Predicting biological activity of chalcone (1,3-dip henyl-2-propen-1-one) derivatives cytotoxicity against HT-29 human colon adenocarcinoma cell linesby by DFT-QSAR models
Majdouline Larif, Samir Chtita, Azeddine Adad, Rachid Hmamouchi, Mohammed Bouachrıne, Tahar Lakhlifi · Journal of computational methods in molecular design · 2014
Chalcones are 1,3-diphenyl-2-propene-1-one, in whic h two aromatic rings are linked by a three carbon α,βunsaturated carbonyl system. These are abundant in edible plants and are considered to be precursors o f flavonoids and isoflavonoids. Our objective is to study the re lationship between the activities and structure, a 3D-QSAR study is applied to a set of 20 molecules for biological activity prediction derivatives. This study was con ducted using the principal component analysis PCA method; the multip le linear regression method MLR and the artificial neural network ANN;The leave-one out cross-validation proc edure was used to validate the ANN model for use it to predict the activity of others new compounds. The relevant descriptors obtained from the ANN showed a correlat ion coefficient of 0.949 models which is a good result. As a result of quantitative structure‐activity relationships, we found that the model proposed in this study is cons tituted of major descriptors used to describe these molecules. The obtained results suggested that the proposed combin ation of several calculated parameters could be use ful to predict the biological activity of derivatives of 1,3-diphenyl-2-propene-1-one.