Computational Approaches to Identify Structural Alerts and Their Applications in Environmental Toxicology and Drug Discovery

Determination of nitrobenzene potential genotoxic impurities in nifedipine with GC-MS

There is an increasing scientific interest in the detection of genotoxic impurities (GTIs), with nitrobenzene compounds being considered potential genotoxic impurities due to their structural alerts, which demonstrates a threat to drug safety for patient. While current reports on the detection of nifedipine impurity primarily focus on general impurities in nifedipine. In this study, an effective and simple gas chromatography-mass spectrometry (GC-MS) method was established and verified for the separation and quantification of 2-nitrotoluene, 2-nitrobenzyl alcohol, 2-nitrobenzaldehyde, 3-nitrobenzaldehyde, 4-nitrobenzaldehyde, and 2-nitrobenzyl bromide in nifedipine, which have not been previously reported. The validation of this GC-MS method was conducted following the International Conference of Harmonization (ICH) guidelines, exhibiting good linearity within the range of 2-40 μg/g and accuracy between 84.6 % and 107.8 %, the RSD% of intra-day and inter-day precision was in the range of 1.77-4.55 %, stability and robustness also met acceptance criteria. This method filled the gap in detection method for nitrobenzene compounds in nifedipine, offering a novel method and technical support for nifedipine quality control.

Prioritizing of potential environmental exposure carcinogens beyond IARC group 1-2B based on weight of evidence (WoE) approach

Environmental exposures are the main cause of cancer, and their carcinogenicity has not been fully evaluated, identifying potential carcinogens that have not been evaluated is critical for safety. This study is the first to propose a weight of evidence (WoE) approach based on computational methods to prioritize potential carcinogens. Computational methods such as read across, structural alert, (Quantitative) structure-activity relationship and chemical-disease association were evaluated and integrated. Four different WoE approach was evaluated, compared to the best single method, the WoE-1 approach gained 0.21 and 0.39 improvement in the area under the receiver operating characteristic curve (AUC) and Matthew's correlation coefficient (MCC) value, respectively. The evaluation of 681 environmental exposures beyond IARC list 1-2B prioritized 52 chemicals of high carcinogenic concern, of which 21 compounds were known carcinogens or suspected carcinogens, and eight compounds were identified as potential carcinogens for the first time. This study illustrated that the WoE approach can effectively complement different computational methods, and can be used to prioritize chemicals of carcinogenic concern.

Computational framework for identifying and evaluating mutagenic and xenoestrogenic potential of food additives

Food additives are chemicals incorporated in food to enhance its flavor, color and prevent spoilage. Some of these are associated with substantial health hazards, including developmental disorders, increase cancer risk, and hormone disruption. Hence, this study aimed to comprehend the in-silico toxicology framework for evaluating mutagenic and xenoestrogenic potential of food additives and their association with breast cancer. A total of 2885 food additives were screened for toxicity based on Threshold of Toxicological Concern (TTC), mutagenicity endpoint prediction, and mutagenic structural alerts/toxicophores identification. Ten food additives were identified as having mutagenic potential based on toxicity screening. Furthermore, Protein-Protein Interaction (PPI) analysis identified ESR1, as a key hub gene in breast cancer. KEGG pathway analysis verified that ESR1 plays a significant role in breast cancer pathogenesis. Additionally, competitive interaction studies of the predicted potential mutagenic food additives with the estrogen receptor-α were evaluated at agonist and antagonist binding sites. Indole, Dichloromethane, Trichloroethylene, Quinoline, 6-methyl quinoline, Ethyl nitrite, and 4-methyl quinoline could act as agonists, and Paraldehyde, Azodicarbonamide, and 2-acetylfuranmay as antagonists. The systematic risk assessment framework reported in this study enables the exploration of mutagenic and xenoestrogenic potential associated with food additives for hazard identification and management.

