Viktor Drgan

Assessment of applicability domain for multivariate counter-propagation artificial neural network predictive models by minimum Euclidean distance space analysis: A case study☆

Alongside the validation, the concept of applicability domain (AD) is probably one of the most important aspects which determine the quality as well as reliability of the established quantitative structure-activity relationship (QSAR) models. To date, a variety of approaches for AD estimation have been devised which can be applied to particular type of QSAR models and their practical utilization is extensively elaborated in the literature. The present study introduces a novel, simple, and effective distance-based method for estimation of the AD in case of developed and validated predictive counter-propagation artificial neural network (CP ANN) models through a proficient exploitation of the euclidean distance (ED) metric in the structure-representation vector space. The performance of the method was evaluated and explained in a case study by using a pre-built and validated CP ANN model for prediction of the transport activity of the transmembrane protein bilitranslocase for a diverse set of compounds. The method was tested on two more datasets in order to confirm its performance for evaluation of the applicability domain in CP ANN models. The chemical compounds determined as potential outliers, i.e., outside of the CP ANN model AD, were confirmed in a comparative AD assessment by using the leverage approach. Moreover, the method offers a graphical depiction of the AD for fast and simple determination of the extreme points.

Mechanistic interpretation of artificial neural network‐based QSAR model for prediction of cathepsin K inhibition potency

Cathepsin K (Cat K) is a lysosomal cysteine protease that plays an important role in many bone diseases including osteoporosis, which makes Cat K an interesting drug target. Several compounds, including balicatib, were tested in clinical trials for their potency as Cat K inhibitors. Balicatib was found as a potent inhibitor; however, the side effects caused by the lysosomotropic drug candidate behavior as a consequence of its basic nature prevented further drug development. Here, we present a counter‐propagation artificial neural network (CP‐ANN) quantitative structure–activity relationship model of benzamide‐containing aminonitriles with good predictive ability. The quality of all models developed was evaluated internally by leave‐one‐out cross‐validation (LOOCV) on the training set and externally by an independent validation set. The best model performed with the LOOCV and external validation squared correlation coefficient of 0.81 and 0.84, respectively. In order to interpret the selection of variables and consequently discuss the mechanism of inhibition, the layer of the CP‐ANN model representing the distribution of individual molecular descriptors was compared with the output layer representing the response surface. The measures indicating the overlap/similarity of the response surface with selected levels in the input layer were introduced. The results signify not only the importance of the covalent bonding parameters, which are responsible for the S1 binding pocket of the enzyme, but also the impact of 3D shapes of the molecules on the inhibitor–enzyme interactions implying the stabilization of the inhibitors poses within the S2 and S3 binding sites. Copyright

Optimization of gradient profiles in ion-exchange chromatography using computer simulation programs

Optimization procedure of gradient separations in ion-exchange chromatography using simplex optimization method in combination with the computer simulation program for ion-exchange chromatography is presented. The optimization of parameters describing gradient profile for the separation in ion chromatography is based on the optimization criterion obtained from calculated chromatograms. The optimization criterion depends on the parameters used for calculations and thus exhibits the quality of gradient conditions for the separation of the analytes. Simplex method is used to calculate new gradient profiles in order to reach optimum separations for the selected set of analytes. The Simplex algorithm works stepwise, for each new combination of parameters that describe the gradient profile a new calculation is performed and from the calculated chromatogram the optimization criterion is determined. The proposed method is efficient and may reduce the time and cost of analyses of complex samples with ion-exchange chromatography.

