Camputational methods and quantitative structure–property relationship study for prediction of melting point of carbocyclic nitroaromatic compounds using chemical and quantum mechanics descriptors: combining DFT and QSPR calculations

Subject Areas :

mehdi nekoei ¹ , mehdi maham ²

1 - Islamic Azad University of shahrood branch
2 - Islamic Azad university of Aliabad Katool

Received: 2017-02-26 Accepted : 2017-07-17 Published : 2016-11-21

Keywords: MLR, melting point, quantitative structure–property relationship, Quantum mechanics descriptors, SVM,

Abstract :

The DFT-B3LYP method, with the base set 6-31G (d), was used to calculate several quantum chemical descriptors of 60 compounds of carbocyclic nitroaromatics. A suitable set of quantum mechanics and chemical descriptors was calculated and quantitative structure–property relationship method for prediction of melting point of carbocyclic nitroaromatic compounds by multiple linear regression (MLR) and support vector machine (SVM) were studied. At first, structure of the compounds were plotted and of quantum mechanics descriptors was calculated and the stepwise method was employed to select those descriptors that resulted in the best fitted models. At first, we developed linear model of MLR. Then the selected molecular descriptors were used as inputs for SVM. The obtained results using SVM were compared with MLR which revealed superiority of the SVM model over the MLR method.