Premium
A Novel QSPR Model for Prediction of Gas to Dimethyl Sulfoxide Solvation Enthalpy of Organic Compounds Based on Support Vector Machine
Author(s) -
Golmohammadi Hassan,
Dashtbozorgi Zahra,
Acree William E.
Publication year - 2012
Publication title -
molecular informatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.481
H-Index - 68
eISSN - 1868-1751
pISSN - 1868-1743
DOI - 10.1002/minf.201200007
Subject(s) - solvation , quantitative structure–activity relationship , chemistry , enthalpy , molecular descriptor , support vector machine , linear regression , thermodynamics , dimethyl sulfoxide , artificial neural network , computational chemistry , molecule , artificial intelligence , machine learning , organic chemistry , stereochemistry , computer science , physics
In this study, a quantitative structureproperty relationship (QSPR) study is developed for the prediction of gas to dimethyl sulfoxide solvation enthalpy (Δ H Solv ) of organic compounds based on molecular descriptors calculated solely from molecular structure considerations. Diverse types of molecular descriptors were calculated to represent the molecular structures of the various compounds studied. Multiple linear regression (MLR) was employed to select an optimal subset of descriptors that have significant contributions to the Δ H Solv overall property. Our investigation revealed that the dependence of physicochemical properties on solvation enthalpy is a nonlinear observable fact and that MLR method is unable to model the solvation enthalpy accurately. It has been observed that support vector machine (SVM) and artificial neural network (ANN) demonstrates better performance compared with MLR. The standard error value of the test set for SVM is 1.731 kJ mol −1 , while it is 2.303 kJ mol −1 and 5.146 kJ mol −1 for ANN and MLR, respectively. The results showed that the calculated Δ H Solv values by SVM were in good agreement with the experimental data, and the performance of the SVM model was superior to those of MLR and ANN ones.