کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
1179436 | 1491529 | 2016 | 6 صفحه PDF | دانلود رایگان |
• The QSAR model of the pyrazolo[1,5-a]pyrimidine derivative inhibitors of Chk1 is constructed by PSO-SVM.
• The stepwise multiple linear regression method is used to select the descriptors.
• A stable model can be constructed by JG14, G3s, R8u+ and RDF085e.
• The PSO-SVM has higher stability and better prediction performance.
Checkpoint kinase 1 (Chk1) is a serine/threonine kinase that plays a key role in the response to DNA-mediated cell injury. In this paper, the quantitative structure–activity relationship (QSAR) models were constructed to predict the activity of pyrazolo[1,5-a]pyrimidine derivatives of Checkpoint kinase 1 (Chk1) by using SVM and PSO-SVM methods. The root-mean-square errors (RMSE) of the training set and the test set for the PSO-SVM model were 0.0886 and 0.1803, respectively. For the SVM model, the values were 0.2185 and 0.4023, respectively. The results showed that the performance of the PSO-SVM model was better than the corresponding SVM model. Thus, it can be inferred that the PSO-SVM analysis will be a promising method and be spread to apply in the QSAR studies.
Journal: Chemometrics and Intelligent Laboratory Systems - Volume 150, 15 January 2016, Pages 23–28