The prediction for gas chromatographic retention index of disulfides on stationary phases of different polarity

Quantitative structure–retention relationship (QSRR) models for the gas chromatographic (GC) Kaváts indices of disulfides on four different polarity stationary phase have been developed. Semi-empirical quantum chemical method (AM1) implemented in hyperchem 4.0 was employed to calculate a set of molecular descriptors of 50 disulfides. The four stationary phases in the research were: Apiezon M, OV-17, Triton X-305 and PEG-1000. By using multiple linear regression (MLR), we obtained four empirical functions with high correlation coefficient (R1=0.995, R2=0.994, R3=0.990, R4=0.976). At the same time, using Thin Plat Spline the Radial Basis Function neural networks models were obtained with root mean squared error (RMS) of training set (RMST1=0.013351, RMST2=0.012973, RMST3=0.023228, RMST4=0.020755) and RMS of validation set (RMSV1=0.007626, RMSV2=0.005897, RMSV3=0.005109, RMSV4=0.007377) and RMS of testing set (RMSX1=0.016676, RMSX2=0.016704, RMSX3=0.017162, RMSX4=0.014755). The results indicated that the QSRR models proposed were very satisfactory.