Prediction of cytochrome P450-mediated bioactivation using machine learning models and in vitro validation

Cytochrome P450 (P450)-mediated bioactivation, which can lead to the hepatotoxicity through the formation of reactive metabolites (RMs), has been regarded as the major problem of drug failures. Herein, we purposed to establish machine learning models to predict the bioactivation of P450. On the basis of the literature-derived bioactivation dataset, models for Benzene ring, Nitrogen heterocycle and Sulfur heterocycle were developed with machine learning methods, i.e., Random Forest, Random Subspace, SVM and Naïve Bayes. The models were assessed by metrics like "Precision", "Recall", "F-Measure", "AUC" (Area Under the Curve), etc. Random Forest algorithms illustrated the best predictability, with nice AUC values of 0.949, 0.973 and 0.958 for the test sets of Benzene ring, Nitrogen heterocycle and Sulfur heterocycle models, respectively. 2D descriptors like topological indices, 2D autocorrelations and Burden eigenvalues, etc. contributed most to the models. Furthermore, the models were applied to predict the occurrence of bioactivation of an external verification set. Drugs like selpercatinib, glafenine, encorafenib, etc. were predicted to undergo bioactivation into toxic RMs. In vitro, IC50 shift experiment was performed to assess the potential of bioactivation to validate the prediction. Encorafenib and tirbanibulin were observed of bioactivation potential with shifts of 3-6 folds or so. Overall, this study provided a reliable and robust strategy to predict the P450-mediated bioactivation, which will be helpful to the assessment of adverse drug reactions (ADRs) in clinic and the design of new candidates with lower toxicities.

Tackling assay interference associated with small molecules

Biochemical and cell-based assays are essential to discovering and optimizing efficacious and safe drugs, agrochemicals and cosmetics. However, false assay readouts stemming from colloidal aggregation, chemical reactivity, chelation, light signal attenuation and emission, membrane disruption, and other interference mechanisms remain a considerable challenge in screening synthetic compounds and natural products. To address assay interference, a range of powerful experimental approaches are available and in silico methods are now gaining traction. This Review begins with an overview of the scope and limitations of experimental approaches for tackling assay interference. It then focuses on theoretical methods, discusses strategies for their integration with experimental approaches, and provides recommendations for best practices. The Review closes with a summary of the critical facts and an outlook on potential future developments.

Prediction of molecular-specific mutagenic alerts and related mechanisms of chemicals by a convolutional neural network (CNN) model based on SMILES split

Structural alerts (SAs) are essential to identify chemicals for toxicity evaluation and health risk assessment. We constructed a novel SMILES split-based deep learning model (SSDL) that was trained and verified with 5850 chemicals from the ISSSTY database and 384 external test chemicals from published papers. The training accuracy was above 0.90 and the evaluation metrics (precision, recall and F1-score) all reached 0.78 or above on both internal and external test chemicals. In this model, the molecular-specific fragment importance of chemicals was first quantified independently. Then, the SA identification method based on the importance of these fragments was statistically analyzed and verified with the ISSSTY test and external test chemicals containing one of 28 typical SAs, and most of the performances were better than that of expert rules. Furthermore, a mutagenicity mechanism prediction method was developed using 237 chemicals with four known mutagenic mechanisms based on molecular similarity calibrated by the SSDL method and fragment importance, which significantly improved accuracy in three mechanisms and had comparable accuracy in the other one compared to traditional methods. Overall, the SSDL model quantifying fragment toxicity within molecules would be a novel potentially powerful tool in the determination and visualization of molecular-specific SAs and the prediction of mutagenicity mechanisms for environmental or industrial compounds and drugs.

In Silico Prediction of Chemical Acute Dermal Toxicity Using Explainable Machine Learning Methods

The research on acute dermal toxicity has consistently been a crucial component in assessing the potential risks of human exposure to active ingredients in pesticides and related plant protection products. However, it is difficult to directly identify the acute dermal toxicity of potential compounds through animal experiments alone. In our study, we separately integrated 1735 experimental data based on rabbits and 1679 experimental data based on rats to construct acute dermal toxicity prediction models using machine learning and deep learning algorithms. The best models for the two animal species achieved AUC values of 78.0 and 82.0%, respectively, on 10-fold cross-validation. Additionally, we employed SARpy to extract structural alerts, and in conjunction with Shapley additive explanation and attentive FP heatmap, we identified important features and structural fragments associated with acute dermal toxicity. This approach offers valuable insights for the detection of positive compounds. Moreover, a standalone software tool was developed to make acute dermal toxicity prediction easier. In summary, our research would provide an effective tool for acute dermal toxicity evaluation of pesticides, cosmetics, and drug safety assessment.

