组建一个分两个阶段的分类器来进行蛋白质二级结构预测。第一阶段由支持向量机分类器组成,在第二阶段中使用第一阶段已预测的结果来进行贝叶斯判别。预测性能的改进表明了结合支持向量机和贝叶斯方法预测性能优越于单独使用支持向量机的预测性能。同时也证明残基在形成二级结构时是相互影响的。
A two stage predictor is constructed to predict protein secondary structures.The first stage consists of one predictor based on the support vector machine.Bayesian discrimination is used at the second stage by considering the predicted labels of neighbor residues.The improvement of prediction performances indicates that this method outperforms the predictors based on SVM algorithm alone.At the same time,it proves that the residues are interactional when they constitute protein secondary structures.