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

ProMiner: rule-based protein and gene entity recognition.

Daniel Hanisch1, Katrin Fundel, Heinz-Theodor Mevissen

  • 1Fraunhofer Institute SCAI, Schloss Birlinghoven, 53754 Sankt Augustin, Germany. Daniel.Hanisch@aventis.com

BMC Bioinformatics
|June 18, 2005
PubMed
Summary

The ProMiner system effectively identifies gene and protein names in biomedical texts, overcoming challenges like evolving nomenclature and ambiguous terms. This tool achieved high accuracy in the BioCreAtIvE challenge for identifying gene and protein mentions.

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

FAIRification on Trial? A Provenance and Reproducible Metadata Build Pipeline for Clinical Research.

Studies in health technology and informatics·2026
Same author

Analysis and visualization of expression patterns with fuzzy sets as FlowSets.

NAR genomics and bioinformatics·2026
Same author

Divergent granulopoiesis at extramedullary sites safeguards antibacterial host defense.

Science immunology·2026
Same author

Applying AI to Support Categorization of Heterogeneous Epidemiological Datasets.

Studies in health technology and informatics·2025
Same author

Immunothrombolytic monocyte-neutrophil axes dominate the single-cell landscape of human thrombosis and correlate with thrombus resolution.

Immunity·2025
Same author

NFDI4Health Workflow and Service for Synthetic Data Generation, Assessment and Risk Management.

Studies in health technology and informatics·2024

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Natural Language Processing

Background:

  • Biomedical text analysis faces challenges in gene and protein name identification due to evolving nomenclature and ambiguous terms.
  • Multiple synonyms and overlapping names complicate accurate entity recognition.
  • The BioCreAtIvE challenge provides a benchmark for evaluating gene and protein name identification systems.

Purpose of the Study:

  • To evaluate the ProMiner system's performance in identifying gene and protein names in biomedical literature.
  • To assess the system's ability to handle nomenclature variations and ambiguities.
  • To compare ProMiner's effectiveness against benchmark datasets in the BioCreAtIvE challenge.

Main Methods:

  • ProMiner utilizes a pre-processed synonym dictionary for identifying potential gene and protein names.

Related Experiment Videos

  • A rule-based approach with a search algorithm optimized for multi-word names is employed.
  • The system incorporates organism-specific variants and organism name detection to enhance accuracy.

    • Main Results:

    • The ProMiner system achieved high performance in the BioCreAtIvE competition.
    • The system obtained an F-measure of approximately 0.8 for mouse and fly, and 0.9 for yeast.
    • These results demonstrate the system's effectiveness in gene and protein name identification across different organisms.

    Conclusions:

    • The ProMiner system demonstrates robust capabilities for gene and protein name identification in biomedical texts.
    • The system's enhancements effectively address challenges posed by nomenclature evolution and ambiguity.
    • ProMiner shows significant promise for applications in biomedical text mining and knowledge extraction.