基于SVM方法分析蛋白酶体裂解位点的特异性

真核细胞中的泛素-蛋白酶体系统在抗原肽加工呈递途径中发挥着重要作用. 为了进一步研究蛋白酶体的酶切位点特异性, 采用支持向量机(support vector machine, SVM)方法建立了蛋白酶体的酶切位点预测模型. 在相同检验集下, 将本模型性能指标与其他预测模型方法比较, 结果是本模型性能指标优先, 预测准确度为83.1%. 由样本数据相应氨基酸对酶切位点形成的权重系数, 得出蛋白酶体酶切位点及其两侧区域氨基酸的裂解特异性, 反映了蛋白酶体裂解抗原蛋白的相互作用信息, 这表明蛋白酶体对抗原蛋白的酶切处理不是随机的, 而是有一定模式和选择性的.

Analysis of Specificity of Proteasome Cleavage Site Based on SVM Method

The ubiquitin-proteasome system of the eukaryote plays an important role in the antigen protein processing and presenting pathway. In order to further study the specificity of the proteasome cleavage sites, the support vector machine (SVM) was used to build the predictive model of proteasomal cleavage sites. Compared to other models with the same test set, the performance of this model is more satisfying, and the predictive accuracy of the model is 83.1%. The specificities of the cleavage sites and their adjacent positions come from the contribution of the amino acids of the samples to the cleavage sites, showing the information about interaction of the proteasome with an antigen protein, which demonstrates that the proteasome cleaves the target protein selectively, but not randomly.