Prediction Of Drug-induced Liver Injury Research Articles

A 3D spheroid model of quadruple cell co-culture with improved liver functions for hepatotoxicity prediction

Drug-induced liver injury (DILI) is one of the major concerns during drug development. Wide acceptance of the 3R principles and the innovation of in-vitro techniques have introduced various novel model options, among which the three-dimensional (3D) cell spheroid cultures have shown a promising prospect in DILI prediction. The present study developed a 3D quadruple cell co-culture liver spheroid model for DILI prediction via self-assembly. Induction by phorbol 12-myristate 13-acetate at the concentration of 15.42ng/mL for 48hours with a following 24-hour rest period was used for THP-1 cell differentiation, resulting in credible macrophagic phenotypes. HepG2 cells, PUMC-HUVEC-T1 cells, THP-1-originated macrophages, and human hepatic stellate cells were selected as the components, which exhibited adaptability in the designated spheroid culture conditions. Following establishment, the characterization demonstrated the competence of the model in long-term stability reflected by the maintenance of morphology, viability, cellular integration, and cell-cell junctions for at least six days, as well as the reliable liver-specific functions including superior albumin and urea secretion, improved drug metabolic enzyme expression and CYP3A4 activity, and the expression of MRP2, BSEP, and P-GP accompanied by the bile acid efflux transport function. In the comparative testing using 22 DILI-positive and 5 DILI-negative compounds among the novel 3D co-culture model, 3D HepG2 spheroids, and 2D HepG2 monolayers, the 3D culture method significantly enhanced the model sensitivity to compound cytotoxicity compared to the 2D form. The novel co-culture liver spheroid model exhibited higher overall predictive power with margin of safety as the classifying tool. In addition, the non-parenchymal cell components could amplify the toxicity of isoniazid in the 3D model, suggesting their potential mediating role in immune-mediated toxicity. The proof-of-concept experiments demonstrated the capability of the model in replicating drug-induced lipid dysregulation, bile acid efflux inhibition, and α-SMA upregulation, which are the key features of liver steatosis and phospholipidosis, cholestasis, and fibrosis, respectively. Overall, the novel 3D quadruple cell co-culture spheroid model is a reliable and readily available option for DILI prediction.

Multi-view uncertainty deep forest: An innovative deep forest equipped with uncertainty estimation for drug-induced liver injury prediction

Drug-induced liver injury (DILI) refers to the harmful effects that certain drugs can have on the liver, potentially leading to severe health issues and even life-threatening conditions. Early detection of potential DILI events is crucial in drug development and toxicity assessment to ensure patient safety and the successful market entry of pharmaceuticals. We introduced a novel model, the Multi-view Uncertainty Deep Forest (MVU-DF), for predicting DILI. This model expands the Deep Forest architecture to multiple views and uses two-stage feature construction: intra-view feature interaction for key information within a view, and inter-view feature interaction for sharing information across views. Additionally, we incorporated uncertainty estimation to evaluate the confidence of predictions, using opinion as an alternative to probability. The opinion measures class support and incorporates uncertainty, enabling more precise differentiation of hard and easy samples in each MVU-DF iteration, enhancing the cascading scheme. The model's high interpretability enhances prediction performance and reliability. Our experiments demonstrate the potential of this research in improving the accuracy and decision-making transparency of hepatotoxicity predictions in drug development.

Computational models for predicting liver toxicity in the deep learning era.

Drug-induced liver injury (DILI) is a severe adverse reaction caused by drugs and may result in acute liver failure and even death. Many efforts have centered on mitigating risks associated with potential DILI in humans. Among these, quantitative structure-activity relationship (QSAR) was proven to be a valuable tool for early-stage hepatotoxicity screening. Its advantages include no requirement for physical substances and rapid delivery of results. Deep learning (DL) made rapid advancements recently and has been used for developing QSAR models. This review discusses the use of DL in predicting DILI, focusing on the development of QSAR models employing extensive chemical structure datasets alongside their corresponding DILI outcomes. We undertake a comprehensive evaluation of various DL methods, comparing with those of traditional machine learning (ML) approaches, and explore the strengths and limitations of DL techniques regarding their interpretability, scalability, and generalization. Overall, our review underscores the potential of DL methodologies to enhance DILI prediction and provides insights into future avenues for developing predictive models to mitigate DILI risk in humans.

