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

Automatically identifying gene/protein terms in MEDLINE abstracts.

Hong Yu1, Vasileios Hatzivassiloglou, Andrey Rzhetsky

  • 1Department of Computer Science, Columbia University, 1214 Amsterdam Avenue, New York, NY 10027, USA. Hongyu@cs.columbia.edu

Journal of Biomedical Informatics
|September 13, 2003
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

An effective encoding of human medical conditions in disease space provides a versatile framework for deciphering disease associations.

Quantitative biology (Beijing, China)·2026
Same author

Longitudinal analysis of electronic health records reveals medical conditions associated with subsequent Alzheimer's disease development.

Alzheimer's research & therapy·2025
Same author

Public Health.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025
Same author

Longitudinal Analysis of Electronic Health Records Reveals Medical Conditions Associated with Subsequent Alzheimer's Disease Development.

medRxiv : the preprint server for health sciences·2025
Same author

Digital twins as global learning health and disease models for preventive and personalized medicine.

Genome medicine·2025
Same author

Prevalence and incidence measures for schizophrenia among commercial health insurance and medicaid enrollees.

Schizophrenia (Heidelberg, Germany)·2024

GPmarkup software automatically identifies gene and protein terms in scientific abstracts. This tool also generates a valuable knowledge source of gene/protein symbols and full names, aiding biological information extraction.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Natural Language Processing

Background:

  • Natural Language Processing (NLP) is crucial for extracting biological information from text.
  • Identifying gene and protein terms is a foundational step for advanced biological NLP tasks.
  • Existing databases may not capture all gene/protein nomenclature variations.

Purpose of the Study:

  • To develop GPmarkup, a software system for automatic identification of gene and protein terms in MEDLINE abstracts.
  • To create a knowledge source of paired gene/protein symbols and full names.
  • To assess the utility of the generated knowledge source for lexicon expansion.

Main Methods:

  • GPmarkup utilizes NLP techniques to parse MEDLINE abstracts.
  • The system identifies both gene/protein symbols and their full names.

Related Experiment Videos

  • A knowledge source of symbol-full name pairs is automatically generated during the markup process.

    • Main Results:

    • GPmarkup achieves 73% recall and 93% precision in identifying gene/protein terms.
    • The generated knowledge source contains gene/protein pairs not found in current databases like GenBank.
    • This indicates potential for automatic lexicon generation.

    Conclusions:

    • GPmarkup effectively identifies gene and protein terms in biomedical literature.
    • The automated generation of a gene/protein nomenclature knowledge base is feasible.
    • The developed methods can contribute to building comprehensive biological lexicons.