MolToxPred: small molecule toxicity prediction using machine learning approach

Different types of chemicals and products may exhibit various health risks when administered into the human body. For toxicity reasons, the number of new drugs entering the market through the conventional drug development process has been reduced over the years. However, with the advent of big data and artificial intelligence, machine learning techniques have emerged as a potential solution for predicting toxicity and ensuring efficient drug development and chemical safety. An ML model for toxicity prediction can reduce experimental costs and time while addressing ethical concerns by drastically reducing the need for animals and clinical trials. Herein, MolToxPred, an ML-based tool, has been developed using a stacked model approach to predict the potential toxicity of small molecules and metabolites. The stacked model consists of random forest, multi-layer perceptron, and LightGBM as base classifiers and Logistic Regression as the meta classifier. For training and validation purposes, a comprehensive set of toxic and non-toxic molecules is curated. Different structural and physicochemical-based features in the form of molecular descriptors and fingerprints were employed. MolToxPred utilizes a comprehensive feature selection process and optimizes its hyperparameters through Bayesian optimization with stratified 5-fold cross-validation. In the evaluation phase, MolToxPred achieved an AUROC of 87.76% on the test set and 88.84% on an external validation set. The McNemar test was used as the post-hoc test to determine if the stacked models' performance was significantly different compared to the base learners. The developed stacked model outperformed its base classifiers and an existing tool in the literature, reaffirming its better performance. The hypothesis is that the incorporation of a diverse set of data, the subsequent feature selection, and a stacked ensemble approach give MolToxPred the edge over other methods. In addition to this, an attempt has been made to identify structural alerts responsible for endpoints of the Tox21 data to determine the association of a molecule with a plausible downstream pathway of action. MolToxPred may be helpful for drug discovery and regulatory pipelines in pharmaceutical and other industries for in silico toxicity prediction of small molecule candidates.

EDC-Predictor: A Novel Strategy for Prediction of Endocrine-Disrupting Chemicals by Integrating Pharmacological and Toxicological Profiles

Identification of endocrine-disrupting chemicals (EDCs) is crucial in the reduction of human health risks. However, it is hard to do so because of the complex mechanisms of the EDCs. In this study, we propose a novel strategy named EDC-Predictor to integrate pharmacological and toxicological profiles for the prediction of EDCs. Different from conventional methods that only focus on a few nuclear receptors (NRs), EDC-Predictor considers more targets. It uses computational target profiles from network-based and machine learning-based methods to characterize compounds, including both EDCs and non-EDCs. The best model constructed by these target profiles outperformed those models by molecular fingerprints. In a case study to predict NR-related EDCs, EDC-Predictor showed a wider applicability domain and higher accuracy than four previous tools. Another case study further demonstrated that EDC-Predictor could predict EDCs targeting other proteins rather than NRs. Finally, a free web server was developed to make EDC prediction easier (http://lmmd.ecust.edu.cn/edcpred/). In summary, EDC-Predictor would be a powerful tool in EDC prediction and drug safety assessment.

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

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

Harnessing Semi-Supervised Machine Learning to Automatically Predict Bioactivities of Per- and Polyfluoroalkyl Substances (PFASs)

Many per- and polyfluoroalkyl substances (PFASs) pose significant health hazards due to their bioactive and persistent bioaccumulative properties. However, assessing the bioactivities of PFASs is both time-consuming and costly due to the sheer number and expense of in vivo and in vitro biological experiments. To this end, we harnessed new unsupervised/semi-supervised machine learning models to automatically predict bioactivities of PFASs in various human biological targets, including enzymes, genes, proteins, and cell lines. Our semi-supervised metric learning models were used to predict the bioactivity of PFASs found in the recent Organisation of Economic Co-operation and Development (OECD) report list, which contains 4730 PFASs used in a broad range of industries and consumers. Our work provides the first semi-supervised machine learning study of structure-activity relationships for predicting possible bioactivities in a variety of PFAS species.

