论文部分内容阅读
为了研究手性二芳基甲烷衍生物的保留因子和分离因子,基于分子结构及邻接矩阵,计算了63个手性二芳基甲烷衍生物的分子连接性指数和电性拓扑状态指数。建立了这些分子保留因子、分离因子与优化得到的结构指数之间的相关性模型,并将筛选的结构参数作为BP神经网络的输入层变量,采用不同的网络结构,获得了令人较为满意的三个预测模型,模型的总相关系数R分别为0.981、0.972和0.992。利用模型计算得到的保留因子和分离因子预测值与实验值的平均误差分别为0.041、0.042和0.010,吻合度较好。结果表明手性二芳基甲烷衍生物的保留因子及分离因子与分子结构参数之间有良好的非线性关系。
In order to study the retention and separation factors of chiral diarylmethane derivatives, the molecular connectivity index and electrical topological index of 63 chiral diarylmethane derivatives were calculated based on the molecular structure and the adjacency matrix. The correlation model between the molecular retention factor, the separation factor and the optimized structure index was established. The selected structural parameters were used as input variables of BP neural network. Different network structures were used to obtain the more satisfactory Three prediction models, the model of the total correlation coefficient R were 0.981,0.972 and 0.992. The average error between the predicted value of the retention factor and the separation factor calculated by the model and the experimental value is respectively 0.041, 0.042 and 0.010, and the good agreement is obtained. The results show that there is a good nonlinear relationship between the retention and separation factors of chiral diarylmethane derivatives and the molecular structure parameters.