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

A domain combination based probabilistic framework for protein-protein interaction prediction.

Dongsoo Han1, Hong-Soog Kim, Jungmin Seo

  • 1School of Engineering, Information and Communications University, PO Box 77, Yusong, Daejeon 305-600, Korea. dshan@icu.ac.kr

Genome Informatics. International Conference on Genome Informatics
|February 12, 2005
PubMed
Summary

This study introduces a novel probabilistic framework using domain combination pairs to predict protein interactions. The new model achieves high sensitivity in identifying interacting protein pairs.

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

Cultivation system and plant health influence root-associated bacterial community structure and interaction networks in strawberry.

Scientific reports·2026
Same author

Effectiveness of Lee Silverman Voice Treatment (LSVT)-BIG for Neurological Diseases Other than Parkinson's Disease: Mini Review.

Brain sciences·2025
Same author

Intracranial Disease Region Composite Interpretation Technology for Enhanced Source Localization in Pediatric Epilepsy Surgery.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2025
Same author

DeepIOD: Towards A Context-Aware Indoor-Outdoor Detection Framework Using Smartphone Sensors.

Sensors (Basel, Switzerland)·2024
Same author

SELID: Selective Event Labeling for Intrusion Detection Datasets.

Sensors (Basel, Switzerland)·2023
Same author

Piezoelectric characteristics of PVA/DL-alanine polycrystals in d<sub>33</sub> mode.

iScience·2023

Area of Science:

  • Computational biology
  • Bioinformatics
  • Systems biology

Background:

  • Predicting protein-protein interactions is crucial for understanding cellular mechanisms.
  • Conventional methods using domain pairs have limitations in accuracy and scope.
  • A more refined unit of prediction is needed to improve protein interaction prediction.

Purpose of the Study:

  • To develop a probabilistic framework for predicting protein interaction probability.
  • To introduce and utilize the concept of domain combination pairs as a fundamental unit for protein interaction prediction.
  • To overcome limitations of existing domain pair-based prediction systems.

Main Methods:

  • A probabilistic framework involving prediction preparation and service stages was developed.

Related Experiment Videos

  • Two appearance probability matrices were constructed based on domain combination pair frequencies in interacting and non-interacting protein sets.
  • A probability equation was devised to map protein pairs to interaction probabilities, generating distinct distributions for interacting and non-interacting sets.

    • Main Results:

    • The framework successfully predicted protein interaction probabilities.
    • Evaluation on a Yeast organism dataset showed high sensitivity (86%) and moderate specificity (56%) when using 80% of DIP interacting protein pairs for learning.
    • The domain combination pair approach demonstrated improved prediction capabilities compared to traditional domain pair methods.

    Conclusions:

    • The proposed probabilistic framework effectively predicts protein-protein interactions using domain combination pairs.
    • This novel approach offers a promising advancement in the field of bioinformatics and computational biology.
    • The framework's high sensitivity suggests its utility in identifying potential protein interactions within biological systems.