Using Machine Learning Methods and Structural Alerts for Prediction of Mitochondrial Toxicity

Advancing toxicity studies of per- and poly-fluoroalkyl substances (pfass) through machine learning: Models, mechanisms, and future directions

Perfluorinated and perfluoroalkyl substances (PFASs), encompassing a vast array of isomeric chemicals, are recognized as typical emerging contaminants with direct or potential impacts on human health and the ecological environment. With the complex and elusive toxicological profiles of PFASs, machine learning (ML) has been increasingly employed in their toxicity studies due to its proficiency in prediction and data analytics. This integration is poised to become a predominant trend in environmental toxicology, propelled by the swift advancements in computational technology. This review diligently examines the literature to encapsulate the varied objectives of employing ML in the toxicity studies of PFASs: (1) Utilizing ML to establish Quantitative Structure-Activity Relationship (QSAR) models for PFASs with diverse toxicity endpoints, facilitating the targeted toxicity prediction of unidentified PFASs; (2) Investigating and substantiating the Adverse Outcome Pathway (AOP) through the synergy of ML and traditional toxicological methods, with this refining the toxicity assessment framework for PFASs; (3) Dissecting and elucidating the features of established ML models to advance Open Research into the toxicity of PFASs, with a primary focus on determinants and mechanisms. The discourse extends to an in-depth examination of ML studies, segregating findings based on their distinct application trajectories. Given that ML represents a nascent paradigm within PFASs research, this review delineates the collective challenges encountered in the ML-mediated study of PFAS toxicity and proffers strategic guidance for ensuing investigations.

Data mining of PubChem bioassay records reveals diverse OXPHOS inhibitory chemotypes as potential therapeutic agents against ovarian cancer

Focused screening on target-prioritized compound sets can be an efficient alternative to high throughput screening (HTS). For most biomolecular targets, compound prioritization models depend on prior screening data or a target structure. For phenotypic or multi-protein pathway targets, it may not be clear which public assay records provide relevant data. The question also arises as to whether data collected from disparate assays might be usefully consolidated. Here, we report on the development and application of a data mining pipeline to examine these issues. To illustrate, we focus on identifying inhibitors of oxidative phosphorylation, a druggable metabolic process in epithelial ovarian tumors. The pipeline compiled 8415 available OXPHOS-related bioassays in the PubChem data repository involving 312,093 unique compound records. Application of PubChem assay activity annotations, PAINS (Pan Assay Interference Compounds), and Lipinski-like bioavailability filters yields 1852 putative OXPHOS-active compounds that fall into 464 clusters. These chemotypes are diverse but have relatively high hydrophobicity and molecular weight but lower complexity and drug-likeness. These chemotypes show a high abundance of bicyclic ring systems and oxygen containing functional groups including ketones, allylic oxides (alpha/beta unsaturated carbonyls), hydroxyl groups, and ethers. In contrast, amide and primary amine functional groups have a notably lower than random prevalence. UMAP representation of the chemical space shows strong divergence in the regions occupied by OXPHOS-inactive and -active compounds. Of the six compounds selected for biological testing, 4 showed statistically significant inhibition of electron transport in bioenergetics assays. Two of these four compounds, lacidipine and esbiothrin, increased in intracellular oxygen radicals (a major hallmark of most OXPHOS inhibitors) and decreased the viability of two ovarian cancer cell lines, ID8 and OVCAR5. Finally, data from the pipeline were used to train random forest and support vector classifiers that effectively prioritized OXPHOS inhibitory compounds within a held-out test set (ROCAUC 0.962 and 0.927, respectively) and on another set containing 44 documented OXPHOS inhibitors outside of the training set (ROCAUC 0.900 and 0.823). This prototype pipeline is extensible and could be adapted for focus screening on other phenotypic targets for which sufficient public data are available.Scientific contributionHere, we describe and apply an assay data mining pipeline to compile, process, filter, and mine public bioassay data. We believe the procedure may be more broadly applied to guide compound selection in early-stage hit finding on novel multi-protein mechanistic or phenotypic targets. To demonstrate the utility of our approach, we apply a data mining strategy on a large set of public assay data to find drug-like molecules that inhibit oxidative phosphorylation (OXPHOS) as candidates for ovarian cancer therapies.

A QSAR study for predicting malformation in zebrafish embryo

BACKGROUND

Developmental toxicity tests are extremely expensive, require a large number of animals, and are time-consuming. It is necessary to develop a new approach to simplify the analysis of developmental endpoints. One of these endpoints is malformation, and one group of ongoing methods for simplifying is in silico models. In this study, we aim to develop a quantitative structure-activity relationship (QSAR) model and identify the best algorithm for predicting malformations, as well as the most important and effective physicochemical properties associated with malformation.

