Identify DNA-Binding Proteins with Optimal Chou’s Amino Acid Composition

Author(s): Xiao-Wei Zhao, Xiang-Tao Li, Zhi-Qiang Ma, Ming-Hao Yin

Journal Name: Protein & Peptide Letters

Volume 19 , Issue 4 , 2012


Become EABM
Become Reviewer
Call for Editor

Abstract:

DNA-binding proteins play an important role in most cellular processes, such as gene regulation, recombination, repair, replication, and DNA modification. In this article, an optimal Chou’s pseudo amino acid composition (PseAAC) based on physicochemical characters of amino acid is proposed to represent proteins for identifying DNAbinding proteins. Six physicochemical characters of amino acids are utilized to generate the sequence features via the web server PseAAC. The optimal values of two important parameters (correlation factor λ and weighting factor w) about PseAAC are determined to get the appropriate representation of proteins, which ultimately result in better prediction performance. Experimental results on the benchmark datasets using random forest show that our method is really promising to predict DNA-binding proteins and may at least be a useful supplement tool to existing methods.

Keywords: DNA-binding proteins, pseudo amino acid composition, random forest (RF), physicochemical character

Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 19
ISSUE: 4
Year: 2012
Page: [398 - 405]
Pages: 8
DOI: 10.2174/092986612799789404
Price: $65

Article Metrics

PDF: 6