Predicting Protein-Protein Interactions Using Correlation Coefficient and Principle Component Analysis

Author

Thanathamathee, Putthiporn ; Lursinsap, Chidchanok

Author_Institution

Dept. of Math., Chulalongkorn Univ., Bangkok, Thailand

fYear

2009

fDate

11-13 June 2009

Firstpage

1

Lastpage

4

Abstract

A new features for predicting protein-protein interaction with neural classification is proposed. Our feature extraction is based on the correlation coefficients of physicochemical properties and the statistical means and standard deviations of five secondary structures, i.e. alpha-helix, beta-sheet, beta-turn, coil, and parallel beta strand. The proposed method is tested with yeast Saccharomyces Cerevisiae proteins. Our result uses fewer features which is 50% less than the other´s and achieves 92.15% accuracy higher than the other other´s.

Keywords

bioinformatics; correlation methods; feature extraction; feedforward neural nets; microorganisms; molecular biophysics; pattern classification; principal component analysis; proteins; correlation coefficient; feature extraction; feed-forward neural network; neural classification; physicochemical property; principle component analysis; protein-protein interactions; secondary structure; yeast Saccharomyces Cerevisiae protein; Accuracy; Amino acids; Biological processes; Cells (biology); Coils; Feature extraction; Fungi; Neural networks; Protein engineering; Protein sequence;

fLanguage

English

Publisher

ieee

Conference_Titel

Bioinformatics and Biomedical Engineering , 2009. ICBBE 2009. 3rd International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-2901-1

Electronic_ISBN

978-1-4244-2902-8

Type

conf

DOI

10.1109/ICBBE.2009.5163211

Filename

5163211