Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data.

Drug-induced liver injury (DILI) is an important safety concern and a major reason to remove a drug from the market. Advancements in recent machine learning methods have led to a wide range of in silico models for DILI predictive methods based on molecule chemical structures (fingerprints). Existing publicly available DILI data sets used for model building are based on the interpretation of drug labels or patient case reports, resulting in a typical binary clinical DILI annotation. We developed a novel phenotype-based annotation to process hepatotoxicity information extracted from repeated dose in vivo preclinical toxicology studies using INHAND annotation to provide a more informative and reliable data set for machine learning algorithms. This work resulted in a data set of 430 unique compounds covering diverse liver pathology findings which were utilized to develop multiple DILI prediction models trained on the publicly available data (TG-GATEs) using the compound's fingerprint. We demonstrate that the TG-GATEs compounds DILI labels can be predicted well and how the differences between TG-GATEs and the external test compounds (Johnson & Johnson) impact the model generalization performance.

AI/ML Models to Predict the Severity of Drug-Induced Liver Injury for Small Molecules.

Drug-induced liver injury (DILI), believed to be a multifactorial toxicity, has been a leading cause of attrition of small molecules during discovery, clinical development, and postmarketing. Identification of DILI risk early reduces the costs and cycle times associated with drug development. In recent years, several groups have reported predictive models that use physicochemical properties or in vitro and in vivo assay endpoints; however, these approaches have not accounted for liver-expressed proteins and drug molecules. To address this gap, we have developed an integrated artificial intelligence/machine learning (AI/ML) model to predict DILI severity for small molecules using a combination of physicochemical properties and off-target interactions predicted in silico. We compiled a data set of 603 diverse compounds from public databases. Among them, 164 were categorized as Most DILI (M-DILI), 245 as Less DILI (L-DILI), and 194 as No DILI (N-DILI) by the FDA. Six machine learning methods were used to create a consensus model for predicting the DILI potential. These methods include k-nearest neighbor (k-NN), support vector machine (SVM), random forest (RF), Naïve Bayes (NB), artificial neural network (ANN), logistic regression (LR), weighted average ensemble learning (WA) and penalized logistic regression (PLR). Among the analyzed ML methods, SVM, RF, LR, WA, and PLR identified M-DILI and N-DILI compounds, achieving a receiver operating characteristic area under the curve of 0.88, sensitivity of 0.73, and specificity of 0.9. Approximately 43 off-targets, along with physicochemical properties (fsp3, log S, basicity, reactive functional groups, and predicted metabolites), were identified as significant factors in distinguishing between M-DILI and N-DILI compounds. The key off-targets that we identified include: PTGS1, PTGS2, SLC22A12, PPARγ, RXRA, CYP2C9, AKR1C3, MGLL, RET, AR, and ABCC4. The present AI/ML computational approach therefore demonstrates that the integration of physicochemical properties and predicted on- and off-target biological interactions can significantly improve DILI predictivity compared to chemical properties alone.

Leveraging Cell Painting Images to Expand the Applicability Domain and Actively Improve Deep Learning Quantitative Structure-Activity Relationship Models.

The search for chemical hit material is a lengthy and increasingly expensive drug discovery process. To improve it, ligand-based quantitative structure-activity relationship models have been broadly applied to optimize primary and secondary compound properties. Although these models can be deployed as early as the stage of molecule design, they have a limited applicability domain─if the structures of interest differ substantially from the chemical space on which the model was trained, a reliable prediction will not be possible. Image-informed ligand-based models partly solve this shortcoming by focusing on the phenotype of a cell caused by small molecules, rather than on their structure. While this enables chemical diversity expansion, it limits the application to compounds physically available and imaged. Here, we employ an active learning approach to capitalize on both of these methods' strengths and boost the model performance of a mitochondrial toxicity assay (Glu/Gal). Specifically, we used a phenotypic Cell Painting screen to build a chemistry-independent model and adopted the results as the main factor in selecting compounds for experimental testing. With the additional Glu/Gal annotation for selected compounds we were able to dramatically improve the chemistry-informed ligand-based model with respect to the increased recognition of compounds from a 10% broader chemical space.

