Toward predictive models for drug-induced liver injury in humans: are we there yet?

Artificial Intelligence: An Emerging Tool for Studying Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is a complex and potentially severe adverse reaction to drugs, herbal products or dietary supplements. DILI can mimic other liver diseases clinical presentation, and currently lacks specific diagnostic biomarkers, which hinders its diagnosis. In some cases, DILI may progress to acute liver failure. Given its public health risk, novel methodologies to enhance the understanding of DILI are crucial. Recently, the increasing availability of larger datasets has highlighted artificial intelligence (AI) as a powerful tool to construct complex models. In this review, we summarise the evidence about the use of AI in DILI research, explaining fundamental AI concepts and its subfields. We present findings from AI-based approaches in DILI investigations for risk stratification, prognostic evaluation and causality assessment and discuss the adoption of natural language processing (NLP) and large language models (LLM) in the clinical setting. Finally, we explore future perspectives and challenges in utilising AI for DILI research.

Physiological liver microtissue 384-well microplate system for preclinical hepatotoxicity assessment of therapeutic small molecule drugs

Hepatotoxicity can lead to the discontinuation of approved or investigational drugs. The evaluation of the potential hepatoxicity of drugs in development is challenging because current models assessing this adverse effect are not always predictive of the outcome in human beings. Cell lines are routinely used for early hepatotoxicity screening, but to improve the detection of potential hepatotoxicity, in vitro models that better reflect liver morphology and function are needed. One such promising model is human liver microtissues. These are spheroids made of primary human parenchymal and nonparenchymal liver cells, which are amenable to high throughput screening. To test the predictivity of this model, the cytotoxicity of 152 FDA (US Food & Drug Administration)-approved small molecule drugs was measured as per changes in ATP content in human liver microtissues incubated in 384-well microplates. The results were analyzed with respect to drug label information, drug-induced liver injury (DILI) concern class, and drug class. The threshold IC50ATP-to-Cmax ratio of 176 was used to discriminate between safe and hepatotoxic drugs. "vMost-DILI-concern" drugs were detected with a sensitivity of 72% and a specificity of 89%, and "vMost-DILI-concern" drugs affecting the nervous system were detected with a sensitivity of 92% and a specificity of 91%. The robustness and relevance of this evaluation were assessed using a 5-fold cross-validation. The good predictivity, together with the in vivo-like morphology of the liver microtissues and scalability to a 384-well microplate, makes this method a promising and practical in vitro alternative to 2D cell line cultures for the early hepatotoxicity screening of drug candidates.

Prediction of Drug-Induced Liver Injury: From Molecular Physicochemical Properties and Scaffold Architectures to Machine Learning Approaches

The process of developing new drugs is widely acknowledged as being time-intensive and requiring substantial financial investment. Despite ongoing efforts to reduce time and expenses in drug development, ensuring medication safety remains an urgent problem. One of the major problems involved in drug development is hepatotoxicity, specifically known as drug-induced liver injury (DILI). The popularity of new drugs often poses a significant barrier during development and frequently leads to their recall after launch. In silico methods have many advantages compared with traditional in vivo and in vitro assays. To establish a more precise and reliable prediction model, it is necessary to utilize an extensive and high-quality database consisting of information on drug molecule properties and structural patterns. In addition, we should also carefully select appropriate molecular descriptors that can be used to accurately depict compound characteristics. The aim of this study was to conduct a comprehensive investigation into the prediction of DILI. First, we conducted a comparative analysis of the physicochemical properties of extensively well-prepared DILI-positive and DILI-negative compounds. Then, we used classic substructure dissection methods to identify structural pattern differences between these two different types of chemical molecules. These findings indicate that it is not feasible to establish property or substructure-based rules for distinguishing between DILI-positive and DILI-negative compounds. Finally, we developed quantitative classification models for predicting DILI using the naïve Bayes classifier (NBC) and recursive partitioning (RP) machine learning techniques. The optimal DILI prediction model was obtained using NBC, which combines 21 physicochemical properties, the VolSurf descriptors and the LCFP_10 fingerprint set. This model achieved a global accuracy (GA) of 0.855 and an area under the curve (AUC) of 0.704 for the training set, while the corresponding values were 0.619 and 0.674 for the test set, respectively. Moreover, indicative substructural fragments favorable or unfavorable for DILI were identified from the best naïve Bayesian classification model. These findings may help prioritize lead compounds in the early stage of drug development pipelines.

Machine Learning to Predict Drug-Induced Liver Injury and Its Validation on Failed Drug Candidates in Development

Drug-induced liver injury (DILI) poses a significant challenge for the pharmaceutical industry and regulatory bodies. Despite extensive toxicological research aimed at mitigating DILI risk, the effectiveness of these techniques in predicting DILI in humans remains limited. Consequently, researchers have explored novel approaches and procedures to enhance the accuracy of DILI risk prediction for drug candidates under development. In this study, we leveraged a large human dataset to develop machine learning models for assessing DILI risk. The performance of these prediction models was rigorously evaluated using a 10-fold cross-validation approach and an external test set. Notably, the random forest (RF) and multilayer perceptron (MLP) models emerged as the most effective in predicting DILI. During cross-validation, RF achieved an average prediction accuracy of 0.631, while MLP achieved the highest Matthews Correlation Coefficient (MCC) of 0.245. To validate the models externally, we applied them to a set of drug candidates that had failed in clinical development due to hepatotoxicity. Both RF and MLP accurately predicted the toxic drug candidates in this external validation. Our findings suggest that in silico machine learning approaches hold promise for identifying DILI liabilities associated with drug candidates during development.

Interpretable machine learning in predicting drug-induced liver injury among tuberculosis patients: model development and validation study

BACKGROUND

The objective of this research was to create and validate an interpretable prediction model for drug-induced liver injury (DILI) during tuberculosis (TB) treatment.

METHODS

A dataset of TB patients from Ningbo City was used to develop models employing the eXtreme Gradient Boosting (XGBoost), random forest (RF), and the least absolute shrinkage and selection operator (LASSO) logistic algorithms. The model's performance was evaluated through various metrics, including the area under the receiver operating characteristic curve (AUROC) and the area under the precision recall curve (AUPR) alongside the decision curve. The Shapley Additive exPlanations (SHAP) method was used to interpret the variable contributions of the superior model.

RESULTS

A total of 7,071 TB patients were identified from the regional healthcare dataset. The study cohort consisted of individuals with a median age of 47 years, 68.0% of whom were male, and 16.3% developed DILI. We utilized part of the high dimensional propensity score (HDPS) method to identify relevant variables and obtained a total of 424 variables. From these, 37 variables were selected for inclusion in a logistic model using LASSO. The dataset was then split into training and validation sets according to a 7:3 ratio. In the validation dataset, the XGBoost model displayed improved overall performance, with an AUROC of 0.89, an AUPR of 0.75, an F1 score of 0.57, and a Brier score of 0.07. Both SHAP analysis and XGBoost model highlighted the contribution of baseline liver-related ailments such as DILI, drug-induced hepatitis (DIH), and fatty liver disease (FLD). Age, alanine transaminase (ALT), and total bilirubin (Tbil) were also linked to DILI status.

