Prediction of enantioselectivity using chirality codes and Classification and Regression Trees

Colorimetric sensor array combined with chemometric methods for the assessment of aroma produced during the drying of tencha

The aroma produced during drying is an important indicator of tencha and needs to be monitored. This study constructed an olfactory visualization system for assessing tencha aroma using colorimetric sensor array (CSA) combined with chemometric methods. The 16 chemically responsive dyes were selected to obtain aroma information of tencha samples and extracted image data of aroma information by machine vision algorithms. Subsequently, k-nearest neighbor, support vector machine, classification and regression tree, and random forest (RF), four qualitative models were applied to build the mathematical models. The RF model with nine principal components was preferred, with recognition rate of 100.00% and 91.07% for the training and prediction sets, respectively. The experimental results showed that CSA combined with the RF model can be effectively applied to assess tencha aroma. This study provided a scientific and novel method to maintain the stability of tencha quality in the production process.

Recent advances in chiral selectors immobilization and chiral mobile phase additives in liquid chromatographic enantio-separations: A review

For decades now, the separation of chiral enantiomers of drugs has been gaining the interest and attention of researchers. In 1991, the first guidelines for development of chiral drugs were firstly released by the US-FDA. Since then, the development in chromatographic enantioseparation tools has been fast and variable, aiming at creating a suitable environment where the physically and chemically identical enantiomers can be separated. Among those tools, the immobilization of chiral selectors (CS) on different stationary phases and the chiral mobile phase additives (CMPA) which have been progressed and studied extensively. This review article highlights the major advances in immobilization of CS together with their different recognition mechanisms as well as CMPA as a cheaper and successful alternative for chiral stationary phases. Moreover, the role of molecular modeling tool as a pre-step in the choice of CS for evaluating possible interactions with different ligands has been pointed up. Illustrations of reported methods and updates for immobilized CS and CMPA have been included.

Modelling the enantiorecognition of structurally diverse pharmaceuticals on O-substituted polysaccharide-based stationary phases

This study aims to develop models to predict the retention, separation and elution sequence of the enantiomers of structurally diverse pharmaceuticals. More specifically, Quantitative Structure Retention Relationships (QSRR) models are built that describe the relationship between molecular descriptors and retention. Eighteen structurally diverse chiral mixtures, each consisting of a pair of enantiomers, were analyzed on two polysaccharide chiral stationary phases, Chiralcel OD-RH (cellulose tris(3,5-dimethylphenylcarbamate)) and Lux amylose-2 (amylose tris(5-chloro-2-methylphenylcarbamate)), applying either a basic or an acidic mobile phase, and their retention factor and elution sequence were determined. Both achiral and, in-house defined, chiral descriptors were used as descriptive variables to build the models. Linear regression techniques, i.e. stepwise multiple linear regression (sMLR) and partial least squares (PLS) regression, were applied to model the retention or separation as a function of the descriptors. In a first step, models were built with only achiral descriptors to model the global retention of both enantiomers of a chiral molecule. Subsequently, models were built with only chiral descriptors to predict the enantioseparation and elution sequence, and finally, models were considered with both descriptor types to predict the retention, the separation and the elution sequence of the enantiomers. The global retention was predicted well by the sMLR models with only achiral descriptors. The models with only chiral descriptors were not found suitable to predict the enantioseparation and elution sequence. Finally, the models containing both chiral and achiral descriptors allowed predicting the retention well, but their ability to predict the elution sequence and separation of the enantiomers differed widely for the chromatographic systems considered.

Quantitative structure-activity relationship analysis of human neutrophil elastase inhibitors using shuffling classification and regression trees and adaptive neuro-fuzzy inference systems