Introduction to a manuscript series on the characterization and use of microphysiological systems (MPS) in pharmaceutical safety and ADME applications.

Safety related drug failures continue to be a challenge for pharmaceutical companies despite the numerous complex and lengthy in vitro assays and in vivo studies that make up the typical safety screening funnel. A lack of complete translation of animal data to humans can explain some of those shortcomings. Differences in sensitivity and drug disposition between animals and humans may also play a role. Many gaps exist for potential target tissues of drugs that cannot be adequately modeled in vitro. Microphysiological systems (MPS) may help to better model these target tissues and provide an opportunity to better assess some aspects of human safety prior to clinical studies. There is hope that these systems can supplement current preclinical drug safety and disposition evaluations, filling gaps and enhancing our ability to predict and understand human relevant toxicities. The International Consortium for Innovation and Quality in Pharmaceutical Development (IQ) MPS Affiliate is a group of pharmaceutical industry scientists who seek to expedite appropriate characterization and incorporation of MPS to potentially improve drug safety assessment and provide safer and more effective medicines to patients. In keeping with this mission, the IQ MPS Affiliate scientists have prepared a series of organotypic manuscripts for several key drug safety and disposition target tissues (lung, liver, kidney, skin, gastrointestinal, cardiovascular, and blood brain barrier/central nervous system). The goal of these manuscripts is to provide key information related to likely initial contexts of use (CoU) and key characterization data needed for incorporation of MPS in pharmaceutical safety screening including a list of characteristic functions, cell types, toxicities, and test agents (representing major mechanisms of toxicity) that can be used by MPS developers. Additional manuscripts focusing on testing biologically based therapeutics and ADME considerations have been prepared as part of this effort. These manuscripts focus on general needs for assessing biologics and ADME endpoints and include similar information to the tissue specific manuscripts where appropriate. The current manuscript is an introduction to several general concepts related to pharmaceutical industry needs with regard to MPS application and other MPS concepts that apply across the organ specific manuscripts.

Moving beyond Binary Predictions of Human Drug-Induced Liver Injury (DILI) toward Contrasting Relative Risk Potential.

The hepatic risk matrix (HRM) was developed and used to differentiate lead clinical and back-up drug candidates against competitor/marketed drugs within the same pharmaceutical class for their potential to cause human drug-induced liver injury (DILI). The hybrid HRM scoring system blends physicochemical properties (Rule of Two Model: dose and lipophilicity or Partition Model: dose, ionization state, lipophilicity, and fractional carbon bond saturation) with common toxicity mechanisms (cytotoxicity, mitochondrial dysfunction, and bile salt export pump (BSEP) inhibition) that promote DILI. HRM scores are based on bracketed safety margins (<1, 1-10, 10-100, and >100× clinical Cmax,total). On the basis of well-established clinical safety experience of marketed/withdrawn drug candidates, the background analysis consists of 200 drugs from the Liver Toxicity Knowledge Base annotated as Most-DILI- (79), Less-DILI- (56), No-DILI- (47), and Ambiguous-DILI-concern (18) drugs. Scores were generated for over 21 internal and 7 external drug candidates discontinued for unacceptable incidence/magnitude of liver transaminase elevations during clinical trials or withdrawn for liver injury severity. Both hybrid scoring systems identified 70-80% Most-DILI-concern drugs, but more importantly, stratified successful/unsuccessful drug candidates for liver safety (incidence/severity of transaminase elevations and approved drug labels). Incorporating other mechanisms (reactive metabolite and cytotoxic metabolite generation and hepatic efflux transport inhibition, other than BSEP) to the HRM had minimal beneficial impact in DILI prediction/stratification. As is, the hybrid scoring system was positioned for portfolio assessments to contrast DILI risk potential of small molecule drug candidates in early clinical development. This stratified approach for DILI prediction aided decisions regarding drug candidate progression, follow-up mechanistic work, back-up selection, clinical dose selection, and due diligence assessments in favor of compounds with less implied clinical hepatotoxicity risk.

