Biomedical subjects

Emilio Benfenati

Publications and source records attributed to Emilio Benfenati.

28 records · Page 2Linked to original sources

PubMedDate not supplied

Modeling toxicity by using supervised kohonen neural networks.

Counterprogation neural network is shown to be a powerful and suitable tool for the investigation of toxicity. This study mined a data set of 568 chemicals. Two hundred eighty-two objects were used as the training set and 286 as the test set. The final model developed presents high performances on the data set R(2) = 0.83 (R(2) = 0.97 on the training set, R(2) = 0.59 on the test set). This technique distinguishes itself also for the ability to give to the expert two-dimensional maps suitable for the study of the distribution/clustering of the data and the identification of outliers.

Journal Article↗

PubMedDate not supplied

Classification of potential endocrine disrupters on the basis of molecular structure using a nonlinear modeling method.

A methodology for the classification of endocrine disruption chemicals is proposed. It is based on a data set of 106 substances extracted from the list of 553 chemicals that were inspected by the European Union Commission for the scientific evidence of their endocrine disruption activity. The substances belong to different categories defined in the EU Commission report: (i) literature evidence for certainly active as endocrine disrupters, (ii) for potentially active, (iii) for less probable active--lacking evidence, and (iv) for certainty nonactive. 3D molecular coordinates were calculated using the AM1or the PM3 optimization method. From 3D coordinates an extensive set of molecular descriptors was calculated. The classification model based on the counterpropagation neural network was constructed and evaluated. This is the first time that the counterpropagation neural network is applied for the classification of compounds regarding their literature evidence for the endocrine disruption activity. The developed classification model is proposed as a tool for a preliminary assessment of potential endocrine disrupters, which would help the assessors to make the priority list for a large amount of chemicals that have to be tested with more expensive in vitro and in vivo methods.

Journal Article↗

PubMedDate not supplied

QSAR in ecotoxicity: an overview of modern classification techniques.

This study deals with classification for toxicity prediction. Using a data set of 235 pesticides and 153 descriptors, we built several models using seven classification algorithms: nearest mean classifier, linear discriminant analysis, quadratic discriminant analysis, regularized discriminant analysis, soft independent modeling of class analogy, K nearest neighbors classification, classification, and regression tree. The performance of the models was then compared with the classifier, the end-points, the number of descriptor, and the diversity of the data set. Finally, we made a critical analysis of the models and descriptors.

Algorithms↗

PubMedDate not supplied

Predictive models for aquatic toxicity of aldehydes designed for various model chemistries.

Predictive models for the aquatic toxicity of aldehydes were designed for a set of 50 aromatic or aliphatic compounds containing at least one aldehyde group, for which the acute toxicity data for the fathead minnow (Pimephales promelas) are available (96 h test assessing 50% lethal waterborne concentration). The molecular descriptors were based on calculations with various semiempirical or ab initio model chemistries. The resulting four-parameter models were evaluated according to the correlation coefficients R(2). The best predictive model was obtained with the HF/STO-3G model chemistry (R(2) = 0.868), while the models designed for descriptors based on ab initio calculations of higher level showed a slightly worse predictivity (the HF/3-21G(d) based model R(2) = 0.800, the HF/6-31G(d) based model R(2) = 0.808, the B3LYP/6-31G(d,p) based model R(2) = 0.812). With the semiempirical methods a good predictivity was observed with the PM3 based model (R(2) = 0.811) and the AM1 based model (R(2) = 0.791), but the MNDO based model showed the worst predictivity (R(2) = 0.760). In all ab initio models and the PM3 model very similar descriptors were involved. The importance of the descriptor logarithm of the partition coefficient logP for toxicity prediction was confirmed. Additionally, the descriptors encoding the negatively charged molecular surface area, hydrogen bonding molecular surface area, and reactivity of aldehyde group were identified as essential for the toxicity prediction of aldehydes.

Aldehydes↗

PubMedDate not supplied

Combining unsupervised and supervised artificial neural networks to predictaquatic toxicity.

Most quantitative structure-activity relationship (QSAR) models are linear relationships and significant for only a limited domain of compounds. Here we propose a data-driven approach with a flexible combination of unsupervised and supervised neural networks able to predict the toxicity of a large set of different chemicals while still respecting the QSAR postulates. Since QSAR is applicable only to similar compounds, which have similar biological and physicochemical properties, large numbers of compounds are clustered before building local models, and local models are ensembled to obtain the final result. The approach has been used to develop models to predict the fish toxicity of Pimephales promelas and Tetrahymena pyriformis, a protozoan.

Journal Article↗

PubMedDate not supplied

3D-QSAR and molecular mechanics study for the differences in the azole activity against yeastlike and filamentous fungi and their relation to P450DM inhibition. 1. 3-substituted-4(3H)-quinazolinones.