METHODS

The dataset was extracted from a reliable database called COMPTOX. Physicochemical properties (descriptors) were calculated using Mordred and RDKit chemoinformatics software. The data were cleaned, preprocessed, and then split into training and testing sets. Machine learning algorithms, such as gradient boosting model (GBM) and logistic regression (LR), as well as deep learning models, including multilayer perceptron (MLP) and neural networks (NNs) trained with train set data and different sets of descriptors. The models were then validated with test set and various statistical parameters, such as Matthew's correlation coefficient (MCC) and balanced accuracy (BAC) score, were used to compare the models.

RESULTS

A set of descriptors containing with 78% AUC was identified as the best set of descriptors. Gradient boosting was determined to be the best algorithm with 78% predictive power.

CONCLUSIONS

The descriptors that were the most effective for developing models directly impact the mechanism of malformation, and GBM is the best model due to its MCC and BAC.

Improved Detection of Drug-Induced Liver Injury by Integrating Predicted In Vivo and In Vitro Data

Drug-induced liver injury (DILI) has been a significant challenge in drug discovery, often leading to clinical trial failures and necessitating drug withdrawals. Over the last decade, the existing suite of in vitro proxy-DILI assays has generally improved at identifying compounds with hepatotoxicity. However, there is considerable interest in enhancing the in silico prediction of DILI because it allows for evaluating large sets of compounds more quickly and cost-effectively, particularly in the early stages of projects. In this study, we aim to study ML models for DILI prediction that first predict nine proxy-DILI labels and then use them as features in addition to chemical structural features to predict DILI. The features include in vitro (e.g., mitochondrial toxicity, bile salt export pump inhibition) data, in vivo (e.g., preclinical rat hepatotoxicity studies) data, pharmacokinetic parameters of maximum concentration, structural fingerprints, and physicochemical parameters. We trained DILI-prediction models on 888 compounds from the DILI data set (composed of DILIst and DILIrank) and tested them on a held-out external test set of 223 compounds from the DILI data set. The best model, DILIPredictor, attained an AUC-PR of 0.79. This model enabled the detection of the top 25 toxic compounds (2.68 LR+, positive likelihood ratio) compared to models using only structural features (1.65 LR+ score). Using feature interpretation from DILIPredictor, we identified the chemical substructures causing DILI and differentiated cases of DILI caused by compounds in animals but not in humans. For example, DILIPredictor correctly recognized 2-butoxyethanol as nontoxic in humans despite its hepatotoxicity in mice models. Overall, the DILIPredictor model improves the detection of compounds causing DILI with an improved differentiation between animal and human sensitivity and the potential for mechanism evaluation. DILIPredictor required only chemical structures as input for prediction and is publicly available at https://broad.io/DILIPredictor for use via web interface and with all code available for download.

Unleashing the potential of cell painting assays for compound activities and hazards prediction

The cell painting (CP) assay has emerged as a potent imaging-based high-throughput phenotypic profiling (HTPP) tool that provides comprehensive input data for in silico prediction of compound activities and potential hazards in drug discovery and toxicology. CP enables the rapid, multiplexed investigation of various molecular mechanisms for thousands of compounds at the single-cell level. The resulting large volumes of image data provide great opportunities but also pose challenges to image and data analysis routines as well as property prediction models. This review addresses the integration of CP-based phenotypic data together with or in substitute of structural information from compounds into machine (ML) and deep learning (DL) models to predict compound activities for various human-relevant disease endpoints and to identify the underlying modes-of-action (MoA) while avoiding unnecessary animal testing. The successful application of CP in combination with powerful ML/DL models promises further advances in understanding compound responses of cells guiding therapeutic development and risk assessment. Therefore, this review highlights the importance of unlocking the potential of CP assays when combined with molecular fingerprints for compound evaluation and discusses the current challenges that are associated with this approach.

Predicting the new psychoactive substance activity of antitussives and evaluating their ecotoxicity to fish

The misuse of antitussives preparations is a continuing problem in the world, and imply that they might have potential new psychoactive substances (NPS) activity. However, few study focus on their ecological toxicity towards fish. In the present study, the machine learning (ML) methods gcForest and random forest (RF) were employed to predict NPS activity in 30 antitussives. The potential toxic target, mode of action (MOA), acute toxicity and chronic toxicity to fish were further investigated. The results showed that both gcForest and RF achieved optimal performance when utilizing combined features of molecular fingerprint (MF) and molecular descriptor (MD), with area under the curve (AUC) = 0.99, accuracy >0.94 and f1 score > 0.94, and were applied to screen the NPS activity in antitussives. A total of 15 antitussives exhibited potential NPS activity, including frequently-used substances like codeine and dextromethorphan. The binding affinity of these antitussives with zebrafish dopamine transporter (zDAT) was high, and even surpassing that of some traditional narcotics and NPS. Some antitussives formed hydrogen bonds or salt bridges with aspartate (Asp) 95, tyrosine (Tyr) 171 of zDAT. For the ecotoxicity, the MOA of these 15 antitussives in fish was predicted as narcosis. The prenoxdiazin, pholcodine, codeine, dextromethorphan and dextrorphan exhibited very toxic/toxic to fish. It was necessary to pay close attention to the ecotoxicity of these antitussives. In this study, the integration of ML, molecular docking and ECOSAR approaches are powerful tools for understanding the toxicity profiles and ecological hazards posed by new pollutants.

