Improved prediction of subcellular location for apoptosis proteins by the dual layer support vector machine英文文献.pdfVIP

Amino Acids (2008) 35: 383–388 DOI 10.1007/s00726-007-0608-y Printed in The Netherlands Improved prediction of subcellular location for apoptosis proteins by the dual-layer support vector machine X.-B. Zhou, C. Chen, Z.-C. Li, and X.-Y. Zou School of Chemistry and Chemical Engineering, Sun Yat-Sen University, Guangzhou, China Received July 20, 2007 Accepted September 18, 2007 Published online December 21, 2007; # Springer-Verlag 2007 Summary. Apoptosis proteins play an important role in the development microscopy and fluorescence microscopy, they are both and homeostasis of an organism. The accurate prediction of subcellular time-consuming and expensive (Chou and Cai, 2002; location for apoptosis proteins is very helpful for understanding the mech- anism of apoptosis and their biological functions. However, most of the Feng, 2002). Therefore, it is very urgent to develop an existing predictive methods are designed by utilizing a single classifier, automatic and reliable prediction system for protein sub- which would limit the further improvement of their performances. In this cellular location. paper, a novel predictive method, which is essentially a multi-classifier system, has been proposed by combing a dual-layer support vector ma- Actually, many predictive methods have been devel- chine (SVM) with multiple compositions including amino acid compos- oped, which in general, can be roughly divided into two ition (AAC), dipeptide composition (DPC) and amphiphilic pseudo amino categories. One is based on N-terminal sorting signal acid composition (Am-Pse-AAC). As a demonstration, the predictive (Nakai and Kanehisa, 1992; Emanuelsson et al., 2000), pe