Development of a Battery of In Silico Prediction Tools for Drug-Induced Liver Injury from the Vantage Point of Translational Safety Assessment

Abstract

Drug-induced liver injury (DILI) remains a challenge when translating knowledge from the preclinical stage to human use cases. Attempts to model human DILI directly based on the information from drug labels have had some success; however, the approach falls short of providing insights or addressing uncertainty due to the difficulty of decoupling the idiosyncratic nature of human DILI outcomes. Our approach in this comparative analysis is to leverage existing preclinical and clinical data as well as information on metabolism to better translate mammalian to human DILI. The human DILI knowledge base from the United States Food and Drug Administration (U.S. FDA) National Center for Toxicology Research contains 1036 pharmaceuticals from diverse therapeutic categories. A human DILI training set of 305 oral marketed drugs was prepared and a binary classification scheme applied. The second knowledge base consists of mammalian repeated dose toxicity with liver toxicity data from various regulatory sources. Within this knowledge base, we identified 278 pharmaceuticals containing 198 marketed or withdrawn oral drugs with data from the U.S. FDA new drug application and 98 active pharmaceutical ingredients from ToxCast. From this collection, a set of 225 oral drugs was prepared as the mammalian hepatotoxicity training set with particular end points of pathology findings in the liver and bile duct. Both human and mammalian data sets were processed using various learning algorithms, including artificial intelligence approaches. The external validations for both models were comparable to the training statistics. These data sets were also used to extract species-differentiating chemotypes that differentiate DILI effects on humans from mammals. A systematic workflow was devised to predict human DILI and provide mechanistic insights. For a given query molecule, both human and mammalian models are run. If the predictions are discordant, both metabolites and parents are investigated for quantitative structure–activity relationship and species-differentiating chemotypes. Their results are combined using the Dempster–Shafer decision theory to yield a final outcome prediction for human DILI with estimated uncertainty. Finally, these tools are implementable within an in silico platform for systematic evaluation.

In silico approaches in organ toxicity hazard assessment: Current status and future needs in predicting liver toxicity

“…Several in silico models for potential use in predicting human hepatotoxicity from molecular structure have been described in the literature [145,[166][167][168][169][170]133,[171][172][173][174][175][176] including advanced modelling based on deep learning algorithms [177][178][179] and prediction models that combine structural descriptors and in vitro ToxCast assay data for the prediction of in vivo organ toxicity [180][181][182][183][184]. Different reviews have thoroughly summarized and discussed available models for this endpoint [126,133,[185][186][187][188][189][190].…”

A Robust, Mechanistically Based In Silico Structural Profiler for Hepatic Cholestasis

“…Selected chemotypes were drawn from those initially reported within Yang et al and further expanded by Rathman et al 30,31 Selectivity with respect to occurrence in cholestasis-positive compounds was quantified through determination of the Z-score, as derived in accordance with protocols described previously. 24,31 Identical analysis was performed upon a selection of 305 marketed pharmaceuticals positive for generalized DILI, sourced from Rathman et al and referred to henceforth as the "human DILI" set. 31 2.4.…”

“…24,31 Identical analysis was performed upon a selection of 305 marketed pharmaceuticals positive for generalized DILI, sourced from Rathman et al and referred to henceforth as the "human DILI" set. 31 2.4. Quantification of Structural Alert Performance and Selectivity.…”

“…ToxPrint chemotypes were generated using the publicly available ChemoTyper application (version 1.0; Molecular Networks, Erlangen, Germany) in order to detect building blocks which may be suitable in forming the basis of structural alerts. Selected chemotypes were drawn from those initially reported within Yang et al and further expanded by Rathman et al , Selectivity with respect to occurrence in cholestasis-positive compounds was quantified through determination of the Z -score, as derived in accordance with protocols described previously. , Identical analysis was performed upon a selection of 305 marketed pharmaceuticals positive for generalized DILI, sourced from Rathman et al and referred to henceforth as the “human DILI” set …”

Introduction to Special Issue: Computational Toxicology

“…Huang et al 30 proposed a property augmentation method with demonstration of significant improvement in DILI prediction by comparing baseline approaches. Rathman et al 31 constructed a knowledge base by leveraging existing preclinical and clinical data as well as information on metabolism to better translate mammalian to human DILI. Their results yielded a final outcome prediction for human DILI with estimated uncertainty and from which a tool could be implemented within an in silico system for systematic evaluation.…”