|
Internet Electronic Journal of Molecular Design - IEJMD, ISSN 1538-6414, CODEN IEJMAT
| ABSTRACT - Internet Electron. J. Mol. Des. April 2002, Volume 1, Number 4, 219-226 |
Support Vector Machines for Predicting Membrane Protein Types by Incorporating
Quasi-Sequence-Order Effect
Yu-Dong Cai, Xiao-Jun Liu, Xue-biao Xu, and Kuo-Chen Chou
Internet Electron. J. Mol. Des. 2002, 1, 219-226
|
Abstract:
Membrane proteins can be classified among the following five types: (1) type I
membrane protein; (2) type II membrane protein; (3) multipass transmembrane proteins;
(4) lipid chain-anchored membrane proteins; (5) GPI-anchored membrane proteins. A
new learning machine, the Support Vector Machine, is applied for predicting the type of a
given membrane protein by incorporating the quasi-sequence-order effect. High success
rates were obtained by the self-consistency test (2030/2059 = 99%), jackknife test
(1696/2059 = 82%), and independent data test (2305/2625 = 88%).
|