CONCLUSION

XGBoost demonstrates improved predictive performance compared to RF and LASSO logistic in this study. Moreover, the introduction of the SHAP method enhances the clinical understanding and potential application of the model. For further research, external validation and more detailed feature integration are necessary.

Roadmap to DILI research in Europe. A proposal from COST action ProEuroDILINet

In the current article the aims for a constructive way forward in Drug-Induced Liver Injury (DILI) are to highlight the most important priorities in research and clinical science, therefore supporting a more informed, focused, and better funded future for European DILI research. This Roadmap aims to identify key challenges, define a shared vision across all stakeholders for the opportunities to overcome these challenges and propose a high-quality research program to achieve progress on the prediction, prevention, diagnosis and management of this condition and impact on healthcare practice in the field of DILI. This will involve 1. Creation of a database encompassing optimised case report form for prospectively identified DILI cases with well-characterised controls with competing diagnoses, biological samples, and imaging data; 2. Establishing of preclinical models to improve the assessment and prediction of hepatotoxicity in humans to guide future drug safety testing; 3. Emphasis on implementation science and 4. Enhanced collaboration between drug-developers, clinicians and regulatory scientists. This proposed operational framework will advance DILI research and may bring together basic, applied, translational and clinical research in DILI.

Deep Learning Algorithm Based on Molecular Fingerprint for Prediction of Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is one the rare adverse drug reaction (ADR) and multifactorial endpoints. Current preclinical animal models struggle to anticipate it, and in silico methods have emerged as a way with significant potential for doing so. In this study, a high-quality dataset of 1573 compounds was assembled. The 48 classification models, which depended on six different molecular fingerprints, were built via deep neural network (DNN) and seven machine learning algorithms. Comparing the results of the DNN and machine learning models, the optional performing model was found as the one developed based on the DNN with ECFP_6 as input, which achieved the area under the receiver operating characteristic curve (AUC) of 0.713, balanced accuracy (BA) of 0.680, and F1 of 0.753. In addition, we used the SHapley Additive exPlanations (SHAP) algorithm to interpret the models, identified the crucial structural fragments related to DILI risk, and selected the top ten substructures with the highest contribution rankings to serve as warning indicators for subsequent drug hepatotoxicity screening studies. The study demonstrates that the DNN models developed based on molecular fingerprints can be a trustworthy and efficient tool for determining the risk of DILI during the pre-development of novel medications.

Hepatotoxicity of AKR1C3 Inhibitor BAY1128688: Findings from an Early Terminated Phase IIa Trial for the Treatment of Endometriosis

INTRODUCTION

BAY1128688 is a selective inhibitor of aldo-keto reductase family 1 member C3 (AKR1C3), an enzyme implicated in the pathology of endometriosis and other disorders. In vivo animal studies suggested a potential therapeutic application of BAY1128688 in treating endometriosis. Early clinical studies in healthy volunteers supported the start of phase IIa.

OBJECTIVE

This manuscript reports the results of a clinical trial (AKRENDO1) assessing the effects of BAY1128688 in adult premenopausal women with endometriosis-related pain symptoms over a 12-week treatment period.

METHODS

Participants in this placebo-controlled, multicenter phase IIa clinical trial (NCT03373422) were randomized into one of five BAY1128688 treatment groups: 3 mg once daily (OD), 10 mg OD, 30 mg OD, 30 mg twice daily (BID), 60 mg BID; or a placebo group. The efficacy, safety, and tolerability of BAY1128688 were investigated.

RESULTS

Dose-/exposure-dependent hepatotoxicity was observed following BAY1128688 treatment, characterized by elevations in serum alanine transferase (ALT) occurring at around 12 weeks of treatment and prompting premature trial termination. The reduced number of valid trial completers precludes conclusions regarding treatment efficacy. The pharmacokinetics and pharmacodynamics of BAY1128688 among participants with endometriosis were comparable with those previously found in healthy volunteers and were not predictive of the subsequent ALT elevations observed.

CONCLUSIONS

The hepatotoxicity of BAY1128688 observed in AKRENDO1 was not predicted by animal studies nor by studies in healthy volunteers. However, in vitro interactions of BAY1128688 with bile salt transporters indicated a potential risk factor for hepatotoxicity at higher doses. This highlights the importance of in vitro mechanistic and transporter interaction studies in the assessment of hepatoxicity risk and suggests further mechanistic understanding is required.

CLINICAL TRIAL REGISTRATION

NCT03373422 (date registered: November 23, 2017).

Hepatotoxicity Induced by Azole Antifungal Agents: A Review Study

Context

Fungal infections are very common, and several medications are used to treat them. Azoles are prescribed widely to treat fungal infections. In addition to therapeutic effects, any drug can be accompanied by side effects in patients. One of the most important complications in this regard is liver injury. Therefore, hepatotoxicity induced by azole antifungal drugs were reviewed in this study.

Evidence Acquisition

English scientific papers were evaluated to review the effects of hepatotoxicity by azole antifungal agents, and the related studies' results were summarized using a table. The systematic search was implemented on electronic databases, including PubMed, Google Scholar, and Science Direct. Original articles and review articles that were published before April 1, 2022, were included in the study. Those articles without available full text or non-English articles were excluded. Also, articles that reported pediatric data were excluded.

Results

Most studies have reported the effects of hepatotoxicity by azole antifungal agents, and their mechanisms have been described.

Conclusions

Clinical evaluations regarding the hepatotoxicity of antifungal agents provided in the literature were reviewed. Therefore, it is recommended to prescribe these drugs with caution in high-risk patients suffering from liver diseases, and patients should be monitored for hepatotoxicity. However, more research is needed to evaluate the hepatotoxicity of azole antifungal agents and select appropriate drugs according to cost-effectiveness and the side effects' profiles, relying on lower incidence of this liver complication.

Development of Liver-on-Chip Integrating a Hydroscaffold Mimicking the Liver’s Extracellular Matrix

The 3Rs guidelines recommend replacing animal testing with alternative models. One of the solutions proposed is organ-on-chip technology in which liver-on-chip is one of the most promising alternatives for drug screening and toxicological assays. The main challenge is to achieve the relevant in vivo-like functionalities of the liver tissue in an optimized cellular microenvironment. Here, we investigated the development of hepatic cells under dynamic conditions inside a 3D hydroscaffold embedded in a microfluidic device. The hydroscaffold is made of hyaluronic acid and composed of liver extracellular matrix components (galactosamine, collagen I/IV) with RGDS (Arg-Gly-Asp-Ser) sites for cell adhesion. The HepG2/C3A cell line was cultured under a flow rate of 10 µL/min for 21 days. After seeding, the cells formed aggregates and proliferated, forming 3D spheroids. The cell viability, functionality, and spheroid integrity were investigated and compared to static cultures. The results showed a 3D aggregate organization of the cells up to large spheroid formations, high viability and albumin production, and an enhancement of HepG2 cell functionalities. Overall, these results highlighted the role of the liver-on-chip model coupled with a hydroscaffold in the enhancement of cell functions and its potential for engineering a relevant liver model for drug screening and disease study.

