A New Method for Remote Protein Classification

Author

Li, YuGang ; Liu, Zhiyong ; Zhang, Fa ; Qiu, ZhenGe

Author_Institution

Beijing Key Lab. for Intell. Inf. Technol., Beijing Inst. of Technol., Beijing, China

fYear

2009

fDate

17-19 Oct. 2009

Firstpage

1

Lastpage

5

Abstract

Protein classification is an important research topic in bioinformatics. The support vector machine (SVM) based methods, e.g. the SVM-PSV algorithm, are among the most successful ones. Based on our current work, this paper presents an alternative algorithm, the LS_StaticEField algorithm, for protein classification. The LS_StaticEField algorithm is more efficient to compute than SVM based ones and provides satisfying accuracy performance when compared with the SVM-PSV method in the experiments of homology detection based on the SCOP database.

Keywords

bioinformatics; molecular biophysics; proteins; support vector machines; LSStaticEField algorithm; SCOP database; SVM-PSV method; bioinformatics; homology detection; position specific value kernel; remote protein classification; support vector machine; Bioinformatics; Classification algorithms; Databases; Hidden Markov models; Kernel; Machine learning algorithms; Proteins; Statistics; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering and Informatics, 2009. BMEI '09. 2nd International Conference on

Conference_Location

Tianjin

Print_ISBN

978-1-4244-4132-7

Electronic_ISBN

978-1-4244-4134-1

Type

conf

DOI

10.1109/BMEI.2009.5302560

Filename

5302560