Improved Detection of Drug-Induced Liver Injury by Integrating Predicted in vivo and in vitro Data

Drug-induced liver injury (DILI) has been significant challenge in drug discovery, often leading to clinical trial failures and necessitating drug withdrawals. The existing suite of in vitro proxy-DILI assays is generally effective at identifying compounds with hepatotoxicity. However, there is considerable interest in enhancing in silico prediction of DILI because it allows for the evaluation of large sets of compounds more quickly and cost-effectively, particularly in the early stages of projects. In this study, we aim to study ML models for DILI prediction that first predicts nine proxy-DILI labels and then uses them as features in addition to chemical structural features to predict DILI. The features include in vitro (e.g., mitochondrial toxicity, bile salt export pump inhibition) data, in vivo (e.g., preclinical rat hepatotoxicity studies) data, pharmacokinetic parameters of maximum concentration, structural fingerprints, and physicochemical parameters. We trained DILI-prediction models on 888 compounds from the DILIst dataset and tested on a held-out external test set of 223 compounds from DILIst dataset. The best model, DILIPredictor, attained an AUC-ROC of 0.79. This model enabled the detection of top 25 toxic compounds compared to models using only structural features (2.68 LR+ score). Using feature interpretation from DILIPredictor, we were able to identify the chemical substructures causing DILI as well as differentiate cases DILI is caused by compounds in animals but not in humans. For example, DILIPredictor correctly recognized 2-butoxyethanol as non-toxic in humans despite its hepatotoxicity in mice models. Overall, the DILIPredictor model improves the detection of compounds causing DILI with an improved differentiation between animal and human sensitivity as well as the potential for mechanism evaluation. DILIPredictor is publicly available at https://broad.io/DILIPredictor for use via web interface and with all code available for download and local implementation via https://pypi.org/project/dilipred/.

Insights into Drug Cardiotoxicity from Biological and Chemical Data: The First Public Classifiers for FDA Drug-Induced Cardiotoxicity Rank

Drug-induced cardiotoxicity (DICT) is a major concern in drug development, accounting for 10-14% of postmarket withdrawals. In this study, we explored the capabilities of chemical and biological data to predict cardiotoxicity, using the recently released DICTrank data set from the United States FDA. We found that such data, including protein targets, especially those related to ion channels (e.g., hERG), physicochemical properties (e.g., electrotopological state), and peak concentration in plasma offer strong predictive ability for DICT. Compounds annotated with mechanisms of action such as cyclooxygenase inhibition could distinguish between most-concern and no-concern DICT. Cell Painting features for ER stress discerned most-concern cardiotoxic from nontoxic compounds. Models based on physicochemical properties provided substantial predictive accuracy (AUCPR = 0.93). With the availability of omics data in the future, using biological data promises enhanced predictability and deeper mechanistic insights, paving the way for safer drug development. All models from this study are available at https://broad.io/DICTrank_Predictor.

Artificial Intelligence and Machine Learning Methods to Evaluate Cardiotoxicity following the Adverse Outcome Pathway Frameworks

Cardiovascular disease is a leading global cause of mortality. The potential cardiotoxic effects of chemicals from different classes, such as environmental contaminants, pesticides, and drugs can significantly contribute to effects on health. The same chemical can induce cardiotoxicity in different ways, following various Adverse Outcome Pathways (AOPs). In addition, the potential synergistic effects between chemicals further complicate the issue. In silico methods have become essential for tackling the problem from different perspectives, reducing the need for traditional in vivo testing, and saving valuable resources in terms of time and money. Artificial intelligence (AI) and machine learning (ML) are among today's advanced approaches for evaluating chemical hazards. They can serve, for instance, as a first-tier component of Integrated Approaches to Testing and Assessment (IATA). This study employed ML and AI to assess interactions between chemicals and specific biological targets within the AOP networks for cardiotoxicity, starting with molecular initiating events (MIEs) and progressing through key events (KEs). We explored methods to encode chemical information in a suitable way for ML and AI. We started with commonly used approaches in Quantitative Structure-Activity Relationship (QSAR) methods, such as molecular descriptors and different types of fingerprint. We then increased the complexity of encoders, incorporating graph-based methods, auto-encoders, and character embeddings employed in neural language processing. We also developed a multimodal neural network architecture, capable of considering the complementary nature of different chemical representations simultaneously. The potential of this approach, compared to more conventional architectures designed to handle a single encoder, becomes apparent when the amount of data increases.

