Predicting Hepatotoxicity Using ToxCastin VitroBioactivity and Chemical Structure

Abstract

The U.S. Tox21 and EPA ToxCast program screen thousands of environmental chemicals for bioactivity using hundreds of high-throughput in vitro assays to build predictive models of toxicity. We represented chemicals based on bioactivity and chemical structure descriptors, then used supervised machine learning to predict in vivo hepatotoxic effects. A set of 677 chemicals was represented by 711 in vitro bioactivity descriptors (from ToxCast assays), 4,376 chemical structure descriptors (from QikProp, OpenBabel, PaDEL, and PubChem), and three hepatotoxicity categories (from animal studies). Hepatotoxicants were defined by rat liver histopathology observed after chronic chemical testing and grouped into hypertrophy (161), injury (101) and proliferative lesions (99). Classifiers were built using six machine learning algorithms: linear discriminant analysis (LDA), Naïve Bayes (NB), support vector machines (SVM), classification and regression trees (CART), k-nearest neighbors (KNN), and an ensemble of these classifiers (ENSMB). Classifiers of hepatotoxicity were built using chemical structure descriptors, ToxCast bioactivity descriptors, and hybrid descriptors. Predictive performance was evaluated using 10-fold cross-validation testing and in-loop, filter-based, feature subset selection. Hybrid classifiers had the best balanced accuracy for predicting hypertrophy (0.84 ± 0.08), injury (0.80 ± 0.09), and proliferative lesions (0.80 ± 0.10). Though chemical and bioactivity classifiers had a similar balanced accuracy, the former were more sensitive, and the latter were more specific. CART, ENSMB, and SVM classifiers performed the best, and nuclear receptor activation and mitochondrial functions were frequently found in highly predictive classifiers of hepatotoxicity. ToxCast and ToxRefDB provide the largest and richest publicly available data sets for mining linkages between the in vitro bioactivity of environmental chemicals and their adverse histopathological outcomes. Our findings demonstrate the utility of high-throughput assays for characterizing rodent hepatotoxicants, the benefit of using hybrid representations that integrate bioactivity and chemical structure, and the need for objective evaluation of classification performance.

Co-culture of Hepatocytes and Kupffer Cells as an In Vitro Model of Inflammation and Drug-Induced Hepatotoxicity

“…Other compounds had unique direct or indirect effects on cytokine levels and metabolic capacity that appeared to reflect known in vitro and in vivo effects or modes of action. 29,37,42,43 Overall, these findings support the use of HKCCs, with proper medium formulation, as a valuable in vitro tool to evaluate and stratify compounds with hepatotoxic liability that would otherwise be overlooked using hepatocytes alone. Moreover, this novel approach can be extended to development of a human-based co-culture model to explore population diversity in innate immunity and its role in IDILI.…”

Molecular similarity-based predictions of the Tox21 screening outcome

“…models, support vector machines, random forests or ensembles of different classification methods can use the similarity defined the molecular structure and properties to make predictions for novel compounds. This concept has also been frequently and successfully applied to predictions of various toxicological endpoints (Drwal et al, 2014;Gadaleta et al, 2014;Li et al, 2014;Liu et al, 2015).…”

sNebula, a network-based algorithm to predict binding between human leukocyte antigens and peptides

“…Prediction confidence has been proposed as one of the metrics to measure performance of predictive models developed in the FDA’s endocrine disruptors knowledge based project6465666768697071 using variety of machine learning methods such as decision tree72, Decision Forest models737475767778 based on molecular descriptors79 that are calculated using the algorithm developed for the expert systems of structure elucidation808182838485, support vector machine8687 and principal component analysis based algorithm8889. The continuous value output from sNebula for prediction of binding between an HLA and a peptide is the measure of likelihood of the peptide is a binder or non-binder of the HLA and indicates the confidence for the prediction.…”