You are here:
Integrating Biological and Chemical Data for Hepatotoxicity Prediction (SOT)
Citation:
Liu, J., K. Mansouri, R. Judson, M. Martin, H. Hong, M. Chen, X. Xu, R. Thomas, AND I. Shah. Integrating Biological and Chemical Data for Hepatotoxicity Prediction (SOT). Presented at SOT Annual Meeting, San Diego, CA, March 22 - 26, 2015. https://doi.org/10.23645/epacomptox.5178859
Impact/Purpose:
poster presented at SOT annual meeting in San Diego, CA on March 24, 2015
Description:
The U.S. EPA ToxCastTM program is screening thousands of environmental chemicals for bioactivity using hundreds of high-throughput in vitro assays to build predictive models of toxicity. A set of 677 chemicals were represented by 711 bioactivity descriptors (from ToxCast assays), 4,376 chemical structure descriptors, and three hepatotoxicity categories (from animal studies), then used supervised machine learning to predict their hepatotoxic effects. 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 classifiers (ENSMB). Classifiers of hepatotoxicity were built using chemical structure, ToxCast bioactivity, and a hybrid representation. 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 (0.78±0.08), injury (0.73±0.10) and proliferative lesions (0.72±0.09). 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 provides the largest and richest data set 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. This abstract does not represent EPA and FDA policy.
