Format

Send to:

Choose Destination
See comment in PubMed Commons below
PLoS One. 2013 May 1;8(5):e62077. doi: 10.1371/journal.pone.0062077. Print 2013.

Construction of ontology augmented networks for protein complex prediction.

Author information

  • 1College of Computer Science and Technology, Dalian University of Technology, Dalian, Liaoning, China. zhyj@dlut.edu.cn

Abstract

Protein complexes are of great importance in understanding the principles of cellular organization and function. The increase in available protein-protein interaction data, gene ontology and other resources make it possible to develop computational methods for protein complex prediction. Most existing methods focus mainly on the topological structure of protein-protein interaction networks, and largely ignore the gene ontology annotation information. In this article, we constructed ontology augmented networks with protein-protein interaction data and gene ontology, which effectively unified the topological structure of protein-protein interaction networks and the similarity of gene ontology annotations into unified distance measures. After constructing ontology augmented networks, a novel method (clustering based on ontology augmented networks) was proposed to predict protein complexes, which was capable of taking into account the topological structure of the protein-protein interaction network, as well as the similarity of gene ontology annotations. Our method was applied to two different yeast protein-protein interaction datasets and predicted many well-known complexes. The experimental results showed that (i) ontology augmented networks and the unified distance measure can effectively combine the structure closeness and gene ontology annotation similarity; (ii) our method is valuable in predicting protein complexes and has higher F1 and accuracy compared to other competing methods.

PMID:
23650509
[PubMed - indexed for MEDLINE]
PMCID:
PMC3641129
Free PMC Article
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Public Library of Science Icon for PubMed Central
    Loading ...
    Write to the Help Desk