Ma. Teresa Salabert‐Salvador

Artificial neural networks and linear discriminant analysis: a valuable combination in the selection of new antibacterial compounds.

A set of topological descriptors has been used to discriminate between antibacterial and nonantibacterial drugs. Topological descriptors are simple integers calculated from the molecular structure represented in SMILES format. The methods used for antibacterial activity discrimination were linear discriminant analysis (LDA) and artificial neural networks of a multilayer perceptron (MLP) type. The following plot frequency distribution diagrams were used: a function of the number of drugs within a value interval of the discriminant function and the output value of the neural network versus these values. Pharmacological distribution diagrams (PDD) were used as a visualizing technique for the identification of antibacterial agents. The results confirmed the discriminative capacity of the topological descriptors proposed. The combined use of LDA and MLP in the guided search and the selection of new structures with theoretical antibacterial activity proved highly effective, as shown by the in vitro activity and toxicity assays conducted.

Drugs and nondrugs: an effective discrimination with topological methods and artificial neural networks.

A set of topological and structural descriptors has been used to discriminate general pharmacological activity. To that end, we selected a group of molecules with proven pharmacological activity including different therapeutic categories, and another molecule group without any activity. As a method for pharmacological activity discrimination, an artificial neural network was used, dividing molecules into active and inactive, to train the network and externally validate it. The following plot frequency distribution diagrams were used: a function of the number of drugs within a value interval, and the output value of the neural network versus these values. Pharmacological distribution diagrams (PDD) were used as a visualizing technique for the identification of drug and nondrug molecules. The results confirmed the discriminative capacity of the topological descriptors proposed.

Artificial neural network applied to the discrimination of antibacterial activity by topological methods

Abstract A new topological method that makes it possible to discriminate the active and inactive molecules on the basis of their chemical structures is applied in the present study to the antibacterial agents. This method uses neural networks in which training algorithms are used as well as different concepts and methods of artificial intelligence with a suitable set of topological descriptors. It is possible to obtain a QSAR interpretation of the information contained in the network after the training has been carried out.

Prediction of chromatographic properties for a group of natural phenolic derivatives by molecular topology

A study was made of the relationship between the RM values obtained by thin-layer chromatography for a group of phenols and connectivity indices proposed by Kier and Hall. By using multivariate regression the corresponding connectivity functions were obtained, which were selected based on their respective statistical parameters. Regression analysis of the connectivity functions showed a correct prediction of the experimental elution sequence for this group of molecules using silica gel stationary phases and mobile phases of different polarity. Random and stability studies of the different prediction models selected were carried out, and good stability and null randomness were obtained in all cases.

Calculation of chromatographic parameters by molecular topology : sulphamides

This investigation was undertaken to test the ability of the molecular connectivity model to predict RF values in thin-layer chromatography (TLC) for a group of sulphamides using multi-variable regression equations with multiple correlation coefficients, standard error of estimate, F-Snedecor function values and Students t-test as criteria of fit. Regression analyses showed that the molecular connectivity model predicts the values for this property in different silica gel stationary phases and different polar mobile phases. Corresponding stability and random studies were made on the selected prediction models which confirmed their goodness of fit. The results also demonstrated that different structural features determine the RF values in TLC of sulphamides.

Prediction of chromatographic parameters for some anilines by molecular connectivity

SummaryThe possible relation existing between RF values obtained by thin-layer chromatography for a group of anilines with connectivity indices proposed by Kier and Hall has been studied. Using multivariable regression the corresponding connectivity functions, selected for their respective correlation coefficients, standard deviations, Snedecor’s F and Student’s t were obtained. Regression analysis of the connectivity functions gives a correct prediction of the experimental elution sequence for this group of substances on silica gel stationary phases and various mobile phases of different polarity. The corresponding random and stability studies of the different prediction models selected were carried out, showing good stability and null randomness in all cases.

Correlation of Pharmacological Properties of a Group of β-Blocker Agents by Molecular Topology

The molecular connectivity method has been applied to the study of pharmacological properties, among which are found the angor treatment dose, α‐distribution half‐life and intravenous LD50 in mouse, of a group of β‐blocker agents, verifying its application in the prediction of theoretic values for said pharmacological properties.

Calculation of chromatographic properties of barbiturates by molecular topology

SummaryA study has been made of the relationship between the RF values obtained by thin layer chromatography for a group of barbiturates and the connectivity indices proposed by Kier and Hall. By using multivariable regression we obtained the corresponding connectivity functions, which were selected on the basis of their respective statistics parameters. The regression analysis of the connectivity functions shows a correct prediction of the experimental elution sequence for this group of molecules on silicagel with two mobile phases of different polarity. The corresponding random and stability studies of the different prediction models selected were carried out, demonstrating good stability and null randomness in all cases. The results also demonstrated that different structural features determine the RF values in TLC of barbiturates.

New Hypolipaemic Agents Designed by Molecular Topology: Pharmacological Studies of 2,6-Di-tert-butyl-4-methylpyridine and 2,6-Di-tert-butylpyridine

New compounds showing hypolipaemic activity have been designed using a computer-aided method based on molecular topology and QSAR analysis. Linear discriminant analysis and connectivity functions were used to design three potentially suitable drugs which were tested for hypolipaemic properties by the Triton WR-1339 test in rats. The pharmacological tests carried out on the newly designed compounds demonstrated the existence of notable activity in phase I for two of them. namely 2,6-Di-tert-butyl-4-methylpyridine (C.A.S. 38222-83-2) and 2,6-Di-tert-butylpyridine (C.A.S. 585-48-8), with respect to the level of total cholesterol. Both substances decrease the lipaemia to lower levels than clofibrate, which was used as a reference drug.

Correlation of Pharmacological Properties of a Group of Hypolipaemic Drugs by Molecular Topology

This investigation was undertaken to test the ability of the molecular connectivity model to predict the percentage of plasma protein binding, the percentage of total cholesterol reduction and oral LD50 in rats of a group of hypolipaemic drugs using multi‐variable regression equations with multiple correlation coefficients, standard error of estimate, degrees of freedom, F‐Snedecor function values, Mallows CP and Students t‐test as criteria of fit.