical outcomes: a systematic review.

The Journal of asthma : official journal of the Association for the Care of Asthma·2026
Same author

Redlining, Community Wealth, and Air Pollution: A Tale of Three Cities-Boston, Nashville, and Detroit.

Journal of urban health : bulletin of the New York Academy of Medicine·2026
Same author

Why do intensive care units in countries without board-certified clinical informatics specialists risk falling behind in the Artificial Intelligence era?

Critical care science·2026
Same author

Metagenomic next-generation sequencing in pediatric infectious disease diagnosis: A comprehensive systematic literature review and meta-analysis.

Diagnostic microbiology and infectious disease·2026

This study introduces a novel gene symbol disambiguation method using gene profiles derived from MEDLINE abstracts and knowledge sources. The approach significantly improves accuracy in text-mining for biomedical research.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Natural Language Processing

Background:

  • Gene symbol ambiguity poses a significant challenge for biomedical text-mining systems.
  • Existing resources like Entrez Gene and MEDLINE contain valuable gene characteristic information.
  • Leveraging these resources can aid in disambiguating gene symbols within scientific literature.

Purpose of the Study:

  • To develop and evaluate a novel method for automatic gene symbol disambiguation.
  • To utilize comprehensive gene profiles for enhancing the accuracy of text-mining applications.
  • To address the challenge of gene symbol ambiguity in biomedical natural language processing.

Main Methods:

  • Creation of gene profiles by extracting information from MEDLINE abstracts and annotated knowledge sources.

Related Experiment Videos

  • Application of an information retrieval method to rank similarity scores between gene mentions and candidate profiles.
  • Selection of the gene profile with the highest similarity score as the correct gene symbol sense.

    • Main Results:

    • The gene profile-based disambiguation method achieved high precision across different organisms.
    • Precision rates were 93.9% for mouse, 77.8% for fly, and 89.5% for yeast.
    • The study demonstrates the effectiveness of the proposed method on automatically generated test sets.

    Conclusions:

    • The developed gene profile approach offers a robust solution for gene symbol disambiguation.
    • This method can significantly enhance the performance of biomedical text-mining systems.
    • The findings contribute to more accurate information extraction from scientific literature.