In vitro cell-based models of drug-induced hepatotoxicity screening: progress and limitation

Drug-induced liver injury (DILI) is one of the major causes of post-approval withdrawal of therapeutics. As a result, there is an increasing need for accurate predictive in vitro assays that reliably detect hepatotoxic drug candidates while reducing drug discovery time, costs, and the number of animal experiments. In vitro hepatocyte-based research has led to an improved comprehension of the underlying mechanisms of chemical toxicity and can assist the prioritization of therapeutic choices with low hepatotoxicity risk. Therefore, several in vitro systems have been generated over the last few decades. This review aims to comprehensively present the development and validation of 2D (two-dimensional) and 3D (three-dimensional) culture approaches on hepatotoxicity screening of compounds and highlight the main factors affecting predictive power of experiments. To this end, we first summarize some of the recognized hepatotoxicity mechanisms and related assays used to appraise DILI mechanisms and then discuss the challenges and limitations of in vitro models.

Relationships between the Structure and Severe Drug-Induced Liver Injury for Low, Medium, and High Doses of Drugs

Assessment of structure-activity relationships (SARs) for predicting severe drug-induced liver injury (DILI) is essential since in vivo and in vitro preclinical methods cannot detect many druglike compounds disrupting liver functions. To date, plenty of SAR models for the prediction of DILI have been developed; however, none of them considered the route of drug administration and daily dose, which may introduce significant bias into prediction results. We have created a dataset of 617 drugs with parenteral and oral administration routes and consistent information on DILI severity. We have found a clear relationship between route, dose, and DILI severity. According to SAR, nearly 40% of moderate- and non-DILI-causing drugs would cause severe DILI if they were administered at high oral doses. We have proposed the following approach to predict severe DILI. New compounds recommended to be used at low oral doses (<∼10 mg daily), or parenterally, can be considered not causing severe DILI. DILI for compounds administered at medium oral doses (∼10-100 mg daily; 22.2% of drugs under consideration) can be considered unpredictable because reasonable SAR models were not obtained due to the small size and heterogeneity of the corresponding dataset. The DILI potential of the compounds recommended to be used at high oral doses (more than ∼100 mg daily) can be estimated using SAR modeling. The balanced accuracy of the approach calculated by a 10-fold cross-validation procedure is 0.803. The developed approach can be used to estimate severe DILI for druglike compounds proposed to use at low and high oral doses or parenterally at the early stages of drug development.

Machine Learning Models for Predicting Liver Toxicity

Liver toxicity is a major adverse drug reaction that accounts for drug failure in clinical trials and withdrawal from the market. Therefore, predicting potential liver toxicity at an early stage in drug discovery is crucial to reduce costs and the potential for drug failure. However, current in vivo animal toxicity testing is very expensive and time consuming. As an alternative approach, various machine learning models have been developed to predict potential liver toxicity in humans. This chapter reviews current advances in the development and application of machine learning models for prediction of potential liver toxicity in humans and discusses possible improvements to liver toxicity prediction.

Drug-Induced Liver Injury: Clinical Evidence of N-Acetyl Cysteine Protective Effects

Oxidative stress is a key pathological feature implicated in both acute and chronic liver diseases, including drug-induced liver injury (DILI). The latter describes hepatic injury arising as a direct toxic effect of administered drugs or their metabolites. Although still underreported, DILI remains a significant cause of liver failure, especially in developed nations. Currently, it is understood that mitochondrial-generated oxidative stress and abnormalities in phase I/II metabolism, leading to glutathione (GSH) suppression, drive the onset of DILI. N-Acetyl cysteine (NAC) has attracted a lot of interest as a therapeutic agent against DILI because of its strong antioxidant properties, especially in relation to enhancing endogenous GSH content to counteract oxidative stress. Thus, in addition to updating information on the pathophysiological mechanisms implicated in oxidative-induced hepatic injury, the current review critically discusses clinical evidence on the protective effects of NAC against DILI, including the reduction of patient mortality. Besides injury caused by paracetamol, NAC can also improve liver function in relation to other forms of liver injury such as those induced by excessive alcohol intake. The implicated therapeutic mechanisms of NAC extend from enhancing hepatic GSH levels to reducing biomarkers of paracetamol toxicity such as keratin-18 and circulating caspase-cleaved cytokeratin-18. However, there is still lack of evidence confirming the benefits of using NAC in combination with other therapies in patients with DILI.

Preclinical models of idiosyncratic drug-induced liver injury (iDILI): Moving towards prediction

Idiosyncratic drug-induced liver injury (iDILI) encompasses the unexpected harms that prescription and non-prescription drugs, herbal and dietary supplements can cause to the liver. iDILI remains a major public health problem and a major cause of drug attrition. Given the lack of biomarkers for iDILI prediction, diagnosis and prognosis, searching new models to predict and study mechanisms of iDILI is necessary. One of the major limitations of iDILI preclinical assessment has been the lack of correlation between the markers of hepatotoxicity in animal toxicological studies and clinically significant iDILI. Thus, major advances in the understanding of iDILI susceptibility and pathogenesis have come from the study of well-phenotyped iDILI patients. However, there are many gaps for explaining all the complexity of iDILI susceptibility and mechanisms. Therefore, there is a need to optimize preclinical human in vitro models to reduce the risk of iDILI during drug development. Here, the current experimental models and the future directions in iDILI modelling are thoroughly discussed, focusing on the human cellular models available to study the pathophysiological mechanisms of the disease and the most used in vivo animal iDILI models. We also comment about in silico approaches and the increasing relevance of patient-derived cellular models.

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

Hepatotoxicity is one of the most frequently observed adverse effects resulting from exposure to a xenobiotic. For example, in pharmaceutical research and development it is one of the major reasons for drug withdrawals, clinical failures, and discontinuation of drug candidates. The development of faster and cheaper methods to assess hepatotoxicity that are both more sustainable and more informative is critically needed. The biological mechanisms and processes underpinning hepatotoxicity are summarized and experimental approaches to support the prediction of hepatotoxicity are described, including toxicokinetic considerations. The paper describes the increasingly important role of in silico approaches and highlights challenges to the adoption of these methods including the lack of a commonly agreed upon protocol for performing such an assessment and the need for in silico solutions that take dose into consideration. A proposed framework for the integration of in silico and experimental information is provided along with a case study describing how computational methods have been used to successfully respond to a regulatory question concerning non-genotoxic impurities in chemically synthesized pharmaceuticals.

