Quantitative structure-activity relationship study and molecular docking of pyrazoline derivatives inhibitors on cyclooxygenase-2 using Chemoinformatic methods

In the present study, quantitative structure-activity relationship study of inhibition characteristic of pyrazoline derivatives as inflammatory cyclooxygenase-2 inhibitors were performed using different chemoinformatics methods. Selective inhibition of cyclooxygenase-2 is an important strategy in designing of potent anti-inflammatory compounds with significantly reduced side effects. Classification and regression tree and stepwise multiple linear regression were used to select the most important molecular descriptors. The final model was developed using adaptive neuro-fuzzy inference system and artificial neural network with selected molecular descriptors. Results of different validation techniques of leave one out, leave multiple out and prediction set show the validation of acquired model. In the next step, molecular docking studies was performed to obtain receptor-ligand binding pattern. Results of molecular docking revealed that the amino acids of Arg44, Glu46, Glu465 and Cys41 have important role in receptor-ligand interaction. In the present study, interpretable quantitative structure-activity relationship and molecular docking techniques were used to predict inhibitory concentration of pyrazoline derivatives. The present results can be used to predict inhibitory concentration of cyclooxygenase-2 inhibitors in drug design with consuming lower cost and time.