Zeitschrift für Proteomik und Bioinformatik
Offener Zugang

Abstrakt

Prediction of Membrane Spanning β Strands in Bacterial Porins by Using Wavelet Support Vector Machine Algorithm

Guang-ming Xian

For accurate prediction of transmembrane β strands in bacterial porins, we proposed a wavelet support vector machine (WSVM) algorithm to predict the transmembrane β strands in bacterial porins based on the application of WSVM algorithm. The method was applied to all the five porins of known structure (three training proteins, porins from Escherichia coli, Rhodobacter capsulatus and Rhodopseudomonas blastic and two test proteins, porin from Klebsiella pneumoniae and Comamonas acidovorans). For all the five proteins the WSVM method predictived the transmembrane strands in bacterial porins to an average accuracy 84.9%, a higher predictive level than SVM (81.6%) and RNFNN (78.8%) methods. The best test result of the SVM is the precictor with wavelet kernel, which is 84.9% better than other three SVM kernel function of the Gaussian RBF kernel, Polynomial kernel as well as Linear kernel that average 81.6%, 80.3%, and 79.8%, respectively. The experimental results demonstrate the efficacy of the proposed WSVM method.