Predicting Antituberculosis Drug-Induced Liver Injury Using an Interpretable Machine Learning Method: Model Development and Validation Study

Background

Tuberculosis (TB) is a pandemic, being one of the top 10 causes of death and the main cause of death from a single source of infection. Drug-induced liver injury (DILI) is the most common and serious side effect during the treatment of TB.

Objective

We aim to predict the status of liver injury in patients with TB at the clinical treatment stage.

Methods

We designed an interpretable prediction model based on the XGBoost algorithm and identified the most robust and meaningful predictors of the risk of TB-DILI on the basis of clinical data extracted from the Hospital Information System of Shenzhen Nanshan Center for Chronic Disease Control from 2014 to 2019.

Results

In total, 757 patients were included, and 287 (38%) had developed TB-DILI. Based on values of relative importance and area under the receiver operating characteristic curve, machine learning tools selected patients’ most recent alanine transaminase levels, average rate of change of patients’ last 2 measures of alanine transaminase levels, cumulative dose of pyrazinamide, and cumulative dose of ethambutol as the best predictors for assessing the risk of TB-DILI. In the validation data set, the model had a precision of 90%, recall of 74%, classification accuracy of 76%, and balanced error rate of 77% in predicting cases of TB-DILI. The area under the receiver operating characteristic curve score upon 10-fold cross-validation was 0.912 (95% CI 0.890-0.935). In addition, the model provided warnings of high risk for patients in advance of DILI onset for a median of 15 (IQR 7.3-27.5) days.

Conclusions

Our model shows high accuracy and interpretability in predicting cases of TB-DILI, which can provide useful information to clinicians to adjust the medication regimen and avoid more serious liver injury in patients.

Modeling approaches for reducing safety-related attrition in drug discovery and development: a review on myelotoxicity, immunotoxicity, cardiovascular toxicity, and liver toxicity

Introduction:Safety and tolerability is a critical area where improvements are needed to decrease the attrition rates during development of new drug candidates. Modeling approaches, when smartly implemented, can contribute to this aim.Areas covered:The focus of this review was on modeling approaches applied to four kinds of drug-induced toxicities: hematological, immunological, cardiovascular (CV) and liver toxicity. Papers, mainly published in the last 10 years, reporting models in three main methodological categories - computational models (e.g., quantitative structure-property relationships, machine learning approaches, neural networks, etc.), pharmacokinetic-pharmacodynamic (PK-PD) models, and quantitative system pharmacology (QSP) models - have been considered.Expert opinion:The picture observed in the four examined toxicity areas appears heterogeneous. Computational models are typically used in all areas as screening tools in the early stages of development for hematological, cardiovascular and liver toxicity, with accuracies in the range of 70-90%. A limited number of computational models, based on the analysis of drug protein sequence, was instead proposed for immunotoxicity. In the later stages of development, toxicities are quantitatively predicted with reasonably good accuracy using either semi-mechanistic PK-PD models (hematological and cardiovascular toxicity), or fully exploited QSP models (immuno-toxicity and liver toxicity).

Immune-Mediated Drug-Induced Liver Injury: Immunogenetics and Experimental Models

Drug-induced liver injury (DILI) is a challenging clinical event in medicine, particularly because of its ability to present with a variety of phenotypes including that of autoimmune hepatitis or other immune mediated liver injuries. Limited diagnostic and therapeutic tools are available, mostly because its pathogenesis has remained poorly understood for decades. The recent scientific and technological advancements in genomics and immunology are paving the way for a better understanding of the molecular aspects of DILI. This review provides an updated overview of the genetic predisposition and immunological mechanisms behind the pathogenesis of DILI and presents the state-of-the-art experimental models to study DILI at the pre-clinical level.

The Promise of AI for DILI Prediction

Drug-induced liver injury (DILI) is a common reason for the withdrawal of a drug from the market. Early assessment of DILI risk is an essential part of drug development, but it is rendered challenging prior to clinical trials by the complex factors that give rise to liver damage. Artificial intelligence (AI) approaches, particularly those building on machine learning, range from random forests to more recent techniques such as deep learning, and provide tools that can analyze chemical compounds and accurately predict some of their properties based purely on their structure. This article reviews existing AI approaches to predicting DILI and elaborates on the challenges that arise from the as yet limited availability of data. Future directions are discussed focusing on rich data modalities, such as 3D spheroids, and the slow but steady increase in drugs annotated with DILI risk labels.

Hepatotoxicity of FDA-approved small molecule kinase inhibitors

Introduction: Given their importance in cellular processes and association with numerous diseases, protein kinases have emerged as promising targets for drugs. The FDA has approved greater than fifty small molecule kinase inhibitors (SMKIs) since 2001. Nevertheless, severe hepatotoxicity and related fatal cases have grown as a potential challenge in the advancement of these drugs, and the identification and diagnosis of drug-induced liver injury (DILI) are thorny problems for clinicians.Areas covered: This article summarizes the progression and analyzes the significant features in the study of SMKI hepatotoxicity, including clinical observations and investigations of the underlying mechanisms.Expert opinion: The understanding of SMKI-associated hepatotoxicity relies on the development of preclinical models and improvement of clinical assessment. With a full understanding of the role of inflammation in DILI and the mediating role of cytokines in inflammation, cytokines are promising candidates as sensitive and specific biomarkers for DILI. The emergence of three-dimensional spheroid models demonstrates potential use in providing clinically relevant data and predicting hepatotoxicity of SMKIs.

Computational Models Using Multiple Machine Learning Algorithms for Predicting Drug Hepatotoxicity with the DILIrank Dataset

Drug-induced liver injury (DILI) remains one of the challenges in the safety profile of both authorized and candidate drugs, and predicting hepatotoxicity from the chemical structure of a substance remains a task worth pursuing. Such an approach is coherent with the current tendency for replacing non-clinical tests with in vitro or in silico alternatives. In 2016, a group of researchers from the FDA published an improved annotated list of drugs with respect to their DILI risk, constituting “the largest reference drug list ranked by the risk for developing drug-induced liver injury in humans” (DILIrank). This paper is one of the few attempting to predict liver toxicity using the DILIrank dataset. Molecular descriptors were computed with the Dragon 7.0 software, and a variety of feature selection and machine learning algorithms were implemented in the R computing environment. Nested (double) cross-validation was used to externally validate the models selected. A total of 78 models with reasonable performance were selected and stacked through several approaches, including the building of multiple meta-models. The performance of the stacked models was slightly superior to other models published. The models were applied in a virtual screening exercise on over 100,000 compounds from the ZINC database and about 20% of them were predicted to be non-hepatotoxic.

