Title :
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
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;
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
DOI :
10.1109/BMEI.2009.5302560
