Multiple linear regression and artificial neural network retention prediction models for ginsenosides on a polyamine-bonded stationary phase in hydrophilic interaction chromatography

Optimizing artificial neural network models for metabolomics and systems biology: an example using HPLC retention index data

BACKGROUND

Artificial Neural Networks (ANN) are extensively used to model 'omics' data. Different modeling methodologies and combinations of adjustable parameters influence model performance and complicate model optimization.

METHODOLOGY

We evaluated optimization of four ANN modeling parameters (learning rate annealing, stopping criteria, data split method, network architecture) using retention index (RI) data for 390 compounds. Models were assessed by independent validation (I-Val) using newly measured RI values for 1492 compounds.

CONCLUSION

The best model demonstrated an I-Val standard error of 55 RI units and was built using a Ward's clustering data split and a minimally nonlinear network architecture. Use of validation statistics for stopping and final model selection resulted in better independent validation performance than the use of test set statistics.

A novel fullerene oxide functionalized silica composite as stationary phase for high performance liquid chromatography

An FO/SiO₂ composite was successfully synthesized and revealed good separation for four kinds of hydrophilic compounds in HILIC.

Recent methodology in ginseng analysis

As much as the popularity of ginseng in herbal prescriptions or remedies, ginseng has become the focus of research in many scientific fields. Analytical methodologies for ginseng, referred to as ginseng analysis hereafter, have been developed for bioactive component discovery, phytochemical profiling, quality control, and pharmacokinetic studies. This review summarizes the most recent advances in ginseng analysis in the past half-decade including emerging techniques and analytical trends. Ginseng analysis includes all of the leading analytical tools and serves as a representative model for the analytical research of herbal medicines.

Comprehensive two-dimensional liquid chromatography — practical impacts of theoretical considerations. A review

A theory of comprehensive two-dimensional separations by liquid chromatographic techniques is overviewed. It includes heart-cutting and comprehensive two-dimensional separation modes, with attention to basic concepts of two-dimensional separations: resolution, peak capacity, efficiency, orthogonality and selectivity. Particular attention is paid to the effects of sample structure on the retention and advantages of a multi-dimensional HPLC for separation of complex samples according to structural correlations. Optimization of 2D separation systems, including correct selection of columns, flow-rate, fraction volumes and mobile phase, is discussed. Benefits of simultaneous programmed elution in both dimensions of LCxLC comprehensive separations are shown.

Experimental setup, modulation of the fraction collection and transfer from the first to the second dimension, compatibility of mobile phases in comprehensive LCxLC, 2D asymmetry and shifts in retention under changing second-dimension elution conditions, are addressed. Illustrative practical examples of comprehensive LCxLC separations are shown.

Development of Ecom₅₀ and retention index models for nontargeted metabolomics: identification of 1,3-dicyclohexylurea in human serum by HPLC/mass spectrometry

The goal of many metabolomic studies is to identify the molecular structure of endogenous molecules that are differentially expressed among sampled or treatment groups. The identified compounds can then be used to gain an understanding of disease mechanisms. Unfortunately, despite recent advances in a variety of analytical techniques, small molecule (<1000 Da) identification remains difficult. Rarely can a chemical structure be determined from experimental "features" such as retention time, exact mass, and collision induced dissociation spectra. Thus, without knowing structure, biological significance remains obscure. In this study, we explore an identification method in which the measured exact mass of an unknown is used to query available chemical databases to compile a list of candidate compounds. Predictions are made for the candidates using models of experimental features that have been measured for the unknown. The predicted values are used to filter the candidate list by eliminating compounds with predicted values substantially different from the unknown. The intent is to reduce the list of candidates to a reasonable number that can be obtained and measured for confirmation. To facilitate this exploration, we measured data and created models for two experimental features; MS Ecom₅₀ (the energy in electronvolts required to fragment 50% of a selected precursor ion) and HPLC retention index. Using a data set of 52 compounds, Ecom₅₀ models were developed based on both Molconn and CODESSA structural descriptors. These models gave r² values of 0.89 to 0.94 depending on the number of inputs, the modeling algorithm chosen, and whether neutral or protonated structures were used. The retention index model was developed with 400 compounds using a back-propagation artificial neural network and 33 Molconn structure descriptors. External validation gave a v² = 0.87 and standard error of 38 retention index units. As a test of the validity of the filtering approach, the Ecom₅₀ and retention index models, along with exact mass and collision induced dissociation spectra matching, were used to identify 1,3-dicyclohexylurea in human plasma. This compound was not previously known to exist in human biofluids and its elemental formula was identical to 315 other candidate compounds downloaded from PubChem. These results suggest that the use of Ecom₅₀ and retention index predictive models can improve nontargeted metabolite structure identification using HPLC/MS derived structural features.

