Synergism between constituents of multicomponent catalysts designed for ethanol steam reforming using partial least squares regression and artificial neural networks

Effects of different catalyst components on the catalytic performance in steam reforming of ethanol have been investigated by means of Artificial Neural Networks (ANNs) and Partial Least Square regression (PLSR). The data base consisted of ca. 400 items (catalysts with varied composition), which were obtained from a former catalyst optimization procedure. Marten's uncertainty (jackknife) test showed that simultaneous addition of Ni and Co has crucial effect on the hydrogen production. The catalyst containing both Ni and Co provided remarkable hydrogen production at 450°C. The addition of Ceas modifier to the bimetallic NiCo catalyst has high importance at lower temperatures: the hydrogen concentration is doubled at 350°C. Addition of Pt had only little effect on the product distribution. The outliers in the data set have been investigated by means of Hotelling T2 control chart. Compositions containing high amount of Cu or Ce have been identified as outliers, which points to the nonlinear effect of Cu and Ce on the catalytic performance. ANNs were used for analysis of the non-linear effects: an optimum was found with increasing amount of Cu and Ce in the catalyst composition. Hydrogen production can be improved by Ce only in the absence of Zn. Additionally, negative cross-effect was evidenced between Ni and Cu. The above relationships have been visualized in Holographic Maps, too. Although predictive ability of PLSR is somewhat worse than that of ANN, PLSR provided indirect evidence that ANNs were trained adequately.     

Optimization of Artificial Neural Networks for Modeling of Atorvastatin and Its Impurities Retention in Micellar Liquid Chromatography

Artificial Neural Networks (ANNs) present a powerful tool for the modeling of chromatographic retention. In this paper, the main objective was to use ANNs as a tool in modeling of atorvastatin and its impurities?? retention in a micellar liquid chromatography (MLC) protocol. Factors referred to MLC were evaluated through 30 experiments defined by the Central Composite Design. In this manner, 5?Cx?C3 topology as a starting point for ANNs?? optimization was defined too. In the next step, in order to set the network with the best performance, network optimization was done. In the first part, the number of nodes in the hidden layer and the number of experimental data points in training set were simultaneously varied, and their importance was estimated with suitable statistical parameters. Furthermore, a series of training algorithms was applied to the current network. The Back Propagation, Conjugate Gradient-descent, Quick Propagation, Quasi-Newton, and Delta-bar-Delta algorithms were used to obtain the optimal network. Finally, the predictive ability of the optimized neural network was confirmed through several statistical tests. The obtained network showed high ability to predict chromatographic retention of atorvastatin and its impurities in MLC.     

Prediction of the antimicrobial activity of quaternary ammonium salts against Staphylococcus aureus using artificial neural networks

The study of the quantitative structure–activity relationship (QSAR) on antibacterial activity in a series of new imidazole derivatives against Staphylococcus aureus was conducted using artificial neural networks (ANNs). Antibacterial activity against S. aureus was associated with a number of physicochemical and structural parameters of the examined imidazole derivatives. The designed regression and classification models were useful in determining the antibacterial properties of quaternary ammonium salts against S. aureus. The developed models of artificial neural networks were characterized by high predictability (93.57% accuracy of classification, regression model: training data R = 0.92, test data R = 0.92, validation data R = 0.91). ANNs are considered to be a useful tool in supporting the design of synthesis and further biological experiments in the logical search for new antimicrobial substances. Data analysis using ANNs enables the optimization and reduction of labor costs by narrowing the compound synthesis to achieve the desired properties.     

Flow injection analysis of fluoride: optimization of experimental conditions and non-linear calibration using artificial neural networks

This paper deals with the application of artificial neural networks (ANNs) to two common problems in spectroscopy: optimization of experimental conditions and non-linear calibration of the result, with particular reference to the determination of fluoride by flow injection analysis (FIA). The FIA system was based on the formation of a blue ternary complex between zirconium(IV), p-methyldibromoarsenazo and F- with the maximum absorption wavelength at 635 nm. First, optimization in terms of sensitivity and sampling rate was carried out by using jointly a central composite design and ANNs, and a neural network with a 3-7-1 structure was confirmed to be able to provide the maximum performance. Second, the relationship between the concentration of fluoride and its absorbance was modeled by ANNs. In this process, cross-validation and leave-k-out were used. The results showed that good prediction was attained in the 1-4-1 neural net. The trained networks proved to be very powerful in both applications. The proposed method was successfully applied to the determination of free fluoride in tea and toothpaste with recoveries between 96 and 101%.     