Metabophore-mediated retro-metabolic ('MeMeReMe') approach in drug design

Preclinical toxicity assessments of new drugs require the use of in silico prediction techniques as ethics, cost, time, and complexity limit in vitro and in vivo methods. This review discusses the fundamental concepts of biophores especially toxicophores and their detection methodologies, tools and techniques, as well as ongoing challenges, and methods for overcoming them. This will guide the design community in manipulating lead compounds via a pre-determined pathway based on the MeMeReMe approach. The ideas discussed will be useful both for predicting toxicity and for de-risking leads through optimization.

Modeling and insights into the structural characteristics of endocrine-disrupting chemicals

Endocrine-disrupting chemicals (EDCs) can cause serious harm to human health and the environment; therefore, it is important to rapidly and correctly identify EDCs. Different computational models have been proposed for the prediction of EDCs over the past few decades, but the reported models are not always easily available, and few studies have investigated the structural characteristics of EDCs. In the present study, we have developed a series of artificial intelligence models targeting EDC receptors: the androgen receptor (AR); estrogen receptor (ER); and pregnane X receptor (PXR). The consensus models achieved good predictive results for validation sets with balanced accuracy values of 87.37%, 90.13%, and 79.21% for AR, ER, and PXR binding assays, respectively. Analysis of the physical-chemical properties suggested that several chemical properties were significantly (p < 0.05) different between EDCs and non-EDCs. We also identified structural alerts that can indicate an EDC, which were integrated into the web server SApredictor. These models and structural characteristics can provide useful tools and information in the discrimination and mechanistic understanding of EDCs in drug discovery and environmental risk assessment.

Modeling and Insights into the Structural Characteristics of Chemical Mitochondrial Toxicity

Mitochondria are the energy metabolism center of cells and are involved in a number of other processes, such as cell differentiation and apoptosis, signal transduction, and regulation of cell cycle and cell proliferation. It is of great significance to evaluate the mitochondrial toxicity of drugs and other chemicals. In the present study, we aimed to propose easily available artificial intelligence (AI) models for the prediction of chemical mitochondrial toxicity and investigate the structural characteristics with the analysis of molecular properties and structural alerts. The consensus model achieved good predictive results with high total accuracy at 87.21% for validation sets. The models can be accessed freely via https://ochem.eu/article/158582. Besides, several commonly used chemical properties were significantly different between chemicals with and without mitochondrial toxicity. We also detected the structural alerts (SAs) responsible for mitochondrial toxicity and integrated them into the web-server SApredictor (www.sapredictor.cn). The study may provide useful tools for in silico estimation of mitochondrial toxicity and be helpful to understand the mechanisms of mitochondrial toxicity.

Chemical rules for optimization of chemical mutagenicity via matched molecular pairs analysis and machine learning methods

Chemical mutagenicity is a serious issue that needs to be addressed in early drug discovery. Over a long period of time, medicinal chemists have manually summarized a series of empirical rules for the optimization of chemical mutagenicity. However, given the rising amount of data, it is getting more difficult for medicinal chemists to identify more comprehensive chemical rules behind the biochemical data. Herein, we integrated a large Ames mutagenicity data set with 8576 compounds to derive mutagenicity transformation rules for reversing Ames mutagenicity via matched molecular pairs analysis. A well-trained consensus model with a reasonable applicability domain was constructed, which showed favorable performance in the external validation set with an accuracy of 0.815. The model was used to assess the generalizability and validity of these mutagenicity transformation rules. The results demonstrated that these rules were of great value and could provide inspiration for the structural modifications of compounds with potential mutagenic effects. We also found that the local chemical environment of the attachment points of rules was critical for successful transformation. To facilitate the use of these mutagenicity transformation rules, we integrated them into ADMETopt2 ( http://lmmd.ecust.edu.cn/admetsar2/admetopt2/ ), a free web server for optimization of chemical ADMET properties. The above-mentioned approach would be extended to the optimization of other toxicity endpoints.

