Polycyclic aromatic hydrocarbons (PAHs) and their halogenated derivatives (X-PAHs), which generally produced from photochemical and thermal reactions of parent PAHs, widely exist in the environment. They are semi-volatile organic chemicals (SVOCs) and the partitioning between gas/particulate phases affects their environmental migration, transformation and fate, which further impacts their toxicity and health risk to human. However, there is a large data missing of the experimental distribution ratio in the atmospheric particulate phase (f), especially for X-PAHs. In this study, we first checked the correlation between experimental f values of 53 PAH derivatives and their octanol-air partitioning coefficients (log KOA), which is frequently used to characterize the distribution of chemicals in organic phase, and yielded R2 = 0.803. Then, quantum chemical descriptors derived from molecular structural optimization by M06-2X/6-311 +G (d,p) method were further employed to develop Quantitative Structure-Property Relationship (QSPR) model. The model contains two descriptors, the average molecular polarizability (α) and the equilibrium parameter of molecular electrostatic potential (τ), and yields better performance with R2 = 0.846 and RMSE = 0.122. The mechanism analysis and validation results by different strategies prove that the model can reveal the molecular properties that dominate the distribution between gas and particulate phases and it can be used to predict f values of other PAHs/X-PAHs, providing basic data for their environmental ecological risk assessment.

Azo dyes are broadly used in different industries through their chemical stability and ease of synthesis. However, these dyes are usually identified as critical environmental pollutants. Hence, a mathematical model for the adsorption affinity of azo dyes can be applied for solving tasks of medicine and ecology. Quantitative structure-property relationships for the adsorption affinity of azo dyes to a substrate (DAF, kJ/mol) were established using the Monte Carlo method by generating optimal SMILES-based descriptors. The index of ideality of correlation (IIC) and the correlation intensity index (CII) improved the model\'s predictive potential, especially when they were used simultaneously. The statistical quality of the best model on the validation set was characterized by n = 18, r2 = 0.9468, and RMSE = 1.26 kJ/mol.

Any active substance with phytosanitary capacity intended to be marketed in Europe must pass exhaustive controls to assess its risk before being marketed and used in European agriculture. Since the implementation of Regulation (EC) No 1107/2009, agrochemical companies have been obliged to study the formation of pesticide transformation products (TPs) during the treatment of drinking water containing pesticide residues. However, there is no consensus on how to address this requirement. In this research work, the open literature collection on alloxydim was used to propose potential chlorination paths from alloxydim isomers. Furthermore, several QSAR/QSPR models have been used to fill the of knowledge gap relative to some key parameters in the physico-chemical, environmental and ecotoxicological areas of potential alloxydim TPs from chlorinated water for which little information exists. In this way, it has been possible to estimate the state of aggregation of these TPs (they exist mainly as liquids) as well as their ease of transit between the different phases, to predict their possible behaviour in the three environmental compartments (e.g., thermophysical properties point to a change in their evolution with respect to the parent alloxydim isomers) and to anticipate their potential risk to human and animal health (e.g., all of them cause developmental toxicity). These and other results highlight that the hazards of several TPs, i.e., both chlorinated and nonchlorinated from parent alloxydim or from those obtained after cleavage of the N - O bond and the subsequent reaction with chlorine, should be seriously considered. The obtained results reopen the debate on the implications of the use of QSAR/QSPR models for pesticide risk assessment in the legislative framework.

Commercial oleogelators rich in monoglycerides (MGs) are complex mixtures of acylglycerides with variable gelling properties, depending on the oil used and their concentration. In this study we developed a chemometric approach to identify the key parameters involved in gelling process. Analytical parameters have been defined, using GC and NMR analysis to identify fatty acids and acylglycerides composing the mixtures. Specific acylglyceride families and compound ratios were calculated to streamline the analytical results. To determine the key analytical parameters, artificial neural networks were used in a QSPR study related to the gelling properties measured by rheology through oscillatory experiments. At low oleogelator concentrations, the MGs especially rich in C16:0 and the ratio of specific isomers both have a positive influence on G\'. For high oleogelator concentrations, C18:0-rich acylglycerides and unsaturated/saturated fatty acid ratios have a positive influence on G\'. Conversely, at low concentrations, C18:0-rich acylglycerides show a lesser effect on G\'.

Predicting the activities and properties of materials via in silico methods has been shown to be a cost- and time-effective way of aiding chemists in synthesizing materials with desired properties. Refractive index (n) is one of the most important defining characteristics of an optical material. Presented in this work is a quantitative structure-property relationship (QSPR) model that was developed to predict the refractive index for a diverse set of polymers. A number of models were created, where a four-variable model showed the best predictive performance with R2 = 0.904 and Q2LOO = 0.897. The robustness and predictability of the best model was validated using the leave-one-out technique, external set and y-scrambling methods. The predictive ability of the model was confirmed with the external set, showing the R2ext = 0.880. For the refractive index, the ionization potential, polarizability, 2D and 3D geometrical descriptors were the most influential properties. The developed model was transparent and mechanistically explainable and can be used in the prediction of the refractive index for new and untested polymers.

