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

Automatic document classification of biological literature.

David Chen1, Hans-Michael Müller, Paul W Sternberg

  • 1Division of Biology and Howard Hughes Medical Institute, California Institute of Technology, Pasadena, California, USA. davidc@caltech.edu

BMC Bioinformatics
|August 9, 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

PIMPC-GNN: Physics-Informed Multiphase Consensus Learning for Enhancing Imbalanced Node Classification in Graph Neural Networks.

IEEE transactions on neural networks and learning systems·2026
Same author

Impact of health system interventions to improve access to external beam radiotherapy: a scoping review.

Frontiers in oncology·2026
Same author

Dual tumour-myeloid targeting of glioblastoma with GPNMB CAR-T cells.

Nature·2026
Same author

The optical origin of the human skin color 'banana' in CIELAB space.

bioRxiv : the preprint server for biology·2026
Same author

Treatment times for rural and urban patients with aneurysmal subarachnoid hemorrhage in a provincial hub-and-spoke network.

Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia·2026
Same author

The Evolving Clinical Utility of Gene Expression Profiling in Cutaneous Melanoma.

Journal of the National Comprehensive Cancer Network : JNCCN·2026

This study introduces a novel two-step algorithm for classifying biological documents, improving upon existing methods. The system, utilizing Textpresso markup and a phrase-based clustering engine, enhances document organization for researchers.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Text Mining

Background:

  • Document classification is crucial for organizing vast amounts of biological literature.
  • Textpresso, a text-mining system, annotates biological texts with relevant terms.
  • This research leverages Textpresso markup for classifying Caenorhabditis elegans literature.

Purpose of the Study:

  • To develop and evaluate an improved document classification algorithm for biological literature.
  • To enhance the organization and retrieval of scientific documents.
  • To investigate the efficacy of a two-step classification approach combining machine learning and clustering.

Main Methods:

  • A two-step text categorization algorithm was developed.
  • The first step employs a support vector machine (SVM) classifier.

Related Experiment Videos

  • The second step utilizes a novel phrase-based clustering algorithm that generates human-understandable labels.

    • Main Results:

    • The classification engine achieved a superior F-value (0.55) on the Reuters 21578 test set compared to prior methods (0.49).
    • The phrase-based clustering autonomously generated descriptive and useful cluster labels.
    • A web interface was developed to facilitate hierarchical navigation and document discovery.

    Conclusions:

    • A simple yet effective method for classifying biological documents was demonstrated, outperforming current techniques.
    • The classification engine, while optimized for Caenorhabditis elegans, is adaptable to other document types.
    • The developed system, including its web interface, aids researchers in efficiently navigating and identifying relevant biological literature.