From Structural Alerts to Signature Fragment Alerts: A Case Study on Pyrrolizidine Alkaloids

Even though modeling is considered a valid alternative to mutagenicity testing for substances with known structures, it can be applied for mixtures only if all of the single chemical structures are identified. Within the present work, we investigate a new avenue to exploit computational toxicology for mixtures, such as plant-based food ingredients. Indeed, considering that in the absence of toxicological information, an important early consideration is whether any substance may be genotoxic through the mutagenic mechanism of action, we tried to establish a correspondence between genotoxic structural alerts (SAs) and so-called signature fragment alerts (SFAs). Once this correspondence is established, chromatograms could be screened for chemical features associated with genotoxic alerts. Pyrrolizidine alkaloids (PAs), a large group of natural toxins (several of them known as genotoxic) were used as a case study because their early identification would bring significant benefits. The method was built using 56 PA pure standards, resulting in the characterization of signature fragment alerts. Finally, the approach was verified in real plant-based samples such as herbal tea and alfalfa, where the screening of signature fragment alerts allowed highlighting quickly the presence of genotoxic PAs in plant-based mixtures. Therefore, the SFA analysis can be used for risk prioritization of newly identified PAs and for their identification in mixtures, contributing to the unnecessary use of animal experimentation for genotoxicity testing.

Machine Learning Modeling and Insights into the Structural Characteristics of Drug-Induced Neurotoxicity

Neurotoxicity can be resulted from many diverse clinical drugs, which has been a cause of concern to human populations across the world. The detection of drug-induced neurotoxicity (DINeurot) potential with biological experimental methods always required a lot of budget and time. In addition, few studies have addressed the structural characteristics of neurotoxic chemicals. In this study, we focused on the computational modeling for drug-induced neurotoxicity with machine learning methods and the insights into the structural characteristics of neurotoxic chemicals. Based on the clinical drug data with neurotoxicity effects, we developed 35 different classifiers by combining five different machine learning methods and seven fingerprint packages. The best-performing model achieved good results on both 5-fold cross-validation (balanced accuracy of 76.51%, AUC value of 0.83, and MCC value of 0.52) and external validation (balanced accuracy of 83.63%, AUC value of 0.87, and MCC value of 0.67). The model can be freely accessed on the web server DINeuroTpredictor (http://dineurot.sapredictor.cn/). We also analyzed the distribution of several key molecular properties between neurotoxic and non-neurotoxic structures. The results indicated that several physicochemical properties were significantly different between the neurotoxic and non-neurotoxic compounds, including molecular polar surface area (MPSA), AlogP, the number of hydrogen bond acceptors (nHAcc) and donors (nHDon), the number of rotatable bonds (nRotB), and the number of aromatic rings (nAR). In addition, 18 structural alerts responsible for chemical neurotoxicity were identified. The structural alerts have been integrated with our web server SApredictor (http://www.sapredictor.cn). The results of this study could provide useful information for the understanding of the structural characteristics and computational prediction for chemical neurotoxicity.

Modeling and insights into the structural characteristics of drug-induced autoimmune diseases

The incidence and complexity of drug-induced autoimmune diseases (DIAD) have been on the rise in recent years, which may lead to serious or fatal consequences. Besides, many environmental and industrial chemicals can also cause DIAD. However, there are few effective approaches to estimate the DIAD potential of drugs and other chemicals currently, and the structural characteristics and mechanism of action of DIAD compounds have not been clarified. In this study, we developed the in silico models for chemical DIAD prediction and investigated the structural characteristics of DIAD chemicals based on the reliable drug data on human autoimmune diseases. We collected 148 medications which were reported can cause DIAD clinically and 450 medications that clearly do not cause DIAD. Several different machine learning algorithms and molecular fingerprints were combined to develop the in silico models. The best performed model provided the good overall accuracy on validation set with 76.26%. The model was made freely available on the website http://diad.sapredictor.cn/. To further investigate the differences in structural characteristics between DIAD chemicals and non-DIAD chemicals, several key physicochemical properties were analyzed. The results showed that AlogP, molecular polar surface area (MPSA), and the number of hydrogen bond donors (nHDon) were significantly different between the DIAD and non-DIAD structures. They may be related to the DIAD toxicity of chemicals. In addition, 14 structural alerts (SA) for DIAD toxicity were detected from predefined substructures. The SAs may be helpful to explain the mechanism of action of drug induced autoimmune disease, and can used to identify the chemicals with potential DIAD toxicity. The structural alerts have been integrated in a structural alert-based web server SApredictor (http://www.sapredictor.cn). We hope the results could provide useful information for the recognition of DIAD chemicals and the insights of structural characteristics for chemical DIAD toxicity.

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.