OBJECTIVE: Sulfonamides (sulfa drugs) are compounds with a wide range of biological activities and they are the basis of several groups of drugs. Quantitative Structure-Property Relationship (QSPR) models are derived to predict the logarithm of water/ 1-octanol partition coefficients (logP) of sulfa drugs.
METHODS: A data set of 43 sulfa drugs was randomly divided into 3 groups: training, test and validation sets consisting of 70%, 15% and 15% of data point, respectively. A large number of molecular descriptors were calculated with Dragon software. The Genetic Algorithm - Multiple Linear Regressions (GA-MLR) and genetic algorithm -artificial neural network (GAANN) were employed to design the QSPR models. The possible molecular geometries of sulfa drugs were optimized at B3LYP/6-31G* level with Gaussian 98 software. The molecular descriptors derived from the Dragon software were used to build a predictive model for prediction logP of mentioned compounds. The Genetic Algorithm (GA) method was applied to select the most relevant molecular descriptors.
RESULTS: The R2 and MSE values of the MLR model were calculated to be 0.312 and 5.074 respectively. R2 coefficients were 0.9869, 0.9944 and 0.9601for the training, test and validation sets of the ANN model, respectively.
CONCLUSIONS: Comparison of the results revealed that the application the GA-ANN method gave better results than GA-MLR method.

BACKGROUND: In this study, we used a hierarchical approach to develop quantitative structure-activity relationship (QSAR) models for modeling physico-chemical properties of quinolone derivatives.
OBJECTIVE: The relationship between some of the molecular descriptors with physic-chemical properties such as refractive index (n), polarizability (α) and HOMO-LUMO energy gap (ΔEH-L) was represented.
METHODS: Quantum mechanical calculations using abinitio method at the #HF/6- 31++G** level were carried out to obtain the optimized geometry and then, the comprehensive set of molecular descriptors was computed by using the Dragon software. Genetic algorithm using multiple linear regression (GA-MLR) with backward method by SPSS software were utilized to construct QSAR models.
RESULTS: The analytical powers of the established theoretical models were discussed using leaveone- out (LOO) cross-validation technique. A multi-parametric equation containing maximum three descriptors with suitable statistical qualities was obtained for predicting the studied properties.
CONCLUSIONS: The QSPR analysis for the prediction of the refractive index, the polarizability and the HOMO-LUMO energy gap of 40 quinolone derivatives using GA-MLR method was performed. The achieved results showed that the best model for predicting the refractive index, the polarizability and the HOMO-LUMO energy gap contains maximum three descriptors. MLR analysis, using genetic algorithms as suitable descriptors selection method showed that the three selected descriptors play a vital role in the prediction of physicochemical properties of quinolone derivatives. It can be noted that the best descriptors in the final obtained models can be used to design and screen new drugs.

The partition coefficient is essential for the analysis of organic chemicals using solid-phase microextraction (SPME) techniques. In this study, a quantitative structure-property relationship (QSPR) model was developed with chemical descriptors for the prediction of the polyacrylate (PA)-water partition coefficient (KPA-w). The major variables influencing KPA-w in the QSPR model were CrippenlogP (crippen octanal-water partition coefficient), RNCG (relative negative charge-most negative charge/total negative charge), VE2_Dzv (average coefficient sum of the last eigenvector from the Barysz matrix/weighted by van der Waals volume), and ATSC4v (centred Broto-Moreau autocorrelation-lag 4/weighted by van der Waals volume). The relative determination coefficient (R2) and cross-validation coefficient (Q2) were 0.898 and 0.858, respectively, which implied that the model had excellent robustness. Mechanistic interpretation suggested that the factors affecting the partitioning process between PA and water are the hydrophobicity, relative negative charge, and van der Waals volume of a chemical. The results of this study provide a good tool for predicting the log KPA-w values of diverse hydrophobic organic compounds (HOCs) within the applicability domain to reduce experimental costs and the time required for innovation.

The acidity of Lewis-Brønsted superacids can be derived from the theoretical calculations as the Gibbs free energy of the deprotonation reaction (ΔGacid ), which describes the tendency of a studied compound to donate a proton. This paper presents the first Quantitative Structure - Property Relationship (QSPR) model that correlates the ΔGacid of superacid (HF/MeX3 formula (X=F, Cl, Br)) with their structure. Developed model is well fitted, roubustness, has good predictive abilities, fulfills all OECD recommendation for good model. Obtained results provide the insight into the relation of structural features of superacids, which are responsible for their acid strength - the structures characterized by strong F-Me dative bond (with relatively large vibrational frequency), small positive partial atomic charge on Me central atom, possibly large polarity exhibit large acid strength. Such assumption can be used in the future as valuable information in the process of the designing new, stronger, more effective superacids.

Artificial neural network (ANN) is one of the most widely used methods to develop accurate predictive models based on artificial intelligence and machine learning. In the present study, the important practical aspects of developing a reliable ANN model e.g. appropriate assignment of the number of neurons, number of hidden layers, transfer function, training algorithm, dataset division and initialization of the network are discussed. As a case study, predictability of the flash point for a dataset of 740 organic compounds using ANNs was investigated via a total number of 484220ANNs to allow covering a wide range of parameters affecting the performance of an ANN. Among all studied parameters, the number of neurons or layers was found to be the most important parameters to develop a reliable ANN with low overfitting risk. To evaluate appropriate number of neurons and layers, a value of equal or greater than 10 for the ratio of the training samples to the ANN constants was suggested as a rule of thumb. More ever, a strategy for evaluation of the authentic performance of ANNs and deciding about the reliability of an ANN model was proposed which is applicable to other models developed by supervised learning. Based on the introduced considerations, an ANN model was proposed for predicting the flash point of pure organic compounds. According to the results, the new model was found to produce the lowest error compared to other available models.