A combination between 3D-QSAR and molecular mechanics (MM)-docking study was used as a tool to detail and model the mechanism of action of 46 antifungal azoles. Two methods of alignment of the ligands were performed: (i) alignment of the main skeleton without substituents and (ii) alignment of a defined substructure. The best model is characterized by q(2) with the values of 0.70 for yeastlike (yeast), 0.66 for filamentous fungi, and 0.70 for the selectivity against filamentous fungi. 3D-QSAR regression maps derived from six models were used to identify the regions responsible for the differences in the compounds activity against yeast and filamentous fungi. The binding energy of the important substructures (Local Binding Energy-LBE) and its standard deviation were calculated in order to demonstrate quantitatively the contribution of substituents reflecting the diversity of the antifungal activity. The comparisons of these results with the same regions of the contour maps indicated a good correspondence between the 3D-QSAR and MM (LBE) approaches allowing association between the maps and the participating residues in the active sites of P450DM of C. albicans and A. fumigatus. The pi-pi interactions of two or more aromatic groups of the ligands with Phe228 and Tyr132 prove to be most important for the differences in activity against C. albicans. In A. fumigatus there was a better occupation of the inner central I-spiral in the areas around the heme. For the activity against A. fumigatus the pi-pi interactions of aromatic groups of the compounds with Phe509, Phe228, and Tyr132 are significant for the activity.

Azoles↗

PubMedDate not supplied

Thermodynamic descriptors derived from density functional theory calculations in prediction of aquatic toxicity.

Ab initio Density Functional Theory methods at the B3LYP/6-311+G(2d,p)//HF/3-21G(d) level in the gas and solvent phases (Conductor-like Polarizable Continuum Model) were used to calculate the thermodynamic and charge related descriptors including the first-order dissociation constant for a set of 53 substituted phenols. The absolute values of the pKa DFT descriptor showed significant deviations from the experimental values of dissociation constants, but the relative trends were well-described (R2=0.929, n=40). The descriptors were used for the design of predictive models for two aquatic species Pimephales promelas and Tetrahymena pyriformis. In both cases the best performing 2-descriptor models were based on the descriptors DeltaH298gas) and ClogP and showed good predictivity with R2=0.853, R2CV=0.834 for Pimephales and R2=0.864, R2CV=0.833 for Tetrahymena. The descriptors, models and the mode of action of the compounds are discussed.

Animals↗

PubMedDate not supplied

Description of the electronic structure of organic chemicals using semiempirical and ab initio methods for development of toxicological QSARs.

The quality of quantitative structure-activity relationship (QSAR) models depends on the quality of their constitutive elements including the biological activity, statistical procedure applied, and the physicochemical and structural descriptors. The aim of this study was to assess the comparative use of ab initio and semiempirical quantum chemical calculations for the development of toxicological QSARs applied to a large and chemically diverse data set. A heterogeneous collection of 568 organic compounds with 96 h acute toxicity measured to the fish fathead minnow (Pimephales promelas) was utilized. A total of 162 descriptors were calculated using the semiempirical AM1 Hamiltonian, and 121 descriptors were compiled using an ab initio (B3LYP/6-31G**) method. The QSARs were derived using multiple linear regression (MLR) and partial least squares (PLS) analyses. Statistically similar models were obtained using AM1 and B3LYP calculated descriptors supported by the use of the logarithm of the octanol-water partition coefficient (log K(ow)). The main difference between the models derived by both MLR and PLS with the two sets of quantum chemical descriptors was concentrated on the type of descriptors selected. It was concluded that for large-scale predictions, irrespective of the mechanism of toxic action, the use of precise but time-consuming ab initio methods does not offer considerable advantage compared to the semiempirical calculations and could be avoided.

Animals↗

PubMedDate not supplied

QSAR model for predicting pesticide aquatic toxicity.

A hierarchical QSAR approach was applied for the prediction of acute aquatic toxicity. Chemical structures were encoded into molecular descriptors by an automated, seamless procedure available within the OpenMolGRID system. Finally, various linear and nonlinear regression techniques were used to obtain stable and thoroughly validated QSARs. The final model was developed by a counterpropagation neural network coupled with genetic algorithms for variable selection. The proposed QSAR is consistent with McFarland's principle for biological activity and makes use of seven molecular descriptors, namely HACA-2, HOMO-LUMO energy gap, Kier and Hall index, HA dependent HDSA-1, BETA polarizability, FHBCA fractional HBSA, and LogP. The model was extensively tested by the test set (R2= 0.79), the y-scrambling test, and sensitivity/stability tests.

Algorithms↗

PubMedDate not supplied

ANVAS: artificial neural variables adaptation system for descriptor selection.

A new algorithm model-oriented for variable selection is presented in this study. It is based on the combination of genetic algorithms (GA) for hyperspace exploration, and counterpropagation artificial neural network (CP ANN) for deriving the fitness score. The proposed method performed very well on both well defined synthetic data sets and real academic data sets.

Algorithms↗