Generic placeholder image

Current Protein & Peptide Science

Editor-in-Chief

ISSN (Print): 1389-2037
ISSN (Online): 1875-5550

Predicting Protein Functions by Using Unbalanced Bi-Random Walk Algorithm on Protein-Protein Interaction Network and Functional Interrelationship Network

Author(s): Wei Peng, Jianxin Wang, Lu Chen, Jiancheng Zhong, Zhen Zhang and Yi Pan

Volume 15, Issue 6, 2014

Page: [529 - 539] Pages: 11

DOI: 10.2174/1389203715666140724085224

Price: $65

Abstract

Accurate annotation of protein functions is still a big challenge for understanding life in the post-genomic era. Recently, some methods have been developed to solve the problem by incorporating functional similarity of GO terms into protein-protein interaction (PPI) network, which are based on the observation that a protein tends to share some common functions with proteins that interact with it in PPI network, and two similar GO terms in functional interrelationship network usually co-annotate some common proteins. However, these methods annotate functions of proteins by considering at the same level neighbors of proteins and GO terms respectively, and few attempts have been made to investigate their difference. Given the topological and structural difference between PPI network and functional interrelationship network, we firstly investigate at which level neighbors of proteins tend to have functional associations and at which level neighbors of GO terms usually co-annotate some common proteins. Then, an unbalanced Bi-random walk (UBiRW) algorithm which iteratively walks different number of steps in the two networks is adopted to find protein-GO term associations according to some known associations. Experiments are carried out on S. cerevisiae data. The results show that our method achieves better prediction performance not only than methods that only use PPI network data, but also than methods that consider at the same level neighbors of proteins and of GO terms.

Keywords: Functional similarity, GO ontology, protein function annotation, protein function prediction, protein-protein interaction network, random walk.


Rights & Permissions Print Cite
© 2024 Bentham Science Publishers | Privacy Policy