Set Of Molecular Descriptors Research Articles

Prediction of gas chromatographic retention indices of a diverse set of toxicologically relevant compounds

For a set of 846 organic compounds, relevant in forensic analytical chemistry, with highly diverse chemical structures, the gas chromatographic Kovats retention indices have been quantitatively modeled by using a large set of molecular descriptors generated by software Dragon. Best and very similar performances for prediction have been obtained by a partial least squares regression (PLS) model using all considered 529 descriptors, and a multiple linear regression (MLR) model using only 15 descriptors obtained by a stepwise feature selection. The standard deviations of the prediction errors (SEP), were estimated in four experiments with differently distributed training and prediction sets. For the best models SEP is about 80 retention index units, corresponding to 2.1–7.2% of the covered retention index interval of 1110–3870. The molecular properties known to be relevant for GC retention data, such as molecular size, branching and polar functional groups are well covered by the selected 15 descriptors. The developed models support the identification of substances in forensic analytical work by GC–MS in cases the retention data for candidate structures are not available.

Derivation and applications of molecular descriptors based on approximate surface area.

Three sets of molecular descriptors that can be computed from a molecular connection table are defined. The descriptors are based on the subdivision and classification of the molecular surface area according to atomic properties (such as contribution to logP, molar refractivity, and partial charge). The resulting 32 descriptors are shown (a) to be weakly correlated with each other; (b) to encode many traditional molecular descriptors; and (c) to be useful for QSAR, QSPAR, and compound classification.

Development of neural network QSPR models for Hansch substituent constants. 1. Method and validations.

In an attempt to develop predictive models for Hansch substituent constants for less common substituents, neural network QSPR (Quantitative Structure-Property Relationship) studies were conducted to correlate Hansch substituent constants for hundreds of chemically diverse functional groups with two different molecular descriptor sets. The Hansch substituent constants under study were pi, MR, F and R, describing the hydrophobic, steric/polarizability, and electronic (field and resonance) characteristics of the substituents, respectively. E-state descriptors were used for pi and MR, while the molecular descriptor set based upon the approach of Kvasnicka, Sklenak, and Pospichal (J. Am. Chem. Soc. 1993, 115, 1495-1500) was adopted for F and R. Both QSPR models demonstrated good predictivity in test sets.

Alternative statistical and theoretical analysis of fluorophilicity

We present quantitative structure–property relationships (QSPR) for the partition of 99 organic compounds between organic and fluorinated solvents. The approach consists of straightforward multivariate regression using the simplest topological molecular descriptors. We discuss how to obtain the best model for each set of molecular descriptors and show that present statistical parameters are comparable to those given by more elaborate descriptors.

Evolutionary optimization, backpropagation, and data preparation issues in QSAR modeling of HIV inhibition by HEPT derivatives

Artificial neural networks (ANNs) can be utilized to generate predictive models of quantitative structure–activity relationships between a set of molecular descriptors and activity. Evolutionary computation provides a means to appropriately search for the set of weights and bias terms associated with artificial neural networks that minimize selected functions of the error between the actual and desired outputs. This method is demonstrated by evolutionary training of artificial neural networks capable of predicting anti-HIV activity for a set of 1-[(2-hydroxyethoxy)methyl]-6-(phenylthio)thymine (HEPT) derivatives. The results of this work further confirm the growing indication that evolutionary computation can outperform backpropagation as a method of artificial neural network training. The results also indicate the degree to which bias in the initial training and testing data can affect performance and the importance of bootstrapping.

Russian paint output drops by more than 10%

This paper describes the construction of a QSAR model to relate the structures of various derivatives of neocryptolepine to their anti-malarial activities. QSAR classification models were build using Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Classification and Regression Trees (CART), Partial Least Squares – Discriminant Analysis (PLS-DA), Orthogonal Projections to Latent Structures – Discriminant Analysis (OPLS-DA), and Support Vector Machines for Classification (SVM-C), using four sets of molecular descriptors as explanatory variables. Prior to classification, the molecules were divided into a training and a test set using the duplex algorithm. The different classification models were compared regarding their predictive ability, simplicity, and interpretability. Both binary and multi-class classification models were constructed. For classification into three classes, CART and One-Against-One (OAO)-SVM-C were found to be the best predictive methods, while for classification into two classes, LDA, QDA and CART were.

