Modeling and quantitative structure-property relationship (QSPR) study to predict the acidic constants of some chemical compounds using multiple linear regression and support vector machine

Subject Areas :

mehdi  nekoei ¹ (Islamic Azad University of shahrood branch)
Abbass  Taheri ² (IAU)
Majid  Mohammadhosseini ³ (IAU)

Received: 2020-12-11 Accepted : 2021-01-26 Published : 2020-02-20

Keywords: multiple linear regression, Quantitative structure-property relationship, acidic constant (pKa), Support vector machine,

Abstract :

Modeling and studying the structure-property quantitative relationship (QSPR) to predict the acidic constants of some chemical compounds were performed using multiple linear regression (MLR) and support vector machine (SVM). First, the structure of chemical compounds was plotted and a suitable group of descriptors was calculated. Then, the step selection method was used to obtain the best descriptors that were most related to the chemical properties of the compounds. Then, linear multiple linear regression (MLR) model and nonlinear vector machine (SVM) model were used to predict the acid constants of the compounds. Statistical data showed that the SVM method was superior to the MLR method.