Developing a GNN-based AI model to predict mitochondrial toxicity using the bagging method

Mitochondrial toxicity has been implicated in the development of various toxicities, including hepatotoxicity. Therefore, mitochondrial toxicity has become a major screening factor in the early discovery phase of drug development. Several models have been developed to predict mitochondrial toxicity based on chemical structures. However, they only provide a binary classification of positive or negative results and do not provide the substructures that contribute to a positive decision. Therefore, we developed an artificial intelligence (AI) model to predict mitochondrial toxicity and visualize structural alerts. To construct the model, we used the open-source software library kMoL, which employs a graph neural network approach that allows learning from chemical structure data. We also utilized the integrated gradient method, which enables the visualization of substructures that contribute to positive results. The dataset used to construct the AI model exhibited a significant imbalance, with significantly more negative than positive data. To address this, we employed the bagging method, which resulted in a model with high predictive performance, as evidenced by an F1 score of 0.839. This model can also be used to visualize substructures that contribute to mitochondrial toxicity using the integrated gradient method. Our AI model predicts mitochondrial toxicity based on chemical structures and may contribute to screening mitochondrial toxicity in the early stages of drug discovery.

Quantitative assessment of mitochondrial morphology relevant for studies on cellular health and environmental toxicity

Mitochondria are essential organelles that play crucial roles in cellular energy metabolism, calcium signaling and apoptosis. Their importance in tissue homeostasis and stress responses, combined to their ability to transition between various structural and functional states, make them excellent organelles for monitoring cellular health. Quantitative assessment of mitochondrial morphology can therefore provide valuable insights into environmentally-induced cell damage. High-content screening (HCS) provides a powerful tool for analyzing organelles and cellular substructures. We developed a fully automated and miniaturized HCS wet-plus-dry pipeline (MITOMATICS) exploiting mitochondrial morphology as a marker for monitoring cellular health or damage. MITOMATICS uses an in-house, proprietary software (MitoRadar) to enable fast, exhaustive and cost-effective analysis of mitochondrial morphology and its inherent diversity in live cells. We applied our pipeline and big data analytics software to assess the mitotoxicity of selected chemicals, using the mitochondrial uncoupler CCCP as an internal control. Six different pesticides (inhibiting complexes I, II and III of the mitochondrial respiratory chain) were tested as individual compounds and five other pesticides present locally in Occitanie (Southern France) were assessed in combination to determine acute mitotoxicity. Our results show that the assayed pesticides exhibit specific signatures when used as single compounds or chemical mixtures and that they function synergistically to impact mitochondrial architecture. Study of environment-induced mitochondrial damage has the potential to open new fields in mechanistic toxicology, currently underexplored by regulatory toxicology and exposome research. Such exploration could inform health policy guidelines and foster pharmacological intervention, water, air and soil pollution control and food safety.

Insights into Drug Cardiotoxicity from Biological and Chemical Data: The First Public Classifiers for FDA DICTrank

Drug-induced cardiotoxicity (DICT) is a major concern in drug development, accounting for 10-14% of postmarket withdrawals. In this study, we explored the capabilities of various chemical and biological data to predict cardiotoxicity, using the recently released Drug-Induced Cardiotoxicity Rank (DICTrank) dataset from the United States FDA. We analyzed a diverse set of data sources, including physicochemical properties, annotated mechanisms of action (MOA), Cell Painting, Gene Expression, and more, to identify indications of cardiotoxicity. We found that such data, including protein targets, especially those related to ion channels (such as hERG), physicochemical properties (such as electrotopological state) as well as peak concentration in plasma offer strong predictive ability as well as valuable insights into DICT. We also found compounds annotated with particular mechanisms of action, such as cyclooxygenase inhibition, could distinguish between most-concern and no-concern DICT compounds. Cell Painting features related to ER stress discern the most-concern cardiotoxic compounds from non-toxic compounds. While models based on physicochemical properties currently provide substantial predictive accuracy (AUCPR = 0.93), this study also underscores the potential benefits of incorporating more comprehensive biological data in future DICT predictive models. With the availability of - omics data in the future, using biological data promises enhanced predictability and delivers deeper mechanistic insights, paving the way for safer therapeutic drug development. All models and data used in this study are publicly released at https://broad.io/DICTrank_Predictor.

Complement System Inhibitory Drugs in a Zebrafish (Danio rerio) Model: Computational Modeling

The dysregulation of complement system activation usually results in acute or chronic inflammation and can contribute to the development of various diseases. Although the activation of complement pathways is essential for innate defense, exacerbated activity of this system may be harmful to the host. Thus, drugs with the potential to inhibit the activation of the complement system may be important tools in therapy for diseases associated with complement system activation. The synthetic peptides Cp40 and PMX205 can be highlighted in this regard, given that they selectively inhibit the C3 and block the C5a receptor (C5aR1), respectively. The zebrafish (Danio rerio) is a robust model for studying the complement system. The aim of the present study was to use in silico computational modeling to investigate the hypothesis that these complement system inhibitor peptides interact with their target molecules in zebrafish, for subsequent in vivo validation. For this, we analyzed molecular docking interactions between peptides and target molecules. Our study demonstrated that Cp40 and the cyclic peptide PMX205 have positive interactions with their respective zebrafish targets, thus suggesting that zebrafish can be used as an animal model for therapeutic studies on these inhibitors.

