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

Graph sharpening plus graph integration: a synergy that improves protein functional classification.

Hyunjung Shin1, Andreas Martin Lisewski, Olivier Lichtarge

  • 1Department of Industrial & Information Systems Engineering, Ajou University, San 5, Wonchun-dong, Yeoungtong-gu, 443-749, Suwon, Korea. shin@ajou.ac.kr

Bioinformatics (Oxford, England)
|November 6, 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

PIEZO1-mediated mechanosensation links aging to bladder dysfunction.

bioRxiv : the preprint server for biology·2026
Same author

Dual-Layer Grain-Boundary In Situ Polymerization Modulates Elastic Modulus for Mechanically Stable Flexible All-Perovskite Tandem Solar Cells.

ACS applied materials & interfaces·2026
Same author

Structural determinants of ligand response specificity in the mast cell activating GPCR, MRGPRX2.

The Journal of biological chemistry·2026
Same author

Synergistic bone regeneration through sequential dual-drug delivery.

Biomedical engineering letters·2026
Same author

Ultra-rare functional variants reveal early-onset breast cancer risk genes and pathways in the UK Biobank and All of Us Research Program.

American journal of human genetics·2026
Same author

EEPD1 evolved a unique DNA clamping dimer protecting reversed replication forks.

Nucleic acids research·2026

Graph sharpening enhances protein function prediction by reducing noise in similarity graphs. This method significantly improves classification accuracy with minimal computational cost, making it a valuable tool in bioinformatics.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Protein Science

Background:

  • Protein function prediction is a critical bioinformatics challenge.
  • Existing methods integrate protein similarity graphs but struggle with noise (inaccurate edges).
  • Noise in graphs can limit the effectiveness of simple integration strategies for accurate functional predictions.

Purpose of the Study:

  • To introduce graph sharpening, a novel graph-based learning method.
  • To reduce noise and improve the efficiency of integrating protein similarity graphs.
  • To enhance the accuracy of protein function prediction.

Main Methods:

  • Developed and applied graph sharpening to protein similarity graphs.
  • Integrated multiple, diverse molecular similarity measures.

Related Experiment Videos

  • Evaluated performance using a test set of 599 proteins across 20 Gene Ontology functional classes.

    • Main Results:

    • Graph sharpening combined with integration improved classification accuracy by nearly 30% (0.17 average AUC increase) compared to integration alone.
    • The method demonstrated robustness against errors and scalability for large protein datasets.
    • Achieved significant accuracy gains at negligible computational cost (average 4.66 CPU seconds for sharpening and integration).

    Conclusions:

    • Graph sharpening effectively reduces noise in protein similarity graphs.
    • The method offers a theoretically sound, practical, and efficient approach for protein function prediction.
    • This technique holds promise for advancing automated protein function annotation in bioinformatics.