论文部分内容阅读
雌激素类化合物由于其对人和野生动物健康的负面影响而受到广泛关注.雌激素受体存在两种亚型(ERα和ERβ),化合物与两种受体亚型在结合活性和化合物结构特征方面存在差异.以31种与雌激素β受体亚型(ERβ)结合的化合物为研究对象,采用启发式变量筛选方法,从1524个变量中筛选出5个与化合物活性(lgRBA)最相关的变量,然后采用多元线性回归(MLR)建立最佳预测模型.模型相关性显著,而且具有良好的稳健性和预测能力(r2=0.829,q2LOO=0.742,r2pred=0.772,q2ext=0.724,RMSEE=0.395).同时揭示了影响化合物与ERβ受体结合的配体化合物分子的结构特征,并对模型的应用域进行了研究.
Estrogen compounds have drawn much attention due to their negative effects on the health of humans and wildlife. There are two subtypes of estrogen receptor (ERa and ERp), the binding activity of compounds to both receptor subtypes and their structural features 31 compounds that bind to estrogen beta receptor subtype (ERβ) were selected as research objects and five of the 1524 variables were screened out by the heuristic variable screening method, the five compounds most relevant to the compound activity (lgRBA) (R2 = 0.829, q2LOO = 0.742, r2pred = 0.772, q2ext = 0.724, RMSEE = 0.395, r = 0.772, r = ) .At the same time reveal the structural characteristics of the ligand compound molecules that affect the binding of the compound to the ERβ receptor, and study the application domains of the model.