Gibbs energy of solution and molecular structural coefficients of 85 solutes on 20 gas chromatographic stationary phases

Selectivity assessment of DB-200 and DB-VRX open-tubular capillary columns

The solvation parameter model is used to study the influence of composition and temperature on the selectivity of two poly(siloxane) stationary phases used for open-tubular capillary column gas chromatography. The poly(methyltrifluoropropyldimethylsiloxane) stationary phase, DB-200, has low cohesion, intermediate dipolarity/polarizability, low hydrogen-bond basicity, no hydrogen-bond acidity, and repulsive electron lone pair interactions. The DB-VRX stationary phase has low cohesion, low dipolarity/polarizability, low hydrogen-bond basicity and no hydrogen-bond acidity and no capacity for electron lone pair interactions. The selectivity of the two stationary phases is complementary to those in a database of 11 stationary phase chemistries determined under the same experimental conditions.

Development of comprehensive descriptors for multiple linear regression and artificial neural network modeling of retention behaviors of a variety of compounds on different stationary phases

A new series of six comprehensive descriptors that represent different features of the gas-liquid partition coefficient, K(L), for commonly used stationary phases is developed. These descriptors can be considered as counterparts of the parameters in the Abraham solvatochromic model of solution. A separate multiple linear regression (MLR) model was developed by using the six descriptors for each stationary phase of poly(ethylene glycol adipate) (EGAD), N,N,N',N'-tetrakis(2-hydroxypropyl) ethylenediamine (THPED), poly(ethylene glycol) (Ucon 50 HB 660) (U50HB), di(2-ethylhexyl)phosphoric acid (DEHPA) and tetra-n-butylammonium N,N-(bis-2-hydroxylethyl)-2-aminoethanesulfonate (QBES). The results obtained using these models are in good agreement with the experiment and with the results of the empirical model based on the solvatochromic theory. A 6-6-5 neural network was developed using the descriptors appearing in the MLR models as inputs. Comparison of the mean square errors (MSEs) shows the superiority of the artificial neural network (ANN) over that of the MLR. This indicates that the retention behavior of the molecules on different columns show some nonlinear characteristics. The experimental solvatochromic parameters proposed by Abraham can be replaced by the calculated descriptors in this work.