Systematic Identification of Molecular Targets and Pathways Related to Human Organ Level Toxicity

In Silico Prediction of Human Organ Toxicity via Artificial Intelligence Methods

Unpredicted human organ level toxicity remains one of the major reasons for drug clinical failure. There is a critical need for cost-efficient strategies in the early stages of drug development for human toxicity assessment. At present, artificial intelligence methods are popularly regarded as a promising solution in chemical toxicology. Thus, we provided comprehensive in silico prediction models for eight significant human organ level toxicity end points using machine learning, deep learning, and transfer learning algorithms. In this work, our results showed that the graph-based deep learning approach was generally better than the conventional machine learning models, and good performances were observed for most of the human organ level toxicity end points in this study. In addition, we found that the transfer learning algorithm could improve model performance for skin sensitization end point using source domain of in vivo acute toxicity data and in vitro data of the Tox21 project. It can be concluded that our models can provide useful guidance for the rapid identification of the compounds with human organ level toxicity for drug discovery.

Data-Driven Quantitative Structure-Activity Relationship Modeling for Human Carcinogenicity by Chronic Oral Exposure

Traditional methodologies for assessing chemical toxicity are expensive and time-consuming. Computational modeling approaches have emerged as low-cost alternatives, especially those used to develop quantitative structure-activity relationship (QSAR) models. However, conventional QSAR models have limited training data, leading to low predictivity for new compounds. We developed a data-driven modeling approach for constructing carcinogenicity-related models and used these models to identify potential new human carcinogens. To this goal, we used a probe carcinogen dataset from the US Environmental Protection Agency's Integrated Risk Information System (IRIS) to identify relevant PubChem bioassays. Responses of 25 PubChem assays were significantly relevant to carcinogenicity. Eight assays inferred carcinogenicity predictivity and were selected for QSAR model training. Using 5 machine learning algorithms and 3 types of chemical fingerprints, 15 QSAR models were developed for each PubChem assay dataset. These models showed acceptable predictivity during 5-fold cross-validation (average CCR = 0.71). Using our QSAR models, we can correctly predict and rank 342 IRIS compounds' carcinogenic potentials (PPV = 0.72). The models predicted potential new carcinogens, which were validated by a literature search. This study portends an automated technique that can be applied to prioritize potential toxicants using validated QSAR models based on extensive training sets from public data resources.

Identification of Potent and Selective Acetylcholinesterase/Butyrylcholinesterase Inhibitors by Virtual Screening

Acetylcholinesterase (AChE) and butyrylcholinesterase (BChE) play important roles in human neurodegenerative disorders such as Alzheimer's disease. In this study, machine learning methods were applied to develop quantitative structure-activity relationship models for the prediction of novel AChE and BChE inhibitors based on data from quantitative high-throughput screening assays. The models were used to virtually screen an in-house collection of ∼360K compounds. The optimal models achieved good performance with area under the receiver operating characteristic curve values ranging from 0.83 ± 0.03 to 0.87 ± 0.01 for the prediction of AChE/BChE inhibition activity and selectivity. Experimental validation showed that the best-performing models increased the assay hit rate by several folds. We identified 88 novel AChE and 126 novel BChE inhibitors, 25% (AChE) and 53% (BChE) of which showed potent inhibitory effects (IC50 < 5 μM). In addition, structure-activity relationship analysis of the BChE inhibitors revealed scaffolds for chemistry design and optimization. In conclusion, machine learning models were shown to efficiently identify potent and selective inhibitors against AChE and BChE and novel structural series for further design and development of potential therapeutics against neurodegenerative disorders.

Predictive Models for Human Cytochrome P450 3A7 Selective Inhibitors and Substrates

Inappropriate use of prescription drugs is potentially more harmful in fetuses/neonates than in adults. Cytochrome P450 (CYP) 3A subfamily undergoes developmental changes in expression, such as a transition from CYP3A7 to CYP3A4 shortly after birth, which provides a potential way to distinguish medication effects on fetuses/neonates and adults. The purpose of this study was to build first-in-class predictive models for both inhibitors and substrates of CYP3A7/CYP3A4 using chemical structure analysis. Three metrics were used to evaluate model performance: area under the receiver operating characteristic curve (AUC-ROC), balanced accuracy (BA), and Matthews correlation coefficient (MCC). The performance varied for each CYP3A7/CYP3A4 inhibitor/substrate model depending on the data set type, model type, rebalancing method, and specific feature set. For the active inhibitor/substrate data set, the optimal models achieved AUC-ROC values ranging from 0.77 ± 0.01 to 0.84 ± 0.01. For the selective inhibitor/substrate data set, the optimal models achieved AUC-ROC values ranging from 0.72 ± 0.02 to 0.79 ± 0.04. The predictive power of the optimal models was validated by compounds with known potencies as CYP3A7/CYP3A4 inhibitors or substrates. In addition, we identified structural features significant for CYP3A7/CYP3A4 selective or common inhibitors and substrates. In summary, the top performing models can be further applied as a tool to rapidly evaluate the safety and efficacy of new drugs separately for fetuses/neonates and adults. The significant structural features could guide the design of new therapeutic drugs as well as aid in the optimization of existing medicine for fetuses/neonates.

