支持向量机方法预测蛋白质结构中的二硫键

在蛋白质结构预测的研究中,一个重要的问题就是正确预测二硫键的连接,二硫键的准确预测可以减少蛋白质构像的搜索空间,有利于蛋白质3D结构的预测,本文将预测二硫键的连接问题转化成对连接模式的分类问题,并成功地将支持向量机方法引入到预测工作中。通过对半胱氨酸局域序列连接模式的分类预测,可以由蛋白质的一级结构序列预测该蛋白质的二硫键的连接。结果表明蛋白质的二硫键的连接与半胱氨酸局域序列连接模式有重要联系,应用支持向量机方法对蛋白质结构的二硫键预测取得了良好的结果。

Prediction of Disulfide Bonding in Protein Structure Based on Support Vector Machine

An important problem in protein structure prediction is the correct location of disulfide bonding in proteins. The location of disulfide bonding can strongly reduce the search in the conformational space of protein structure.Therefore the correct prediction of the disulfide bonding starting from the protein residue sequence may also help in predicting its 3D structure. The correct location of disulfide bonding is seen as the classification of connecting model of disulfide bonding and the support vector machine method is successfully applied to predict the disulfide bonding of protein structure in this paper. Therefore the disulfide bonding can be predicted by its primary structure when we predict the classification of connecting model of the local sequence arrangement of cysteine. We find that the local sequence arrangement of cysteine is of great significance to the disulfide bonding. This method is used to predict disulfide bonding in protein structure and a fine result is got.