A novel approach to predict aquatic toxicity from molecular structure

The main aim of the study was to develop quantitative structure-activity relationship (QSAR) models for the prediction of aquatic toxicity using atom-based non-stochastic and stochastic linear indices. The used dataset consist of 392 benzene derivatives, separated into training and test sets, for which toxicity data to the ciliate Tetrahymena pyriformis were available. Using multiple linear regression, two statistically significant QSAR models were obtained with non-stochastic (R2=0.791 and s=0.344) and stochastic (R2=0.799 and s=0.343) linear indices. A leave-one-out (LOO) cross-validation procedure was carried out achieving values of q2=0.781 (scv=0.348) and q2=0.786 (scv=0.350), respectively. In addition, a validation through an external test set was performed, which yields significant values of Rpred2 of 0.762 and 0.797. A brief study of the influence of the statistical outliers in QSAR's model development was also carried out. Finally, our method was compared with other approaches implemented in the Dragon software achieving better results. The non-stochastic and stochastic linear indices appear to provide an interesting alternative to costly and time-consuming experiments for determining toxicity.     

Prediction of the adsorption capability onto activated carbon of a large data set of chemicals by local lazy regression method

Accurate quantitative structure–property relationship (QSPR) models based on a large data set containing a total of 3483 organic compounds were developed to predict chemicals’ adsorption capability onto activated carbon in gas phrase. Both global multiple linear regression (MLR) method and local lazy regression (LLR) method were used to develop QSPR models. The results proved that LLR has prediction accuracy 10% higher than that of MLR model. By applying LLR method we can predict the test set (787 compounds) with Q²_ext of 0.900 and root mean square error (RMSE) of 0.129. The accurate model based on this large data set could be useful to predict adsorption property of new compounds since such model covers a highly diverse structural space.     

QSPR study on soil sorption coefficient for persistent organic pollutants

Quantitative structure-property relationship (QSPR) models of soil sorption coefficients for 32 persistent organic pollutants were constructed using our recently introduced Lu index and novel distance-based atom-type DAI topological indices. Using multiple linear regression technique, a 6-variable model was obtained with the correlation coefficient of estimations (R) being 0.95, and the standard error of estimations (s) being 0.23, and the correlation coefficient (R(cv)) and the standard error (s(cv)) in the leave-4-out cross-validation procedure are 0.90 and 0.31, respectively. The results in this study indicate that soil sorption coefficients of POPs are dominated by molecular size while some DAI indices have smaller influence.     

Prediction of ozone concentrations in Oporto city with statistical approaches

The performance of three statistical methods: time-series, multiple linear regression and feedforward artificial neural networks models were compared to predict the daily mean ozone concentrations. The study here reported was based on data from one urban site with traffic influences and one rural background site. The studies were performed for the year 2002 and the respective four trimesters separately. In the multiple linear regression and feedforward artificial neural network models, the concentrations of ozone, the concentrations of its precursors (nitrogen oxides) and some meteorological variables for one and two days before the prediction day were used as predictors. For the application of these models in the validation step, the inputs of ozone concentration for one and two days before were replaced by the ozone concentrations predicted by the models. The results showed that time-series modelling was not profitable. In the development step, similar performances were obtained with multiple linear regression and feedforward artificial neural network. Better performance indexes were achieved with feedforward artificial neural network models in validation step. Concluding, feedforward artificial neural network models were more efficient to predict ozone concentrations.     

Classifying environmental pollutants: Part 3. External validation of the classification system

In order to validate a classification system for the prediction of the toxic effect concentrations of organic environmental pollutants to fish, all available fish acute toxicity data were retrieved from the ECETOC database, a database of quality-evaluated aquatic toxicity measurements created and maintained by the European Centre for the Ecotoxicology and Toxicology of Chemicals. The individual chemicals for which these data were available were classified according to the rulebase under consideration and predictions of effect concentrations or ranges of possible effect concentrations were generated. These predictions were compared to the actual toxicity data retrieved from the database. The results of this comparison show that generally, the classification system provides adequate predictions of either the aquatic toxicity (class 1) or the possible range of toxicity (other classes) of organic compounds. A slight underestimation of effect concentrations occurs for some highly water soluble, reactive chemicals with low log K(ow) values. On the other end of the scale, some compounds that are classified as belonging to a relatively toxic class appear to belong to the so-called baseline toxicity compounds. For some of these, additional classification rules are proposed. Furthermore, some groups of compounds cannot be classified, although they should be amenable to predictions. For these compounds additional research as to class membership and associated prediction rules is proposed.     

3D QSAR studies of dioxins and dioxin-like compounds using CoMFA and CoMSIA

In the present study we have performed comparative molecular field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMSIA) on structurally diverse ligands of Ah (dioxin) receptor to explore the physico-chemical requirements for binding. All CoMFA and CoMSIA models have given q(2) value of more than 0.5 and r(2) value of more than 0.84. The predictive ability of the models was validated by an external test set, which gave satisfactory predictive r(2) values. Best predictions were obtained with CoMFA model of combined modified training set (q(2) = 0.631, r(2) = 0.900), giving predictive residual value = 0.02 log unit for the test compound. Addition of CoMSIA study has elucidated the role of hydrophobicity and hydrogen bonding along with the effect of steric and electrostatic properties revealed by CoMFA. We have suggested a model comprises of four structurally different compounds, which offers a good predictability for various ligands. Our QSAR model is consistent with all previously established QSAR models with less structurally diverse ligands.     

