Application of genetic algorithm - multiple linear regressions to predict the activity of RSK inhibitors
This paper deals with developing a linear quantitative structure-activity relationship (QSAR) model for predicting the RSK inhibition activity of some new compounds. A dataset consisting of 62 pyrazino [1,2-α] indole, diazepino [1,2-α] indole, and imidazole derivatives with known inhibitory...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Serbian Chemical Society
2015-01-01
|
| Series: | Journal of the Serbian Chemical Society |
| Subjects: | |
| Online Access: | http://www.doiserbia.nb.rs/img/doi/0352-5139/2015/0352-51391400064A.pdf |
| Summary: | This paper deals with developing a linear quantitative structure-activity
relationship (QSAR) model for predicting the RSK inhibition activity of some
new compounds. A dataset consisting of 62 pyrazino [1,2-α] indole, diazepino
[1,2-α] indole, and imidazole derivatives with known inhibitory activities
was used. Multiple linear regressions (MLR) technique combined with the
stepwise (SW) and the genetic algorithm (GA) methods as variable selection
tools was employed. For more checking stability, robustness and
predictability of the proposed models, internal and external validation
techniques were used. Comparison of the results obtained, indicate that the
GA-MLR model is superior to the SW-MLR model and that it isapplicable for
designing novel RSK inhibitors. |
|---|---|
| ISSN: | 0352-5139 1820-7421 |