Improved CoMFA modeling by optimization of settings

The possibility of improving the predictive ability of comparative molecular field analysis (CoMFA) by settings optimization has been evaluated to show that CoMFA predictive ability can be improved. Ten different CoMFA settings are evaluated, producing a total of 6120 models. This method has been applied to nine different data sets, including the widely used benchmark steroid data set, as well as eight other data sets proposed as QSAR benchmarking data sets by Sutherland et al. (J. Med. Chem. 2004, 47, 5541-5554). All data sets have been studied using training and test sets to allow for both internal (q(2)) and external (r(2)(pred)) predictive ability assessment. CoMFA settings optimization was successful in developing models with improved q(2) and r(2)(pred) as compared to default CoMFA modeling. Optimized CoMFA is compared with comparative molecular similarity indices analysis (CoMSIA) and holographic quantitative structure-activity relationship (HQSAR) models and found to consistently produce models with improved or equivalent q(2) and r(2)(pred). The ability of settings optimization to improve model predictive ability has been validated using both internal and external predictions, and the risk of chance correlation has been evaluated using response variable randomization tests.     

Prediction of rheological behavior of MWCNTs–SiO2/EG–water non-Newtonian hybrid nanofluid by designing new correlations and optimal artificial neural networks

In this paper, at the first, new correlations were proposed to predict the rheological behavior of MWCNTs–SiO₂/EG–water non-Newtonian hybrid nanofluid using different sets of experimental data for the viscosity, consistency and power law indices. Then, based on minimum prediction errors, two optimal artificial neural network models (ANNs) were considered to forecast the rheological behavior of the non-Newtonian hybrid nanofluid. One hundred and ninety-eight experimental data were employed for predicting viscosity (Model I). Two sets of forty-two experimental data also were considered to predict the consistency and power law indices (Model II). The data sets were divided to training and test sets which contained respectively 80 and 20% of data points. Comparisons between the correlations and ANN models showed that ANN models were much more accurate than proposed correlations. Moreover, it was found that the neural network is a powerful instrument in establishing the relationship between a large numbers of experimental data. Thus, this paper confirmed that the neural network is a reliable method for predicting the rheological behavior of non-Newtonian nanofluids in different models.

     

Prediction of Chromatographic Retention of Pyrazine and Alkylpyrazines in RP-LC

Retention prediction models for a group of pyrazines chromatographed under reversed-phase mode were developed using multiple linear regression (MLR) and artificial neural networks (ANNs). Using MLR, the retention of the analytes were satisfactorily described by a two-predictor model based on the logarithm of the partition coefficient of the analytes (log P) and the percentage of the organic modifier in the mobile phase (ACN or MeOH). ANN prediction models were also derived using the predictors derived from MLR as inputs and log k as outputs. The best network architecture was found to be 2-2-1 for both ACN and MeOH data sets. The optimized ANNs showed better predictive properties than the MLR models especially for the ACN data set. In the case of the MeOH data set, the MLR and ANN models have comparable predictive performance.     

A journey into low-dimensional spaces with autoassociative neural networks

The compression and the visualization of the data have been always a subject of a great deal of excitement. Since multidimensional data sets are difficult to interpret and visualize, much of the attention is drawn how to compress them efficiently. Usually, the compression of dimensionality is considered as the first step of exploratory data analysis. Here, we focus our attention on autoassociative neural networks (ANNs), which in a very elegant manner provide data compression and visualization. ANNs can deal with linear and nonlinear correlation among variables, what makes them a very powerful tool in exploratory data analysis. In the literature, ANNs are often referred as nonlinear principal component analysis (PCA), and due to their specific structure they are also known as bottleneck neural networks. In this paper, ANNs are discussed in details. Different training modes are described and illustrated on real example. The usefulness of ANNs for nonlinear data compression and visualization purposes is proven with the aid of chemical data sets, being the subject of analysis. The comparison of ANNs with well-known PCA is also presented.     