In silico modeling-based new alternative methods to predict drug and herb-induced liver injury: A review

New approach methods (NAMs) have been developed to predict a wide range of toxicities through innovative technologies. Liver injury is one of the most extensively studied endpoints due to its severity and frequency, occurring among populations that consume drugs or dietary supplements. In this review, we focus on recent developments of in silico modeling for liver injury prediction using deep learning and in vitro data based on adverse outcome pathways (AOPs). Despite these models being mainly developed using datasets generated from drug-like molecules, they were also applied to the prediction of hepatotoxicity caused by herbal products. As deep learning has achieved great success in many different fields, advanced machine learning algorithms have been actively applied to improve the accuracy of in silico models. Additionally, the development of liver AOPs, combined with big data in toxicology, has been valuable in developing in silico models with enhanced predictive performance and interpretability. Specifically, one approach involves developing structure-based models for predicting molecular initiating events of liver AOPs, while others use in vitro data with structure information as model inputs for making predictions. Even though liver injury remains a difficult endpoint to predict, advancements in machine learning algorithms and the expansion of in vitro databases with relevant biological knowledge have made a huge impact on improving in silico modeling for drug-induced liver injury prediction.

Opportunities and challenges in application of artificial intelligence in pharmacology

Artificial intelligence (AI) is a machine science that can mimic human behaviour like intelligent analysis of data. AI functions with specialized algorithms and integrates with deep and machine learning. Living in the digital world can generate a huge amount of medical data every day. Therefore, we need an automated and reliable evaluation tool that can make decisions more accurately and faster. Machine learning has the potential to learn, understand and analyse the data used in healthcare systems. In the last few years, AI is known to be employed in various fields in pharmaceutical science especially in pharmacological research. It helps in the analysis of preclinical (laboratory animals) and clinical (in human) trial data. AI also plays important role in various processes such as drug discovery/manufacturing, diagnosis of big data for disease identification, personalized treatment, clinical trial research, radiotherapy, surgical robotics, smart electronic health records, and epidemic outbreak prediction. Moreover, AI has been used in the evaluation of biomarkers and diseases. In this review, we explain various models and general processes of machine learning and their role in pharmacological science. Therefore, AI with deep learning and machine learning could be relevant in pharmacological research.

Mitochondrial toxicity evaluation of traditional Chinese medicine injections with a dual in vitro approach

There are technical obstacles in the safety evaluation of traditional Chinese medicine (TCM) injections due to their complex chemical nature and the lack of rapid and accurate in vitro methods. Here, we established a dual in vitro mitochondrial toxicity approach combing the conventional "glucose/galactose" assay in HepG2 cells with the cytotoxic assay in mitochondrial respiration deficient cells. Using this dual in vitro approach, for the first time, we systematically assessed the mitochondrial toxicity of TCM injections. Four of the 35 TCM injections, including Xiyanping, Dengzhanhuasu, Shuanghuanglian, and Yinzhihuang, significantly reduced cellular ATP production in galactose medium in the first assay, and presented less cytotoxic in the respiration deficient cells in the second assay, indicating that they have mitochondrial toxicity. Furthermore, we identified scutellarin, rutin, phillyrin, and baicalin could be the potential mitochondrial toxic ingredients in the 4 TCM injections by combining molecular docking analysis with experimental validation. Collectively, the dual in vitro approach is worth applying to the safety evaluation of more TCM products, and mitochondrial toxic TCM injections and ingredients found in this study deserve more attention.

Integrating cell morphology with gene expression and chemical structure to aid mitochondrial toxicity detection

Mitochondrial toxicity is an important safety endpoint in drug discovery. Models based solely on chemical structure for predicting mitochondrial toxicity are currently limited in accuracy and applicability domain to the chemical space of the training compounds. In this work, we aimed to utilize both -omics and chemical data to push beyond the state-of-the-art. We combined Cell Painting and Gene Expression data with chemical structural information from Morgan fingerprints for 382 chemical perturbants tested in the Tox21 mitochondrial membrane depolarization assay. We observed that mitochondrial toxicants differ from non-toxic compounds in morphological space and identified compound clusters having similar mechanisms of mitochondrial toxicity, thereby indicating that morphological space provides biological insights related to mechanisms of action of this endpoint. We further showed that models combining Cell Painting, Gene Expression features and Morgan fingerprints improved model performance on an external test set of 244 compounds by 60% (in terms of F1 score) and improved extrapolation to new chemical space. The performance of our combined models was comparable with dedicated in vitro assays for mitochondrial toxicity. Our results suggest that combining chemical descriptors with biological readouts enhances the detection of mitochondrial toxicants, with practical implications in drug discovery.