A novel potentiometric approach for detection of beta-adrenergics and beta-adrenolytics in high-performance liquid chromatography

Potentiometric approach enabling sensitive and reliable detection for a series of 20 autonomic beta-adrenergic ligands with the use of poly(vinyl chloride) (PVC) based liquid membrane electrode coatings in the normal-bore cation exchange HPLC and narrow-bore reversed phase HPLC system is presented. It was found that in both kinds of HPLC modes with a contemporary hybrid polymer-silica packings an application of electrodes containing a tetrakis( p-chlorophenyl)borate (TCPB) gives limits of detection below to 8.0×10 −7 mol l −1 (injected concentrations). In case of highly hydrophobic beta-adrenergic drugs the use of binary aqueous mobile phases with high concentrations of acetonitrile (up to 25% v/v) shifting an observable detection limits (DL) down to 2.0×10 −8 mol l −1, especially for electrodes with addition of trioctylated α-cyclodextrin. The characteristics of developed potentiometric detectors was established by proposed a quantitative structure–potentiometric response relationships (QSPRRs) for a series of diversified beta-adrenergic compounds and for a set of the PVC based electrodes using TCPB alone as well as in combination with trioctylated α-cyclodextrin, dibenzo-18-crown-6, or calix[6]arene hexaethylester as the neutral macrocycle ionophore. A highly significant QSPRRs equations were obtained leading to reasonable prediction of the DL of specified electrodes in terms of the computationally derived set of molecular descriptors of beta-adrenergics and beta-blocking agents and similar amino alcohol type xenobiotics.

Prediction of bioconcentration factor using genetic algorithm and artificial neural network

In this paper, genetic algorithm (GA) and stepwise multiple regression variable selection methods were used as a feature-selection tools and neural network was employed for feature mapping. To provide an extended test of these hybrid methods, a data set consists of the bioconcentration factors (BCF) for 53 molecules were selected. Suitable set of molecular descriptors were calculated and the important descriptors were selected by genetic algorithm and stepwise multiple regression methods. These variables serve as inputs to generated neural networks. After optimization and training of the networks, they were used for the calculation of bioconcentration factors for the prediction set. Comparison between results obtained showed the superiority of genetic algorithm over stepwise multiple regression method in feature-selection. For network that used the genetic algorithm for feature-selection methods the average relative error between predicted and experimental values of bioconcentration factor for training and prediction set are 0.07 and 0.13, respectively. Also the standard error of calibration and standard error of prediction are 0.26 and 0.40%, respectively, for this model. An analysis of the descriptor selected by genetic algorithm showed that they are essential to implies the steric and electrostatic attributes of studied molecules to obtain a satisfactory quantitative structure–activity relationship (QSAR) model.

A Fuzzy ARTMAP‐Based Quantitative Structure—Property Relationship (QSPR) for the Henry′s Law Constant of Organic Compounds.

Quantitative structure−property relationships (QSPRs) for estimating a dimensionless Henry's Law constant of organic compounds at 25 °C were developed based on a fuzzy ARTMAP and back-propagation neural networks using a heterogeneous set of 495 organic compounds. A set of molecular descriptors developed from PM3 semiempirical MO-theory and topological descriptors (second-order molecular connectivity index) were used as input parameters to the neural networks. Quantum chemical input descriptors included average molecular polarizability, dipole moments (total point charge, total hybridization, and total sum), ionization potential, and heat of formation. The fuzzy ARTMAP/QSPR correlated Henry's Law constant for −6.72 ≤ logH ≤ 2.87 with average absolute errors of 0.03 and 0.13 logH units for the overall data and the test set, respectively. The optimal 7−17−1 back-propagation/QSPR model was less accurate and exhibited larger average absolute errors of 0.28 and 0.27 logH units for the validation (recall) and te...

