ABSTRACT
The linear solvent strength model was used to predict coverage in online comprehensive two-dimensional reversed-phase liquid chromatography. The prediction model uses a parallelogram to describe the separation space covered with peaks in a system with limited orthogonality. The corners of the parallelogram are assumed to behave like chromatographic peaks and the position of these pseudo-compounds was predicted. A mix of 25 polycyclic aromatic compounds were used as a test. The precision of the prediction, span 0-25, was tested by varying input parameters, and was found to be acceptable with root mean square errors of 3. The accuracy of the prediction was assessed by comparing with the experimental coverages. Less than half of experimental coverages were outside prediction ± 1 × root mean square error and none outside prediction ± 2 × root mean square error. Accuracy was lower when retention factors were low, or when gradient conditions affected parameters not included in the model, e.g. second dimension gradient time affects the second dimension equilibration time. The concept shows promise as a tool for gradient optimization in online comprehensive two-dimensional liquid chromatography, as it mitigates the tedious registration and modeling of all sample constituents, a circumstance that is particularly appealing when dealing with complex samples.
ABSTRACT
A method for choosing orthogonal columns for a specific sample set in on-line comprehensive two-dimensional liquid chromatography (LC×LC) was developed on the basis of the hydrophobic subtraction model. The method takes into account the properties of the sample analytes by estimating new F-weights for the prediction of orthogonality. We compared sets of F-weights and used these F-weights to predict orthogonal column combinations: (1) the standard F-weights determined by Gilroy et al. [1], (2) F-weights determined from the retention of sample analytes, and the same procedure of calculation as described by Gilroy et al. [1], (3) F-weights determined from the retention of sample analytes but using principal component analysis (PCA) for the estimation, and (4) the Gilroy F-weights modified by excluding the C-term in the hydrophobic subtraction model, as suggested by Dolan and Snyder [2]. The retention of 13 neutral and 4 acidic oxygenated polycyclic aromatic compounds (PACs) and 3 nitrogen-containing PAC bases was measured isocratically on 12 columns. The isocratic runs were used to determine the hydrophobic subtraction model analyte parameters, and these were used to estimate new F-weights and predict orthogonal column combinations. LC×LC-DAD analysis was then performed on a test mix using these column sets. We found that the column combination predicted from the new F-weights provide a more orthogonal separation of the PACs than those predicted using the standard F-weights and the F-weights modified by excluding the C-term. This emphasizes the necessity of considering the nature of the sample when choosing orthogonal columns.
