Quantifying drug-induced structural toxicity in hepatocytes and cardiomyocytes derived from hiPSCs using a deep learning method

The use of artificial intelligence in induced pluripotent stem cell-based technology over 10-year period: A systematic scoping review

BACKGROUND

Stem cell research, particularly in the domain of induced pluripotent stem cell (iPSC) technology, has shown significant progress. The integration of artificial intelligence (AI), especially machine learning (ML) and deep learning (DL), has played a pivotal role in refining iPSC classification, monitoring cell functionality, and conducting genetic analysis. These enhancements are broadening the applications of iPSC technology in disease modelling, drug screening, and regenerative medicine. This review aims to explore the role of AI in the advancement of iPSC research.

METHODS

In December 2023, data were collected from three electronic databases (PubMed, Web of Science, and Science Direct) to investigate the application of AI technology in iPSC processing.

RESULTS

This systematic scoping review encompassed 79 studies that met the inclusion criteria. The number of research studies in this area has increased over time, with the United States emerging as a leading contributor in this field. AI technologies have been diversely applied in iPSC technology, encompassing the classification of cell types, assessment of disease-specific phenotypes in iPSC-derived cells, and the facilitation of drug screening using iPSC. The precision of AI methodologies has improved significantly in recent years, creating a foundation for future advancements in iPSC-based technologies.

CONCLUSIONS

Our review offers insights into the role of AI in regenerative and personalized medicine, highlighting both challenges and opportunities. Although still in its early stages, AI technologies show significant promise in advancing our understanding of disease progression and development, paving the way for future clinical applications.

AI-organoid integrated systems for biomedical studies and applications

In this review, we explore the growing role of artificial intelligence (AI) in advancing the biomedical applications of human pluripotent stem cell (hPSC)-derived organoids. Stem cell-derived organoids, these miniature organ replicas, have become essential tools for disease modeling, drug discovery, and regenerative medicine. However, analyzing the vast and intricate datasets generated from these organoids can be inefficient and error-prone. AI techniques offer a promising solution to efficiently extract insights and make predictions from diverse data types generated from microscopy images, transcriptomics, metabolomics, and proteomics. This review offers a brief overview of organoid characterization and fundamental concepts in AI while focusing on a comprehensive exploration of AI applications in organoid-based disease modeling and drug evaluation. It provides insights into the future possibilities of AI in enhancing the quality control of organoid fabrication, label-free organoid recognition, and three-dimensional image reconstruction of complex organoid structures. This review presents the challenges and potential solutions in AI-organoid integration, focusing on the establishment of reliable AI model decision-making processes and the standardization of organoid research.

Artificial Intelligence Supports Automated Characterization of Differentiated Human Pluripotent Stem Cells

Revolutionary advances in AI and deep learning in recent years have resulted in an upsurge of papers exploring applications within the biomedical field. Within stem cell research, promising results have been reported from analyses of microscopy images to, that is, distinguish between pluripotent stem cells and differentiated cell types derived from stem cells. In this work, we investigated the possibility of using a deep learning model to predict the differentiation stage of pluripotent stem cells undergoing differentiation toward hepatocytes, based on morphological features of cell cultures. We were able to achieve close to perfect classification of images from early and late time points during differentiation, and this aligned very well with the experimental validation of cell identity and function. Our results suggest that deep learning models can distinguish between different cell morphologies, and provide alternative means of semi-automated functional characterization of stem cell cultures.

A Review on the Recent Applications of Deep Learning in Predictive Drug Toxicological Studies

Drug toxicity prediction is an important step in ensuring patient safety during drug design studies. While traditional preclinical studies have historically relied on animal models to evaluate toxicity, recent advances in deep-learning approaches have shown great promise in advancing drug safety science and reducing animal use in preclinical studies. However, deep-learning-based approaches also face challenges in handling large biological data sets, model interpretability, and regulatory acceptance. In this review, we provide an overview of recent developments in deep-learning-based approaches for predicting drug toxicity, highlighting their potential advantages over traditional methods and the need to address their limitations. Deep-learning models have demonstrated excellent performance in predicting toxicity outcomes from various data sources such as chemical structures, genomic data, and high-throughput screening assays. The potential of deep learning for automated feature engineering is also discussed. This review emphasizes the need to address ethical concerns related to the use of deep learning in drug toxicity studies, including the reduction of animal use and ensuring regulatory acceptance. Furthermore, emerging applications of deep learning in drug toxicity prediction, such as predicting drug-drug interactions and toxicity in rare subpopulations, are highlighted. The integration of deep-learning-based approaches with traditional methods is discussed as a way to develop more reliable and efficient predictive models for drug safety assessment, paving the way for safer and more effective drug discovery and development. Overall, this review highlights the critical role of deep learning in predictive toxicology and drug safety evaluation, emphasizing the need for continued research and development in this rapidly evolving field. By addressing the limitations of traditional methods, leveraging the potential of deep learning for automated feature engineering, and addressing ethical concerns, deep-learning-based approaches have the potential to revolutionize drug toxicity prediction and improve patient safety in drug discovery and development.

