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

Extracting human protein interactions from MEDLINE using a full-sentence parser.

Nikolai Daraselia1, Anton Yuryev, Sergei Egorov

  • 1Ariadne Genomics, Inc., 9700 Great Seneca Hwy, Rockville, MD 20850, USA. nikolai@ariadnegenomics.com

Bioinformatics (Oxford, England)
|March 23, 2004
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

Structural and isotopic peculiarities of a Сhernobyl fuel "hot" particle.

Journal of environmental radioactivity·2026
Same author

Intra-host GI.1 norovirus evolution is shaped by genetic drift and purifying selection.

Virus evolution·2026
Same author

Unbiased metagenomic exploration of transfusion-transmitted infections with nanopore sequencing.

Transfusion·2025
Same author

Temperature Dependence of the Inverse Haven Ratio in Ionic Liquids and "Solvent-in-Salt" Systems.

The journal of physical chemistry. B·2025
Same author

GII.17 norovirus re-emerged in the 2020s as a result of dynamic and adaptive evolutionary processes.

Nature communications·2025
Same author

Effect of the Cooling Liquid on the Milled Interface in the Combined Process of Milling and Direct Metal Deposition.

Materials (Basel, Switzerland)·2024
Same journal

Probabilistic RNA designability via interpretable ensemble approximation and dynamic decomposition.

Bioinformatics (Oxford, England)·2026
Same journal

Quantifying domain-specific relevance of computational biology Wikipedia articles using TF-IDF and cosine similarity.

Bioinformatics (Oxford, England)·2026
Same journal

GATSBI: improving context-aware protein embeddings through biologically motivated data splits.

Bioinformatics (Oxford, England)·2026
Same journal

BiMba: using Vision Mamba to predict protein sites that bind other proteins.

Bioinformatics (Oxford, England)·2026
Same journal

ProMeta: a meta-learning framework for robust disease diagnosis and prediction from plasma proteomics.

Bioinformatics (Oxford, England)·2026
Same journal

Is a Win-Win possible? Achieving pareto-optimal privacy-utility balance in fine-tuned genome language model embeddings against embedding reconstruction attacks.

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

Researchers developed MedScan, an automated system for extracting human protein interactions from scientific literature. This tool significantly aids in organizing biological data, overcoming manual curation limitations for computational analysis.

Area of Science:

  • Life Sciences
  • Bioinformatics
  • Computational Biology

Background:

  • The cell's complexity relies on protein function and interactions.
  • Knowledge of protein interactions is fragmented across scientific publications.
  • Manual data curation is impractical due to exponential information growth.

Purpose of the Study:

  • To develop an automated system for extracting protein interaction data.
  • To create a computational approach for biological data organization.
  • To address the bottleneck in research caused by scattered information.

Main Methods:

  • Utilized natural language processing (NLP) for information extraction.
  • Developed the MedScan system for automated data retrieval.
  • Processed MEDLINE abstracts published after 1988.

Related Experiment Videos

Main Results:

  • Extracted 2976 human protein interactions with 91% precision.
  • Identified 96% of extracted information as novel compared to existing databases.
  • Achieved a recall rate of 21% for protein interactions.

Conclusions:

  • MedScan offers a viable, automated solution for biological data extraction.
  • MEDLINE abstracts are a rich, accessible source for protein function information.
  • Automated extraction enables efficient data mining and computational analysis.