Drug-Induced Mitochondrial Toxicity in the Geriatric Population: Challenges and Future Directions.

Mitochondrial function declines with age, leading to a variety of age-related diseases (metabolic, central nervous system-related, cancer, etc.) and medication usage increases with age due to the increase in diseases. Drug-induced mitochondrial toxicity has been described for many different drug classes and can lead to liver, muscle, kidney and central nervous system injury and, in rare cases, to death. Many of the most prescribed medications in the geriatric population carry mitochondrial liabilities. We have demonstrated that, over the past decade, each class of drugs that demonstrated mitochondrial toxicity contained drugs with both more and less adverse effects on mitochondria. As patient treatment is often essential, we suggest using medication(s) with the best safety profile and the avoidance of concurrent usage of multiple medications that carry mitochondrial liabilities. In addition, we also recommend lifestyle changes to further improve one's mitochondrial function, such as weight loss, exercise and nutrition.

Evaluation of in Vitro Mitochondrial Toxicity Assays and Physicochemical Properties for Prediction of Organ Toxicity Using 228 Pharmaceutical Drugs.

Mitochondrial toxicity has been shown to contribute to a variety of organ toxicities such as liver, cardiac, and kidney. In the past decades, two high-throughput applicable screening assays (isolated rat liver mitochondria; glucose-galactose grown HepG2 cells) to assess mitochondrial toxicity have been deployed in many pharmaceutical companies, and numerous publications have demonstrated its usefulness for mechanistic investigations. However, only two publications have demonstrated the utility of these screens as a predictor of human drug-induced liver injury. In the present study, we screened 73 hepatotoxicants, 46 cardiotoxicants, 49 nephrotoxicants, and 60 compounds not known to cause human organ toxicity for their effects on mitochondrial function(s) in the assays mentioned above. Predictive performance was evaluated using specificity and sensitivity of the assays for predicting organ toxicity. Our results show that the predictive performance of the mitochondrial assays are superior for hepatotoxicity as compared to cardiotoxicity and nephrotoxicity (sensitivity 63% vs 33% and 28% with similar specificity of 93%), when the analysis was done at 100* Cmax (drug concentration in human plasma level). We further explored the association of mitochondrial toxicity with physicochemical properties such as calculated log partition coefficient (cLogP), topological polar surface area, ionization status, and molecular weight of the drugs and found that cLogP was most significantly associated mitochondrial toxicity. Since these assays are amenable to higher throughput, we recommend that chemists use these assays to perform structure activity relationship early in the drug discovery process, when chemical matter is abundant. This assures that compounds that lack the propensity to cause mitochondrial dysfunction (and associated organ toxicity) will move forward into animals and humans.

High-Throughput Analysis of Mitochondrial Oxygen Consumption.

Interest in the investigation of mitochondrial dysfunction has seen a resurgence over recent years due to the implication of such dysfunction in both drug-induced toxicity and a variety of disease states. Here we describe a methodology to assist in such investigations whereby the oxygen consumption of isolated mitochondria is assessed in a high-throughput fashion using a phosphorescent oxygen-sensitive probe , standard microtiter plates, and plate reader detection. The protocols provided describe the required isolation procedures, initial assay optimization, and subsequent compound screening. Typical data is also provided illustrating the expected activity levels as well as recommended plate maps and data analysis approaches.

Guidelines on experimental methods to assess mitochondrial dysfunction in cellular models of neurodegenerative diseases.