Reproducibility of drug-induced effects on the contractility of an engineered heart tissue derived from human pluripotent stem cells

Introduction: Engineered heart tissues (EHTs) are three-dimensional culture platforms with cardiomyocytes differentiated from human pluripotent stem cells (hPSCs) and were designed for assaying cardiac contractility. For drug development applications, EHTs must have a stable function and provide reproducible results. We investigated these properties with EHTs made with different tissue casting batches and lines of differentiated hPSC-cardiomyocytes and analyzed them at different times after being fabricated. Methods: A video-optical assay was used for measuring EHT contractile outputs, and these results were compared with results from motion traction analysis of beating hPSC-cardiomyocytes cultured as monolayers in two-dimensional cultures. The reproducibility of induced contractile variations was tested using compounds with known mechanistic cardiac effects (isoproterenol, EMD-57033, omecamtiv mecarbil, verapamil, ranolazine, and mavacamten), or known to be clinically cardiotoxic (doxorubicin, sunitinib). These drug-induced variations were characterized at different electrical pacing rates and variations in intracellular calcium transients were also assessed in EHTs. Results: To ensure reproducibility in experiments, we established EHT quality control criteria based on excitation-contraction coupling and contractile sensitivity to extracellular calcium concentration. In summary, a baseline contractile force of 0.2 mN and excitation-contraction coupling of EHTs were used as quality control criteria to select suitable EHTs for analysis. Overall, drug-induced contractile responses were similar between monolayers and EHTs, where a close relationship was observed between contractile output and calcium kinetics. Contractile variations at multiple time points after adding cardiotoxic compounds were also detectable in EHTs. Discussion: Reproducibility of drug-induced effects in EHTs between experiments and relative to published work on these cellular models was generally observed. Future applications for EHTs may require additional mechanistic criteria related to drug effects and cardiac functional outputs to be measured in regard to specific contexts of use.

New science, drug regulation, and emergent public health issues: The work of FDA's division of applied regulatory science

The U.S. Food and Drug Administration (FDA) Division of Applied Regulatory Science (DARS) moves new science into the drug review process and addresses emergent regulatory and public health questions for the Agency. By forming interdisciplinary teams, DARS conducts mission-critical research to provide answers to scientific questions and solutions to regulatory challenges. Staffed by experts across the translational research spectrum, DARS forms synergies by pulling together scientists and experts from diverse backgrounds to collaborate in tackling some of the most complex challenges facing FDA. This includes (but is not limited to) assessing the systemic absorption of sunscreens, evaluating whether certain drugs can convert to carcinogens in people, studying drug interactions with opioids, optimizing opioid antagonist dosing in community settings, removing barriers to biosimilar and generic drug development, and advancing therapeutic development for rare diseases. FDA tasks DARS with wide ranging issues that encompass regulatory science; DARS, in turn, helps the Agency solve these challenges. The impact of DARS research is felt by patients, the pharmaceutical industry, and fellow regulators. This article reviews applied research projects and initiatives led by DARS and conducts a deeper dive into select examples illustrating the impactful work of the Division.

