Quantitative Structure-Property Relationship Study for Prediction of the Solvent Polarity Using Quantum Mechanics Descriptors and Support Vector Machine
Subject Areas :
mehdi
nekoei
1
(Islamic Azad University of shahrood branch)
بهزاد
چهکندی
2
(IAU)
Keywords: Support vector machine (SVM), Quantitative structure- property relationship (QSPR), Quantum mechanics descriptors, Solvent polarity,
Abstract :
Quantitative structure-property relationship (QSPR) study for prediction of the polarity some of solvents using quantum mechanics descriptors and support vector machine. Experimental S′ values for 69 solvents were assembled. This set included saturated and unsaturated hydrocarbons, solvents containing halogen, cyano, nitro, amide, sulfide, mercapto, sulfone, phosphate, ester, ether, etc. After drawing the structure of the molecules, the suitable molecular descriptors were calculated. Then, the stepwise multiple linear regressions (SW-MLR) variable selection method was subsequently employed to select and implement the prominent descriptors having the most significant contributions to the polarity of the molecules. At first, multiple linear regressions (MLR) model was constructed. Then, support vector machine (SVM) model was used for to obtain better results. A comparison of results by the two methodologies indicated the superiority of SW-SVM over the SW-MLR method.
_||_