Modeling and insights into the structural basis of chemical acute aquatic toxicity

It has become a top global regulatory priority to prevent and control pollution from the release of synthetic chemicals, which continues to affect the aquatic communities. In the past decades, computational tools were largely used to significantly reduce the budget and time cost of chemical acute aquatic toxicity assessment. But the structural basis of toxic compounds was rarely analyzed. In the present study, we collected 1438, 485 and 961 chemicals with acute toxicity data records for three representative aquatic species, including Tetrahymena pyriformis, Daphnia magna, and Fathead minnow, respectively. A series of artificial intelligence models were developed using OCHEM tools. For each aquatic toxicity endpoint, a consensus model was developed based on the top performed individual models. The consensus models provided good performance on external validation sets with total accuracy values 96.88 %, 90.63 %, and 84.90 % for Tetrahymena pyriformis toxicity (TPT), Daphnia magna toxicity (DMT), and Fathead minnow toxicity (FMT), respectively. The models can be freely accessed via https://ochem.eu/article/146910. Moreover, the analysis of physical-chemical properties suggested that several key molecular properties of aquatic toxic compounds were significantly different with those of non-toxic compounds. Thus, these descriptors may be associated to chemical acute aquatic toxicity, and may be useful for the understand of chemical aquatic toxicity. Besides, in this study, the structural alerts for aquatic toxicity were detected using f-score and frequency ratio analysis of predefined substructures. A total of 112, 58 and 33 structural alerts were identified responsible for TPT, DMT, and FMT, respectively. These structural alerts could provide useful information for the mechanisms of chemical aquatic toxicity and visual alerts for environmental assessment. All the structural alerts were integrated in the web-server SApredictor (www.sapredictor.cn).

A scheme to evaluate structural alerts to predict toxicity - Assessing confidence by characterising uncertainties

Structure-activity relationships (SARs) in toxicology have enabled the formation of structural rules which, when coded as structural alerts, are essential tools in in silico toxicology. Whilst other in silico methods have approaches for their evaluation, there is no formal process to assess the confidence that may be associated with a structural alert. This investigation proposes twelve criteria to assess the uncertainty associated with structural alerts, allowing for an assessment of confidence. The criteria are based around the stated purpose, description of the chemistry, toxicology and mechanism, performance and coverage, as well as corroborating and supporting evidence of the alert. Alerts can be given a confidence assessment and score, enabling the identification of areas where more information may be beneficial. The scheme to evaluate structural alerts was placed in the context of various use cases for industrial and regulatory applications. The analysis of alerts, and consideration of the evaluation scheme, identifies the different characteristics an alert may have, such as being highly specific or generic. These characteristics may determine when an alert can be used for specific uses such as identification of analogues for read-across or hazard identification.

•

Structural alerts are useful tools for predictive toxicology.

•

12 criteria to evaluate structural alerts have been identified.

•

A strategy to determine confidence of structural alerts is presented.

•

Different use cases require different characteristics of structural alerts.

•

A Scheme to Evaluate Structural Alerts to Predict Toxicity – Assessing Confidence By Characterising Uncertainties.

SApredictor: An Expert System for Screening Chemicals Against Structural Alerts

The rapid and accurate evaluation of chemical toxicity is of great significance for estimation of chemical safety. In the past decades, a great number of excellent computational models have been developed for chemical toxicity prediction. But most machine learning models tend to be “black box”, which bring about poor interpretability. In the present study, we focused on the identification and collection of structural alerts (SAs) responsible for a series of important toxicity endpoints. Then, we carried out effective storage of these structural alerts and developed a web-server named SApredictor (www.sapredictor.cn) for screening chemicals against structural alerts. People can quickly estimate the toxicity of chemicals with SApredictor, and the specific key substructures which cause the chemical toxicity will be intuitively displayed to provide valuable information for the structural optimization by medicinal chemists.

Review of the state of science and evaluation of currently available in silico prediction models for reproductive and developmental toxicity: A case study on pesticides

BACKGROUND

In silico methods for toxicity prediction have increased significantly in recent years due to the 3Rs principle. This also applies to predicting reproductive toxicology, which is one of the most critical factors in pesticide approval. The widely used quantitative structure-activity relationship (QSAR) models use experimental toxicity data to create a model that relates experimentally observed toxicity to molecular structures to predict toxicity. Aim of the study was to evaluate the available prediction models for developmental and reproductive toxicity regarding their strengths and weaknesses in a pesticide database.

