Using QSAR calculation of amid derivatives for the treatment of Parkinson’s disease

Parkinson's disease is one of the most common neurological disease is considered malicious. Parkinson's disease is a chronic condition and always in progress. The goal of treatment for patients with symptoms but not eliminate the symptoms under control [1]. On the pattern, quantitative structure–activity relationship (QSAR) study has been done on a series of Amid derivatives for the treatment of Parkinson’s disease [2]. Multiple linear regression (MLR), partial least squares (PLS) and principal component regression (PCR) were used to create QSAR models. For this purpose, ab initio geometry optimization performed at B3LYP level with a known basis set (6–31G). Hyperchem, ChemOffice and Gaussian 33W softwares were used for geometry optimization of the molecules and calculation of the quantum chemical descriptors. Finally, Unscrambler program was used for analysis of data. In the present study, the root mean square error of the calibration and R2 using MLR method, were obtained 390.0 and 39036 According to the obtained results, we found that MLR model is the most favorable method toward the other statistical methods and is suitable for being used in QSAR models. The 3D structures of the molecules were generated using the built optimum option of Hyperchem software (version 093). Geometry optimization of compounds was carried out by B3LYP method employing 6-31G(d) basis set. All calculations were performed using Gaussian 3. program. Using Dragon (version 595) were employed to calculate the molecular descriptors, using MATAB for GA, ANN, MLR. In the work stepwise multiple linear regression (stepwise-MLR) and GA variable subset selection methods were used for the selection of the most relevant descriptors from all of discriptors. These descriptors would be used as inputs of the ANN. So, it was necessary to reduce the number of descriptors in three steps.The root-mean-square errors of the training set and the test set for GA-ANN model using Jack-knife were 393357, 391735, R2 = 390.37, the training and test set for GA-ANN cross validation were 39231. , 3912.7.

کلیدواژه ها:

Parkinson’s disease ، Quantitative structure activity relationship ، Amid derivatives ، Multiple linear regression