The purpose of this study was to develop quantitative structure-activity relationship models for N-benzoylindazole derivatives as inhibitors of human neutrophil elastase. These models were developed with the aid of classification and regression trees (CART) and an adaptive neuro-fuzzy inference system (ANFIS) combined with a shuffling cross-validation technique using interpretable descriptors. More than one hundred meaningful descriptors, representing various structural characteristics for all 51 N-benzoylindazole derivatives in the data set, were calculated and used as the original variables for shuffling CART modelling. Five descriptors of average Wiener index, Kier benzene-likeliness index, subpolarity parameter, average shape profile index of order 2 and folding degree index selected by the shuffling CART technique have been used as inputs of the ANFIS for prediction of inhibition behaviour of N-benzoylindazole derivatives. The results of the developed shuffling CART-ANFIS model compared to other techniques, such as genetic algorithm (GA)-partial least square (PLS)-ANFIS and stepwise multiple linear regression (MLR)-ANFIS, are promising and descriptive. The satisfactory results r2p = 0.845, Q2(LOO) = 0.861, r2(L25%O) = 0.829, RMSE(LOO)  = 0.305 and RMSE(L25%O)  = 0.336) demonstrate that shuffling CART-ANFIS models present the relationship between human neutrophil elastase inhibitor activity and molecular descriptors, and they yield predictions in excellent agreement with the experimental values.

Integrating classification and regression tree (CART) with GIS for assessment of heavy metals pollution

The classification and regression tree (CART) model integrated with geographical information systems and the assessment of heavy-metals pollution system was developed to assess the heavy metals pollution in Fuyang, Zhejiang, China. The integration of the decision tree model with ArcGIS Engine 9 using a COM implementation in Microsoft Visual Basic 6.0 provided an approach for assessing the spatial distribution of soil Zn content with high predictive accuracy. The Zn concentration classes estimated by CART assigned the right classes with an accuracy of near 90%. This is a great improvement compared to the ordinary Kriging method for the spatial autocorrelation of the study area severely destroyed by human activities. Also, it can be used to investigate the inter-relationships between the heavy metals pollution and environmental and anthropogenic variables. Moreover, the research presents model predictions over space for further applications and investigations.

Physicochemical stereodescriptors of atomic chiral centers

Physicochemical atomic stereodescriptors (PAS) were implemented that represent the chirality of an atomic chiral center on the basis of empirical physicochemical properties of the ligands. The ligands are ranked according to a specific property, and the chiral center takes an S/R-like descriptor relative to that property. The procedure is performed for a series of properties, yielding a chirality profile. Application of the PAS descriptors to the prediction of enantioselectivity in chemical reactions, from the molecular structures, is illustrated here. The relationship between the molecular structures, represented by the PAS descriptors, and the enantioselectivity was learned by neural networks, decision trees, or random forests. In a first application, a data set was employed with chiral amino alcohols that enantioselectively catalyze the addition of diethylzinc to benzaldehyde. Prediction of the major enantiomer obtained in the reaction, from the molecular structure of the catalyst, was achieved with accuracy up to 90%. The second application investigated the enantiopreference of Pseudomonas cepacia lipase (PCL) toward primary alcohols. The learned models could make correct predictions about the preferred enantiomer, from the molecular structure of the substrate, in up to 93% of the cases. These included substrates with and without O-atoms bonded to the chiral center. The properties automatically selected to build the models can give indications on the relevant factors guiding the observed chemical behavior.

Enantiomeric separation and determination of absolute stereochemistry of asymmetric molecules in drug discovery—Building chiral technology toolboxes

The application of Chiral Technology, or the (extensive) use of techniques or tools for the determination of absolute stereochemistry and the enantiomeric or chiral separation of racemic small molecule potential lead compounds, has been critical to successfully discovering and developing chiral drugs in the pharmaceutical industry. This has been due to the rapid increase over the past 10-15 years in potential drug candidates containing one or more asymmetric centers. Based on the experiences of one pharmaceutical company, a summary of the establishment of a Chiral Technology toolbox, including the implementation of known tools as well as the design, development, and implementation of new Chiral Technology tools, is provided.

Classification Tree Models for the Prediction of Blood−Brain Barrier Passage of Drugs

The use of classification trees for modeling and predicting the passage of molecules through the blood-brain barrier was evaluated. The models were built and evaluated using a data set of 147 molecules extracted from the literature. In the first step, single classification trees were built and evaluated for their predictive abilities. In the second step, attempts were made to improve the predictive abilities using a set of 150 classification trees in a boosting approach. Two boosting algorithms, discrete and real adaptive boosting, were used and compared. High-predictive classification trees were obtained for the data set used, and the models could be improved with boosting. In the context of this research, discrete adaptive boosting gives slightly better results than real adaptive boosting.