Metatox - Web application for generation of metabolic pathways and toxicity estimation

Xenobiotics biotransformation in humans is a process of the chemical modifications, which may lead to the formation of toxic metabolites. The prediction of such metabolites is very important for drug development and ecotoxicology studies. We created the web-application MetaTox ( http://way2drug.com/mg ) for the generation of xenobiotics metabolic pathways in the human organism. For each generated metabolite, the estimations of the acute toxicity (based on GUSAR software prediction), organ-specific carcinogenicity and adverse effects (based on PASS software prediction) are performed. Generation of metabolites by MetaTox is based on the fragments datasets, which describe transformations of substrates structures to a metabolites structure. We added three new classes of biotransformation reactions: Dehydrogenation, Glutathionation, and Hydrolysis, and now metabolite generation for 15 most frequent classes of xenobiotic's biotransformation reactions are available. MetaTox calculates the probability of formation of generated metabolite - it is the integrated assessment of the biotransformation reactions probabilities and their sites using the algorithm of PASS ( http://way2drug.com/passonline ). The prediction accuracy estimated by the leave-one-out cross-validation (LOO-CV) procedure calculated separately for the probabilities of biotransformation reactions and their sites is about 0.9 on the average for all reactions.

Transcriptome profiling of hiPSC-derived LSECs with nanoCAGE

Liver Sinusoidal Endothelial Cells (LSECs) are an important component of the liver as they compose the microvasculature which allows the supply of oxygen, blood, and nutrients. However, maintenance of these cells in vitro remains challenging as they tend to rapidly lose some of their characteristics such as fenestration or as their immortalized counterparts present poor characteristics. In this work, human induced pluripotent stem cells (hiPSCs) have been differentiated toward an LSEC phenotype. After differentiation, the RNA quantification allowed demonstration of high expression of specific vascular markers (CD31, CD144, and STAB2). Immunostaining performed on the cells was found to be positive for both Stabilin-1 and Stabilin-2. Whole transcriptome analysis performed with the nanoCAGE method further confirmed the overall vascular commitment of the cells. The gene expression profile revealed the upregulation of the APLN, LYVE1, VWF, ESAM and ANGPT2 genes while VEGFA appeared to be downregulated. Analysis of promoter motif activities highlighted several transcription factors (TFs) of interest in LSECs (IRF2, ERG, MEIS2, SPI1, IRF7, WRNIP1, HIC2, NFIX_NFIB, BATF, and PATZ1). Based on this investigation, we compiled the regulatory network involving the relevant TFs, their target genes as well as their related signaling pathways. The proposed hiPSC-derived LSEC model and its regulatory network were then confirmed by comparing the experimental data to primary human LSEC reference datasets. Thus, the presented model appears as a promising tool to generate more complex in vitro liver multi-cellular tissues.

Narrowing the Gap Between In Vitro and In Vivo Genetic Profiles by Deconvoluting Toxicogenomic Data In Silico

Toxicogenomics (TGx) is a powerful method to evaluate toxicity and is widely used in both in vivo and in vitro assays. For in vivo TGx, reduction, refinement, and replacement represent the unremitting pursuit of live-animal tests, but in vitro assays, as alternatives, usually demonstrate poor correlation with real in vivo assays. In living subjects, in addition to drug effects, inner-environmental reactions also affect genetic variation, and these two factors are further jointly reflected in gene abundance. Thus, finding a strategy to factorize inner-environmental factor from in vivo assays based on gene expression levels and to further utilize in vitro data to better simulate in vivo data is needed. We proposed a strategy based on post-modified non-negative matrix factorization, which can estimate the gene expression profiles and contents of major factors in samples. The applicability of the strategy was first verified, and the strategy was then utilized to simulate in vivo data by correcting in vitro data. The similarities between real in vivo data and simulated data (single-dose 0.72, repeat-doses 0.75) were higher than those observed when directly comparing real in vivo data with in vitro data (single-dose 0.56, repeat-doses 0.70). Moreover, by keeping environment-related factor, a simulation can always be generated by using in vitro data to provide potential substitutions for in vivo TGx and to reduce the launch of live-animal tests.

Glutathione Conjugation and Protein Adduction Derived from Oxidative Debromination of Benzbromarone in Mice

Benzbromarone (BBR), a uricosuric agent, has been known to induce hepatotoxicity, and its toxicity has a close relation to cytochrome P450-mediated metabolic activation. An oxidative debromination metabolite of BBR has been reported in microsomal incubations. The present study attempted to define the oxidative debromination pathway of BBR in vivo. One urinary mercapturic acid (M1) and one glutathione (GSH) conjugate (M2) derived from the oxidative debromination metabolite were detected in BBR-treated mice after solid phase extraction. M1 and M2 shared the same chromatographic behavior and mass spectral identities as those detected in N-acetylcysteine/GSH- and BBR-fortified microsomal incubations. The structure of M1 was characterized by chemical synthesis, along with mass spectrometry analysis. In addition, hepatic protein modification that occurs at cysteine residues (M'3) was observed in mice given BBR. The observed protein adduction reached its peak 4 hours after administration and occurred in a dose-dependent manner. A GSH conjugate derived from oxidative debromination of BBR was detected in livers of mice treated with BBR, and the formation of the GSH conjugate apparently took place earlier than the protein adduction. In summary, our in vivo work provided strong evidence for the proposed oxidative debromination pathway of BBR, which facilitates the understanding of the mechanisms of BBR-induced hepatotoxicity. SIGNIFICANCE STATEMENT: This study investigated the oxidative debromination pathway of benzbromarone (BBR) in vivo. One urinary mercapturic acid (M1) and one glutathione (GSH) conjugate (M2) derived from the oxidative debromination metabolite were detected in BBR-treated mice. M1 and M2 were also observed in microsomal incubations. The structure of M1 was characterized by chemical synthesis followed by mass spectrometry analyses. More importantly, protein adduction derived from oxidative debromination of BBR (M'3) was observed in mice given BBR, and occurred in dose- and time-dependent manners. The success in detection of GSH conjugate, urinary N-acetylcysteine conjugate, and hepatic protein adduction in mice given BBR provided solid evidence for in vivo oxidative debromination of BBR. The studies allowed a better understanding of the metabolic activation of BBR.

Current insights in the complexities underlying drug-induced cholestasis

Drug-induced cholestasis (DIC) poses a major challenge to the pharmaceutical industry and regulatory agencies. It causes both drug attrition and post-approval withdrawal of drugs. DIC represents itself as an impaired secretion and flow of bile, leading to the pathological hepatic and/or systemic accumulation of bile acids (BAs) and their conjugate bile salts. Due to the high number of mechanisms underlying DIC, predicting a compound's cholestatic potential during early stages of drug development remains elusive. A profound understanding of the different molecular mechanisms of DIC is, therefore, of utmost importance. Although many knowledge gaps and caveats still exist, it is generally accepted that alterations of certain hepatobiliary membrane transporters and changes in hepatocellular morphology may cause DIC. Consequently, liver models, which represent most of these mechanisms, are valuable tools to predict human DIC. Some of these models, such as membrane-based in vitro models, are exceptionally well-suited to investigate specific mechanisms (i.e. transporter inhibition) of DIC, while others, such as liver slices, encompass all relevant biological processes and, therefore, offer a better representation of the in vivo situation. In the current review, we highlight the principal molecular mechanisms associated with DIC and offer an overview and critical appraisal of the different liver models that are currently being used to predict the cholestatic potential of drugs.

