Applied Chemistry Today2981-243762120111222Application of genetic algorithm with multiple linear regressions for prediction of medicinal activity pyrazole derivativesApplication of genetic algorithm with multiple linear regressions for prediction of medicinal activity pyrazole derivatives354459210.22075/chem.2017.592FAMehdi NekoeMajid MohammadhosseiniPourbasheerMahamJournal Article20170115Quantitative structure-activity relationship (QSAR) study for prediction of medicinal activity of pyrazole derivatives is developed using structural descriptors and multiple linear regression (MLR) method. Molecular descriptors are selected by genetic algorithm. Then a simple, strong, descriptive and interpretable model with low error and high correlation coefficient is construct. The results illustrated that the linear techniques such as MLR combined with a successful variable selection procedure are capable to generate an efficient QSAR model for predicting the activity of different compounds. This model was used for the prediction of activity values of some medicinal compounds which were not used in the modeling procedure.Quantitative structure-activity relationship (QSAR) study for prediction of medicinal activity of pyrazole derivatives is developed using structural descriptors and multiple linear regression (MLR) method. Molecular descriptors are selected by genetic algorithm. Then a simple, strong, descriptive and interpretable model with low error and high correlation coefficient is construct. The results illustrated that the linear techniques such as MLR combined with a successful variable selection procedure are capable to generate an efficient QSAR model for predicting the activity of different compounds. This model was used for the prediction of activity values of some medicinal compounds which were not used in the modeling procedure.https://chemistry.semnan.ac.ir/article_592_bf5625db39754698d4361adc592ff5ff.pdf