Cell Morphological Profiling Enables High-Throughput Screening for PROteolysis TArgeting Chimera (PROTAC) Phenotypic Signature

PROteolysis TArgeting Chimeras (PROTACs) use the ubiquitin-proteasome system to degrade a protein of interest for therapeutic benefit. Advances made in targeted protein degradation technology have been remarkable, with several molecules having moved into clinical studies. However, robust routes to assess and better understand the safety risks of PROTACs need to be identified, which is an essential step toward delivering efficacious and safe compounds to patients. In this work, we used Cell Painting, an unbiased high-content imaging method, to identify phenotypic signatures of PROTACs. Chemical clustering and model prediction allowed the identification of a mitotoxicity signature that could not be expected by screening the individual PROTAC components. The data highlighted the benefit of unbiased phenotypic methods for identifying toxic signatures and the potential to impact drug design.

Artificial Intelligence-Based Toxicity Prediction of Environmental Chemicals: Future Directions for Chemical Management Applications

Recently, research on the development of artificial intelligence (AI)-based computational toxicology models that predict toxicity without the use of animal testing has emerged because of the rapid development of computer technology. Various computational toxicology techniques that predict toxicity based on the structure of chemical substances are gaining attention, including the quantitative structure-activity relationship. To understand the recent development of these models, we analyzed the databases, molecular descriptors, fingerprints, and algorithms considered in recent studies. Based on a selection of 96 papers published since 2014, we found that AI models have been developed to predict approximately 30 different toxicity end points using more than 20 toxicity databases. For model development, molecular access system and extended-connectivity fingerprints are the most commonly used molecular descriptors. The most used algorithm among the machine learning techniques is the random forest, while the most used algorithm among the deep learning techniques is a deep neural network. The use of AI technology in the development of toxicity prediction models is a new concept that will aid in achieving a scientific accord and meet regulatory applications. The comprehensive overview provided in this study will provide a useful guide for the further development and application of toxicity prediction models.

Study on the Characteristics of Small-Molecule Kinase Inhibitors-Related Drug-Induced Liver Injury

Background and Aim: More than half of the small-molecule kinase inhibitors (KIs) induced liver injury clinically. Meanwhile, studies have shown a close relationship between mitochondrial damage and drug-induced liver injury (DILI). We aimed to study KIs and the binding between drugs and mitochondrial proteins to find factors related to DILI occurrence.

Methods: A total of 1,223 oral FDA-approved drugs were collected and analyzed, including 44 KIs. Fisher’s exact test was used to analyze DILI potential and risk of different factors. A total of 187 human mitochondrial proteins were further collected, and high-throughput molecular docking was performed between human mitochondrial proteins and drugs in the data set. The molecular dynamics simulation was used to optimize and evaluate the dynamic binding behavior of the selected mitochondrial protein/KI complexes.

Results: The possibility of KIs to produce DILI is much higher than that of other types (OR = 46.89, p = 9.28E-13). A few DILI risk factors were identified, including molecular weight (MW) between 400 and 600, the defined daily dose (DDD) ≥ 100 mg/day, the octanol–water partition coefficient (LogP) ≥ 3, and the degree of liver metabolism (LM) more than 50%. Drugs that met this combination of rules were found to have a higher DILI risk than controls (OR = 8.28, p = 4.82E-05) and were more likely to cause severe DILI (OR = 8.26, p = 5.06E-04). The docking results showed that KIs had a significant higher affinity with human mitochondrial proteins (p = 4.19E-11) than other drug types. Furthermore, the five proteins with the lowest docking score were selected for molecular dynamics simulation, and the smallest fluctuation of the backbone RMSD curve was found in the protein 5FS8/KI complexes, which indicated the best stability of the protein 5FS8 bound to KIs.

Conclusions: KIs were found to have the highest odds ratio of causing DILI. MW was significantly related to the production of DILI, and the average docking scores of KI drugs were found to be significantly different from other classes. Further analysis identified the top binding mitochondrial proteins for KIs, and specific binding sites were analyzed. The optimization of molecular docking results by molecular dynamics simulation may contribute to further studying the mechanism of DILI.

Prescription Drugs and Mitochondrial Metabolism

Mitochondria are central to the physiology and survival of nearly all eukaryotic cells and house diverse metabolic processes including oxidative phosphorylation, reactive oxygen species buffering, metabolite synthesis/exchange, and Ca2+ sequestration. Mitochondria are phenotypically heterogeneous and this variation is essential to the complexity of physiological function among cells, tissues, and organ systems. As a consequence of mitochondrial integration with so many physiological processes, small molecules that modulate mitochondrial metabolism induce complex systemic effects. In the case of many common prescribed drugs, these interactions may contribute to drug therapeutic mechanisms, induce adverse drug reactions, or both. The purpose of this article is to review historical and recent advances in the understanding of the effects of prescription drugs on mitochondrial metabolism. Specific 'modes' of xenobiotic-mitochondria interactions are discussed to provide a set of qualitative models that aid in conceptualizing how the mitochondrial energy transduction system may be affected. Findings of recent in vitro high-throughput screening studies are reviewed, and a few candidate drug classes are chosen for additional brief discussion (i.e. antihyperglycemics, antidepressants, antibiotics, and antihyperlipidemics). Finally, recent improvements in pharmacokinetic models that aid in quantifying systemic effects of drug-mitochondria interactions are briefly considered.