Predicting Drug-Induced Liver Injury with Bayesian Machine Learning

Drug induced liver injury (DILI) can require significant risk management in drug development and on occasion can cause morbidity or mortality, leading to drug attrition. Optimizing candidates preclinically can minimize hepatotoxicity risk, but it is difficult to predict due to multiple etiologies encompassing DILI, often with multifactorial and overlapping mechanisms. In addition to epidemiological risk factors, physicochemical properties, dose, disposition, lipophilicity, and hepatic metabolic function are also relevant for DILI risk. Better human-relevant, predictive models are required to improve hepatotoxicity risk assessment in drug discovery. Our hypothesis is that integrating mechanistically relevant hepatic safety assays with Bayesian machine learning will improve hepatic safety risk prediction. We present a quantitative and mechanistic risk assessment for candidate nomination using data from in vitro assays (hepatic spheroids, BSEP, mitochondrial toxicity, and bioactivation), together with physicochemical (cLogP) and exposure (Cmax_total) variables from a chemically diverse compound set (33 no/low-, 40 medium-, and 23 high-severity DILI compounds). The Bayesian model predicts the continuous underlying DILI severity and uses a data-driven prior distribution over the parameters to prevent overfitting. The model quantifies the probability that a compound falls into either no/low-, medium-, or high-severity categories, with a balanced accuracy of 63% on held-out samples, and a continuous prediction of DILI severity along with uncertainty in the prediction. For a binary yes/no DILI prediction, the model has a balanced accuracy of 86%, a sensitivity of 87%, a specificity of 85%, a positive predictive value of 92%, and a negative predictive value of 78%. Combining physiologically relevant assays, improved alignment with FDA recommendations, and optimal statistical integration of assay data leads to improved DILI risk prediction.

Herb-Induced Liver Injury: Phylogenetic Relationship, Structure-Toxicity Relationship, and Herb-Ingredient Network Analysis

Currently, hundreds of herbal products with potential hepatotoxicity were available in the literature. A comprehensive summary and analysis focused on these potential hepatotoxic herbal products may assist in understanding herb-induced liver injury (HILI). In this work, we collected 335 hepatotoxic medicinal plants, 296 hepatotoxic ingredients, and 584 hepatoprotective ingredients through a systematic literature retrieval. Then we analyzed these data from the perspectives of phylogenetic relationship and structure-toxicity relationship. Phylogenetic analysis indicated that hepatotoxic medicinal plants tended to have a closer taxonomic relationship. By investigating the structures of the hepatotoxic ingredients, we found that alkaloids and terpenoids were the two major groups of hepatotoxicity. We also identified eight major skeletons of hepatotoxicity and reviewed their hepatotoxic mechanisms. Additionally, 15 structural alerts (SAs) for hepatotoxicity were identified based on SARpy software. These SAs will help to estimate the hepatotoxic risk of ingredients from herbs. Finally, a herb-ingredient network was constructed by integrating multiple datasets, which will assist to identify the hepatotoxic ingredients of herb/herb-formula quickly. In summary, a systemic analysis focused on HILI was conducted which will not only assist to identify the toxic molecular basis of hepatotoxic herbs but also contribute to decipher the mechanisms of HILI.

Developing a Multi-Dose Computational Model for Drug-Induced Hepatotoxicity Prediction Based on Toxicogenomics Data

Drug-induced hepatotoxicity may cause acute and chronic liver disease, leading to great concern for patient safety. It is also one of the main reasons for drug withdrawal from the market. Toxicogenomics data has been widely used in hepatotoxicity prediction. In our study, we proposed a multi-dose computational model to predict the drug-induced hepatotoxicity based on gene expression and toxicity data. The dose/concentration information after drug treatment is fully utilized in our study based on the dose-response curve, thus a more informative representative of the dose-response relationship is considered. We also proposed a new feature selection method, named MEMO, which is also one important aspect of our multi-dose model in our study, to deal with the high-dimensional toxicogenomics data. We validated the proposed model using the TG-GATEs, which is a large database recording toxicogenomics data from multiple views. The experimental results show that the drug-induced hepatotoxicity can be predicted with high accuracy and efficiency using the proposed predictive model.

An In Silico Model for Predicting Drug-Induced Hepatotoxicity

As one of the leading causes of drug failure in clinical trials, drug-induced liver injury (DILI) seriously impeded the development of new drugs. Assessing the DILI risk of drug candidates in advance has been considered as an effective strategy to decrease the rate of attrition in drug discovery. Recently, there have been continuous attempts in the prediction of DILI. However, it indeed remains a huge challenge to predict DILI successfully. There is an urgent need to develop a quantitative structure-activity relationship (QSAR) model for predicting DILI with satisfactory performance. In this work, we reported a high-quality QSAR model for predicting the DILI risk of xenobiotics by incorporating the use of eight effective classifiers and molecular descriptors provided by Marvin. In model development, a large-scale and diverse dataset consisting of 1254 compounds for DILI was built through a comprehensive literature retrieval. The optimal model was attained by an ensemble method, averaging the probabilities from eight classifiers, with accuracy (ACC) of 0.783, sensitivity (SE) of 0.818, specificity (SP) of 0.748, and area under the receiver operating characteristic curve (AUC) of 0.859. For further validation, three external test sets and a large negative dataset were utilized. Consequently, both the internal and external validation indicated that our model outperformed prior studies significantly. Data provided by the current study will also be a valuable source for modeling/data mining in the future.

[Xenobiotic toxicity prediction combined with xenobiotic metabolism prediction in the human body]

The majority of xenobiotics undergo a number of chemical reactions known as biotransformation in human body. The biological activity, toxicity, and other properties of the metabolites may significantly differ from those of the parent compound. Not only xenobiotic itself and its final metabolites produced in large quantities, but the intermediate and final metabolites that are formed in trace quantities, can cause undesirable effects. We have developed a freely available web resource MetaTox (http://www.way2drug.com/mg/) for integral assessment of xenobiotics toxicity taking into account their metabolism in the humans. The generation of the metabolite structures is based on the reaction fragments. The estimates of the probability of the reaction of a certain class and the probability of site of biotransformation are used at the generation of the xenobiotic metabolism pathways. The web resource MetaTox allows researchers to assess the metabolism of compounds in the humans and to obtain assessment of their acute, chronic toxicity, and adverse effects.

