摘要
为建立咪唑类ALK5抑制剂活性的QSAR预测模型,分析了61个咪唑类ALK5抑制剂的分子结构与活性的关系;计算了这些抑制剂分子的分子形状指数、电性拓扑状态指数和电性距离矢量;优化筛选了分子形状指数的K_1和K_3,电性拓扑状态指数的E_(19)、E_(21)和E_(24),电性距离矢量的M_(26)、M_(30)和M_(56),共8个参数.将这8个参数作为人工神经网络的输入神经元变量,活性pIC50作为输出神经元变量,采用8∶4∶1的神经网络结构,获得了令人较为满意的神经网络预测模型,模型的总相关系数r为0.956.pIC_(50)的预测值与实验值较为吻合,平均相对误差仅为0.85%.结果表明,本法建构的神经网络模型具有较强的稳健性和良好的预测能力.研究结果可为合成高活性的抗癌新药提供理论指导.
In order to establish the QSAR model to predict activities of imidazole ALK5 inhibitors,the relationship between molecular structures and the activities(p IC 50)of 61 kinds of imidazole ALK5 inhibitors was analyzed.Moreover,the molecule shape indices,electrical topological state indices and electric distance vectors of these compounds were calculated.The molecule shape indices K 1 and K 3,the electrical topological state indices E 19,E 21 and E 24,as well as electric distance vectors M 26,M 30 and M 56,were optimized and screened.The eight parameters were used as input layer neuron variables of neural network and the activity data p IC 50 was used as output layer neuron variable,the 8∶4∶1 neural network structure was adopted and the artificial neural network method was used to establish a more satisfying QSAR prediction model.The total correlation coefficient r is 0.956.The predicted values of p IC 50 and experimental values are very close,and the mean relative error is 0.85%.The results showed that the neural network model has strong stability and good predictive ability.It can provide guidance for the synthesis of new anticancer drugs with high activity.
作者
堵锡华
李靖
吴琼
周俊
陈艳
石春玲
冯惠
DU Xi-Hua;LI Jing;WU Qiong;ZHOU Jun;CHEN Yan;SHI Chun-Ling;FENG Hui(School of Chemistry and Chemical Engineering,Xuzhou Institute of Technology,Xuzhou 221018,China)
出处
《四川大学学报(自然科学版)》
CAS
CSCD
北大核心
2019年第5期933-938,共6页
Journal of Sichuan University(Natural Science Edition)
基金
国家自然科学基金(21472071)
江苏省自然科学基金(BK20171168)
关键词
咪唑类衍生物
ALK5抑制剂
分子结构参数
神经网络法
多元回归分析
Imidazole derivatives
ALK5 inhibitors
Molecular structure parameter
Neural network method
Multiple regression analysis