论文部分内容阅读
采用量子化学密度泛函B3LYP法,用6-311+G(d,p)基组,计算38个苯烷基胺类化合物的电子结构参数;利用多元线性回归(multiple linear regression,MLR)法,筛选出影响化合物迷幻活性显著的6个变量,并建立其结构参数与迷幻活性之间的定量关系(MLR模型);同时,利用人工神经网络(artificial neural network,ANN)法建立相应的QSAR模型(ANN模型)以资对比。所建MLR模型的相关系数R=0.9340,标准误差Se=0.2068;ANN模型的相关系数R=0.9992,标准误差Se=0.0036。结果表明人工神经网络法获得了比多元线性回归方法更精密的拟合效果,可望在QSAR研究中发挥重要作用。
Quantum chemical density functional B3LYP method was used to calculate the electronic structure parameters of 38 phenylalkylamines using the 6-311 + G (d, p) basis set. Using multiple linear regression (MLR) The six variables influencing the psychedelic activity of the compounds were screened out and the quantitative relationship between their structural parameters and psychedelic activity was established (MLR model). At the same time, artificial neural network (ANN) was used to establish the corresponding QSAR Model (ANN model) for capital comparison. The correlation coefficient R = 0.9340, the standard error Se = 0.2068, the correlation coefficient R = 0.9992, the standard error Se = 0.0036 for the MLR model. The results show that the artificial neural network method is more precise than the multivariate linear regression fitting effect, is expected to play an important role in the QSAR study.