An AI-based prediction model for drug-drug interactions in osteoporosis and Paget's diseases from SMILES

Referring to common skeletal-related diseases, osteoporosis and Paget's are two of the most frequently found diseases in the elderly. Nowadays, the combination of multiple drugs is the optimal therapy to decelerate osteoporosis and Paget's pathologic process, which contains various underlying adverse effects due to drug-drug interactions (DDIs). Artificial intelligence (AI) has the potential to evaluate the interaction, pharmacodynamics, and possible side effects between drugs. In this research, we created an AI-based machine-learning model to predict the outcomes of interactions between drugs used for osteoporosis and Paget's treatment, furthermore, to mitigate cost and time in implementing the best combination of medications in clinical practice. Our dataset was collected from the DrugBank database, and we then extracted a variety of chemical features from the simplified molecular-input line-entry system (SMILES) of defined drug pairs that interact with each other. Finally, machine-learning algorithms have been implemented to learn the extracted features. Our stack ensemble model from Random Forest and XGBoost reached an average accuracy of 74% in predicting DDIs. It was superior to individual models and previous methods in most measurement metrics. This study showed the potential of AI models in predicting DDIs of Osteoporosis-Paget's disease in particular, and other diseases in general.

Screening of 6000 Compounds for Uncoupling Activity: A Comparison Between a Mechanistic Biophysical Model and the Structural Alert Profiler Mitotox

Protonophoric uncoupling of phosphorylation is an important factor when assessing chemicals for their toxicity, and has recently moved into focus in pharmaceutical research with respect to the treatment of diseases such as cancer, diabetes, or obesity. Reliably identifying uncoupling activity is thus a valuable goal. To that end, we screened more than 6000 anionic compounds for in vitro uncoupling activity, using a biophysical model based on ab initio COSMO-RS input parameters with the molecular structure as the only external input. We combined these results with a model for baseline toxicity (narcosis). Our model identified more than 1250 possible uncouplers in the screening dataset, and identified possible new uncoupler classes such as thiophosphoric acids. When tested against 423 known uncouplers and 612 known inactive compounds in the dataset, the model reached a sensitivity of 83% and a specificity of 96%. In a direct comparison, it showed a similar specificity than the structural alert profiler Mitotox (97%), but much higher sensitivity than Mitotox (47%). The biophysical model thus allows for a more accurate screening for uncoupling activity than existing structural alert profilers. We propose to use our model as a complementary tool to screen large datasets for protonophoric uncoupling activity in drug development and toxicity assessment.

FP-ADMET: a compendium of fingerprint-based ADMET prediction models

MOTIVATION

The absorption, distribution, metabolism, excretion, and toxicity (ADMET) of drugs plays a key role in determining which among the potential candidates are to be prioritized. In silico approaches based on machine learning methods are becoming increasing popular, but are nonetheless limited by the availability of data. With a view to making both data and models available to the scientific community, we have developed FPADMET which is a repository of molecular fingerprint-based predictive models for ADMET properties. In this article, we have examined the efficacy of fingerprint-based machine learning models for a large number of ADMET-related properties. The predictive ability of a set of 20 different binary fingerprints (based on substructure keys, atom pairs, local path environments, as well as custom fingerprints such as all-shortest paths) for over 50 ADMET and ADMET-related endpoints have been evaluated as part of the study. We find that for a majority of the properties, fingerprint-based random forest models yield comparable or better performance compared with traditional 2D/3D molecular descriptors.

AVAILABILITY

The models are made available as part of open access software that can be downloaded from https://gitlab.com/vishsoft/fpadmet .

Unmasking of crucial structural fragments for coronavirus protease inhibitors and its implications in COVID-19 drug discovery

Fragment based drug discovery (FBDD) by the aid of different modelling techniques have been emerged as a key drug discovery tool in the area of pharmaceutical science and technology. The merits of employing these methods, in place of other conventional molecular modelling techniques, endorsed clear detection of the possible structural fragments present in diverse set of investigated compounds and can create alternate possibilities of lead optimization in drug discovery. In this work, two fragment identification tools namely SARpy and Laplacian-corrected Bayesian analysis were used for previous SARS-CoV PLpro and 3CLpro inhibitors. A robust and predictive SARpy based fragments identification was performed which have been validated further by Laplacian-corrected Bayesian model. These comprehensive approaches have advantages since fragments are straight forward to interpret. Moreover, distinguishing the key molecular features (with respect to ECFP_6 fingerprint) revealed good or bad influences for the SARS-CoV protease inhibitory activities. Furthermore, the identified fragments could be implemented in the medicinal chemistry endeavors of COVID-19 drug discovery.

