作者: Eslam Pourbasheer , Siavash Riahi , Mohammad Reza Ganjali , Parviz Norouzi
DOI: 10.1007/S11030-010-9283-0
关键词:
摘要: Multiple linear regressions (MLR) and support vector machine (SVM) were used to develop quantitative structure–activity relationship (QSAR) models of novel Hepatitis C virus (HCV) NS5B polymerase inhibitors. Various kinds molecular descriptors calculated represent the structures compounds, such as chemical, topological, geometrical, quantum descriptors. Principal component analysis (PCA) was select training set. A variable selection method utilizing a genetic algorithm (GA) employed from large pool descriptors, an optimal subset which have significant contribution overall inhibitory activity. The validated using Leave-One-Out (LOO) Leave-Group-Out (LGO) crossvalidation, Y-randomization test. Results demonstrated SVM model offers powerful prediction capabilities.