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 to extract relations for protein annotation.

Jee-Hyub Kim1, Alex Mitchell, Teresa K Attwood

  • 1Artificial Intelligence Laboratory, University of Geneva, CH-1211 Geneva 4, Switzerland. jee.kim@cui.unige.ch

Bioinformatics (Oxford, England)
|July 25, 2007
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

Reducing the impact of diabetic foot ulcers (REDUCE): study protocol for an effectiveness and cost-effectiveness randomised controlled trial with embedded process evaluation.

BMJ open·2026
Same author

A study protocol for a randomised controlled trial investigating the clinical effectiveness, cost effectiveness and acceptability of Behavioural Activation for Young people (BAY) in CAMHS settings.

Trials·2026
Same author

Machine Learning Models in the Prediction of Adverse Outcomes in Peripheral Arterial Disease: Meta-Analysis.

Annals of vascular surgery·2026
Same author

People with severe mental illness have low rates of screening for non-communicable diseases: Findings of a multi-country cross-sectional study in South Asia.

Global mental health (Cambridge, England)·2026
Same author

Effectiveness of polyhexanide, chlorhexidine with neomycin and mupirocin for nasal methicillin-resistant Staphylococcus aureus (MRSA) decolonisation: non-inferiority RCT (TIDE).

Health technology assessment (Winchester, England)·2026
Same author

Dose de-escalation of alemtuzumab in matched unrelated donor haematopoietic stem cell transplantation.

British journal of haematology·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
Same journal

Informative Relational Learning for Adverse Reaction Prediction with Enhanced Generalization to Novel Drugs.

Bioinformatics (Oxford, England)·2026
Same journal

An interpretable deep learning framework uncovers features governing CRISPR-Cas9 genome-editing efficiency.

Bioinformatics (Oxford, England)·2026
Same journal

3DICE: Interpretable 3D Cross-Modal Learning for Drug-Target Interaction Prediction and Large-Scale Drug Discovery.

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

Automating protein annotation using information extraction (IE) is crucial due to the rapid growth of biomedical literature. This study presents an IE system that learns annotation rules from relevant and irrelevant sentences, simplifying the process.

Area of Science:

  • Biomedical Informatics
  • Computational Biology
  • Text Mining

Background:

  • Protein annotation is essential for understanding protein function, often relying on manual curation of biomedical literature.
  • The exponential increase in scientific publications makes manual annotation increasingly challenging and necessitates automated solutions.
  • Existing information extraction (IE) methods for protein annotation typically require extensive pre-defined rules or annotated data, which are difficult to obtain in the biomedical domain.

Purpose of the Study:

  • To develop an automated information extraction (IE) system for protein annotation.
  • To overcome the limitations of manual annotation and traditional IE approaches in the biomedical field.
  • To create a system that requires minimal expert input, focusing on sentence relevance labeling.

Related Experiment Videos

Main Methods:

  • Developed an IE system that learns annotation rules from labeled sentences.
  • The system identifies relevant and irrelevant sentences pertaining to specific protein topics.
  • Utilized domain expert-labeled sentences to train the IE model for relation and rule extraction.

Main Results:

  • Successfully applied the IE system to annotate proteins for a major protein family database.
  • The system demonstrated the ability to automatically extract relations related to protein disease, function, and structure.
  • Learned annotation rules and relations effectively from a limited set of relevant and irrelevant sentences.

Conclusions:

  • The developed IE system offers an efficient and scalable approach to protein annotation.
  • This method reduces the reliance on manual annotation and complex rule engineering.
  • The system shows promise for enhancing the annotation of protein family databases and advancing biomedical knowledge discovery.