METHODS

The reproductive toxicity of 315 pesticides, which have a GHS classification by ECHA, was compared with the prediction of different in silico models: VEGA, OECD (Q)SAR Toolbox, Leadscope Model Applier, and CASE Ultra by MultiCASE.

RESULTS

In all models, a large proportion (up to 77%) of all pesticides were outside the chemical space of the model. Analysis of the prediction of remaining pesticides revealed a balanced accuracy of the models between 0.48 and 0.66.

CONCLUSION

Overall, predictions were only meaningful in rare cases and therefore always require evaluation by an expert. The critical factors were the underlying data and determination of molecular similarity, which offer great potential for improvement.

IDL-PPBopt: A Strategy for Prediction and Optimization of Human Plasma Protein Binding of Compounds via an Interpretable Deep Learning Method

The prediction and optimization of pharmacokinetic properties are essential in lead optimization. Traditional strategies mainly depend on the empirical chemical rules from medicinal chemists. However, with the rising amount of data, it is getting more difficult to manually extract useful medicinal chemistry knowledge. To this end, we introduced IDL-PPBopt, a computational strategy for predicting and optimizing the plasma protein binding (PPB) property based on an interpretable deep learning method. At first, a curated PPB data set was used to construct an interpretable deep learning model, which showed excellent predictive performance with a root mean squared error of 0.112 for the entire test set. Then, we designed a detection protocol based on the model and Wilcoxon test to identify the PPB-related substructures (named privileged substructures, PSubs) for each molecule. In total, 22 general privileged substructures (GPSubs) were identified, which shared some common features such as nitrogen-containing groups, diamines with two carbon units, and azetidine. Furthermore, a series of second-level chemical rules for each GPSub were derived through a statistical test and then summarized into substructure pairs. We demonstrated that these substructure pairs were equally applicable outside the training set and accordingly customized the structural modification schemes for each GPSub, which provided alternatives for the optimization of the PPB property. Therefore, IDL-PPBopt provides a promising scheme for the prediction and optimization of the PPB property and would be helpful for lead optimization of other pharmacokinetic properties.

A Computational Approach for Respiratory Hazard Identification of Flavor Chemicals in Tobacco Products

Flavor chemicals contribute to the appeal and toxicity of tobacco products, including electronic nicotine delivery systems (ENDS). The assortment of flavor chemicals available for use in tobacco products is extensive. In this study, a chemistry-driven computational approach was used to evaluate flavor chemicals based on intrinsic hazardous structures and reactivity of chemicals. A large library of 3012 unique flavor chemicals was compiled from publicly available information. Next, information was computed and collated based on their (1) physicochemical properties, (2) global harmonization system (GHS) health hazard classification, (3) structural alerts linked to the chemical's reactivity, instability, or toxicity, and (4) common substructure shared with FDA's harmful and potentially harmful constituents (HPHCs) flavor chemicals that are respiratory toxicants. Computational analysis of the constructed flavor library flagged 638 chemicals with GHS classified respiratory health hazards, 1079 chemicals with at least one structural alert, and 2297 chemicals with substructural similarity to FDA's established and proposed list of HPHCs. A subsequent analysis was performed on a subset of 173 chemicals in the flavor library that are respiratory health hazards, contain structural alerts as well as flavor HPHC substructures. Four general toxicophore structures with an increased potential for respiratory toxicity were then identified. In summary, computational methods are efficient tools for hazard identification and understanding structure-toxicity relationship. With appropriate context of use and interpretation, in silico methods may provide scientific evidence to support toxicological evaluations of chemicals in or emitted from tobacco products.

