Ester Papa

QSARINS: A new software for the development, analysis and validation of QSAR MLR models

QSARINS (QSAR‐INSUBRIA) is a new software for the development and validation of multiple linear regression Quantitative Structure‐Activity Relationship (QSAR) models by Ordinary Least Squares method and Genetic Algorithm for variable selection. This program is mainly focused on the external validation of QSAR models. Various tools for explorative analysis of the datasets by Principal Component Analysis, prereduction of input molecular descriptors, splitting of datasets in training and prediction sets, detection of outliers and interpolated or extrapolated predictions, internal and external validation by different parameters, consensus modeling and various plots for visualizations are implemented. QSARINS is a user‐friendly platform for QSAR modeling in agreement with the OECD Principles and for the analysis of the reliability of the obtained predicted data. The Insubria Persistent Bioaccumulative and Toxic (PBT) Index model for the prediction of the cumulative behavior of new chemicals as PBTs is implemented. Additionally, QSARINS allows the user to validate single models, predeveloped using also different software.

Combinatorial QSAR Modeling of Chemical Toxicants Tested against Tetrahymena pyriformis

Selecting most rigorous quantitative structure-activity relationship (QSAR) approaches is of great importance in the development of robust and predictive models of chemical toxicity. To address this issue in a systematic way, we have formed an international virtual collaboratory consisting of six independent groups with shared interests in computational chemical toxicology. We have compiled an aqueous toxicity data set containing 983 unique compounds tested in the same laboratory over a decade against Tetrahymena pyriformis. A modeling set including 644 compounds was selected randomly from the original set and distributed to all groups that used their own QSAR tools for model development. The remaining 339 compounds in the original set (external set I) as well as 110 additional compounds (external set II) published recently by the same laboratory (after this computational study was already in progress) were used as two independent validation sets to assess the external predictive power of individual models. In total, our virtual collaboratory has developed 15 different types of QSAR models of aquatic toxicity for the training set. The internal prediction accuracy for the modeling set ranged from 0.76 to 0.93 as measured by the leave-one-out cross-validation correlation coefficient ( Q abs2). The prediction accuracy for the external validation sets I and II ranged from 0.71 to 0.85 (linear regression coefficient R absI2) and from 0.38 to 0.83 (linear regression coefficient R absII2), respectively. The use of an applicability domain threshold implemented in most models generally improved the external prediction accuracy but at the same time led to a decrease in chemical space coverage. Finally, several consensus models were developed by averaging the predicted aquatic toxicity for every compound using all 15 models, with or without taking into account their respective applicability domains. We find that consensus models afford higher prediction accuracy for the external validation data sets with the highest space coverage as compared to individual constituent models. Our studies prove the power of a collaborative and consensual approach to QSAR model development. The best validated models of aquatic toxicity developed by our collaboratory (both individual and consensus) can be used as reliable computational predictors of aquatic toxicity and are available from any of the participating laboratories.

Validated QSAR Prediction of OH Tropospheric Degradation of VOCs: Splitting into Training−Test Sets and Consensus Modeling

The rate constant for hydroxyl radical tropospheric degradation of 460 heterogeneous organic compounds is predicted by QSAR modeling. The applied Multiple Linear Regression is based on a variety of theoretical molecular descriptors, selected by the Genetic Algorithms-Variable Subset Selection (GA-VSS) procedure. The models were validated for predictivity by both internal and external validation. For the external validation two splitting approaches, D-optimal Experimental Design and Kohonen Artificial Neural Networks (K-ANN), were applied to the original data set to compare the two methodologies. We emphasize that external validation is the only way to establish a reliable QSAR model for predictive purposes. Predicted data by consensus modeling from different models are also proposed.