Integrating nonlinear analysis and machine learning for human induced pluripotent stem cell-based drug cardiotoxicity testing

Utilizing recent advances in human induced pluripotent stem cell (hiPSC) technology, nonlinear analysis and machine learning we can create novel tools to evaluate drug-induced cardiotoxicity on human cardiomyocytes. With cardiovascular disease remaining the leading cause of death globally it has become imperative to create effective and modern tools to test the efficacy and toxicity of drugs to combat heart disease. The calcium transient signals recorded from hiPSC-derived cardiomyocytes (hiPSC-CMs) are highly complex and dynamic with great degrees of response characteristics to various drug treatments. However, traditional linear methods often fail to capture the subtle variation in these signals generated by hiPSC-CMs. In this work, we integrated nonlinear analysis, dimensionality reduction techniques and machine learning algorithms for better classifying the contractile signals from hiPSC-CMs in response to different drug exposure. By utilizing extracted parameters from a commercially available high-throughput testing platform, we were able to distinguish the groups with drug treatment from baseline controls, determine the drug exposure relative to IC50 values, and classify the drugs by its unique cardiac responses. By incorporating nonlinear parameters computed by phase space reconstruction, we were able to improve our machine learning algorithm's ability to predict cardiotoxic levels and drug classifications. We also visualized the effects of drug treatment and dosages with dimensionality reduction techniques, t-distributed stochastic neighbor embedding (t-SNE). We have shown that integration of nonlinear analysis and artificial intelligence has proven to be a powerful tool for analyzing cardiotoxicity and classifying toxic compounds through their mechanistic action.

Phenotypic screening with deep learning identifies HDAC6 inhibitors as cardioprotective in a BAG3 mouse model of dilated cardiomyopathy

Dilated cardiomyopathy (DCM) is characterized by reduced cardiac output, as well as thinning and enlargement of left ventricular chambers. These characteristics eventually lead to heart failure. Current standards of care do not target the underlying molecular mechanisms associated with genetic forms of heart failure, driving a need to develop novel therapeutics for DCM. To identify candidate therapeutics, we developed an in vitro DCM model using induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) deficient in B-cell lymphoma 2 (BCL2)-associated athanogene 3 (BAG3). With these BAG3-deficient iPSC-CMs, we identified cardioprotective drugs using a phenotypic screen and deep learning. From a library of 5500 bioactive compounds and siRNA validation, we found that inhibiting histone deacetylase 6 (HDAC6) was cardioprotective at the sarcomere level. We translated this finding to a BAG3 cardiomyocyte-knockout (BAG3^cKO) mouse model of DCM, showing that inhibiting HDAC6 with two isoform-selective inhibitors (tubastatin A and a novel inhibitor TYA-018) protected heart function. In BAG3^cKO and BAG3^E455K mice, HDAC6 inhibitors improved left ventricular ejection fraction and reduced left ventricular diameter at diastole and systole. In BAG3^cKO mice, TYA-018 protected against sarcomere damage and reduced Nppb expression. Based on integrated transcriptomics and proteomics and mitochondrial function analysis, TYA-018 also enhanced energetics in these mice by increasing expression of targets associated with fatty acid metabolism, protein metabolism, and oxidative phosphorylation. Our results demonstrate the power of combining iPSC-CMs with phenotypic screening and deep learning to accelerate drug discovery, and they support developing novel therapies that address underlying mechanisms associated with heart disease.

Assessing Drug-Induced Mitochondrial Toxicity in Cardiomyocytes: Implications for Preclinical Cardiac Safety Evaluation

Drug-induced cardiotoxicity not only leads to the attrition of drugs during development, but also contributes to the high morbidity and mortality rates of cardiovascular diseases. Comprehensive testing for proarrhythmic risks of drugs has been applied in preclinical cardiac safety assessment for over 15 years. However, other mechanisms of cardiac toxicity have not received such attention. Of them, mitochondrial impairment is a common form of cardiotoxicity and is known to account for over half of cardiovascular adverse-event-related black box warnings imposed by the U.S. Food and Drug Administration. Although it has been studied in great depth, mitochondrial toxicity assessment has not yet been incorporated into routine safety tests for cardiotoxicity at the preclinical stage. This review discusses the main characteristics of mitochondria in cardiomyocytes, drug-induced mitochondrial toxicities, and high-throughput screening strategies for cardiomyocytes, as well as their proposed integration into preclinical safety pharmacology. We emphasize the advantages of using adult human primary cardiomyocytes for the evaluation of mitochondrial morphology and function, and the need for a novel cardiac safety testing platform integrating mitochondrial toxicity and proarrhythmic risk assessments in cardiac safety evaluation.