Kinase-kernel models: accurate in silico screening of 4 million compounds across the entire human kinome

Reliable in silico prediction methods promise many advantages over experimental high-throughput screening (HTS): vastly lower time and cost, affinity magnitude estimates, no requirement for a physical sample, and a knowledge-driven exploration of chemical space. For the specific case of kinases, given several hundred experimental IC(50) training measurements, the empirically parametrized profile-quantitative structure-activity relationship (profile-QSAR) and surrogate AutoShim methods developed at Novartis can predict IC(50) with a reliability approaching experimental HTS. However, in the absence of training data, prediction is much harder. The most common a priori prediction method is docking, which suffers from many limitations: It requires a protein structure, is slow, and cannot predict affinity. (1) Highly accurate profile-QSAR (2) models have now been built for roughly 100 kinases covering most of the kinome. Analyzing correlations among neighboring kinases shows that near neighbors share a high degree of SAR similarity. The novel chemogenomic kinase-kernel method reported here predicts activity for new kinases as a weighted average of predicted activities from profile-QSAR models for nearby neighbor kinases. Three different factors for weighting the neighbors were evaluated: binding site sequence identity to the kinase neighbors, similarity of the training set for each neighbor model to the compound being predicted, and accuracy of each neighbor model. Binding site sequence identity was by far most important, followed by chemical similarity. Model quality had almost no relevance. The median R(2) = 0.55 for kinase-kernel interpolations on 25% of the data of each set held out from method optimization for 51 kinase assays, approached the accuracy of median R(2) = 0.61 for the trained profile-QSAR predictions on the same held out 25% data of each set, far faster and far more accurate than docking. Validation on the full data sets from 18 additional kinase assays not part of method optimization studies also showed strong performance with median R(2) = 0.48. Genetic algorithm optimization of the binding site residues used to compute binding site sequence identity identified 16 privileged residues from a larger set of 46. These 16 are consistent with the kinase selectivity literature and structural biology, further supporting the scientific validity of the approach. A priori kinase-kernel predictions for 4 million compounds were interpolated from 51 existing profile-QSAR models for the remaining >400 novel kinases, totaling 2 billion activity predictions covering the entire kinome. The method has been successfully applied in two therapeutic projects to generate predictions and select compounds for activity testing.     

IDSite: An accurate approach to predict P450-mediated drug metabolism

Accurate prediction of drug metabolism is crucial for drug design. Since a large majority of drugs metabolism involves P450 enzymes, we herein describe a computational approach, IDSite, to predict P450-mediated drug metabolism. To model induced-fit effects, IDSite samples the conformational space with flexible docking in Glide followed by two refinement stages using the Protein Local Optimization Program (PLOP). Sites of metabolism (SOMs) are predicted according to a physical-based score that evaluates the potential of atoms to react with the catalytic iron center. As a preliminary test, we present in this paper the prediction of hydroxylation and O-dealkylation sites mediated by CYP2D6 using two different models: a physical-based simulation model, and a modification of this model in which a small number of parameters are fit to a training set. Without fitting any parameters to experimental data, the Physical IDSite scoring recovers 83% of the experimental observations for 56 compounds with a very low false positive rate. With only 4 fitted parameters, the Fitted IDSite was trained with the subset of 36 compounds and successfully applied to the other 20 compounds, recovering 94% of the experimental observations with high sensitivity and specificity for both sets.     

Predicting and evaluating separation quality of micellar electrokinetic capillary chromatography by artificial neural networks

Computer-aided optimization of micellar electrokinetic capillary chromatography (MEKC) separations was demonstrated by artificial neural networks (ANNs) using a Levenberg-Marquardt algorithm and an orthogonal experimental design. A novel criterion, named Q, for evaluating the separation quality of MEKC was firstly presented, which considered both separation selectivity and analysis time. MEKC separation conditions of seven plant hormones were then simulated and optimized using ANNs based on this novel criterion. The result was further compared to that obtained using ANNs based on a traditionally used criterion of overall normalization resolution (named r). Finally, the separation under optimum conditions predicted by ANNs using the criterion Q was compared to, and proved to be better than that obtained by empirical step-by-step optimization procedures. This method may also be adapted to other separation methods due to its generality.