Neurodegenerative diseases are a spectrum of chronic, debilitating disorders characterised by the progressive degeneration and death of neurons. Mitochondrial dysfunction has been implicated in most neurodegenerative diseases, but in many instances it is unclear whether such dysfunction is a cause or an effect of the underlying pathology, and whether it represents a viable therapeutic target. It is therefore imperative to utilise and optimise cellular models and experimental techniques appropriate to determine the contribution of mitochondrial dysfunction to neurodegenerative disease phenotypes. In this consensus article, we collate details on and discuss pitfalls of existing experimental approaches to assess mitochondrial function in in vitro cellular models of neurodegenerative diseases, including specific protocols for the measurement of oxygen consumption rate in primary neuron cultures, and single-neuron, time-lapse fluorescence imaging of the mitochondrial membrane potential and mitochondrial NAD(P)H. As part of the Cellular Bioenergetics of Neurodegenerative Diseases (CeBioND) consortium ( www.cebiond.org ), we are performing cross-disease analyses to identify common and distinct molecular mechanisms involved in mitochondrial bioenergetic dysfunction in cellular models of Alzheimer's, Parkinson's, and Huntington's diseases. Here we provide detailed guidelines and protocols as standardised across the five collaborating laboratories of the CeBioND consortium, with additional contributions from other experts in the field.

An Industry Perspective on the 2017 EMA Guideline on First-in-Human and Early Clinical Trials.

The European Medicines Agency (EMA) in 2017 issued a revised guideline on nonclinical and clinical aspects of first-in-human (FIH) and early clinical trials (CTs). External input was solicited during a draft comment phase, and although some industry suggestions were adopted, others were not. We agree that subject safety is of utmost priority, and believe that minimizing risk must be balanced with efficient and informative study designs to bring new medicines to patients.

Prediction of metabolism-induced hepatotoxicity on three-dimensional hepatic cell culture and enzyme microarrays.

Human liver contains various oxidative and conjugative enzymes that can convert nontoxic parent compounds to toxic metabolites or, conversely, toxic parent compounds to nontoxic metabolites. Unlike primary hepatocytes, which contain myriad drug-metabolizing enzymes (DMEs), but are difficult to culture and maintain physiological levels of DMEs, immortalized hepatic cell lines used in predictive toxicity assays are easy to culture, but lack the ability to metabolize compounds. To address this limitation and predict metabolism-induced hepatotoxicity in high-throughput, we developed an advanced miniaturized three-dimensional (3D) cell culture array (DataChip 2.0) and an advanced metabolizing enzyme microarray (MetaChip 2.0). The DataChip is a functionalized micropillar chip that supports the Hep3B human hepatoma cell line in a 3D microarray format. The MetaChip is a microwell chip containing immobilized DMEs found in the human liver. As a proof of concept for generating compound metabolites in situ on the chip and rapidly assessing their toxicity, 22 model compounds were dispensed into the MetaChip and sandwiched with the DataChip. The IC50 values obtained from the chip platform were correlated with rat LD50 values, human C max values, and drug-induced liver injury categories to predict adverse drug reactions in vivo. As a result, the platform had 100% sensitivity, 86% specificity, and 93% overall predictivity at optimum cutoffs of IC50 and C max values. Therefore, the DataChip/MetaChip platform could be used as a high-throughput, early stage, microscale alternative to conventional in vitro multi-well plate platforms and provide a rapid and inexpensive assessment of metabolism-induced toxicity at early phases of drug development.

Metabolic Syndrome and Associated Diseases: From the Bench to the Clinic.