Unsupervised identification of disease states from high-dimensional physiological and histopathological profiles

The liver and kidney in mammals play central roles in protecting the organism from xenobiotics and are at high risk of xenobiotic-induced injury. Xenobiotic-induced tissue injury has been extensively studied from both classical histopathological and biochemical perspectives. Here, we introduce a machine-learning approach to analyze toxicological response. Unsupervised characterization of physiological and histological changes in a large toxicogenomic dataset revealed nine discrete toxin-induced disease states, some of which correspond to known pathology, but others were novel. Analysis of dynamics revealed transitions between disease states at constant toxin exposure, mostly toward decreased pathology, implying induction of tolerance. Tolerance correlated with induction of known xenobiotic defense genes and decrease of novel ferroptosis sensitivity biomarkers, suggesting ferroptosis as a druggable driver of tissue pathophysiology. Lastly, mechanism of body weight decrease, a known primary marker for xenobiotic toxicity, was investigated. Combined analysis of food consumption, body weight, and molecular biomarkers indicated that organ injury promotes cachexia by whole-body signaling through Gdf15 and Igf1, suggesting strategies for therapeutic intervention that may be broadly relevant to human disease.

In Silico Approaches to Predict Drug-Transporter Interaction Profiles: Data Mining, Model Generation, and Link to Cholestasis

Transport proteins play a crucial role in drug distribution, disposition, and clearance by mediating cellular drug influx and efflux. Inhibition of these transporters may lead to drug-drug interactions or even drug-induced liver injury, such as cholestasis, which comprises a major challenge in drug development process. Thus, computer-based (in silico) models that can predict the pharmacological and toxicological profiles of these small molecules with respect to liver transporters may help in the early prioritization of compounds and hence may lower the high attrition rates. In this chapter, we provide a protocol for in silico prediction of cholestasis by generating validated predictive models. In addition to the two-dimensional molecular descriptors, we include transporter inhibition predictions as descriptors and evaluate the influence of the same on the performance of the cholestasis models.

Harnessing Human Microphysiology Systems as Key Experimental Models for Quantitative Systems Pharmacology

Two technologies that have emerged in the last decade offer a new paradigm for modern pharmacology, as well as drug discovery and development. Quantitative systems pharmacology (QSP) is a complementary approach to traditional, target-centric pharmacology and drug discovery and is based on an iterative application of computational and systems biology methods with multiscale experimental methods, both of which include models of ADME-Tox and disease. QSP has emerged as a new approach due to the low efficiency of success in developing therapeutics based on the existing target-centric paradigm. Likewise, human microphysiology systems (MPS) are experimental models complementary to existing animal models and are based on the use of human primary cells, adult stem cells, and/or induced pluripotent stem cells (iPSCs) to mimic human tissues and organ functions/structures involved in disease and ADME-Tox. Human MPS experimental models have been developed to address the relatively low concordance of human disease and ADME-Tox with engineered, experimental animal models of disease. The integration of the QSP paradigm with the use of human MPS has the potential to enhance the process of drug discovery and development.

Characterisation of the NRF2 transcriptional network and its response to chemical insult in primary human hepatocytes: implications for prediction of drug-induced liver injury

The transcription factor NRF2, governed by its repressor KEAP1, protects cells against oxidative stress. There is interest in modelling the NRF2 response to improve the prediction of clinical toxicities such as drug-induced liver injury (DILI). However, very little is known about the makeup of the NRF2 transcriptional network and its response to chemical perturbation in primary human hepatocytes (PHH), which are often used as a translational model for investigating DILI. Here, microarray analysis identified 108 transcripts (including several putative novel NRF2-regulated genes) that were both downregulated by siRNA targeting NRF2 and upregulated by siRNA targeting KEAP1 in PHH. Applying weighted gene co-expression network analysis (WGCNA) to transcriptomic data from the Open TG-GATES toxicogenomics repository (representing PHH exposed to 158 compounds) revealed four co-expressed gene sets or ‘modules’ enriched for these and other NRF2-associated genes. By classifying the 158 TG-GATES compounds based on published evidence, and employing the four modules as network perturbation metrics, we found that the activation of NRF2 is a very good indicator of the intrinsic biochemical reactivity of a compound (i.e. its propensity to cause direct chemical stress), with relatively high sensitivity, specificity, accuracy and positive/negative predictive values. We also found that NRF2 activation has lower sensitivity for the prediction of clinical DILI risk, although relatively high specificity and positive predictive values indicate that false positive detection rates are likely to be low in this setting. Underpinned by our comprehensive analysis, activation of the NRF2 network is one of several mechanism-based components that can be incorporated into holistic systems toxicology models to improve mechanistic understanding and preclinical prediction of DILI in man.

In Silico Prediction of Drug-Induced Liver Injury Based on Adverse Drug Reaction Reports

Drug-induced liver injury (DILI) is a major cause of drug attrition. Currently existing Quantitative Structure-Activity Relationship models have limited predictive capabilities for DILI. Furthermore, their practical applications were limited by lack of new hepatotoxicity data. In this study, we first collected and curated a novel set of 122 DILI-positive and 932 DILI-negative drugs from online adverse drug reports using proportional reporting ratios as the signal detection method. Second, three strategies (under-sampling the majority class, synthetic minority over-sampling technique, and adjusting decision threshold approach) were employed to develop predictive classification models to cope with the unbalanced dataset. Random forest (RF) models using CDK, MACCS, and Mold2 descriptors based on the under-sampling and over-sampling strategies afforded correct classification ratio (CCR) of ∼0.77 and 0.78, respectively. Recursive RF models based on the last strategy tremendously reduced modeling descriptors (at most 95.4% for Mold2) while apparently improved the predictability with a consensus CCR of 0.84 (sensitivity of 0.88 and specificity of 0.79). Structural analysis showed that pyrimidine derivatives, purine derivatives, and halogenated hydrocarbon were critical for drugs' hepatotoxicity. The reporting frequency of many drugs was gender-dependent (eg, antiviral and anti-cancer drugs for males and antibacterial drugs for females) as well as age-dependent (eg, antiviral and anti-cancer drugs for the middle age group of 20-29, 30-39, and 40-49). Approximately 84% of total cases were reported during the first 6 months of administration. The curated hepatotoxicity dataset along with the predictive classification models presented here should provide insight into future studies of DILI.

A multi-center preclinical study of gadoxetate DCE-MRI in rats as a biomarker of drug induced inhibition of liver transporter function

Drug-induced liver injury (DILI) is a leading cause of acute liver failure and transplantation. DILI can be the result of impaired hepatobiliary transporters, with altered bile formation, flow, and subsequent cholestasis. We used gadoxetate dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), combined with pharmacokinetic modelling, to measure hepatobiliary transporter function in vivo in rats. The sensitivity and robustness of the method was tested by evaluating the effect of a clinical dose of the antibiotic rifampicin in four different preclinical imaging centers. The mean gadoxetate uptake rate constant for the vehicle groups at all centers was 39.3 +/- 3.4 s^-1 (n = 23) and 11.7 +/- 1.3 s^-1 (n = 20) for the rifampicin groups. The mean gadoxetate efflux rate constant for the vehicle groups was 1.53 +/- 0.08 s^-1 (n = 23) and for the rifampicin treated groups was 0.94 +/- 0.08 s^-1 (n = 20). Both the uptake and excretion transporters of gadoxetate were statistically significantly inhibited by the clinical dose of rifampicin at all centers and the size of this treatment group effect was consistent across the centers. Gadoxetate is a clinically approved MRI contrast agent, so this method is readily transferable to the clinic. Conclusion: Rate constants of gadoxetate uptake and excretion are sensitive and robust biomarkers to detect early changes in hepatobiliary transporter function in vivo in rats prior to established biomarkers of liver toxicity.

