Combining In Vivo Data with In Silico Predictions for Modeling Hepatic Steatosis by Using Stratified Bagging and Conformal Prediction
Open Access
- 21 December 2020
- journal article
- research article
- Published by American Chemical Society (ACS) in Chemical Research in Toxicology
- Vol. 34 (2) , 656-668
Abstract
Hepatic steatosis (fatty liver) is a severe liver disease induced by the excessive accumulation of fatty acids in hepatocytes. In this study, we developed reliable in silico models for predicting hepatic steatosis on the basis of an in vivo data set of 1041 compounds measured in rodent studies with repeated oral exposure. The imbalanced nature of the data set (1:8, with the “steatotic” compounds belonging to the minority class) required the use of meta-classifiers—bagging with stratified under-sampling and Mondrian conformal prediction—on top of the base classifier random forest. One major goal was the investigation of the influence of different descriptor combinations on model performance (tested by predicting an external validation set): physicochemical descriptors (RDKit), ToxPrint features, as well as predictions from in silico nuclear receptor and transporter models. All models based upon descriptor combinations including physicochemical features led to reasonable balanced accuracies (BAs between 0.65 and 0.69 for the respective models). Combining physicochemical features with transporter predictions and further with ToxPrint features gave the best performing model (BAs up to 0.7 and efficiencies of 0.82). Whereas both meta-classifiers proved useful for this highly imbalanced toxicity data set, the conformal prediction framework also guarantees the error level and thus might be favored for future studies in the field of predictive toxicology.Keywords
Funding Information
- Austrian Science Fund (P 29712, W1232)
- H2020 Research Infrastructures (681002)
This publication has 39 references indexed in Scilit:
- Drug-Induced SteatohepatitisClinics in Liver Disease, 2013
- Development of Dimethyl Sulfoxide Solubility Models Using 163 000 Molecules: Using a Domain Applicability Metric to Select More Reliable PredictionsJournal of Chemical Information and Modeling, 2013
- Quantifying the chemical beauty of drugsNature Chemistry, 2012
- Molecular Mechanisms and Therapeutic Targets in Steatosis and SteatohepatitisPharmacological Reviews, 2008
- KNIME: The Konstanz Information Miner2008
- Glutathione‐dependent Bioactivation of Haloalkanes and HaloalkenesDrug Metabolism Reviews, 2004
- Transcriptional regulation of ABC drug transportersOncogene, 2003
- Impaired mitochondrial function in microvesicular steatosis effects of drugs, ethanol, hormones and cytokinesJournal of Hepatology, 1997
- The Properties of Known Drugs. 1. Molecular FrameworksJournal of Medicinal Chemistry, 1996
- Inhibition of mitochondrial beta-oxidation as a mechanism of hepatotoxicityPharmacology & Therapeutics, 1995