Predicting Toxicity against the fathead Minnow by Adaptive Fuzzy Partition

AbstractRecent progress in the development of powerful tools suitable to design and to classify large chemical libraries can be fruitfully extended also to the ecotoxicity domain. Amidst these methods, Fuzzy Logic concepts, based on the possibility to handle the “concept of partial truth”, constitute interesting approaches to developing general predictive models.

Prediction of oral bioavailability by adaptive fuzzy partitioning

An adaptive fuzzy partition (AFP) algorithm was applied on two bioavailability data sets subdivided into four ranges of activity. A large set of molecular descriptors was tested and the most relevant parameters were selected with help of a procedure based on genetic algorithm concepts and stepwise method. After building several AFP models on a training set, the best ones were able to predict correctly 75% of the validation set compounds. Furthermore, an improvement of about 15% in the validation results was got, on the same data set, as regard to other prediction methods. The importance to work with data sets including a large molecular diversity, and to use tools able to manage it, was also shown. The prediction power was increased up to 25% employing a data set with a better-optimised molecular diversity.

The prediction for gas chromatographic retention index of disulfides on stationary phases of different polarity

Quantitative structure–retention relationship (QSRR) models for the gas chromatographic (GC) Kaváts indices of disulfides on four different polarity stationary phase have been developed. Semi-empirical quantum chemical method (AM1) implemented in hyperchem 4.0 was employed to calculate a set of molecular descriptors of 50 disulfides. The four stationary phases in the research were: Apiezon M, OV-17 , Triton X-305 and PEG-1000 . By using multiple linear regression (MLR), we obtained four empirical functions with high correlation coefficient ( R 1=0.995, R 2=0.994, R 3=0.990, R 4=0.976). At the same time, using Thin Plat Spline the Radial Basis Function neural networks models were obtained with root mean squared error (RMS) of training set (RMS T1=0.013351, RMS T2=0.012973, RMS T3=0.023228, RMS T4=0.020755) and RMS of validation set (RMS V1=0.007626, RMS V2=0.005897, RMS V3=0.005109, RMS V4=0.007377) and RMS of testing set (RMS X1=0.016676, RMS X2=0.016704, RMS X3=0.017162, RMS X4=0.014755). The results indicated that the QSRR models proposed were very satisfactory.

A fuzzy ARTMAP-based quantitative structure-property relationship (QSPR) for the Henry's law constant of organic compounds.

Quantitative structure-property relationships (QSPRs) for estimating a dimensionless Henry's Law constant of organic compounds at 25 degrees C were developed based on a fuzzy ARTMAP and back-propagation neural networks using a heterogeneous set of 495 organic compounds. A set of molecular descriptors developed from PM3 semiempirical MO-theory and topological descriptors (second-order molecular connectivity index) were used as input parameters to the neural networks. Quantum chemical input descriptors included average molecular polarizability, dipole moments (total point charge, total hybridization, and total sum), ionization potential, and heat of formation. The fuzzy ARTMAP/QSPR correlated Henry's Law constant for -6.72 </= logH </= 2.87 with average absolute errors of 0.03 and 0.13 logH units for the overall data and the test set, respectively. The optimal 7-17-1 back-propagation/QSPR model was less accurate and exhibited larger average absolute errors of 0.28 and 0.27 logH units for the validation (recall) and test sets, respectively. The fuzzy ARTMAP-based QSPR was superior to the back-propagation and multiple linear regression/QSPR models for Henry's Law constant of organic compounds.

A comparison between the two general sets of linear free energy descriptors of Abraham and Klamt.

