Please use this identifier to cite or link to this item:
Title: An improved sequence-based prediction protocol for protein-protein interactions using amino acids substitution matrix and rotation forest ensemble classifiers
Authors: You, ZH
Li, X
Chan, KC
Keywords: Ensemble classifier
Protein sequence
Protein-protein interaction
Rotation forest
Substitution matrix
Issue Date: 2017
Publisher: Elsevier
Source: Neurocomputing, 2017, v. 228, p. 277-282 How to cite?
Journal: Neurocomputing 
Abstract: Protein-protein Interactions (PPIs) play important roles in a wide variety of cellular processes, including metabolic cycles, DNA transcription and replication, and signaling cascades. High-throughput biological experiments for identifying PPIs are beginning to provide valuable information about the complexity of PPI networks, but are expensive, cumbersome, and extremely time-consuming. Hence, there is a need for accurate and robust computational methods for predicting PPIs. In this article, a sequence-based approach is proposed by combining a novel amino acid substitution matrix feature representation and Rotation Forest (RF) classifier. Given the protein sequences as input, the proposed method predicts whether or not the pair of proteins interacts. When performed on the PPI data of Saccharomyces cerevisiae, the proposed method achieved 93.74% prediction accuracy with 90.05% sensitivity at the precision of 97.08%. Extensive experiments are performed to compare our method with the existing sequence-based method. Experimental results demonstrate that PPIs can be reliably predicted using only sequence-derived information. Achieved results show that the proposed approach offers an inexpensive method for computational construction of PPI networks, so it can be a useful supplementary tool for future proteomics studies.
ISSN: 0925-2312
EISSN: 1872-8286
DOI: 10.1016/j.neucom.2016.10.042
Appears in Collections:Journal/Magazine Article

SFX Query Show full item record


Last Week
Last month
Citations as of Dec 10, 2017


Last Week
Last month
Citations as of Dec 17, 2017

Page view(s)

Last Week
Last month
Citations as of Dec 17, 2017

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.