论文部分内容阅读
收集天然氨基酸的1369种0D-3D结构信息参数,经主成分分析得一组新氨基酸描述子—氨基酸0D-3D信息得分矢量,将其用于人免疫缺陷病毒蛋白酶(HIVPR)裂解位点预测,以线性判别分析与支持向量机建模预测HIVPR裂解位点.线性判别分析与支持向量机模型对646个训练集样本的自检验识别、留一法交互验证及对100个测试集样本外部验证的马休斯相关系数分别为0.879和0.911,0.849和0.901,0.822和0.846.经受试者操作特征曲线分析表明,支持向量机对HIVPR裂解位点的预测结果优于线性判别分析.研究显示,氨基酸0D-3D信息得分矢量可进一步用于HIVPR裂解位点预测.
A total of 1369 0D-3D structural information parameters of natural amino acids were collected. A new set of amino acid descriptors - amino acid 0D-3D information scoring vector was obtained by principal component analysis, which was used to predict HIVPR cleavage sites. Linear discriminant analysis and support vector machines were used to predict the HIVPR cleavage sites.Linear discriminant analysis and support vector machine (SVM) model were used to test 646 training samples for self-verification, one-leave-one-pair verification and external validation of 100 test samples Mathews correlation coefficients were 0.879 and 0.911, 0.849 and 0.901, 0.822 and 0.846, respectively.The analysis of the operating characteristic curves of the subjects showed that the prediction results of the support vector machine for HIVPR cleavage sites were superior to the linear discriminant analysis.The study showed that amino acids 0D The -3D information score vector can be further used for HIVPR cleavage site prediction.