Structure-toxicity Relationship Models Research Articles

Development of reliable quantitative structure-toxicity relationship models for toxicity prediction of benzene derivatives using semiempirical descriptors

: Health and environmental hazards by benzene and nitrobenzene derivatives has remained topic of interest of researchers. In silico methods for prediction of toxicity of chemicals have proved their worth in accurate forecast of environmental as well as health toxicity and are strongly recommended by regulatory authorities. Two quantitative structure-toxicity relationship models explaining Scenedesmus obliquus toxicity trends among 39 benzene derivatives and Tetrahymena pyriformis toxicity of 103 nitrobenzene and 392 benzene derivatives are developed using semiempirical quantum chemical parameters. The best constructed QSTR models have good fitting ability (R2 =0.8053, 0.7591, 0.8283) and robustness (Q2 LOO =0.7507, 0.7227, 0.8194; Q2 LMO =0.7338, 0.7153, 0.8172). The external predictivity of all the models are quite good (R2 EXT =0.8256, 0.9349, 0.8698). Electronegativity, Cosmo volume, total energy and molecular weight are responsible for increase and decrease of toxicity of benzene derivatives against Scenedesmus obliquus while electronegativity, electrophilicity index, heat of formation, total energy, hydrophobicity and cosmo volume are responsible for modulation of toxicity of nitrobenzene and benzene derivatives towards Tetrahymena pyriformis. These models fulfill the requirements of all the five OECD principles.

Development of in silico prediction models for drug-induced liver malignant tumors based on the activity of molecular initiating events: Biologically interpretable features.

Liver malignant tumors (LMTs) have recently been reported as severe and life-threatening adverse drug events associated with drug-induced liver injury (DILI). DILIs are the most common adverse drug event and can cause the withdrawal of medicinal products or major regulatory action. To reduce the attrition rate and cost of drug discovery, various quantitative structure-toxicity relationship models have been proposed to predict the probability of a DILI based on the chemical structure of a drug. However, there are many unresolved issues regarding the predictors of LMT-inducing drugs, and biologically interpretable prediction models for LMT have not been developed. Here, we constructed prediction models for whether a drug is LMT-inducing based on the activity of molecular initiating events (MIEs), which are biologically interpretable features and are defined as the initial interaction between a molecule and biosystem. We then constructed five machine learning models (i.e., LightGBM, XGBoost, random forest, neural network, and support vector machine) and evaluated their predictive performances. LightGBM achieved the best performance among the tested models. The MIEs making the highest contribution to the model construction for drug-induced LMT were inducement of Enhanced Level of Genome Instability Gene 1 (human ATAD5), nuclear factor-κ B, and activation of thyrotropin-releasing hormone receptor. These results support the previous literature and can be related to the mechanism onset of drug-induced LMT. Our findings may provide useful knowledge for drug development, research, and regulatory decision-making and will contribute to building more accurate and meaningful DILI prediction models by increasing understanding of biological predictors.

Norm index in QSTR work for predicting toxicity of ionic liquids on Vibrio fischeri

Ionic liquids have been becoming new ‘green solvent’ because of the low saturation vapor pressure, less volatilization and more recycling utilization. Since most ILs are soluble in water, it should be indispensable to evaluate the ecotoxicology effect of ILs on aquatic environment before using them widely. Based on the concept of norm index, a set of norm descriptors were proposed for anions, cations and ILs. The whole IL structure optimization method has been used to build a predictive norm index-based quantitative structure-toxicity relationship model for the toxicity of ILs on Vibrio fischeri. Statistical results indicated that norm descriptors were reliable and robust in expressing the relationship between structural information and toxicity of ILs. Meanwhile, a series of ILs without experimental values were predicted based on this stable QSTR model. The results indicated that for imidazole-based ILs, an increase in the length of substituent in the branch could enhance the toxicity of ILs on Vibrio fischeri, and the branch contains hydroxyl group, double bond or triple bonds might reduce the toxicity of ILs. Results obtained in this present work would be valuable for the molecular design and the toxicity evaluation toward aquatic organism of ILs.

