A SVM-based system for predicting protein-protein interactions using a novel representation of protein sequences

Authors:
Zhuhong You;Zhong Ming;Ben Niu;Suping Deng;Zexuan Zhu
Affiliations:
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China;College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China;College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China;Department of Computer Science and Technology, Tongji University, Shanghai, P.R. China;College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China
Venue:
ICIC'13 Proceedings of the 9th international conference on Intelligent Computing Theories
Year:
2013

Citing 5
Cited 0

Support-Vector Networks

Machine Learning
Recursive prediction for long term time series forecasting using advanced models

Neurocomputing
Optimizing amino acid groupings for GPCR classification

Bioinformatics
Using manifold embedding for assessing and predicting protein interactions from high-throughput experimental data

Bioinformatics
Increasing reliability of protein interactome by combining heterogeneous data sources with weighted network topological metrics

ICIC'10 Proceedings of the 6th international conference on Advanced intelligent computing theories and applications: intelligent computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Protein-protein interactions (PPIs) are crucial for almost all cellular processes, including metabolic cycles, DNA transcription and replication, and signaling cascades. However, the experimental methods for identifying PPIs are both time-consuming and expensive. Therefore, it is important to develop computational approaches for predicting PPIs. In this article, a sequence-based method is developed by combining a novel feature representation using binary coding and Support Vector Machine (SVM). The binary-coding-based descriptors account for the interactions between residues a certain distance apart in the protein sequence, thus this method adequately takes the neighboring effect into account and mine interaction information from the continuous and discontinuous amino acids segments at the same time. When performed on the PPI data of Saccharomyces cerevisiae, the proposed method achieved 86.93% prediction accuracy with 86.99% sensitivity at the precision of 86.90%. Extensive experiments are performed to compare our method with the existing sequence-based method. Achieved results show that the proposed approach is very promising for predicting PPI, so it can be a useful supplementary tool for future proteomics studies.