Isolation and analysis of ginseng: advances and challenges

Ginseng occupies a prominent position in the list of best-selling natural products in the world. Because of its complex constituents, multidisciplinary techniques are needed to validate the analytical methods that support ginseng's use worldwide. In the past decade, rapid development of technology has advanced many aspects of ginseng research. The aim of this review is to illustrate the recent advances in the isolation and analysis of ginseng, and to highlight new applications and challenges. Emphasis is placed on recent trends and emerging techniques.

Stationary and mobile phases in hydrophilic interaction chromatography: a review

Hydrophilic interaction chromatography (HILIC) is valuable alternative to reversed-phase liquid chromatography separations of polar, weakly acidic or basic samples. In principle, this separation mode can be characterized as normal-phase chromatography on polar columns in aqueous-organic mobile phases rich in organic solvents (usually acetonitrile). Highly organic HILIC mobile phases usually enhance ionization in the electrospray ion source of a mass spectrometer, in comparison to mobile phases with higher concentrations of water generally used in reversed-phase (RP) LC separations of polar or ionic compounds, which is another reason for increasing popularity of this technique. Various columns can be used in the HILIC mode for separations of peptides, proteins, oligosaccharides, drugs, metabolites and various natural compounds: bare silica gel, silica-based amino-, amido-, cyano-, carbamate-, diol-, polyol-, zwitterionic sulfobetaine, or poly(2-sulphoethyl aspartamide) and other polar stationary phases chemically bonded on silica gel support, but also ion exchangers or zwitterionic materials showing combined HILIC-ion interaction retention mechanism. Some stationary phases are designed to enhance the mixed-mode retention character. Many polar columns show some contributions of reversed phase (hydrophobic) separation mechanism, depending on the composition of the mobile phase, which can be tuned to suit specific separation problems. Because the separation selectivity in the HILIC mode is complementary to that in reversed-phase and other modes, combinations of the HILIC, RP and other systems are attractive for two-dimensional applications. This review deals with recent advances in the development of HILIC phase separation systems with special attention to the properties of stationary phases. The effects of the mobile phase, of sample structure and of temperature on separation are addressed, too.

Prediction of HPLC retention index using artificial neural networks and IGroup E-state indices

A back-propagation artificial neural network (ANN) was used to create a 10-fold leave-10%-out cross-validated ensemble model of high performance liquid chromatography retention index (HPLC-RI) for a data set of 498 diverse druglike compounds. A 10-fold multiple linear regression (MLR) ensemble model of the same data was developed for comparison. Molecular structure was described using IGroup E-state indices, a novel set of structure-information representation (SIR) descriptors, along with molecular connectivity chi and kappa indices and other SIR descriptors previously reported. The same input descriptors were used to develop models by both learning algorithms. The MLR model yielded marginally acceptable statistics with training correlation r(2) = 0.65, mean absolute error (MAE) = 83 RI units. External validation of 104 compounds not used for model development yielded validation v(2) = 0.49 and MAE = 73 RI units. The distribution of residuals for the fit and validate data sets suggest a nonlinear relationship between retention index and molecular structure as described by the SIR indices. Not surprisingly, the ANN model was significantly more accurate for both training and validation with training set r(2) = 0.93, MAE = 30 RI units and validation v(2) = 0.84, MAE = 41 RI units. For the ANN model, a total of 91% of validation predictions were within 100 RI units of the experimental value.