InterDILI: interpretable prediction of drug-induced liver injury through permutation feature importance and attention mechanism

Safety is one of the important factors constraining the distribution of clinical drugs on the market. Drug-induced liver injury (DILI) is the leading cause of safety problems produced by drug side effects. Therefore, the DILI risk of approved drugs and potential drug candidates should be assessed. Currently, in vivo and in vitro methods are used to test DILI risk, but both methods are labor-intensive, time-consuming, and expensive. To overcome these problems, many in silico methods for DILI prediction have been suggested. Previous studies have shown that DILI prediction models can be utilized as prescreening tools, and they achieved a good performance. However, there are still limitations in interpreting the prediction results. Therefore, this study focused on interpreting the model prediction to analyze which features could potentially cause DILI. For this, five publicly available datasets were collected to train and test the model. Then, various machine learning methods were applied using substructure and physicochemical descriptors as inputs and the DILI label as the output. The interpretation of feature importance was analyzed by recognizing the following general-to-specific patterns: (i) identifying general important features of the overall DILI predictions, and (ii) highlighting specific molecular substructures which were highly related to the DILI prediction for each compound. The results indicated that the model not only captured the previously known properties to be related to DILI but also proposed a new DILI potential substructural of physicochemical properties. The models for the DILI prediction achieved an area under the receiver operating characteristic (AUROC) of 0.88–0.97 and an area under the Precision-Recall curve (AUPRC) of 0.81–0.95. From this, we hope the proposed models can help identify the potential DILI risk of drug candidates at an early stage and offer valuable insights for drug development.

Predicting drug-induced liver injury using graph attention mechanism and molecular fingerprints

Drug-induced liver injury (DILI) is a significant issue in drug development and clinical treatment due to its potential to cause liver dysfunction or damage, which, in severe cases, can lead to liver failure or even fatality. DILI has numerous pathogenic factors, many of which remain incompletely understood. Consequently, it is imperative to devise methodologies and tools for anticipatory assessment of DILI risk in the initial phases of drug development. In this study, we present DMFPGA, a novel deep learning predictive model designed to predict DILI. To provide a comprehensive description of molecular properties, we employ a multi-head graph attention mechanism to extract features from the molecular graphs, representing characteristics at the level of compound nodes. Additionally, we combine multiple fingerprints of molecules to capture features at the molecular level of compounds. The fusion of molecular fingerprints and graph features can more fully express the properties of compounds. Subsequently, we employ a fully connected neural network to classify compounds as either DILI-positive or DILI-negative. To rigorously evaluate DMFPGA's performance, we conduct a 5-fold cross-validation experiment. The obtained results demonstrate the superiority of our method over four existing state-of-the-art computational approaches, exhibiting an average AUC of 0.935 and an average ACC of 0.934. We believe that DMFPGA is helpful for early-stage DILI prediction and assessment in drug development.

Industry Review of Best Practices for Risk Management of Drug-Induced Liver Injury from Development to Real-World Use.

