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

Protein function prediction via graph kernels.

Karsten M Borgwardt1, Cheng Soon Ong, Stefan Schönauer

  • 1Institute for Computer Science, Ludwig-Maximilians-University Munich Oettingenstrasss e 67, 80538 Munich, Germany. borgwardt@dbs.ifi.lmu.de

Bioinformatics (Oxford, England)
|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

Natural History Collections at the Crossroads: Shifting Priorities and Data-Driven Opportunities.

Ecology letters·2025
Same author

Machine Learning for Biological Design.

Methods in molecular biology (Clifton, N.J.)·2024
Same author

Author Correction: Inferring structural variant cancer cell fraction.

Nature communications·2022
Same author

Prediction of recovery from multiple organ dysfunction syndrome in pediatric sepsis patients.

Bioinformatics (Oxford, England)·2022
Same author

Machine Learning Guided Batched Design of a Bacterial Ribosome Binding Site.

ACS synthetic biology·2022
Same author

Determinants of SARS-CoV-2 transmission to guide vaccination strategy in an urban area.

Virus evolution·2022
Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

Bioinformatics (Oxford, England)·2026
Same journal

SpaMFG: a Spatial Multi-omics Integration Method based on Feature Grouping.

Bioinformatics (Oxford, England)·2026
Same journal

CSCN: Inference of Cell-Specific Causal Networks Using Single-Cell RNA-Seq Data.

Bioinformatics (Oxford, England)·2026
Same journal

Sparse CCA-Based Mediation Analysis with High-Dimensional Exposures and Mediators.

Bioinformatics (Oxford, England)·2026
Same journal

Enhancing Cross-Context Generalization in Drug Perturbation Prediction with a Multimodal Conditional Diffusion Framework.

Bioinformatics (Oxford, England)·2026
Same journal

Primer Design through Submodular Function Estimation.

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

This study introduces a novel graph-based protein model integrating sequence, structure, and chemical data for improved function prediction. The approach demonstrates competitive accuracy, outperforming traditional models when additional features are included.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Structural Biology

Background:

  • Protein function prediction is crucial for understanding biological systems.
  • Existing computational methods rely on diverse protein features like sequence, structure, and motifs.
  • Integrating multiple data types remains a challenge for enhancing prediction accuracy.

Purpose of the Study:

  • To develop a novel graph-based model for protein function prediction.
  • To integrate sequential, structural, and chemical information into a unified protein representation.
  • To evaluate the model's performance against existing methods.

Main Methods:

  • Constructing a graph model representing proteins using sequential, structural, and chemical attributes.
  • Employing graph kernels and support vector machine classification for functional class prediction.

Related Experiment Videos

  • Utilizing hyperkernels for optimal selection and combination of node attributes.

    • Main Results:

    • The proposed graph model, using only sequence and structure, shows competitive performance.
    • Incorporating additional information like surface pocket size significantly boosts accuracy.
    • The model outperforms traditional vector-based models in protein function prediction.

    Conclusions:

    • The developed graph model offers an effective way to integrate diverse protein information.
    • This approach lays the groundwork for a robust protein function prediction system.
    • The method efficiently combines various data sources for enhanced biological insights.