An Effective Tuning Method for Cysteine State Classification

Abstract

For solving the problem of cysteine state classification, we propose a 2-stage prediction method. In the first stage, we invoke the SVM to get the initial prediction. The features involved in SVM classification include the local profile PSSM, order of cysteines with the normalized protein length, physiochemical properties and structure probabilities. Then, in the second stage, we propose a tuning method for refining the predicted result obtained by SVM. We validate it with a dataset derived from PDB, which contains 969 non-homologous proteins and 4136 cysteines. We adopt a 20-fold crossvalidation test and achieve 90.7% accuracy and 0.79 Matthews correlation coefficient. With our tuning method, we can improve the performance from the initial prediction by about 20% in the protein-based accuracy and 5% in the cysteine-based accuracy. The prediction accuracies are better than the previous works.