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

Learning anchor verbs for biological interaction patterns from published text articles.

Vasileios Hatzivassiloglou1, Wubin Weng

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

International Journal of Medical Informatics
|December 4, 2002
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

Efficient Catalytic Ozonation of Dimethyl Carbonate on M‑Mn (M = Cr, Cu, Co)/ZSM‑5 Zeolites: Further Analysis of Reaction Mechanism.

ACS omega·2026
Same author

Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences.

Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing·2026
Same author

Quantitative measurement of atomic sodium in combustion environments using tunable laser absorption spectroscopy.

Optics letters·2025
Same author

Ruthenium-based electrocatalyst for efficient acidic water oxidation in PEM water electrolysis for H<sub>2</sub> production.

RSC advances·2025
Same author

Quantitative Hydrogen Chloride Detection in Combustion Environments Using Tunable Diode Laser Absorption Spectroscopy with Comprehensive Investigation of Hot Water Interference.

Applied spectroscopy·2022
Same author

Long non-‑coding RNA SNHG16 functions as a tumor activator by sponging miR‑373‑3p to regulate the TGF‑β‑R2/SMAD pathway in prostate cancer.

Molecular medicine reports·2021

This study introduces AVAD, an automated system for identifying biological interaction verbs in text. AVAD significantly improves the efficiency and coverage of molecular biology knowledge bases.

Area of Science:

  • Molecular Biology
  • Bioinformatics
  • Computational Biology

Background:

  • Knowledge modeling in molecular biology relies on understanding interactions between biological entities like proteins and genes.
  • Manual extraction of these interactions is time-consuming, costly, and limits the scope of biological knowledge bases.
  • Automated methods are needed to efficiently and comprehensively capture these crucial biological interactions.

Purpose of the Study:

  • To develop an automated system (AVAD) for learning and identifying biological interaction verbs directly from scientific literature.
  • To enhance the creation and coverage of molecular biology knowledge bases through automatic pattern retrieval.
  • To compare the performance of the automated approach against manually curated databases.

Main Methods:

Related Experiment Videos

  • The AVAD system learns to identify interaction verbs by analyzing text features that link verbs with genes and proteins.
  • Statistical tests and a logistic regression model are employed to classify verbs as interaction-related.
  • The system was evaluated on an 11 million word corpus of scientific journal articles.

Main Results:

  • The AVAD system achieved high performance with over 87% precision and 82% recall in identifying interaction verbs.
  • Automated extraction significantly enriched manually curated lists of interaction verbs.
  • Rarer interaction verbs, often missed in manual efforts, were successfully detected by the AVAD system.

Conclusions:

  • Automated identification of biological interaction verbs using systems like AVAD is a viable and effective approach.
  • This method substantially improves the efficiency, cost-effectiveness, and coverage of molecular biology knowledge bases.
  • AVAD offers a powerful tool for researchers to expand and refine our understanding of molecular interactions.