The relative treatment benefit of a drug for patients during development, marketing authorization review, or after approval includes an assessment of the risk of drug-induced liver injury (DILI). In this article, the Pharmacovigilance and Risk Mitigation Working Group of the IQ-DILI Initiative launched in June 2016 within the International Consortium for Innovation and Quality in Pharmaceutical Development presents and reviews three key topics for essential risk management activities to identify, characterize, monitor, mitigate, and communicate DILI risk associated with small molecules during drug development. The three topics are: (1) Current best practices for characterizing the DILI phenotype and the severity and incidence of DILI in the treatment population, including DILI identification, prediction and recovery. (2) Characterization of the relative treatment benefit for patients who will be exposed to a drug and the attendant risk of DILI in conjunction with existing global risk mitigation strategies. (3) Implementation of risk mitigation strategies during drug development highlighting patient factors, healthcare settings and site of product administration, and prescriber and healthcare provider factors. Industry guidance is provided for assessing whether the product labeling is sufficient to minimize the risk of DILI or whether a United States Food and Drug Administration (FDA) Risk Evaluation and Mitigation Strategy (REMS) or European Medicines Agency (EMA) Risk Management Plan (RMP) with additional Risk Minimization Measures (aRMM) is needed.

GeoDILI: A Robust and Interpretable Model for Drug-Induced Liver Injury Prediction Using Graph Neural Network-Based Molecular Geometric Representation.

Drug-induced liver injury (DILI) is a significant cause of drug failure and withdrawal due to liver damage. Accurate prediction of hepatotoxic compounds is crucial for safe drug development. Several DILI prediction models have been published, but they are built on different data sets, making it difficult to compare model performance. Moreover, most existing models are based on molecular fingerprints or descriptors, neglecting molecular geometric properties and lacking interpretability. To address these limitations, we developed GeoDILI, an interpretable graph neural network that uses a molecular geometric representation. First, we utilized a geometry-based pretrained molecular representation and optimized it on the DILI data set to improve predictive performance. Second, we leveraged gradient information to obtain high-precision atomic-level weights and deduce the dominant substructure. We benchmarked GeoDILI against recently published DILI prediction models, as well as popular GNN models and fingerprint-based machine learning models using the same data set, showing superior predictive performance of our proposed model. We applied the interpretable method in the DILI data set and derived seven precise and mechanistically elucidated structural alerts. Overall, GeoDILI provides a promising approach for accurate and interpretable DILI prediction with potential applications in drug discovery and safety assessment. The data and source code are available at GitHub repository (https://github.com/CSU-QJY/GeoDILI).

A blinded in vitro analysis of the intrinsic immunogenicity of hepatotoxic drugs: implications for preclinical risk assessment.

In vitro preclinical drug-induced liver injury (DILI) risk assessment relies largely on the use of hepatocytes to measure drug-specific changes in cell function or viability. Unfortunately, this does not provide indications toward the immunogenicity of drugs and/or the likelihood of idiosyncratic reactions in the clinic. This is because the molecular initiating event in immune DILI is an interaction of the drug-derived antigen with MHC proteins and the T-cell receptor. This study utilized immune cells from drug-naïve donors, recently established immune cell coculture systems and blinded compounds with and without DILI liabilities to determine whether these new methods offer an improvement over established assessment methods for the prediction of immune-mediated DILI. Ten blinded test compounds (6 with known DILI liabilities; 4 with lower DILI liabilities) and 5 training compounds, with known T-cell-mediated immune reactions in patients, were investigated. Naïve T-cells were activated with 4/5 of the training compounds (nitroso sulfamethoxazole, vancomycin, Bandrowski's base, and carbamazepine) and clones derived from the priming assays were activated with drug in a dose-dependent manner. The test compounds with DILI liabilities did not stimulate T-cell proliferative responses during dendritic cell-T-cell coculture; however, CD4+ clones displaying reactivity were detected toward 2 compounds (ciprofloxacin and erythromycin) with known liabilities. Drug-responsive T-cells were not detected with the compounds with lower DILI liabilities. This study provides compelling evidence that assessment of intrinsic drug immunogenicity, although complex, can provide valuable information regarding immune liabilities of some compounds prior to clinical studies or when immune reactions are observed in patients.