Quantitative structure-toxicity relationship model for acute toxicity of organophosphates via multiple administration routes in rats and mice

Organophosphates (OPs) are highly toxic compounds, with widespread application in agricultural and chemical industries, whose introduction into the environment poses serious hazards to humans and ecological systems. To assess and ultimately mitigate these hazards, this study predicted the acute toxicity of OPs according to their chemical structure and administration route. The acute toxicity data of 161 OPs in two species via six different administration routes were manually collected and used to develop a series of quantitative structure–toxicity relationship (QSTR) models with robust and practical predictive abilities. The random forest algorithm was used to develop the models, employing both quantum chemical and two-dimensional descriptors according to OECD guidelines. Correlation results and feature similarities indicated that whereas acute toxicity data from rats and mice via the same administration route were combinable for modeling, data from different routes were not. Six QSTR models for each route in a single species and two QSTR models for a single route in the two species were constructed, achieving practical predictive performance. Despite significant variances in their datasets, the prediction models could predict the acute toxicity of novel or unknown OPs, realize rapid assessment, and provide guidance for regulatory decisions to reduce the hazards of OPs.

Predicting the acute neurotoxicity of diverse organic solvents using probabilistic neural networks based QSTR modeling approaches

Organic solvents are widely used chemicals and the neurotoxic properties of some are well established. In this study, we established nonlinear qualitative and quantitative structure-toxicity relationship (STR) models for predicting neurotoxic classes and neurotoxicity of structurally diverse solvents in rodent test species following OECD guideline principles for model development. Probabilistic neural network (PNN) based qualitative and generalized regression neural network (GRNN) based quantitative STR models were constructed using neurotoxicity data from rat and mouse studies. Further, interspecies correlation based quantitative activity–activity relationship (QAAR) and global QSTR models were also developed using the combined data set of both rodent species for predicting the neurotoxicity of solvents. The constructed models were validated through deriving several statistical coefficients for the test data and the prediction and generalization abilities of these models were evaluated. The qualitative STR models (rat and mouse) yielded classification accuracies of 92.86% in the test data sets, whereas, the quantitative STRs yielded correlation (R2) of >0.93 between the measured and model predicted toxicity values in both the test data (rat and mouse). The prediction accuracies of the QAAR (R2 0.859) and global STR (R2 0.945) models were comparable to those of the independent local STR models. The results suggest the ability of the developed QSTR models to reliably predict binary neurotoxicity classes and the endpoint neurotoxicities of the structurally diverse organic solvents.

QSTR with extended topochemical atom (ETA) indices. 13. Modelling of hERG K+ channel blocking activity of diverse functional drugs using different chemometric tools

To accelerate the drug discovery process, early prediction of human ether a-go-go (hERG) K+ channel affinity of drug candidates is becoming an important aspect. We have therefore developed quantitative structure–toxicity relationship models with extended topochemical atom (ETA) indices for hERG K+ channel blocking activity of diverse functional drugs using different chemometric tools like factor analysis followed by multiple linear regression (FA-MLR), stepwise regression and partial least squares. The data set was divided into a training set of 50 compounds and a test set of 17 compounds based on K-means clustering technique. The ETA models were compared with those developed with a pool of other topological indices. Finally, an attempt was made to develop models from the combined pool of topological (ETA and non-ETA) descriptors. It was found that on using ETA parameters along with non-ETA ones, there was a considerable increase in the quality of the models. The best model came from stepwise regression using a combined set of descriptors (Q 2 = 0.546, = 0.619). The ETA model suggests that hERG channel blocking increases with the increase of molecular bulk and electron richness and decreases with the increase of functionalities of the carboxylic acid group and the aliphatic tertiary nitrogen fragment.

In Silico Quantitative Structure–Toxicity Relationship Study of Aromatic Nitro Compounds

Small molecules often have toxicities that are a function of molecular structural features. Minor variations in structural features can make large difference in such toxicity. Consequently, in silico techniques may be used to correlate such molecular toxicities with their structural features. Relative to nine different sets of aromatic nitro compounds having known observed toxicities against different targets, we developed ligand-based 2D quantitative structure-toxicity relationship models using 20 selected topological descriptors. The topological descriptors have several advantages such as conformational independency, facile and less time-consuming computation to yield good results. Multiple linear regression analysis was used to correlate variations of toxicity with molecular properties. The information index on molecular size, lopping centric index and Kier flexibility index were identified as fundamental descriptors for different kinds of toxicity, and further showed that molecular size, branching and molecular flexibility might be particularly important factors in quantitative structure-toxicity relationship analysis. This study revealed that topological descriptor-guided quantitative structure-toxicity relationship provided a very useful, cost and time-efficient, in silico tool for describing small-molecule toxicities.

