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

RelEx--relation extraction using dependency parse trees.

Katrin Fundel1, Robert Küffner, Ralf Zimmer

  • 1Institut für Informatik, Ludwig-Maximilians-Universität München, Amalienstrasse 17, 80333 München, Germany. katrin.fundel@bio.ifi.lmu.de

Bioinformatics (Oxford, England)
|December 5, 2006
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

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

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

Immunity·2025
Same author

Resident and recruited macrophages differentially contribute to cardiac healing after myocardial ischemia.

eLife·2024
Same author

Multiomic analyses uncover immunological signatures in acute and chronic coronary syndromes.

Nature medicine·2024
Same author

Peripheral priming induces plastic transcriptomic and proteomic responses in circulating neutrophils required for pathogen containment.

Science advances·2024
Same journal

Biomedical Concept Recognition with Error-aware Negative-enhanced Ranking Framework.

Bioinformatics (Oxford, England)·2026
Same journal

TEDLH: Domain HMMs for sensitive detection of remote homologues.

Bioinformatics (Oxford, England)·2026
Same journal

PLNFGL: Joint Estimation of Multi-Condition Gene Networks from Single-cell RNA-seq Data.

Bioinformatics (Oxford, England)·2026
Same journal

MCFST: Spatial domain identification method based on multi-view graph convolutional network and graph fusion network.

Bioinformatics (Oxford, England)·2026
Same journal

SpaBiT: Enhancing Spatial Transcriptomics Resolution via Bidirectional Attention Transformers.

Bioinformatics (Oxford, England)·2026
Same journal

EDEL: Enhancing Dense Retrievers for Curation of Biomedical Knowledge Bases.

Bioinformatics (Oxford, England)·2026
See all related articles

This study introduces RelEx, a novel relation extraction tool for identifying gene and protein interactions from biomedical texts. RelEx achieves high precision and recall, aiding in the discovery of biological pathways and disease models.

Area of Science:

  • Biomedical Informatics
  • Computational Biology
  • Bioinformatics

Background:

  • Discovering biological regulatory pathways, signal cascades, metabolic processes, and disease models necessitates understanding gene and protein interactions.
  • A significant gap exists as many interactions described in biomedical literature are not yet cataloged in structured databases.
  • Extracting these interactions from free text is crucial for advancing biological research.

Purpose of the Study:

  • To develop and evaluate RelEx, an automated approach for extracting gene and protein relations from unstructured biomedical text.
  • To improve the accessibility of structured biological interaction data for research purposes.

Main Methods:

  • RelEx utilizes natural language processing (NLP) techniques, including dependency parsing, to analyze biomedical abstracts.

Related Experiment Videos

  • A set of simple rules is applied to the generated parse trees to identify and extract relations.
  • The approach was tested on a large corpus of one million MEDLINE abstracts.

    • Main Results:

    • RelEx successfully extracted approximately 150,000 gene and protein relations from the analyzed corpus.
    • The system demonstrated high performance, achieving an estimated 80% precision and 80% recall.
    • This indicates a robust capability for identifying interactions within biomedical literature.

    Conclusions:

    • RelEx provides an effective method for extracting valuable gene and protein interaction data from free text.
    • The tool's high performance and the availability of associated resources facilitate the construction of comprehensive biological knowledge bases.
    • This contributes to a deeper understanding of biological processes and disease mechanisms.