Integrating Liver-Chip data into pharmaceutical decision-making processes

ABSTRACT Introduction Drug-induced liver injury (DILI) is a potentially lethal condition that heavily impacts the pharmaceutical industry, causing approximately 21% of drug withdrawals and 13% of clinical trial failures. Recent evidence suggests that the use of Liver-Chip technology in preclinical safety testing may significantly reduce DILI-related clinical trial failures and withdrawals. However, drug developers and regulators would benefit from guidance on the integration of Liver-Chip data into decision-making processes to facilitate the technology’s adoption. Areas covered This perspective builds on the findings of the performance assessment of the Emulate Liver-Chip in the context of DILI prediction and introduces two new decision-support frameworks: the first uses the Liver-Chip’s quantitative output to elucidate DILI severity and enable more nuanced risk analysis; the second integrates Liver-Chip data with standard animal testing results to help assess whether to progress a candidate drug into clinical trials. Expert opinion There is now strong evidence that Liver-Chip technology could significantly reduce the incidence of DILI in drug development. As this is a patient safety issue, it is imperative that developers and regulators explore the incorporation of the technology. The frameworks presented enable the integration of the Liver-Chip into various stages of preclinical development in support of safety assessment.

Busulfan induces steatosis in HepaRG cells but not in primary human hepatocytes: Possible explanations and implication for the prediction of drug-induced liver injury.

The antineoplastic drug busulfan can induce different hepatic lesions including cholestasis and sinusoidal obstruction syndrome. However, hepatic steatosis has never been reported in patients. This study aimed to determine whether busulfan could induce steatosis in primary human hepatocytes (PHH) and differentiated HepaRG cells. Neutral lipids were determined in PHH and HepaRG cells. Mechanistic investigations were performed in HepaRG cells by measuring metabolic fluxes linked to lipid homeostasis, reduced glutathione (GSH) levels, and expression of genes involved in lipid metabolism and endoplasmic reticulum (ER) stress. Analysis of two previous transcriptomic datasets was carried out. Busulfan induced lipid accumulation in HepaRG cells but not in six different batches of PHH. In HepaRG cells, busulfan impaired VLDL secretion, increased fatty acid uptake, and induced ER stress. Transcriptomic data analysis and decreased GSH levels suggested that busulfan-induced steatosis might be linked to the high expression of glutathione S-transferase (GST) isoenzyme A1, which is responsible for the formation of the hepatotoxic sulfonium cation conjugate. In keeping with this, the GST inhibitor ethacrynic acid and the chemical chaperone tauroursodeoxycholic acid alleviated busulfan-induced lipid accumulation in HepaRG cells supporting the role of the sulfonium cation conjugate and ER stress in steatosis. While the HepaRG cell line is an invaluable tool for pharmacotoxicological studies, it might not be always an appropriate model to predict and mechanistically investigate drug-induced liver injury. Hence, we recommend carrying out toxicological investigations in both HepaRG cells and PHH to avoid drawing wrong conclusions on the potential hepatotoxicity of drugs and other xenobiotics.

Development and Verification of Time-Series Deep Learning for Drug-Induced Liver Injury Detection in Patients Taking Angiotensin II Receptor Blockers: A Multicenter Distributed Research Network Approach.

The objective of this study was to develop and validate a multicenter-based, multi-model, time-series deep learning model for predicting drug-induced liver injury (DILI) in patients taking angiotensin receptor blockers (ARBs). The study leveraged a national-level multicenter approach, utilizing electronic health records (EHRs) from six hospitals in Korea. A retrospective cohort analysis was conducted using EHRs from six hospitals in Korea, comprising a total of 10,852 patients whose data were converted to the Common Data Model. The study assessed the incidence rate of DILI among patients taking ARBs and compared it to a control group. Temporal patterns of important variables were analyzed using an interpretable timeseries model. The overall incidence rate of DILI among patients taking ARBs was found to be 1.09%. The incidence rates varied for each specific ARB drug and institution, with valsartan having the highest rate (1.24%) and olmesartan having the lowest rate (0.83%). The DILI prediction models showed varying performance, measured by the average area under the receiver operating characteristic curve, with telmisartan (0.93), losartan (0.92), and irbesartan (0.90) exhibiting higher classification performance. The aggregated attention scores from the models highlighted the importance of variables such as hematocrit, albumin, prothrombin time, and lymphocytes in predicting DILI. Implementing a multicenter-based timeseries classification model provided evidence that could be valuable to clinicians regarding temporal patterns associated with DILI in ARB users. This information supports informed decisions regarding appropriate drug use and treatment strategies.

