TY - JOUR T1 - A PREDICTIVE LIGAND-BASED BAYESIAN MODEL FOR HUMAN DRUG INDUCED LIVER INJURY JF - Drug Metabolism and Disposition JO - Drug Metab Dispos DO - 10.1124/dmd.110.035113 SP - dmd.110.035113 AU - Sean Ekins AU - Antony J Williams AU - Jinghai J Xu Y1 - 2010/09/15 UR - http://dmd.aspetjournals.org/content/early/2010/09/15/dmd.110.035113.abstract N2 - Drug-induced liver injury (DILI) is one of the most important reasons for drug development failure at both pre-approval and post-approval stages. There has been increased interest in developing predictive in vivo, in vitro and in silico models to identify compounds that cause idiosyncratic hepatotoxicity. In the current study we applied machine learning, Bayesian modeling method with extended connectivity fingerprints and other interpretable descriptors. The model that was developed and internally validated (using a training set of 295 compounds) was then applied to a large test set relative to the training set (237 compounds) for external validation. The resulting concordance of 60%, sensitivity of 56%, and specificity of 67% were comparable to internal validation. The Bayesian model with ECFC_6 fingerprint and interpretable descriptors suggested several substructures that are chemically reactive and may also be important for DILI-causing compounds, e.g. ketones, diols and α-methyl styrene type structures. Using SMARTS filters published by several pharmaceutical companies we evaluated whether such reactive substructures could be readily detected by any of the published filters. It was apparent that the most stringent filters used in this study, like the Abbott alerts which captures thiol traps and other compounds, may be of utility in identifying DILI-causing compounds (sensitivity 67%). A significant outcome of the present study is that we provide predictions for many compounds that cause DILI by using the knowledge we have available from previous studies. These computational models may represent a cost effective selection criteria prior to in vitro or in vivo experimental studies. ER -