Extended molecular connectivity: Prediction of boiling points of alkanes

It is shown that extended molecular connectivity may be used for “structure-property” studies. The statistical parameters of the correlation relations of boiling points with extended molecular connectivity indices found for a sample of alkanes (n = 74) are the following: the best two-parameter correlation r = 0.9948, s = 4.7; the best three-parameter correlation r = 0.9971, s = 3.5. Translated fromZhurnal Strukturnoi Khimii, Vol. 38, No. 6, pp. 1154–1159, November–December, 1997.     

The index of ideality of correlation: improvement of models for toxicity to algae

Toxicity to algae is important characteristic of substances from ecologic point of view. The CORAL software (http://www.insilico.eu/coral) gives possibility to build up model of toxicity to algae using data on the molecular architecture and experimental toxicity, without additional data on physicochemical and/or biochemical parameters. Considerable improvement of the model is observed in the case of using the index of ideality of correlation (IIC) in the role of additional criterion of predictive potential. The IIC is calculated with using of the correlation coefficient between experimental and calculated values of endpoint for the calibration set, with taking into account the positive and negative dispersions between experimental and calculated values. The best model calculated with use the IIC is characterized (the validation set) by n?=?50, r²?=?0.947, RMSE?=?0.401 whereas, model calculated without use the IIC is characterized by n?=?50, r²?=?0.805, and RMSE?=?0.539. The suggested models are built up in accordance to five OECD principles.

     

QSAR models for biocides: The example of the prediction of Daphnia magna acute toxicity

ABSTRACT

Biocides are multi-component products used to control undesired and harmful organisms able to affect human or animal health or to damage natural and manufactured products. Because of their widespread use, aquatic and terrestrial ecosystems could be contaminated by biocides. The environmental impact of biocides is evaluated through eco-toxicological studies with model organisms of terrestrial and aquatic ecosystems. We focused on the development of in silico models for the evaluation of the acute toxicity (EC₅₀) of a set of biocides collected from different sources on the freshwater crustacean Daphnia magna, one of the most widely used model organisms in aquatic toxicology. Toxicological data specific for biocides are limited, so we developed three models for daphnid toxicity using different strategies (linear regression, random forest, Monte Carlo (CORAL)) to overcome this limitation. All models gave satisfactory results in our datasets: the random forest model showed the best results with a determination coefficient r² = 0.97 and 0.89, respectively, for the training (TS) and the validation sets (VS) while linear regression model and the CORAL model had similar but lower performance (r² = 0.83 and 0.75, respectively, for TS and VS in the linear regression model and r² = 0.74 and 0.75 for the CORAL model).     

QSPR Modeling of Gibbs Free Energy of Organic Compounds by Weighting of Nearest Neighboring Codes

We examine the encoding of chemical structure of organic compounds by Labeled Hydrogen-Filled Graphs (LHFGs). Quantitative Structure-Property Relationships (QSPR) for a representative set of 150 organic molecules have been derived by means of the optimization of correlation weights of local invariants of the LHFGs. We have tested as local invariants Morgan extended connectivity of zero- and first order, numbers of path of length 2 (P2) and valence shells of distance of 2 (S2) associated with each atom in the molecular structure, and the Nearest Neighboring Codes (NNC). The best statistical characteristics for the Gibbs free energy has been obtained for the NNC weighting. Statistical parameters corresponding to this model are the following n = 100, r² = 0.9974, s = 5.136 kJ/mol, F = 38319 (training set); n = 50, r² = 0.9990, s = 3.405 kJ/mol, F = 48717 (test set). Some possible further developments are pointed out.     

Towards predicting the solubility of CO2 and N2 in different polymers using a quasi-SMILES based QSPR approach

The solubility of gases in various polymers plays an important role for the design of new polymeric materials. Quantitative structure–property relationship (QSPR) models were designed to predict the solubility of gases such as CO₂ and N₂ in polyethylene (PE), polypropylene (PP), polystyrene (PS), polyvinyl acetate (PVA) and poly (butylene succinate) (PBS) at different temperatures and pressures by using quasi-SMILES codes. The dataset of 315 systems was split randomly into training, calibration and validation sets; random split 1 led to 214 training (r² = 0.870 and RMSE = 0.019), 51 calibration (r² = 0.858 and RMSE = 0.020) and 50 validation (r² = 0.869 and RMSE = 0.017) sets. The suggested approach based on the quasi-SMILES, which are analogues of the traditional SMILES gives reasonable good predictions for solubility of CO₂ and N₂ in different polymers. The described methodology is universal for situations where the aim is to predict the response of an eclectic system upon a variety of physicochemical and/or biochemical conditions.     

Idealization of correlations between optimal simplified molecular input-line entry system-based descriptors and skin sensitization

The Index of Ideality of Correlation (IIC) is a new criterion of the predictive potential for quantitative structure–property/activity relationships. The value of the IIC is a mathematical function sensitive to the value of the correlation coefficient and dispersion (expressed via mean absolute error). The IIC has been applied to develop QSAR models for skin sensitization achieving good predictive potential. The ‘ideal correlation’ is based on elementary fragments of simplified molecular input-line entry system (SMILES) and on the taking into account of the total numbers of nitrogen, oxygen, sulphur and phosphorus in the molecule.