Metabolic Syndrome and Associated Diseases: From the Bench to the Clinic, a Society of Toxicology Contemporary Concepts in Toxicology (CCT) workshop was held on March 11, 2017. The meeting was convened to raise awareness of metabolic syndrome and its associated diseases and serve as a melting pot with scientists of multiple disciplines (eg, toxicologists, clinicians, regulators) so as to spur research and understanding of this condition. The criteria for metabolic syndrome include obesity, dyslipidemia (low high-density lipoprotein and/or elevated triglycerides), elevated blood pressure, and alterations in glucose metabolism. It can lead to a greater potential of type 2 diabetes, lipid disorders, cardiovascular disease, hepatic steatosis, and other circulatory disorders. Although there are no approved drugs specifically for this syndrome, many drugs target diseases associated with this syndrome thus potentially increasing the likelihood of drug-drug interactions. There is currently significant research focusing on understanding the key pathways that control metabolism, which would be likely targets of risk factors (eg, exposure to xenobiotics, genetics) and lifestyle factors (eg, microbiome, nutrition, and exercise) that contribute to metabolic syndrome. Understanding these pathways could also lead to the development of pharmaceutical interventions. As individuals with metabolic syndrome have signs similar to that of toxic responses (eg, oxidative stress and inflammation) and organ dysfunction, these alterations should be taken into account in drug development. With the increasing frequency of metabolic syndrome in the general population, the idea of a "normal" individual may need to be redefined. This paper reports on the substance and outcomes of this workshop.

Navigating tissue chips from development to dissemination: A pharmaceutical industry perspective.

Tissue chips are poised to deliver a paradigm shift in drug discovery. By emulating human physiology, these chips have the potential to increase the predictive power of preclinical modeling, which in turn will move the pharmaceutical industry closer to its aspiration of clinically relevant and ultimately animal-free drug discovery. Despite the tremendous science and innovation invested in these tissue chips, significant challenges remain to be addressed to enable their routine adoption into the industrial laboratory. This article describes the main steps that need to be taken and highlights key considerations in order to transform tissue chip technology from the hands of the innovators into those of the industrial scientists. Written by scientists from 13 pharmaceutical companies and partners at the National Institutes of Health, this article uniquely captures a consensus view on the progression strategy to facilitate and accelerate the adoption of this valuable technology. It concludes that success will be delivered by a partnership approach as well as a deep understanding of the context within which these chips will actually be used. Impact statement The rapid pace of scientific innovation in the tissue chip (TC) field requires a cohesive partnership between innovators and end users. Near term uptake of these human-relevant platforms will fill gaps in current capabilities for assessing important properties of disposition, efficacy and safety liabilities. Similarly, these platforms could support mechanistic studies which aim to resolve challenges later in development (e.g. assessing the human relevance of a liability identified in animal studies). Building confidence that novel capabilities of TCs can address real world challenges while they themselves are being developed will accelerate their application in the discovery and development of innovative medicines. This article outlines a strategic roadmap to unite innovators and end users thus making implementation smooth and rapid. With the collective contributions from multiple international pharmaceutical companies and partners at National Institutes of Health, this article should serve as an invaluable resource to the multi-disciplinary field of TC development.

Current nonclinical testing paradigms in support of safe clinical trials: An IQ Consortium DruSafe perspective.

The transition from nonclinical to First-in-Human (FIH) testing is one of the most challenging steps in drug development. In response to serious outcomes in a recent Phase 1 trial (sponsored by Bial), IQ Consortium/DruSafe member companies reviewed their nonclinical approach to progress small molecules safely to FIH trials. As a common practice, safety evaluation begins with target selection and continues through iterative in silico and in vitro screening to identify molecules with increased probability of acceptable in vivo safety profiles. High attrition routinely occurs during this phase. In vivo exploratory and pivotal FIH-enabling toxicity studies are then conducted to identify molecules with a favorable benefit-risk profile for humans. The recent serious incident has reemphasized the importance of nonclinical testing plans that are customized to the target, the molecule, and the intended clinical plan. Despite the challenges and inherent risks of transitioning from nonclinical to clinical testing, Phase 1 studies have a remarkably good safety record. Given the rapid scientific evolution of safety evaluation, testing paradigms and regulatory guidance must evolve with emerging science. The authors posit that the practices described herein, together with science-based risk assessment and management, support safe FIH trials while advancing development of important new medicines.

Fluorescence-Based Microplate Assays for In Vitro Assessment of Mitochondrial Toxicity, Metabolic Perturbation, and Cellular Oxygenation.

