分子表面随机采样分析用于HIV整合酶抑制剂的QSAR研究

QSAR studies of HIV-1 integrase inhibitors using random sampling analysis on molecular surface

采用分子表面随机采样分析对26个香豆素类衍生物抗艾滋病药物进行定量构效关系研究。运用多元线性回归(multiple linear regression,MLR)建模,同时采用内部及外部双重验证的办法对所得模型稳定性能进行深入分析和检验。MLR建模的复相关系数(_(cum)~2)、留一法(1eave-one-out,LOO)交互校验(cross-validation,CV)复相关系数(Q_(CV)~2)和外部样本校验复相关系数r^2(test)分别为0.936、0.894、0.772。结果表明,RASMS能较好表征香豆素类衍生物抗艾滋病药物分子的结构信息,且所建模型具有良好稳定性和预测能力,可用于研发新型HIV整合酶抑制剂。

RASMS （random sampling analysis on molecular surface） was used to describe the quantitative structure-activity relationship of anti HIV drugs - 26 coumarin derivatives. A multiple linear regression model was built. The estimation stability and generalization ability of the model was strictly analyzed by both internal and external validations. The correlation coefficient （Rcum2） of established model, Leave-One-Out （LOO） Cross-Validation （CV） correlation coefficient （Qcv2）, predicted values versus experimental ones r2（test） of external samples were 0.934, 0.894 and 0.772 respectively. The model had favorable estimation stability and good prediction capabilities. Satisfactory results showed that RASMS could preferably express information related to biological activity of coumarin derivatives. The model had favorable stability and good prediction capability, and RASMS had the prospect to study novel HIV-1 integrase inhibitors.