Free variable selection QSPR study to predict 19F chemical shifts of some fluorinated organic compounds using Random Forest and RBF-PLS methods

•We developed QSPR model based on RF to predict the 19F chemical shift values of some fluorinated organic compounds.•The number of trees (nt) and the number of randomly selected variables to split each node (m) affect the RF prediction power.•RF model is not required to make a variable selection in advance, and does not suffer from the overfitting problem.•The performances of the RF model were superior to the RBF-PLS.•To the best of our knowledge, there have been no reports yet on the use of RF method to predict the chemical shift.

In this work, two new and powerful chemometrics methods are applied for the modeling and prediction of the 19F chemical shift values of some fluorinated organic compounds. The radial basis function-partial least square (RBF-PLS) and random forest (RF) are employed to construct the models to predict the 19F chemical shifts. In this study, we didn't used from any variable selection method and RF method can be used as variable selection and modeling technique. Effects of the important parameters affecting the ability of the RF prediction power such as the number of trees (nt) and the number of randomly selected variables to split each node (m) were investigated. The root-mean-square errors of prediction (RMSEP) for the training set and the prediction set for the RBF-PLS and RF models were 44.70, 23.86, 29.77, and 23.69, respectively. Also, the correlation coefficients of the prediction set for the RBF-PLS and RF models were 0.8684 and 0.9313, respectively. The results obtained reveal that the RF model can be used as a powerful chemometrics tool for the quantitative structure–property relationship (QSPR) studies.

Graphical abstractThe RMSE counter plot of OOB data for two parameters of ntree and m.Figure optionsDownload full-size imageDownload as PowerPoint slide