Statistically Validated QSARs, Based on Theoretical Descriptors, for Modeling Aquatic Toxicity of Organic Chemicals in Pimephales promelas (Fathead Minnow)

The use of Quantitative Structure-Activity Relationships in assessing the potential negative effects of chemicals plays an important role in ecotoxicology. (LC50)(96h) in Pimephales promelas (Duluth database) is widely modeled as an aquatic toxicity end-point. The object of this study was to compare different molecular descriptors in the development of new statistically validated QSAR models to predict the aquatic toxicity of chemicals classified according to their MOA and in a unique general model. The applied multiple linear regression approach (ordinary least squares) is based on theoretical molecular descriptor variety (1D, 2D, and 3D, from DRAGON package, and some calculated logP). The best combination of modeling descriptors was selected by the Genetic Algorithm-Variable Subset Selection procedure. The robustness and the predictive performance of the proposed models was verified using both internal (cross-validation by LOO, bootstrap, Y-scrambling) and external statistical validations (by splitting the original data set into training and validation sets by Kohonen-artificial neural networks (K-ANN)). The model applicability domain (AD) was checked by the leverage approach to verify prediction reliability.

QSAR Modeling is not “Push a Button and Find a Correlation”: A Case Study of Toxicity of (Benzo-)triazoles on Algae

A case study of toxicity of (benzo)triazoles ((B)TAZs) to the algae Pseudokirchneriella subcapitata is used to discuss some problems and solutions in QSAR modeling, particularly in the environmental context. The relevance of data curation (not only of experimental data, but also of chemical structures and input formats for the calculation of molecular descriptors), the crucial points of QSAR model validation and the potential application for new chemicals (internal robustness, exclusion of chance correlation, external predictivity, applicability domain) are described, while developing MLR‐OLS models based on molecular descriptors, calculated by various QSAR software tools (commercial DRAGON, free PaDEL‐Descriptor and QSPR‐THESAURUS). Additionally, the utility of consensus models is highlighted. This work summarizes a methodology for a rigorous statistical approach to obtain reliable QSAR predictions, also for a large number of (B)TAZs in the ECHA preregistration list of REACH (even if starting from limited experimental data availability), and has evidenced some ambiguities and discrepancies related to SMILES notations from different databases; furthermore it highlighted some general problems related to QSAR model generation and was useful in the implementation of the PaDEL‐Descriptor software.

Daphnia and fish toxicity of (benzo)triazoles: Validated QSAR models, and interspecies quantitative activity–activity modelling

Due to their chemical properties synthetic triazoles and benzo-triazoles ((B)TAZs) are mainly distributed to the water compartments in the environment, and because of their wide use the potential effects on aquatic organisms are cause of concern. Non testing approaches like those based on quantitative structure-activity relationships (QSARs) are valuable tools to maximize the information contained in existing experimental data and predict missing information while minimizing animal testing. In the present study, externally validated QSAR models for the prediction of acute (B)TAZs toxicity in Daphnia magna and Oncorhynchus mykiss have been developed according to the principles for the validation of QSARs and their acceptability for regulatory purposes, proposed by the Organization for Economic Co-operation and Development (OECD). These models are based on theoretical molecular descriptors, and are statistically robust, externally predictive and characterized by a verifiable structural applicability domain. They have been applied to predict acute toxicity for over 300 (B)TAZs without experimental data, many of which are in the pre-registration list of the REACH regulation. Additionally, a model based on quantitative activity-activity relationships (QAAR) has been developed, which allows for interspecies extrapolation from daphnids to fish. The importance of QSAR/QAAR, especially when dealing with specific chemical classes like (B)TAZs, for screening and prioritization of pollutants under REACH, has been highlighted.

QSAR classification models for the prediction of endocrine disrupting activity of brominated flame retardants.

The identification of potential endocrine disrupting (ED) chemicals is an important task for the scientific community due to their diffusion in the environment; the production and use of such compounds will be strictly regulated through the authorization process of the REACH regulation. To overcome the problem of insufficient experimental data, the quantitative structure-activity relationship (QSAR) approach is applied to predict the ED activity of new chemicals. In the present study QSAR classification models are developed, according to the OECD principles, to predict the ED potency for a class of emerging ubiquitary pollutants, viz. brominated flame retardants (BFRs). Different endpoints related to ED activity (i.e. aryl hydrocarbon receptor agonism and antagonism, estrogen receptor agonism and antagonism, androgen and progesterone receptor antagonism, T4-TTR competition, E2SULT inhibition) are modeled using the k-NN classification method. The best models are selected by maximizing the sensitivity and external predictive ability. We propose simple QSARs (based on few descriptors) characterized by internal stability, good predictive power and with a verified applicability domain. These models are simple tools that are applicable to screen BFRs in relation to their ED activity, and also to design safer alternatives, in agreement with the requirements of REACH regulation at the authorization step.

