Application of genetic algorithm - multiple linear regressions to predict the activity of RSK inhibitors

Abstract

This paper considers the development of a linear quantitative structure-activity relationship (QSAR) model for predicting the ribosomal S6 kinase (RSK) inhibition activity of some new compounds. A dataset consisting of 59 pyrazino[1,2-α]indole, diazepino[1,2-α]indole, and imidazole derivatives with known inhibitory activities was used. The multiple linear regressions (MLR) technique combined with stepwise (SW) and the genetic algorithm (GA) methods as variable selection tools was employed. For more checking of the stability, robustness and predictability of the proposed models, internal and external validation techniques were used. Comparison of the obtained results, indicate that the GA-MLR model is superior to the SW-MLR model and that it is applicable for designing novel RSK inhibitors.

Ontological model of multi-agent Smart-system for predicting drug properties based on modified algorithms of artificial immune systems

“…The results showed a good prognostic ability of the model and the ability to use it for the creation of a similar group of antimalarial compounds. The article [ 8 ] discusses the development of a linear quantitative model of the structure-activity ratio in order to predict the activity of inhibiting the ribosomal S6 kinase (RSK) of some new compounds. Multiple linear regression (MLR) was used as a tool for selecting variables in combination with GA.…”