High-throughput in vitro cell metabolism assays are of particular use for identification and delineation of mitochondrial toxicity and related metabolic perturbation. Here, a panel of fluorescence-based metabolism assays are described for measuring oxygen consumption, glycolytic flux, and cellular oxygenation. They can be applied to analysis of both isolated mitochondria and cell models. Sample data are presented illustrating how these protocols can be used to examine drug treatment, the interplay between oxidative and glycolytic ATP generation, and the impact of cell oxygenation on this balance. Descriptions are provided on how these measurements can be applied to 3D systems and how they can be multiplexed with other relevant metabolic readouts. Mitochondrial isolation and cell permeabilization protocols are also provided. © 2016 by John Wiley & Sons, Inc.

Key Challenges and Opportunities Associated with the Use of In Vitro Models to Detect Human DILI: Integrated Risk Assessment and Mitigation Plans.

Drug-induced liver injury (DILI) is a major cause of late-stage clinical drug attrition, market withdrawal, black-box warnings, and acute liver failure. Consequently, it has been an area of focus for toxicologists and clinicians for several decades. In spite of considerable efforts, limited improvements in DILI prediction have been made and efforts to improve existing preclinical models or develop new test systems remain a high priority. While prediction of intrinsic DILI has improved, identifying compounds with a risk for idiosyncratic DILI (iDILI) remains extremely challenging because of the lack of a clear mechanistic understanding and the multifactorial pathogenesis of idiosyncratic drug reactions. Well-defined clinical diagnostic criteria and risk factors are also missing. This paper summarizes key data interpretation challenges, practical considerations, model limitations, and the need for an integrated risk assessment. As demonstrated through selected initiatives to address other types of toxicities, opportunities exist however for improvement, especially through better concerted efforts at harmonization of current, emerging and novel in vitro systems or through the establishment of strategies for implementation of preclinical DILI models across the pharmaceutical industry. Perspectives on the incorporation of newer technologies and the value of precompetitive consortia to identify useful practices are also discussed.

Development of a cell viability assay to assess drug metabolite structure-toxicity relationships.

Many adverse drug reactions are caused by the cytochrome P450 (CYP)-dependent activation of drugs into reactive metabolites. In order to reduce attrition due to metabolism-induced toxicity and to improve the safety of drug candidates, we developed a simple cell viability assay by combining a bioactivation system (human CYP3A4, CYP2D6 and CYP2C9) with Hep3B cells. We screened a series of drugs to explore structural motifs that may be responsible for CYP450-dependent activation caused by reactive metabolite formation, which highlighted specific liabilities regarding certain phenols and anilines.

Toxicology Strategies for Drug Discovery: Present and Future.

Attrition due to nonclinical safety represents a major issue for the productivity of pharmaceutical research and development (R&D) organizations, especially during the compound optimization stages of drug discovery and the early stages of clinical development. Focusing on decreasing nonclinical safety-related attrition is not a new concept, and various approaches have been experimented with over the last two decades. Front-loading testing funnels in Discovery with in vitro toxicity assays designed to rapidly identify unfavorable molecules was the approach adopted by most pharmaceutical R&D organizations a few years ago. However, this approach has also a non-negligible opportunity cost. Hence, significant refinements to the "fail early, fail often" paradigm have been proposed recently to reflect the complexity of accurately categorizing compounds with early data points without taking into account other important contextual aspects, in particular efficacious systemic and tissue exposures. This review provides an overview of toxicology approaches and models that can be used in pharmaceutical Discovery at the series/lead identification and lead optimization stages to guide and inform chemistry efforts, as well as a personal view on how to best use them to meet nonclinical safety-related attrition objectives consistent with a sustainable pharmaceutical R&D model. The scope of this review is limited to small molecules, as large molecules are associated with challenges that are quite different. Finally, a perspective on how several emerging technologies may impact toxicity evaluation is also provided.