Two sets of molecular descriptors, the five experimental Abraham, and the five COSMOments of Klamt's COSMO-RS, have been compared for a data set of 470 compounds. Both sets are considered as almost complete sets of LFER. The two sets of descriptors are shown to exhibit a large overlap as far as their chemical content. The chemical information however is distributed differently in each set with the Abraham set incorporating extra information in the excess molar refraction descriptor E. Regression equations have been constructed to predict the experimental Abraham descriptors from theoretically calculated COSMOments. The chemical interpretation of these equations is however difficult because of the lack of clustering which characterizes the distribution of chemical information through the two sets of descriptors. The predictability of the regression equations is tested successfully using a reasonably large set of data, and the method is compared to recent attempts to calculate the Abraham descriptors from various theoretical bases.

Integrated acquisition of analytical and biopharmaceutical screening data for beta-adrenergic-drugs employing diversified macrocycle supported potentiometric detection in HPLC systems.

Potentiometric detection with poly(vinyl chloride) (PVC) based liquid membrane electrode coatings is presented for a series of eighteen beta-adrenoceptor binding drugs (five agonists and thirteen antagonists) in cation exchange-HPLC and RP-HPLC systems. Incorporation of lipophilic cation-exchanger tetrakis(p-chlorophenyl)borate (TCPB) alone or in combination with trioctylated alpha-cyclodextrin into the polymeric liquid membrane gives very sensitive responses for racemic forms of bufuralol, propranolol, carazolol, clenbuterol, mabuterol, cimaterol, bisoprolol, oxprenolol, alprenolol, tertatolol, and bevantolol, especially in the cation-exchange HPLC system applying acetonitrile -- 40 mM phosphoric acid (15: 85, v/v, pH* = 2.35) as the mobile phase. In both applied orthogonal HPLC modes we observed that use of TCPB containing electrodes (no addition of neutral macrocyclic ionophores) gives more than five fold improvement in limit of detection down to 10(-7) M for mabuterol, bufuralol, alprenolol and tertatolol in comparison with UV detection. These results suggest that potentiometric detection, especially in RP-HPLC employing hybrid polymer-silica packings, can be considered as the promising alternative in the high-throughput drug abuse or doping control procedures of investigated beta-adrenergic agonists and beta-adrenolytics in humans and animals. The quantitative structure - potentiometric response relationships were developed for a set of eighteen beta-adrenenergic drugs and a set of PVC based electrodes using TCPB alone or in admixture with trioctylated alpha-cyclodextrin, dibenzo-18-crown-6 or calix[6]arene hexaethylacetate ester. A multiple linear regression model based on computationally derived set of molecular descriptors was used to predict detection limits of beta-blocking agents and beta-adrenergic agonists from their molecular structure in the developed potentiometric detectors. Principal components analysis (PCA) of data considering determined potentiometric detection limits revealed that it can be used to establish a reliable pharmacological classification of compounds with beta-adrenoceptor activity, especially for the differentiation of cardioselective and non-cardioselective beta1-antagonists.

Descriptors, physical properties, and drug-likeness.

We have investigated techniques for distinguishing between drugs and nondrugs using a set of molecular descriptors derived from semiempirical molecular orbital (AM1) calculations. The "drug" data set of 2105 compounds was derived from the World Drug Index (WDI) using a procedure designed to select real drugs. The "nondrug" data set was the Maybridge database. We have first investigated the dimensionality of physical properties space based on a set of 26 descriptors that we have used successfully to build absorption, distribution, metabolism, and excretion-related quantitative structure-property relationship models. We discuss the general nature of the descriptors for physical property space and the ability of these descriptors to distinguish between drugs and nondrugs. The third most significant principal component of this set of descriptors serves as a useful numerical index of drug-likeness, but no others are able to distinguish between drugs and nondrugs. We have therefore extended our set of descriptors to a total of 66 and have used recursive partitioning to identify the descriptors that can distinguish between drugs and nondrugs. This procedure pointed to two of the descriptors that play an important role in the principal component found above and one more from the set of 40 extra descriptors. These three descriptors were then used to train a Kohonen artificial neural net for the entire Maybridge data set. Projecting the drug database onto the map obtained resulted in a clear distinction not only between drugs and nondrugs but also, for instance, between hormones and other drugs. Projection of 42 131 compounds from the WDI onto the Kohonen map also revealed pronounced clustering in the regions of the map assigned as druglike.

