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

Systematic feature evaluation for gene name recognition.

Jörg Hakenberg1, Steffen Bickel, Conrad Plake

  • 1Computer Science Department, Humboldt-Universität zu Berlin, 10099 Berlin, Germany. hakenberg@informatik.hu-berlin.de

BMC Bioinformatics
|June 18, 2005
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

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

Bioinformatics (Oxford, England)·2026
Same author

Knowledge-augmented pre-trained language models for biomedical relation extraction.

BMC bioinformatics·2025
Same author

PanThera: predictive analysis of higher-order combination therapies using deep neural networks.

Briefings in bioinformatics·2025
Same author

Explaining care need assessment surveys: qualitative and quantitative evaluation of state-of-the-art local and global explainable artificial intelligence methods.

JAMIA open·2025
Same author

Joint Item Response Models for Manual and Automatic Scores on Open-Ended Test Items.

Psychometrika·2025
Same author

The promise and challenges of computer mouse trajectories in DMHIs - A feasibility study on pre-treatment dropout predictions.

Internet interventions·2025

This study introduces a Support Vector Machine (SVM) system for identifying gene and protein names in text. Recursive feature elimination (RFE) optimized feature selection, improving performance and efficiency.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Natural Language Processing

Background:

  • Accurate identification of gene and protein names in scientific literature is crucial for biological research.
  • Existing methods often struggle with the complexity and variability of biological nomenclature.
  • The BioCreAtIvE evaluation task 1A specifically challenged systems to recognize gene/protein entities in natural language.

Purpose of the Study:

  • To develop and evaluate a robust system for recognizing gene and protein names in text.
  • To systematically assess the impact of different feature sets on classification performance.
  • To optimize the feature selection process for improved efficiency and understanding.

Main Methods:

  • A word classification system was built using a sliding window approach with a Support Vector Machine (SVM).

Related Experiment Videos

  • Pattern-based post-processing was employed for phrase recognition.
  • Recursive Feature Elimination (RFE) was utilized to systematically evaluate and reduce feature sets.
  • Features considered included pre/postfixes, character n-grams, capitalization patterns, and surrounding word classifications.

    • Main Results:

    • The SVM system demonstrated effectiveness in gene and protein name recognition.
    • Recursive Feature Elimination (RFE) improved classification performance by 0.7% compared to using all features.
    • A significant reduction in features (less than 5%) still yielded performance close to the maximum, indicating robustness to redundancy.
    • The study quantified the impact of various feature sets on classification accuracy.

    Conclusions:

    • The developed SVM-based system is effective for gene and protein name recognition.
    • Systematic feature evaluation using RFE is valuable for optimizing performance and understanding feature importance.
    • Efficient feature selection can lead to faster, more interpretable, and highly performant biological named entity recognition systems.