An ensemble model of QSAR tools for regulatory risk assessment

Abstract

Quantitative structure activity relationships (QSARs) are theoretical models that relate a quantitative measure of chemical structure to a physical property or a biological effect. QSAR predictions can be used for chemical risk assessment for protection of human and environmental health, which makes them interesting to regulators, especially in the absence of experimental data. For compatibility with regulatory use, QSAR models should be transparent, reproducible and optimized to minimize the number of false negatives. In silico QSAR tools are gaining wide acceptance as a faster alternative to otherwise time-consuming clinical and animal testing methods. However, different QSAR tools often make conflicting predictions for a given chemical and may also vary in their predictive performance across different chemical datasets. In a regulatory context, conflicting predictions raise interpretation, validation and adequacy concerns. To address these concerns, ensemble learning techniques in the machine learning paradigm can be used to integrate predictions from multiple tools. By leveraging various underlying QSAR algorithms and training datasets, the resulting consensus prediction should yield better overall predictive ability. We present a novel ensemble QSAR model using Bayesian classification. The model allows for varying a cut-off parameter that allows for a selection in the desirable trade-off between model sensitivity and specificity. The predictive performance of the ensemble model is compared with four in silico tools (Toxtree, Lazar, OECD Toolbox, and Danish QSAR) to predict carcinogenicity for a dataset of air toxins (332 chemicals) and a subset of the gold carcinogenic potency database (480 chemicals). Leave-one-out cross validation results show that the ensemble model achieves the best trade-off between sensitivity and specificity (accuracy: 83.8 % and 80.4 %, and balanced accuracy: 80.6 % and 80.8 %) and highest inter-rater agreement [kappa (κ): 0.63 and 0.62] for both the datasets. The ROC curves demonstrate the utility of the cut-off feature in the predictive ability of the ensemble model. This feature provides an additional control to the regulators in grading a chemical based on the severity of the toxic endpoint under study.Electronic supplementary materialThe online version of this article (doi:10.1186/s13321-016-0164-0) contains supplementary material, which is available to authorized users.

Decision tree models to classify nanomaterials according to theDF4nanoGroupingscheme

“…The first, sensitivity, measures the proportion of active nanomaterials that were correctly identified as such (Equation (2)). The second, specificity, defines the proportion of inactive nanomaterials that were correctly identified as such (Equation (3)) (Baldi et al 2000;Lever, Krzywinski, and Altman 2016;Pradeep et al 2016).…”

Mixtures of QSAR models: Learning application domains of pKpredicto rs

“…A ME model was formulated using local ANNs in order to recognise the adulteration of Italian wines . Moreover, multiple QSAR models were combined to enhance the predictive performance at various toxic endpoints, predict the biological activity of tyrosine kinase inhibitors, or predict skin penetration . Stochastic gradient boosting as a technique to build a sequence of models to combine their predictions and increase the performance of QSAR modelling was applied, and the results were analysed in ten cheminformatics data sets .…”

On the Virtues of Automated Quantitative Structure–Activity Relationship: The New Kid on the Block

“…Over half a century later and thousands of papers disclosing applications in numerous areas including medicinal chemistry, [3][4][5] environmental, [6][7][8][9] food, [10][11][12] and material [13][14][15][16] sciences, as well as regulatory [17][18][19] across academy, industry, and government, QSAR has proved an invaluable tool for experts and non-experts alike in identifying patterns in datasets and assisting in the process of making quantitative predictions [20][21]. In drug discovery, QSAR represents a ligand-based method, which generates models by building relationships between structural information or properties for a set of compounds and related experimental data of interest (e.g., biological activity) as the target property [22][23].…”