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 classification using probabilistic chain graphs and the Gene Ontology structure.

Steven Carroll1, Vladimir Pavlovic

  • 1Department of Computer Science, Rutgers University, Piscataway, NJ 08854, USA.

Bioinformatics (Oxford, England)
|May 18, 2006
PubMed
Summary

This study introduces a novel method for protein classification by directly incorporating the Gene Ontology structure. This approach enhances predictive accuracy compared to traditional models, improving protein functional annotation.

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, Swelling, and In Vitro Digestion Behavior of DEGDA-Crosslinked Semi-IPN Dextran/Inulin Hydrogels.

Gels (Basel, Switzerland)·2026
Same author

Microscopic modeling of attention-based movement behaviors.

Transportation research. Part C, Emerging technologies·2025
Same author

SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models.

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision·2025
Same author

Horseradish (Armoracia rusticana L.) leaf juice encapsulated within polysaccharides-blend-based carriers: Characterization and application as potential antioxidants in mayonnaise production.

Food chemistry·2024
Same author

Comparative Studies of the Structural and Physicochemical Properties of the First Fullerene Derivative FD-C<sub>60</sub> (Fullerenol) and Second Fullerene Derivate SD-C<sub>60</sub> (3HFWC).

Nanomaterials (Basel, Switzerland)·2024
Same author

Influence of Ultrasonic and Chemical Pretreatments on Quality Attributes of Dried Pepper (<i>Capsicum annuum</i>).

Foods (Basel, Switzerland)·2023

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Systems Biology

Background:

  • Probabilistic graphical models are used for protein classification.
  • Gene Ontology classifications often validate these models.
  • Existing methods do not fully leverage the Gene Ontology's structure.

Purpose of the Study:

  • To directly incorporate the Gene Ontology structure into a graphical model for protein classification.
  • To improve protein classification accuracy by modeling functional dependencies.

Main Methods:

  • Representing each protein with a replicate of the Gene Ontology structure.
  • Connecting proteins based on functional similarity measures.
  • Employing belief propagation for predictions across ontology terms.

Related Experiment Videos

Main Results:

  • The proposed method significantly improves predictive ability for protein classification.
  • Directly utilizing the Gene Ontology outperforms traditional models.
  • An average accuracy increase of 27.8% was observed for term predictions.

Conclusions:

  • Directly incorporating Gene Ontology structure enhances protein classification.
  • The novel method offers improved accuracy over existing approaches.
  • This work provides a more effective framework for protein functional annotation.