Assessment of Skin Toxicity in an in Vitro Reconstituted Human Epidermis Model Using Deep Learning

Skin toxicity is a common safety concern associated with drugs that inhibit epidermal growth factor receptors as well as other targets involved in epidermal growth and differentiation. Recently, the use of a three-dimensional reconstructed human epidermis model enabled large-scale drug screening and showed potential for predicting skin toxicity. Although a decrease in epidermal thickness was often observed when the three-dimensional reconstructed tissues were exposed to drugs causing skin toxicity, the thickness evaluation of epidermal layers from a pathologist was subjective and not easily reproducible or scalable. In addition, the subtle differences in thickness among tissues, as well as the large number of samples tested, made cross-study comparison difficult when a manual evaluation strategy was used. The current study used deep learning and image-processing algorithms to measure the viable epidermal thickness from multiple studies and found that the measured thickness was not only significantly correlated with a pathologist's semi-quantitative evaluation but was also in close agreement with the quantitative measurement performed by pathologists. Moreover, a sensitivity of 0.8 and a specificity of 0.75 were achieved when predicting the toxicity of 18 compounds with clinical observations with these epidermal thickness algorithms. This approach is fully automated, reproducible, and highly scalable. It not only shows reasonable accuracy in predicting skin toxicity but also enables cross-study comparison and high-throughput compound screening.

Recent progress of iPSC technology in cardiac diseases

It has been nearly 15 years since the discovery of human-induced pluripotent stem cells (iPSCs). During this time, differentiation methods to targeted cells have dramatically improved, and many types of cells in the human body can be currently generated at high efficiency. In the cardiovascular field, the ability to generate human cardiomyocytes in vitro with the same genetic background as patients has provided a great opportunity to investigate human cardiovascular diseases at the cellular level to clarify the molecular mechanisms underlying the diseases and discover potential therapeutics. Additionally, iPSC-derived cardiomyocytes have provided a powerful platform to study drug-induced cardiotoxicity and identify patients at high risk for the cardiotoxicity; thus, accelerating personalized precision medicine. Moreover, iPSC-derived cardiomyocytes can be sources for cardiac cell therapy. Here, we review these achievements and discuss potential improvements for the future application of iPSC technology in cardiovascular diseases.

Deep learning detects cardiotoxicity in a high-content screen with induced pluripotent stem cell-derived cardiomyocytes

Drug-induced cardiotoxicity and hepatotoxicity are major causes of drug attrition. To decrease late-stage drug attrition, pharmaceutical and biotechnology industries need to establish biologically relevant models that use phenotypic screening to detect drug-induced toxicity in vitro. In this study, we sought to rapidly detect patterns of cardiotoxicity using high-content image analysis with deep learning and induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs). We screened a library of 1280 bioactive compounds and identified those with potential cardiotoxic liabilities in iPSC-CMs using a single-parameter score based on deep learning. Compounds demonstrating cardiotoxicity in iPSC-CMs included DNA intercalators, ion channel blockers, epidermal growth factor receptor, cyclin-dependent kinase, and multi-kinase inhibitors. We also screened a diverse library of molecules with unknown targets and identified chemical frameworks that show cardiotoxic signal in iPSC-CMs. By using this screening approach during target discovery and lead optimization, we can de-risk early-stage drug discovery. We show that the broad applicability of combining deep learning with iPSC technology is an effective way to interrogate cellular phenotypes and identify drugs that may protect against diseased phenotypes and deleterious mutations.

Human induced pluripotent stem cell (iPSC)-derived cardiomyocytes as an in vitro model in toxicology: strengths and weaknesses for hazard identification and risk characterization

INTRODUCTION

Human induced pluripotent stem cell (iPSC)-derived cardiomyocytes is one of the most widely used cell-based models that resulted from the discovery of how non-embryonic stem cells can be differentiated into multiple cell types. In just one decade, iPSC-derived cardiomyocytes went from a research lab to widespread use in biomedical research and preclinical safety evaluation for drugs and other chemicals.

AREAS COVERED

This manuscript reviews data on toxicology applications of human iPSC-derived cardiomyocytes. We detail the outcome of a systematic literature search on their use (i) in hazard assessment for cardiotoxicity liabilities, (ii) for risk characterization, (iii) as models for population variability, and (iv) in studies of personalized medicine and disease.

EXPERT OPINION

iPSC-derived cardiomyocytes are useful to increase the accuracy, precision, and efficiency of cardiotoxicity hazard identification for both drugs and non-pharmaceuticals, with recent efforts beginning to demonstrate their utility for risk characterization. Notable limitations include the needs to improve the maturation of cells in culture, to better understand their potential use identifying structural cardiotoxicity, and for additional case studies involving population-wide and disease-specific risk characterization. Ultimately, the greatest future benefits are likely for non-pharmaceutical chemicals, filling a critical gap where no routine testing for cardiotoxicity is currently performed.