In silico prediction of drug-induced liver injury with a complementary integration strategy based on hybrid representation.

Drug-induced liver injury (DILI) is one of the major causes of drug withdrawals, acute liver injury and blackbox warnings. Clinical diagnosis of DILI is a huge challenge due to the complex pathogenesis and lack of specific biomarkers. In recent years, machine learning methods have been used for DILI risk assessment, but the model generalization does not perform satisfactorily. In this study, we constructed a large DILI data set and proposed an integration strategy based on hybrid representations for DILI prediction (HR-DILI). Benefited from feature integration, the hybrid graph neural network models outperformed single representation-based models, among which hybrid-GraphSAGE showed balanced performance in cross-validation with AUC (area under the curve) as 0.804 ± 0.019. In the external validation set, HR-DILI improved the AUC by 6.4%-35.9% compared to the base model with a single representation. Compared with published DILI prediction models, HR-DILI had better and balanced performance. The performance of local models for natural products and synthetic compounds were also explored. Furthermore, eight key descriptors and six structural alerts associated with DILI were analyzed to increase the interpretability of the models. The improved performance of HR-DILI indicated that it would provide reliable guidance for DILI risk assessment.

Comprehensive characterization of natural products of Polygonum multiflorum by cheminformatics analysis

IntroductionA growing body of evidence has suggested that Polygonum multiflorum Thunb. (PM) may cause PM-herb-induced liver injury (PM-HILI). However, the compounds triggering PM-HILI remain controversial. Herein, we set out to investigate the relationships among natural products of PM (NPPM), drug-induced liver injury (DILI) positive (POS), and negative (NEG) compounds by using cheminformatics methods. MethodsA total of 197 NPPM and 2384 annotated DILI dataset were collected from the literature. Chemical space, physicochemical properties, drug-likeness, intra-set similarity, and scaffold diversity were compared to gain insights into the multiple features of NPPM. An ensemble machine learning (ML) model was constructed to predict the DILI potential of NPPM. Twelve NPPM were selected and tested on HepaRG cells to validate the prediction results. ResultsResults of the principal component analysis suggest that NPPM bears more similarity to NEG in terms of chemical space when compared with POS. Besides, NPPM share a moderate overall scaffold diversity and one-third ingredients in NPPM compiled the drug-like rules. The predictive results of ML model show that 28.9% of the small molecules in NPPM bear DILI potential. Further in vitro study by detecting cytotoxicity of representative compounds on HepaRG cells showed that trans- and cis-emodin-physcion dianthrone exhibited the lowest IC50 values of 53.05 µM and 17.11 µM, respectively. ConclusionML methods and further validation recognize the liver toxicity of dianthonres and emodins. A proportion of NPPM components exhibit drug-likeness profiles and might offer complementary resources for drug discovery. The results demonstrated machine learning-powered DILI prediction as a useful tool to study potential DILI risk of compounds, providing a basis for further identification of toxins or leads in PM. The codes used and generated in this study are freely available at https://github.com/dreadlesss/Polygonum_database_analysis.