Development of structure-toxicity relationship models of chemicals with respect to Guppy

Classification models are constructed using various methods of multidimensional data analysis for the discrimination of compounds with respect to four possible models of action (MOA) on Guppy. Classification models are also obtained for the discrimination of chemicals with general toxicity MOA and with polar narcosis MOA with respect to all other chemicals. Regression models are generated for the description of the toxicity of chemicals with nonpolar and polar narcosis MOA. In particular, a good two-parameter model based on molecular polarizability and proton-acceptor ability of molecules is proposed. A difference between the mechanisms of polar narcosis MOA and general toxicity MOA is identified. The proposed classification and regression models for the description of toxicity of chemicals with reactive and specific MOA are considered as formalized and preliminary. These models can be further improved by providing a more detailed structure description using not only 2D but also 3D descriptors.

Prediction of mutagenic toxicity by combination of Recursive Partitioning and Support Vector Machines

The study of prediction of toxicity is very important and necessary because measurement of toxicity is typically time-consuming and expensive. In this paper, Recursive Partitioning (RP) method was used to select descriptors. RP and Support Vector Machines (SVM) were used to construct structure-toxicity relationship models, RP model and SVM model, respectively. The performances of the two models are different. The prediction accuracies of the RP model are 80.2% for mutagenic compounds in MDL's toxicity database, 83.4% for compounds in CMC and 84.9% for agrochemicals in in-house database respectively. Those of SVM model are 81.4%, 87.0% and 87.3% respectively.

Prediction of toxicity using a novel RBF neural network training methodology

A neural network methodology based on the radial basis function (RBF) architecture is introduced in order to establish quantitative structure-toxicity relationship models for the prediction of toxicity. The dataset used consists of 221 phenols and their corresponding toxicity values to Tetrahymena pyriformis. Physicochemical parameters and molecular descriptors are used to provide input information to the models. The performance and predictive abilities of the RBF models are compared to standard multiple linear regression (MLR) models. The leave-one-out cross validation procedure and validation through an external test set produce statistically significant R2 and RMS values for the RBF models, which prove considerably more accurate than the MLR models. [Figure: see text].

A quantitative structure-toxicity relationships model for the dermal sensitization guinea pig maximization assay

We have developed quantitative structure-toxicity relationship (QSTR) models for assessing dermal sensitization using guinea pig maximization test (GPMT) results. The models are derived from 315 carefully evaluated chemicals. There are two models, one for aromatics (excluding one-benzene-ring compounds), and the other for aliphatics and one-benzene-ring compounds. For sensitizers, the models can resolve whether they are weak/moderate or severe sensitizers. The statistical methodology, based on linear discriminant analysis, incorporates an optimum prediction space (OPS) algorithm. This algorithm ensures that the QSTR model will be used only to make predictions on query structures which fall within its domain. Calculation of the similarities between a query structure and the database compounds from which the applicable model was developed are used to validate each skin sensitization assessment. The cross-validated specificity of the equations ranges between 81 and 91%, and the sensitivity between 85 and 95%. For an independent test set, specificity is 79%, and sensitivity 82%.

Assessment of developmental toxicity potential of chemicals by quantitative structure-toxicity relationship models

Statistically significant quantitative structure-toxicity relationship (QSTR) models have been developed for assessing developmental toxicity potential (DTP) of chemicals. Three submodels, one each for aliphatic, heteroaromatic and carboaromatic compounds, have been cross-validated to ascertain their robustness. The specificities of the models range from 86% to 97%, and their sensitivities between 86% and 89%. For convenient computer-assisted application, the models are installed in a toxicity assessment software package, TOPKAT, which has been recently enhanced with algorithms to identify whether or not a query structure is inside the optimum prediction space (OPS) of a QSTR model. Different functionalities of the TOPKAT program have been explained by assessing the DTP of a number of compounds not used in the model training sets. The DTP of 18 existing drugs was assessed using these models; the DT assay results were available for 5 of these. Three of these 5 molecules were identified to be inside the OPS and their TOPKAT assessment matched their experimental assignment.