Oxidative Stress as a Common Key Event in Developmental Neurotoxicity

The developing brain is extremely sensitive to many chemicals. Perinatal exposure to neurotoxicants has been implicated in several neurodevelopmental disorders, including autism spectrum disorder, attention-deficit hyperactive disorder, and schizophrenia. Studies of the molecular and cellular events related to developmental neurotoxicity have identified a number of “adverse outcome pathways,” many of which share oxidative stress as a key event. Oxidative stress occurs when the balance between the production of free oxygen radicals and the activity of the cellular antioxidant system is dysregulated. In this review, we describe some of the developmental neurotoxins that target the antioxidant system and the mechanisms by which they elicit stress, including oxidative phosphorylation in mitochondria and plasma membrane redox system in rodent models. We also discuss future directions for identifying adverse outcome pathways related to oxidative stress and developmental neurotoxicity, with the goal of improving our ability to quickly and accurately screen chemicals for their potential developmental neurotoxicity.

Beyond Pseudo-natural Products: Sequential Ugi/Pictet-Spengler Reactions Leading to Steroidal Pyrazinoisoquinolines That Trigger Caspase-Independent Death in HepG2 Cells

In this work, we describe how stereochemically complex polycyclic compounds can be generated by applying a synthetic sequence comprising an intramolecular Ugi reaction followed by a Pictet-Spengler cyclization on steroid-derived scaffolds. The resulting compounds, which combine a fragment derived from a natural product and a scaffold not found in nature. are both structurally distinct and globally similar to natural products at the same time, and interrogate an alternative region of the chemical space. One of the new compounds showed significant antiproliferative activity on HepG2 cells through a caspase-independent cell-death mechanism, an appealing feature when new antitumor compounds are searched.

In silico prediction of mitochondrial toxicity of chemicals using machine learning methods

Mitochondria are important organelles in human cells, providing more than 95% of the energy. However, some drugs and environmental chemicals could induce mitochondrial dysfunction, which might cause complex diseases and even worsen the condition of patients with mitochondrial damage. Some drugs have been withdrawn from the market due to their severe mitochondrial toxicity, such as troglitazone. Therefore, there is an urgent need to develop models that could accurately predict the mitochondrial toxicity of chemicals. In this paper, suitable data were obtained from literature and databases first. Then nine types of fingerprints were used to characterize these compounds. Finally, different algorithms were used to build models. Meanwhile, the applicability domain of the prediction models was defined. We have also explored the structural alerts of mitochondrial toxicity, which would be helpful for medicinal chemists to better predict mitochondrial toxicity and further optimize lead compounds.

Setting the stage for next-generation risk assessment with non-animal approaches: the EU-ToxRisk project experience

In 2016, the European Commission launched the EU-ToxRisk research project to develop and promote animal-free approaches in toxicology. The 36 partners of this consortium used in vitro and in silico methods in the context of case studies (CSs). These CSs included both compounds with a highly defined target (e.g. mitochondrial respiratory chain inhibitors) as well as compounds with poorly defined molecular initiation events (e.g. short-chain branched carboxylic acids). The initial project focus was on developing a science-based strategy for read-across (RAx) as an animal-free approach in chemical risk assessment. Moreover, seamless incorporation of new approach method (NAM) data into this process (= NAM-enhanced RAx) was explored. Here, the EU-ToxRisk consortium has collated its scientific and regulatory learnings from this particular project objective. For all CSs, a mechanistic hypothesis (in the form of an adverse outcome pathway) guided the safety evaluation. ADME data were generated from NAMs and used for comprehensive physiological-based kinetic modelling. Quality assurance and data management were optimized in parallel. Scientific and Regulatory Advisory Boards played a vital role in assessing the practical applicability of the new approaches. In a next step, external stakeholders evaluated the usefulness of NAMs in the context of RAx CSs for regulatory acceptance. For instance, the CSs were included in the OECD CS portfolio for the Integrated Approach to Testing and Assessment project. Feedback from regulators and other stakeholders was collected at several stages. Future chemical safety science projects can draw from this experience to implement systems toxicology-guided, animal-free next-generation risk assessment.

Using Machine Learning Methods and Structural Alerts for Prediction of Mitochondrial Toxicity

Over the last few years more and more organ and idiosyncratic toxicities were linked to mitochondrial toxicity. Despite well-established assays, such as the seahorse and Glucose/Galactose assay, an in silico approach to mitochondrial toxicity is still feasible, particularly when it comes to the assessment of large compound libraries. Therefore, in silico approaches could be very beneficial to indicate hazards early in the drug development pipeline. By combining multiple endpoints, we derived the largest so far published dataset on mitochondrial toxicity. A thorough data analysis shows that molecules causing mitochondrial toxicity can be distinguished by physicochemical properties. Finally, the combination of machine learning and structural alerts highlights the suitability for in silico risk assessment of mitochondrial toxicity.