Significance of histological assessment in drug-induced liver injury

Liver histological assessment is of great clinical significance for the diagnosis, classification, and prognosis prediction of drug-induced liver injury (DILI). Liver histological evaluation can effectively supplement RUCAM. The clinical phenotypes of DILI are complex and diverse, including acute, chronic and severe hepatic injury. DILI has multiple insult-targets, including hepatocytes, cholangiocytes, and vascular endothelial cells and others. The pathological damage patterns are similar to many types of non-DILI liver diseases, therefore making differential diagnosis difficult. New anti-tumor drugs such as immune checkpoints inhibitors and targeted therapy are widely used in clinical antineoplastic practice, thus the growing incidence of related liver injury occurs. Liver histological examination can effectively assess the pathological phenotypes and severity of DILI, so as to guide treatment. In uncommon conditions such as special types of DILI (such as hepatic vascular disease), DILI with other competitive etiology overlapping, chronic DILI, and DILI induced liver failure, liver histological assessment can provide strong support for identifying the cause, rational treatment, and prognosis. Currently, the histological evaluation system for drug-induced liver injury seems to be a lack of consensus, and the diagnosis of DILI is short of highly specific and sensitive serological markers. All in all, liver histological assessment plays a crucial role in the diagnosis and differential diagnosis of DILI.

Supervised chemical graph mining improves drug-induced liver injury prediction

Drug-induced liver injury (DILI) is the main cause of drug failure in clinical trials. The characterization of toxic compounds in terms of chemical structure is important because compounds can be metabolized to toxic substances in the liver. Traditional machine learning approaches have had limited success in predicting DILI, and emerging deep graph neural network (GNN) models are yet powerful enough to predict DILI. In this study, we developed a completely different approach, supervised subgraph mining (SSM), a strategy to mine explicit subgraph features by iteratively updating individual graph transitions to maximize DILI fidelity. Our method outperformed previous methods including state-of-the-art GNN tools in classifying DILI on two different datasets: DILIst and TDC-benchmark. We also combined the subgraph features by using SMARTS-based frequent structural pattern matching and associated them with drugs' ATC code.

Applications of In Silico Models to Predict Drug-Induced Liver Injury.

Drug-induced liver injury (DILI) is a major cause of the withdrawal of pre-marketed drugs, typically attributed to oxidative stress, mitochondrial damage, disrupted bile acid homeostasis, and innate immune-related inflammation. DILI can be divided into intrinsic and idiosyncratic DILI with cholestatic liver injury as an important manifestation. The diagnosis of DILI remains a challenge today and relies on clinical judgment and knowledge of the insulting agent. Early prediction of hepatotoxicity is an important but still unfulfilled component of drug development. In response, in silico modeling has shown good potential to fill the missing puzzle. Computer algorithms, with machine learning and artificial intelligence as a representative, can be established to initiate a reaction on the given condition to predict DILI. DILIsym is a mechanistic approach that integrates physiologically based pharmacokinetic modeling with the mechanisms of hepatoxicity and has gained increasing popularity for DILI prediction. This article reviews existing in silico approaches utilized to predict DILI risks in clinical medication and provides an overview of the underlying principles and related practical applications.

DeepCausality: A general AI-powered causal inference framework for free text: A case study of LiverTox.

Causality plays an essential role in multiple scientific disciplines, including the social, behavioral, and biological sciences and portions of statistics and artificial intelligence. Manual-based causality assessment from a large number of free text-based documents is very time-consuming, labor-intensive, and sometimes even impractical. Herein, we proposed a general causal inference framework named DeepCausality to empirically estimate the causal factors for suspected endpoints embedded in the free text. The proposed DeepCausality seamlessly incorporates AI-powered language models, named entity recognition and Judea Pearl's Do-calculus, into a general framework for causal inference to fulfill different domain-specific applications. We exemplified the utility of the proposed DeepCausality framework by employing the LiverTox database to estimate idiosyncratic drug-induced liver injury (DILI)-related causal terms and generate a knowledge-based causal tree for idiosyncratic DILI patient stratification. Consequently, the DeepCausality yielded a prediction performance with an accuracy of 0.92 and an F-score of 0.84 for the DILI prediction. Notably, 90% of causal terms enriched by the DeepCausality were consistent with the clinical causal terms defined by the American College of Gastroenterology (ACG) clinical guideline for evaluating suspected idiosyncratic DILI (iDILI). Furthermore, we observed a high concordance of 0.91 between the iDILI severity scores generated by DeepCausality and domain experts. Altogether, the proposed DeepCausality framework could be a promising solution for causality assessment from free text and is publicly available through https://github.com/XingqiaoWang/https-github.com-XingqiaoWang-DeepCausality-LiverTox.