Clinical Trial in a Dish: Using Patient-Derived Induced Pluripotent Stem Cells to Identify Risks of Drug-Induced Cardiotoxicity

Drug-induced cardiotoxicity is a significant clinical issue, with many drugs in the market being labeled with warnings on cardiovascular adverse effects. Treatments are often prematurely halted when cardiotoxicity is observed, which limits their therapeutic potential. Moreover, cardiotoxicity is a major reason for abandonment during drug development, reducing available treatment options for diseases and creating a significant financial burden and disincentive for drug developers. Thus, it is important to minimize the cardiotoxic effects of medications that are in use or in development. To this end, identifying patients at a higher risk of developing cardiovascular adverse effects for the drug of interest may be an effective strategy. The discovery of human induced pluripotent stem cells has enabled researchers to generate relevant cell types that retain a patient's own genome and examine patient-specific disease mechanisms, paving the way for precision medicine. Combined with the rapid development of pharmacogenomic analysis, the ability of induced pluripotent stem cell-derivatives to recapitulate patient-specific drug responses provides a powerful platform to identify subsets of patients who are particularly vulnerable to drug-induced cardiotoxicity. In this review, we will discuss the current use of patient-specific induced pluripotent stem cells in identifying populations who are at risk to drug-induced cardiotoxicity and their potential applications in future precision medicine practice. Graphic Abstract: A graphic abstract is available for this article.

Improving cardiotoxicity prediction in cancer treatment: integration of conventional circulating biomarkers and novel exploratory tools

Early detection strategies and improvements in cancer treatment have dramatically reduced the cancer mortality rate in the United States (US). However, cardiovascular (CV) side effects of cancer therapy are frequent among the 17 million cancer survivors in the US today, and cardiovascular disease (CVD) has become the second leading cause of morbidity and mortality among cancer survivors. Circulating biomarkers are ideal for detecting and monitoring CV side effects of cancer therapy. Here, we summarize the current state of clinical studies on conventional serum and plasma CVD biomarkers to detect and prevent cardiac injury during cancer treatment. We also review how novel exploratory tools such as genetic testing, human stem cell-derived cardiomyocytes, Omics technologies, and artificial intelligence can elucidate underlying molecular and genetic mechanisms of CV injury and to improve predicting cancer therapy-related cardiotoxicity (CTRC). Current regulatory requirements for biomarker qualifications are also addressed. We present generally applicable lessons learned from published studies, particularly on how to improve reproducibility. The combination of conventional circulating biomarkers and novel exploratory tools will pave the way for precision medicine and improve the clinical practice of prediction, detection, and management of CTRC.

Twenty years of safety pharmacology model validation and the wider implications of this to drug discovery

This editorial summarizes the content of the current themed issue of J Pharm Tox Methods derived from the 2019 Annual Safety Pharmacology Society (SPS) meeting held in Barcelona, Spain, and reflects on 20 years of innovation in the elaboration of methods for evaluating adversity, particularly during the nonclinical research phase. Given the success of safety pharmacology (SP) in the last 20 years, we propose that the rubric for SP method invention and validation be examined in more detail to explore whether it may have wider relevance to the drug discovery process. Articles arising from the Barcelona meeting are summarized here. They reflect current areas of controversy and innovation in SP. Not for the first time in recent years, the suitability of the No Observable Adverse Effect Level (NOAEL) as a variable in SP was considered in an article derived from a survey of SPS members. It was found from the survey and concluded from the analysis that the NOAEL is not necessary for assessing the safety of a New Chemical Entity (NCE). The meeting included scientific content from more than 190 abstracts (reproduced in the current volume of J Pharm Tox Methods). The impact of the INSPIRE program on the educational endeavor of SP, cardiovascular SP with regard to hERG and advances in CiPA and stem cells assays, the use of the echocardiogram in SP, the applicability of deep learning methods in SP and toxicology studies, the role of biomarkers in renal SP studies, and advances in CNS SP are highlighted in this issue of the Journal. This continued innovation reflects a rubric in SP that identifies problems, seeks solutions and, importantly, validates the solutions. If there is a lesson to be learned from the 20 years of annual SP methods themed issues it is that drug discovery efforts may benefit from a more rigorous validation process for discovery methods, using positive and negative controls for validation, as is done in SP method validation.