Artificial Intelligence and Machine Learning for Lead-to-Candidate Decision-Making and Beyond

The use of artificial intelligence (AI) and machine learning (ML) in pharmaceutical research and development has to date focused on research: target identification; docking-, fragment-, and motif-based generation of compound libraries; modeling of synthesis feasibility; rank-ordering likely hits according to structural and chemometric similarity to compounds having known activity and affinity to the target(s); optimizing a smaller library for synthesis and high-throughput screening; and combining evidence from screening to support hit-to-lead decisions. Applying AI/ML methods to lead optimization and lead-to-candidate (L2C) decision-making has shown slower progress, especially regarding predicting absorption, distribution, metabolism, excretion, and toxicology properties. The present review surveys reasons why this is so, reports progress that has occurred in recent years, and summarizes some of the issues that remain. Effective AI/ML tools to derisk L2C and later phases of development are important to accelerate the pharmaceutical development process, ameliorate escalating development costs, and achieve greater success rates.

Generation and maturation of human iPSC-derived 3D organotypic cardiac microtissues in long-term culture

Cardiovascular diseases remain the leading cause of death worldwide; hence there is an increasing focus on developing physiologically relevant in vitro cardiovascular tissue models suitable for studying personalized medicine and pre-clinical tests. Despite recent advances, models that reproduce both tissue complexity and maturation are still limited. We have established a scaffold-free protocol to generate multicellular, beating human cardiac microtissues in vitro from hiPSCs-namely human organotypic cardiac microtissues (hOCMTs)-that show some degree of self-organization and can be cultured for long term. This is achieved by the differentiation of hiPSC in 2D monolayer culture towards cardiovascular lineage, followed by further aggregation on low-attachment culture dishes in 3D. The generated hOCMTs contain multiple cell types that physiologically compose the heart and beat without external stimuli for more than 100 days. We have shown that 3D hOCMTs display improved cardiac specification, survival and metabolic maturation as compared to standard monolayer cardiac differentiation. We also confirmed the functionality of hOCMTs by their response to cardioactive drugs in long-term culture. Furthermore, we demonstrated that they could be used to study chemotherapy-induced cardiotoxicity. Due to showing a tendency for self-organization, cellular heterogeneity, and functionality in our 3D microtissues over extended culture time, we could also confirm these constructs as human cardiac organoids (hCOs). This study could help to develop more physiologically-relevant cardiac tissue models, and represent a powerful platform for future translational research in cardiovascular biology.

Machine learning in the identification, prediction and exploration of environmental toxicology: Challenges and perspectives

Over the past few decades, data-driven machine learning (ML) has distinguished itself from hypothesis-driven studies and has recently received much attention in environmental toxicology. However, the use of ML in environmental toxicology remains in the early stages, with knowledge gaps, technical bottlenecks in data quality, high-dimensional/heterogeneous/small-sample data analysis and model interpretability, and a lack of an in-depth understanding of environmental toxicology. Given the above problems, we review the recent progress in the literature and highlight state-of-the-art toxicological studies using ML (such as learning and predicting toxicity in complicated biosystems and multiple-factor environmental scenarios of long-term and large-scale pollution). Beyond predicting simple biological endpoints by integrating untargeted omics and adverse outcome pathways, ML development should focus on revealing toxicological mechanisms. The integration of data-driven ML with other methods (e.g., omics analysis and adverse outcome pathway frameworks) endows ML with widely promising application in revealing toxicological mechanisms. High-quality databases and interpretable algorithms are urgently needed for toxicology and environmental science. Addressing the core issues and future challenges for ML in this review may narrow the knowledge gap between environmental toxicity and computational science and facilitate the control of environmental risk in the future.

A systems approach to enable effective team science from the internal research program of the National Center for Advancing Translational Sciences

The internal research program of the National Center for Advancing Translational Sciences (NCATS) at the National Institutes of Health aims to fundamentally transform the preclinical translational research process to get more treatments to more people more quickly. The program develops and implements innovative scientific and operational approaches that accelerate and enhance translation across many diverse projects. Cross-disciplinary team science is a defining feature of our organization, with scientists at all levels engaged in multiple research teams. Here, we share our systems approach to nurturing cross-disciplinary team science, which leverages organizational policies, structures, and processes. Policies including the organizational mission statement, principles for ethical conduct of research, performance review criteria, and training program objectives and approaches reinforce the value of team science to achieve the program's scientific goals. Structures including an organizational structure designed around solving translational problems, co-location of employees in a single state-of-the-art scientific facility, and shared-use laboratories, expertise and instrumentation facilitate collaboration. Processes including fluid team assembly, specialized project management, cross-agency partnerships, and decision making based on clear screening criteria and milestones enable effective team assembly and functioning. We share evidence of the impact of these approaches on the science and commercialization of findings and discuss pathways to broad adoption of similar approaches.

Engineering spatial-organized cardiac organoids for developmental toxicity testing

Emerging technologies in stem cell engineering have produced sophisticated organoid platforms by controlling stem cell fate via biomaterial instructive cues. By micropatterning and differentiating human induced pluripotent stem cells (hiPSCs), we have engineered spatially organized cardiac organoids with contracting cardiomyocytes in the center surrounded by stromal cells distributed along the pattern perimeter. We investigated how geometric confinement directed the structural morphology and contractile functions of the cardiac organoids and tailored the pattern geometry to optimize organoid production. Using modern data-mining techniques, we found that pattern sizes significantly affected contraction functions, particularly in the parameters related to contraction duration and diastolic functions. We applied cardiac organoids generated from 600 μm diameter circles as a developmental toxicity screening assay and quantified the embryotoxic potential of nine pharmaceutical compounds. These cardiac organoids have potential use as an in vitro platform for studying organoid structure-function relationships, developmental processes, and drug-induced cardiac developmental toxicity.

•

Micropattern-based geometric confinement directs cardiac organoid development

•

Cardiac organoid structure-function relationships are guided by organoid size

•

Cardiac organoids can be used as an in vitro embryotoxicity assessment tool