Prediction of gas-to-ionic liquid partition coefficient of organic solutes dissolved in 1-(2-methoxyethyl)-1-methylpyrrolidinium tris(pentafluoroethyl)trifluorophosphate using QSPR approaches

The present work represents a quantitative structure-property relationship (QSPR) study for predicting the gas-to-ionic liquid partition coefficients (log K) of organic solutes dissolved in 1-(2-methoxyethyl)-1-methylpyrrolidinium tris(pentafluoroethyl)trifluorophosphate based on replacement method (RM) and support vector machine (SVM). The variable selection technique of replacement method (RM) was employed to select the most favorable subset of descriptors from the more than 1000 theoretical descriptors calculated using the Dragon package. The six descriptors selected were used as inputs of SVM to predict the gas-to-ionic liquid partition coefficient of a set of 92 aliphatic and aromatic solutes dissolved in 1-(2-methoxyethyl)-1-methylpyrrolidinium tris(pentafluoroethyl)trifluorophosphate. Results of our computations demonstrate that SVM can be used as a substitute powerful modeling tool for QSPR studies. The log K values calculated by SVM were in good agreement with the experimental data, and the performances of the SVM models were superior to RM one.