Evaluation of the Relevance of DILI Predictive Hypotheses in Early Drug Development: Review of In Vitro Methodologies vs BDDCS Classification

Drug-induced liver injury (DILI) is a major safety concern; it occurs frequently; it is idiosyncratic; it cannot be adequately predicted; and a multitude of underlying mechanisms has been postulated. A number of experimental approaches to predict human DILI have been proposed utilizing in vitro screening such as inhibition of mitochondrial function, hepatobiliary transporter inhibition, reactive metabolite formation with and without covalent binding, and cellular health, but they have achieved only minimal success. Several studies have shown total administered dose alone or in combination with drug lipophilicity to be correlated with a higher risk of DILI. However, it would be best to have a predictive DILI methodology early in drug development, long before the clinical dose is known. Here we discuss the extent to which Biopharmaceutics Drug Disposition Classification System (BDDCS) defining characteristics, independent of knowing actual drug pharmacokinetics/pharmacodynamics and dose, can be used to evaluate prior published predictive proposals. Our results show that BDDCS Class 2 drugs exhibit the highest DILI severity, and that all of the short-lived published methodologies evaluated here, except when daily dose is known, do not yield markedly better predictions than BDDCS. The assertion that extensively metabolized compounds are at higher risk of developing DILI is confirmed, but can be enhanced by differentiating BDDCS Class 2 from Class 1 drugs.

CONCLUSION

Our published analyses suggest that comparison of proposed DILI prediction methodologies with BDDCS classification is a useful tool to evaluate the potential reliability of newly proposed algorithms, although BDDCS classification itself is not sufficiently predictive. Almost all of the predictive DILI metrics do no better than just avoiding BDDCS Class 2 drugs, although some early data with microliver platforms enabling long-enduring metabolic competency show promising results.

Metabolomics of Hydrazine-Induced Hepatotoxicity in Rats for Discovering Potential Biomarkers

Metabolic pathway disturbances associated with drug-induced liver injury remain unsatisfactorily characterized. Diagnostic biomarkers for hepatotoxicity have been used to minimize drug-induced liver injury and to increase the clinical safety. A metabolomics strategy using rapid-resolution liquid chromatography/tandem mass spectrometry (RRLC-MS/MS) analyses and multivariate statistics was implemented to identify potential biomarkers for hydrazine-induced hepatotoxicity. The global serum and urine metabolomics of 30 hydrazine-treated rats at 24 or 48 h postdosing and 24 healthy rats were characterized by a metabolomics approach. Multivariate statistical data analyses and receiver operating characteristic (ROC) curves were performed to identify the most significantly altered metabolites. The 16 most significant potential biomarkers were identified to be closely related to hydrazine-induced liver injury. The combination of these biomarkers had an area under the curve (AUC) > 0.85, with 100% specificity and sensitivity, respectively. This high-quality classification group included amino acids and their derivatives, glutathione metabolites, vitamins, fatty acids, intermediates of pyrimidine metabolism, and lipids. Additionally, metabolomics pathway analyses confirmed that phenylalanine, tyrosine, and tryptophan biosynthesis as well as tyrosine metabolism had great interactions with hydrazine-induced liver injury in rats. These discriminating metabolites might be useful in understanding the pathogenesis mechanisms of liver injury and provide good prospects for drug-induced liver injury diagnosis clinically.

Safety data and withdrawal of hepatotoxic drugs

BACKGROUND AND AIM

The occurrence of drug induced liver injury (DILI) is the most common reason of post-marketing withdrawals. DILI in humans is difficult to predict using in vitro cytotoxicity screening and animal studies. A review of hepatotoxicity data was performed with the aim of identifying relevant factors that could have predicted the occurrence of serious DILI.

METHODS

The drugs withdrawn from the market due to hepatotoxicity in Europe and/or in USA either by marketing authorization holders or by Regulatory agencies from 1997 to 2016 were selected. The liver safety data and the withdrawal decisions were identified from a search within the European medicine agency (EMA) website, the Food and drug administration (FDA) orange book and PubMed^®.

RESULTS

From 1997 to 2016, eight drugs were withdrawn from the market for hepatotoxicity reason: tolcapone, troglitazone, trovafloxacin, bromfenac, nefazodone, ximelagatran, lumiracoxib and sitaxentan. The safety data suggest that while liver test abnormalities have been detected during clinical trials, other relevant factors leading to the discontinuation of these drugs have been identified: lack of predictability of animal models, inappropriate liver function test, non-compliance with drug treatment, less attention paid to rare adverse drug reactions, unpredictable occurrence and irreversible outcome of liver toxicity.

CONCLUSION

Several relevant factors may contribute to an inadequate risk management leading to the discontinuation of the drugs. Preclinical safety data are not sufficient to allow early prediction of DILI in humans and post-marketing safety monitoring and signal detection still should be used to identify potential serious cases of DILI. However, it seems that changes in Pharmacovigilance legislation with a closer management of drug safety may have contributed to the improvement of the risk minimization.

The development and application of in silico models for drug induced liver injury

Drug-induced liver injury (DILI), caused by drugs, herbal agents or nutritional supplements, is a major issue for patients and the pharmaceutical industry. It has been a leading cause of clinical trials failure and withdrawal of FDA approval. In this research, we focused on in silico estimation of chemical DILI potential on humans based on structurally diverse organic chemicals. We developed a series of binary classification models using five different machine learning methods and eight different feature reduction methods. The model, developed with the support vector machine (SVM) and the MACCS fingerprint, performed best both on the test set and external validation. It achieved a prediction accuracy of 80.39% on the test set and 82.78% on external validation. We made this model available at http://opensource.vslead.com/. The user can freely predict the DILI potential of molecules. Furthermore, we analyzed the difference of distributions of 12 key physical-chemical properties between DILI-positive and DILI-negative compounds and 20 privileged substructures responsible for DILI were identified from the Klekota-Roth fingerprint. Moreover, since traditional Chinese medicine (TCM)-induced liver injury is also one of the major concerns among the toxic effects, we evaluated the DILI potential of TCM ingredients using the MACCS_SVM model developed in this study. We hope the model and privileged substructures could be useful complementary tools for chemical DILI evaluation.