QSPR as a support for the EU REACH regulation and rational design of environmentally safer chemicals: PBT identification from molecular structure†

The chemicals that are jointly Persistent, Bioaccumulative and Toxic (PBT) are substances of very high concern (SVHC) and subject to an authorization step in the new European REACH regulation, which includes plans for safer substitutions of recognized hazardous compounds. The limited availability of experimental data necessary for the hazard/risk assessment of chemicals and the expected high costs have increased the interest, also in REACH, for alternative predictive in silico methods, such as Quantitative Structure–Activity (Property) Relationships (QSA(P)Rs). A structurally-based approach is proposed here for a holistic screening of potential PBTs in the environment. Persistence, bioconcentration and toxicity data available for a set of 180 organic chemicals, some of which are known PBTs, have been combined in a multivariate approach by Principal Component Analysis. This method is applied to rank the studied compounds according to their cumulative PBT behaviour; this ranking can be defined as a PBT Index. A simple, robust and externally predictive QSPR multiple linear regression model (MLR), which is based on four molecular descriptors, has been developed for the PBT Index. This QSPR model is proposed as a hazard screening tool, applicable also by regulators, for the early identification and prioritization of not yet known PBTs, only on the basis of the knowledge of their molecular structure. New, safer chemicals can be designed as alternatives to hazardous PBT chemicals by applying the proposed QSPR model, according to the green chemistry philosophy of “benign by design”. A consensus approach is also proposed from the comparison of the results obtained by different screening methods.

Predicting the NO3 radical tropospheric degradability of organic pollutants by theoretical molecular descriptors

Abstract The rate constant for the nighttime degradation of 114 heterogeneous organic compounds, through reaction with nitrate radicals in the troposphere, is predicted here by quantitative structure–activity relationships modelling. The multiple linear regression approach is based on a variety of theoretical molecular descriptors, selected by the genetic algorithms-variable subset selection procedure. The proposed model, calculated on a limited subset of compounds selected by a D-optimal experimental design and checked for reliability and robustness, has good predictivity, verified by internal (QLMO2=89.6%) and “external” validation (QEXT2=95.7%). The model applicability domain was always verified by the leverage approach in order to propose reliable predicted data. The average root-mean square error for the prediction of log k NO3 was 0.57, similar to (and even smaller than) the typical experimental error range.

QSAR Modeling and Prediction of the Endocrine-Disrupting Potencies of Brominated Flame Retardants

In the European Union REACH regulation, the chemicals with particularly harmful behaviors, such as endocrine disruptors (EDs), are subject to authorization, and the identification of safer alternatives to these chemicals is required. In this context, the use of quantitative structure-activity relationships (QSAR) becomes particularly useful to fill the data gap due to the very small number of experimental data available to characterize the environmental and toxicological profiles of new and emerging pollutants with ED behavior such as brominated flame retardants (BFRs). In this study, different QSAR models were developed on different responses of endocrine disruption measured for several BFRs. The multiple linear regression approach was applied to a variety of theoretical molecular descriptors, and the best models, which were identified from all of the possible combinations of the structural variables, were internally validated for their performance using the leave-one-out (Q(LOO)(2) = 73-91%) procedure and scrambling of the responses. External validation was provided, when possible, by splitting the data sets in training and test sets (range of Q(EXT)(2) = 76-90%), which confirmed the predictive ability of the proposed equations. These models, which were developed according to the principles defined by the Organization for Economic Co-operation and Development to improve the regulatory acceptance of QSARs, represent a simple tool for the screening and characterization of BFRs.