A novel simple QSAR model for the prediction of anti-HIV activity using multiple linear regression analysis
A novel simple QSAR model for the prediction of anti-HIV activity using multiple linear regression analysis
复制标题
DOI：
10.1007/s11030-005-9012-2
复制
发表时间：
2006-08-01
影响因子：
3.8
通讯作者：
Igglessi-Markopoulou, Olga
中科院分区：
文献类型：
--
作者：
Afantitis, Antreas;Melagraki, Georgia;Igglessi-Markopoulou, Olga
采用多元线性回归分析方法，对80个具有显著抗HIV活性的1-[2-羟乙氧基甲基]-6-苯硫基胸腺嘧啶（HEPT）衍生物进行了定量构效关系研究。为了在37个不同的描述符中选择最佳的描述符，使用了消除选择逐步回归法（ES-SWR）。结果表明，QSAR模型（R-CV（2）= 0.8160; S-PRESS = 0.5680）在训练和预测阶段都非常准确。
A quantitative-structure activity relationship was obtained by applying Multiple Linear Regression Analysis to a series of 80 1-[2-hydroxyethoxy-methyl]-6-(phenylthio) thymine (HEPT) derivatives with significant anti-HIV activity. For the selection of the best among 37 different descriptors, the Elimination Selection Stepwise Regression Method (ES-SWR) was utilized. The resulting QSAR model (R-CV(2) = 0.8160; S-PRESS = 0.5680) proved to be very accurate both in training and predictive stages.