Structure/response correlations and similarity/diversity analysis by GETAWAY descriptors. 1. Theory of the novel 3D molecular descriptors.

Novel molecular descriptors based on a leverage matrix similar to that defined in statistics and usually used for regression diagnostics are presented. This leverage matrix, called Molecular Influence Matrix (MIM), is here proposed as a new molecular representation easily calculated from the spatial coordinates of the molecule atoms in a chosen conformation. The proposed molecular descriptors are called GETAWAY (GEometry, Topology, and Atom-Weights AssemblY) as they try to match 3D-molecular geometry provided by the molecular influence matrix and atom relatedness by molecular topology, with chemical information by using different atomic weightings (atomic mass, polarizability, van der Waals volume, and electronegativity, together with unit weights). A first set of molecular descriptors, called H-GETAWAY, is derived by using only the information provided by the molecular influence matrix, while a second set, called R-GETAWAY, combines this information with geometric interatomic distances in the molecule. The prediction ability in structure-property correlations of the new descriptors was tested by analyzing regressions of these descriptors for selected properties of octanes.

Structure/response correlations and similarity/diversity analysis by GETAWAY descriptors. 2. Application of the novel 3D molecular descriptors to QSAR/QSPR studies.

In a previous paper the theory of the new molecular descriptors called GETAWAY (GEometry, Topology, and Atom-Weights AssemblY) was explained. These descriptors have been proposed with the aim of matching 3D-molecular geometry, atom relatedness, and chemical information. In this paper prediction ability in structure-property correlations of GETAWAY descriptors has been tested extensively by analyzing the regressions of these descriptors for selected properties of some reference compound classes. Moreover, the general performance of the new descriptors in QSAR/QSPR has been evaluated with respect to other well-known sets of molecular descriptors.

Fuzzy ARTMAP and back-propagation neural networks based quantitative structure-property relationships (QSPRs) for octanol-water partition coefficient of organic compounds.

Quantitative structure-property relationships (QSPRs) for estimating the logarithm octanol/water partition coefficients, logK(ow), at 25 degrees C were developed based on fuzzy ARTMAP and back-propagation neural networks using a heterogeneous set of 442 organic compounds. The set of molecular descriptors were derived from molecular connectivity indices and quantum chemical descriptors calculated from PM3 semiempirical MO-theory. Quantum chemical input descriptors include average polarizability, dipole moments, exchange energy, total electrostatic interaction energy, total two-center energy, and ionization potential. The fuzzy ARTMAP/QSPR performed, for a logK(ow) range of -1.6 to 7.9, with average absolute errors of 0.03 and 0.14 logK(ow) for the overall data and test sets, respectively. The optimal 12-11-1 back-propagation/QSPR model, for the same range of logK(ow), exhibited larger average absolute errors of 0.23 and 0.27 logK(ow) for the test and validation data sets, respectively, over the same range of logK(ow) values. The present results with the fuzzy ARTMAP-based QSPR are encouraging and suggest that high performance logK(ow) QSPR that encompasses a wider range of chemical groups could be developed, following the present approach, by training with a larger heterogeneous data set.

A structure–activity relationship (SAR) study of synthetic neolignans and related compounds with biological activity against Escherichia coli

Structure–activity relationship techniques were employed to classify neolignan compounds and related analogues against Escherichia coli. The AM1 (Austin Model) method was used to calculate a set of molecular descriptors (properties) for 16 synthetic neolignan compounds. The descriptors were further analyzed using the principal component analysis (PCA), hierarchical cluster analysis (HCA) and K-nearest neighbor (KNN) chemometric methods. The PCA and HCA methods showed quite efficient to classify the 16 compounds in two groups (active and inactive) and three descriptors were found to be important in the classification. By using the chemometric results, 14 new neolignan molecules were analyzed through the PCA, HCA and KNN methods and 11 of them are proposed as molecules potentially active against E. coli.