Computational method for modeling of gradient separation in ion-exchange chromatography

A model for the simulation of the gradient separation in ion-exchange chromatography is presented. It is based on discontinuous plate model and simulates the distribution of analytes in the ion-exchange column during the separation process. It enables calculations of chromatograms for the analytes with integer and non-integer effective charges under complex gradient profiles. Equilibrium concentrations of all analytes are calculated using the same mathematical equations and expressions regardless of the effective charge on the analyte. The main parameters required for the simulations have to be determined under isocratic elution. The suitability of the model was tested with different types of gradients. A comparison of retention times and chromatograms shows that reliable predictions for all tested gradients are achieved. The observed average of the absolute values of the relative errors of the retention times obtained for any analyte in the present study from the calculated chromatograms is below 4%, while the average error considering all analytes in the study is below 2%.

Quantitative structure-activation barrier relationship modeling for Diels-Alder ligations utilizing quantum chemical structural descriptors

BackgroundIn the present study, we show the correlation of quantum chemical structural descriptors with the activation barriers of the Diels-Alder ligations. A set of 72 non-catalysed Diels-Alder reactions were subjected to quantitative structure-activation barrier relationship (QSABR) under the framework of theoretical quantum chemical descriptors calculated solely from the structures of diene and dienophile reactants. Experimental activation barrier data were obtained from literature. Descriptors were computed using Hartree-Fock theory using 6-31G(d) basis set as implemented in Gaussian 09 software.ResultsVariable selection and model development were carried out by stepwise multiple linear regression methodology. Predictive performance of the quantitative structure-activation barrier relationship (QSABR) model was assessed by training and test set concept and by calculating leave-one-out cross-validated Q2 and predictive R2 values. The QSABR model can explain and predict 86.5% and 80% of the variances, respectively, in the activation energy barrier training data. Alternatively, a neural network model based on back propagation of errors was developed to assess the nonlinearity of the sought correlations between theoretical descriptors and experimental reaction barriers.ConclusionsA reasonable predictability for the activation barrier of the test set reactions was obtained, which enabled an exploration and interpretation of the significant variables responsible for Diels-Alder interaction between dienes and dienophiles. Thus, studies in the direction of QSABR modelling that provide efficient and fast prediction of activation barriers of the Diels-Alder reactions turn out to be a meaningful alternative to transition state theory based computation.

CPANNatNIC software for counter-propagation neural network to assist in read-across

BackgroundCPANNatNIC is software for development of counter-propagation artificial neural network models. Besides the interface for training of a new neural network it also provides an interface for visualisation of the results which was developed to aid in interpretation of the results and to use the program as a tool for read-across.ResultsThe work presents the details of the program’s interface. Parts of the interface are presented and how they can be used. The examples provided show how the user can build a new model and view the results of predictions using the interface. Examples are given to show how the software may be used in read-across.ConclusionsCPANNatNIC provides a simple user interface for model development and visualisation. The interface implements options which may simplify read-across procedure. Statistical results show better prediction accuracy of read-across predictions than model predictions where similar compounds could be identified, which indicates the importance of using read-across and usefulness of the program.

Hard modeling of ion chromatography separations on hydroxide-selective stationary phase.

In the present paper the development and testing of the computer software for the simulation of the on-column ion chromatography separation processes are presented. The computer algorithm based exclusively on the selectivity coefficients of the tested analytes has been upgraded to cope with the 2:1 and 1:1 ratios of the analyte-to-eluent ion charge. The analytical solution of the cubic equation, which is needed for calculation of chromatograms for doubly charged analytes in the presence of singly charged eluent, is presented. The developed modeling approach was tested on the data sets produced by the system composed of hydroxide-selective stationary phase in combination with on-line electrolytically generated OH(-)-based eluents. Retention behavior of the selected anions on the AS15 (DIONEX, USA) stationary phase was investigated. The study of the dependence of the peak widths on the number of theoretical column segments considered in the calculated chromatograms enabled us to choose the optimal number of column segments. The average error in the retention time of the calculated chromatograms for the data set used in the study, i.e. seven different ions at eight different eluent concentrations was found to be 1.4%. A good match with the experimental chromatograms allows us to use the information of the intermediate states of calculations to get a detailed insight into the time-dependent on-column analyte distribution.