A new hybrid system of QSAR models for predicting bioconcentration factors (BCF)

The aim was to develop a reliable and practical quantitative structure–activity relationship (QSAR) model validated by strict conditions for predicting bioconcentration factors (BCF). We built up several QSAR models starting from a large data set of 473 heterogeneous chemicals, based on multiple linear regression (MLR), radial basis function neural network (RBFNN) and support vector machine (SVM) methods. To improve the results, we also applied a hybrid model, which gave better prediction than single models. All models were statistically analysed using strict criteria, including an external test set. The outliers were also examined to understand better in which cases large errors were to be expected and to improve the predictive models. The models offer more robust tools for regulatory purposes, on the basis of the statistical results and the quality check on the input data.     

A new hybrid system of QSAR models for predicting bioconcentration factors (BCF)

The aim was to develop a reliable and practical quantitative structure-activity relationship (QSAR) model validated by strict conditions for predicting bioconcentration factors (BCF). We built up several QSAR models starting from a large data set of 473 heterogeneous chemicals, based on multiple linear regression (MLR), radial basis function neural network (RBFNN) and support vector machine (SVM) methods. To improve the results, we also applied a hybrid model, which gave better prediction than single models. All models were statistically analysed using strict criteria, including an external test set. The outliers were also examined to understand better in which cases large errors were to be expected and to improve the predictive models. The models offer more robust tools for regulatory purposes, on the basis of the statistical results and the quality check on the input data.     

Quantitative structure-activity relationships for the inhibition toxicity to root elongation of Cucumis sativus of selected phenols and interspecies correlation with Tetrahymena pyriformis

The comparative toxicities of selected phenols to higher plants Cucumis sativus were measured and the negative logarithm molar concentration of the root elongation median inhibition (IRC50) were derived. Quantitative structure-activity relationships (QSARs) were developed to explore the toxicity influencing factors and for predictive purpose. The toxicity data, fell into two classes: polar narcosis and bio-reactive. For polar narcotic phenols, a highly significant two-parameter QSAR based on 1-octanol/water partition coefficient (logKow) and energy of the lowest unoccupied orbital (E(lumo)) was derived (IRC50 = 0.77 log Kow - 0.39E(lumo) + 2.36 n = 22 r2 = 0.89). The five bio-reactive chemicals proved to show elevated toxicity due to their typical substructure involved diverse reactive mechanisms. In an effort to model all chemicals, a robust multiple-variable QSAR combining logKow, E(lumo) and Qmax, the most negative net atomic charge, was developed (IRC50 = 0.65 logKow - 0.72E(lumo) + 0.23Qmax + 2.81 n = 27 r2 = 0.94), indicating that hydrophobicity, electrophilicity and hydrogen bond interaction contribute mainly to the phytotoxicity. The toxicological data was compared with Tetrahymena pyriformis 2-d population growth inhibition toxicity (IGC50) and excellent interspecies correlations were observed both for the polar narcotics and for five reactive chemicals (for polar narcotics: IRC50 = 0.95IGC50 + 1.07 n = 16 r2 = 0.89; for bio-reactive chemicals: IRC50 = 0.98IGC50 + 2.19 n = 5 r2 = 0.97; and for all: IRC50 = 0.93IGC50 + 1.63 n = 21 r2 = 0.87). This suggested that T pyriformis toxicity could serve as a surrogate of C. sativus toxicity for phenols and interspecies correlation also could be established for reactive chemicals.     

Regression comparisons of Tetrahymena pyriformis and Poecilia reticulata toxicity

The toxicity data of chemicals common to both the Poecilia reticulata mortality assay and the Tetrahymena pyriformis growth impairment assay were evaluated. Two chemicals were not toxic at saturation in the T. pyriformis assay. In addition, due to abiotic transformation, a third chemical was removed from further consideration. Each chemical was a priori assigned a mode of toxic action: neutral non-covalent, polar non-covalent, or electrophilic covalent toxicity. To further investigate comparisons between endpoints, polar and electrophilic chemicals were separated into class-based groups. The polar non-covalent chemicals were separated into phenols and anilines, while the electrophilic chemicals were separated into those reacting via Schiff-base formation (i.e., aldehydes) and those reacting via bimolecular substitution to a nucleophile (i.e., selected nitroaromatics). A comparison of toxic potency as a collective set was statistically described by the relationship; log(LC50(-1)) = 1.05(log(IGC50(-1))) + 0.56, n = 124; r2 = 0.85; s = 0.42; F = 682; Pr > F = 0.0001. The relationship between endpoints was inversely proportional to reactivity associated with the mode of action. While the comparative toxicity for neutral narcotics exhibited an excellent fit (r2 = 0.94), the fits for polar narcotics and electrophiles were poorer, r2 = 0.69 and 0.62, respectively. Investigations into class-based groupings indicated fit of toxic potency data for aldehydes (r2 = 0.85) and phenols (r2 = 0.81) were quite good. However, fits for anilines (r2 = 0.43) and nitroaromatics (r2 = 0.68) revealed that toxicity was not as well related between endpoints for these chemicals.     

Neural network and multiple regression models for PM10 prediction in Athens: a comparative assessment

Particulate atmospheric pollution in urban areas is considered to have significant impact on human health. Therefore, the ability to make accurate predictions of particulate ambient concentrations is important to improve public awareness and air quality management. This study examines the possibility of using neural network methods as tools for daily average particulate matter with aerodynamic diameter <10 microm (PM10) concentration forecasting, providing an alternative to statistical models widely used up to this day. Based on a data inventory, in a fixed central site in Athens, Greece, ranging over a two-year period, and using mainly meteorological variables as inputs, neural network models and multiple linear regression models were developed and evaluated. Comparison statistics used indicate that the neural network approach has an edge over regression models, expressed both in terms of prediction error (root mean square error values lower by 8.2-9.4%) and of episodic prediction ability (false alarm rate values lower by 7-13%). The results demonstrate that artificial neural networks (ANNs), if properly trained and formed, can provide adequate solutions to particulate pollution prognostic demands.