Merck
  • Home
  • Search Results
  • A predictive ligand-based Bayesian model for human drug-induced liver injury.

A predictive ligand-based Bayesian model for human drug-induced liver injury.

Drug metabolism and disposition: the biological fate of chemicals (2010-09-17)
Sean Ekins, Antony J Williams, Jinghai J Xu
ABSTRACT

Drug-induced liver injury (DILI) is one of the most important reasons for drug development failure at both preapproval and postapproval 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, a 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 results for internal validation. The Bayesian model with extended connectivity functional class fingerprints of maximum diameter 6 (ECFC_6) 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 Smiles Arbitrary Target Specification (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, such as the Abbott alerts, which captures thiol traps and other compounds, may be of use 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 cost-effective selection criteria before in vitro or in vivo experimental studies.

MATERIALS
Product Number
Brand
Product Description

Sigma-Aldrich
Hydrazine solution, 1.0 M in ethanol
Sigma-Aldrich
1,2-Dichloroethane, suitable for HPLC, ≥99.8%
Supelco
Oxibendazole, VETRANAL®, analytical standard
Supelco
Betamethasone, VETRANAL®, analytical standard
Supelco
Melting point standard 235-237°C, analytical standard
Aflatoxin B1 solution, 3.79 μg/g in acetonitrile, ERM®, certified reference material
Supelco
Temozolomide, VETRANAL®, analytical standard
Sigma-Aldrich
Temozolomide, ≥98% (HPLC)
Sigma-Aldrich
13-cis-Retinoic acid, ≥98% (HPLC)
Sigma-Aldrich
Folic acid, meets USP testing specifications
Sigma-Aldrich
Amoxicillin, 95.0-102.0% anhydrous basis
Sigma-Aldrich
Acetylcholine chloride, ≥99% (TLC)
Sigma-Aldrich
Folic acid, BioReagent, suitable for cell culture, suitable for insect cell culture, suitable for plant cell culture, ≥97%
Sigma-Aldrich
Folic acid, ≥97%
Sigma-Aldrich
Ergocalciferol, 40,000,000 USP units/g
Sigma-Aldrich
Acetylcholine chloride, suitable for cell culture
Sigma-Aldrich
L-Arginine, from non-animal source, meets EP, USP testing specifications, suitable for cell culture, 98.5-101.0%
Sigma-Aldrich
(+)-Pseudoephedrine hydrochloride, ≥98%
Sigma-Aldrich
Rotenone, ≥95%
Sigma-Aldrich
L-Arginine, reagent grade, ≥98%
Sigma-Aldrich
Nalidixic acid, ≥98%
Sigma-Aldrich
Menadione, crystalline
Sigma-Aldrich
Menadione, meets USP testing specifications
Sigma-Aldrich
Clotrimazole
Sigma-Aldrich
Betamethasone, ≥98%
Sigma-Aldrich
Estradiol, meets USP testing specifications
Supelco
Busulfan, analytical standard, for drug analysis
Sigma-Aldrich
Caffeine, meets USP testing specifications, anhydrous
Sigma-Aldrich
Caffeine, BioXtra
Sigma-Aldrich
Valproic acid sodium salt, 98%