In Vitro Models for Studying Chronic Drug-Induced Liver Injury.

Drug-induced liver injury (DILI) is a major clinical problem in terms of patient morbidity and mortality, cost to healthcare systems and failure of the development of new drugs. The need for consistent safety strategies capable of identifying a potential toxicity risk early in the drug discovery pipeline is key. Human DILI is poorly predicted in animals, probably due to the well-known interspecies differences in drug metabolism, pharmacokinetics, and toxicity targets. For this reason, distinct cellular models from primary human hepatocytes or hepatoma cell lines cultured as 2D monolayers to emerging 3D culture systems or the use of multi-cellular systems have been proposed for hepatotoxicity studies. In order to mimic long-term hepatotoxicity in vitro, cell models, which maintain hepatic phenotype for a suitably long period, should be used. On the other hand, repeated-dose administration is a more relevant scenario for therapeutics, providing information not only about toxicity, but also about cumulative effects and/or delayed responses. In this review, we evaluate the existing cell models for DILI prediction focusing on chronic hepatotoxicity, highlighting how better characterization and mechanistic studies could lead to advance DILI prediction.

Prediction of drug-induced liver injury and cardiotoxicity using chemical structure and in vitro assay data

Drug-induced liver injury (DILI) and cardiotoxicity (DICT) are major adverse effects triggered by many clinically important drugs. To provide an alternative to in vivo toxicity testing, the U.S. Tox21 consortium has screened a collection of ∼10K compounds, including drugs in clinical use, against >70 cell-based assays in a quantitative high-throughput screening (qHTS) format. In this study, we compiled reference compound lists for DILI and DICT and compared the potential of Tox21 assay data with chemical structure information in building prediction models for human in vivo hepatotoxicity and cardiotoxicity. Models were built with four different machine learning algorithms (e.g., Random Forest, Naïve Bayes, eXtreme Gradient Boosting, and Support Vector Machine) and model performance was evaluated by calculating the area under the receiver operating characteristic curve (AUC-ROC). Chemical structure-based models showed reasonable predictive power for DILI (best AUC-ROC = 0.75 ± 0.03) and DICT (best AUC-ROC = 0.83 ± 0.03), while Tox21 assay data alone only showed better than random performance. DILI and DICT prediction models built using a combination of assay data and chemical structure information did not have a positive impact on model performance. The suboptimal predictive performance of the assay data is likely due to insufficient coverage of an adequately predictive number of toxicity mechanisms. The Tox21 consortium is currently expanding coverage of biological response space with additional assays that probe toxicologically important targets and under-represented pathways that may improve the prediction of in vivo toxicity such as DILI and DICT.

ToxSTAR: drug-induced liver injury prediction tool for the web environment.

Drug-induced liver injury (DILI) is a challenging endpoint in predictive toxicology because of the complex reactive metabolites that cause liver damage and the wide range of mechanisms involved in the development of the disease. ToxSTAR provides structural similarity-based DILI analysis and in-house DILI prediction models that predict four DILI subtypes (cholestasis, cirrhosis, hepatitis and steatosis) based on drug and drug metabolite molecules. ToxSTAR is freely available at https://toxstar.kitox.re.kr/. Supplementary data are available at Bioinformatics online.