Title :
Influence of encoding scheme on protein secondary structure prediction
Author :
Zou, Dongsheng ; He, Zhongshi ; He, Jingyuan ; Huang, Xiaofeng
Author_Institution :
Coll. of Comput. Sci., Chongqing Univ., Chongqing
Abstract :
Secondary structure prediction of proteins has increasingly been a central research area in bioinformatics. In order to know which data encoding approach is more effective whiling predicting secondary structure using SVM, five approaches: ENCOrth, ENCFive, ENCCodBas, ENCCodExt and ENCProf are discussed in this paper. The results of data encoding are used as input of SVM. By performing ENCProf approach, the accuracy of Q3 can be improved 19.4%~23.9% more than the other four approaches.
Keywords :
bioinformatics; data handling; proteins; support vector machines; ENCCodBas; ENCCodExt; ENCFive; ENCOrth; ENCProf; SVM; bioinformatics; data encoding scheme; protein secondary structure prediction; support vector machine; Automation; Bioinformatics; Computer science; Educational institutions; Electronic mail; Encoding; Intelligent control; Proteins; Support vector machines; Profile encoding; SVM; data encoding; protein secondary structure prediction;
Conference_Titel :
Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-2113-8
Electronic_ISBN :
978-1-4244-2114-5
DOI :
10.1109/WCICA.2008.4593133