Exploration of structural requirements for azole chemicals towards human aromatase CYP19A1 activity: Classification modeling, structure-activity relationships and read-across study

Human aromatase, also called CYP19A1, plays a major role in the conversion of androgens into estrogens. Inhibition of aromatase is an important target for estrogen receptor (ER)-responsive breast cancer therapy. Use of azole compounds as aromatase inhibitors is widespread despite their low selectivity. A toxicological evaluation of commonly used azole-based drugs and agrochemicals with respect to CYP19A1is currently requested by the European Union- Registration, Evaluation, Authorization and Restriction of Chemicals (EU-REACH) regulations due to their potential as endocrine disruptors. In this connection, identification of structural alerts (SAs) is an effective strategy for the toxicological assessment and safe drug design. The present study describes the identification of SAs of azole-based chemicals as guiding experts to predict the aromatase activity. Total 21 SAs associated with aromatase activity were extracted from dataset of 326 azole-based drugs/chemicals obtained from Tox21 library. A cross-validated classification model having high accuracy (error rate 5%) was proposed which can precisely classify azole chemicals into active/inactive toward aromatase. In addition, mechanistic details and toxicological properties (agonism/antagonism) of azoles with respect to aromatase were explored by comparing active and inactive chemicals using structure-activity relationships (SAR). Lastly, few structural alerts were applied to form chemical categories for read-across applications.

ADENet: a novel network-based inference method for prediction of drug adverse events

Identification of adverse drug events (ADEs) is crucial to reduce human health risks and improve drug safety assessment. With an increasing number of biological and medical data, computational methods such as network-based methods were proposed for ADE prediction with high efficiency and low cost. However, previous network-based methods rely on the topological information of known drug-ADE networks, and hence cannot make predictions for novel compounds without any known ADE. In this study, we introduced chemical substructures to bridge the gap between the drug-ADE network and novel compounds, and developed a novel network-based method named ADENet, which can predict potential ADEs for not only drugs within the drug-ADE network, but also novel compounds outside the network. To show the performance of ADENet, we collected drug-ADE associations from a comprehensive database named MetaADEDB and constructed a series of network-based prediction models. These models obtained high area under the receiver operating characteristic curve values ranging from 0.871 to 0.947 in 10-fold cross-validation. The best model further showed high performance in external validation, which outperformed a previous network-based and a recent deep learning-based method. Using several approved drugs as case studies, we found that 32-54% of the predicted ADEs can be validated by the literature, indicating the practical value of ADENet. Moreover, ADENet is freely available at our web server named NetInfer (http://lmmd.ecust.edu.cn/netinfer). In summary, our method would provide a promising tool for ADE prediction and drug safety assessment in drug discovery and development.

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.

DeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation

Carcinogenicity testing plays an essential role in identifying carcinogens in environmental chemistry and drug development. However, it is a time-consuming and label-intensive process to evaluate the carcinogenic potency with conventional 2-years rodent animal studies. Thus, there is an urgent need for alternative approaches to providing reliable and robust assessments on carcinogenicity. In this study, we proposed a DeepCarc model to predict carcinogenicity for small molecules using deep learning-based model-level representations. The DeepCarc Model was developed using a data set of 692 compounds and evaluated on a test set containing 171 compounds in the National Center for Toxicological Research liver cancer database (NCTRlcdb). As a result, the proposed DeepCarc model yielded a Matthews correlation coefficient (MCC) of 0.432 for the test set, outperforming four advanced deep learning (DL) powered quantitative structure-activity relationship (QSAR) models with an average improvement rate of 37%. Furthermore, the DeepCarc model was also employed to screen the carcinogenicity potential of the compounds from both DrugBank and Tox21. Altogether, the proposed DeepCarc model could serve as an early detection tool (https://github.com/TingLi2016/DeepCarc) for carcinogenicity assessment.

In silico prediction of chemical-induced hematotoxicity with machine learning and deep learning methods

Chemical-induced hematotoxicity is an important concern in the drug discovery, since it can often be fatal when it happens. It is quite useful for us to give special attention to chemicals which can cause hematotoxicity. In the present study, we focused on in silico prediction of chemical-induced hematotoxicity with machine learning (ML) and deep learning (DL) methods. We collected a large data set contained 632 hematotoxic chemicals and 1525 approved drugs without hematotoxicity. Computational models were built using several different machine learning and deep learning algorithms integrated on the Online Chemical Modeling Environment (OCHEM). Based on the three best individual models, a consensus model was developed. It yielded the prediction accuracy of 0.83 and balanced accuracy of 0.77 on external validation. The consensus model and the best individual model developed with random forest regression and classification algorithm (RFR) and QNPR descriptors were made available at https://ochem.eu/article/135149 , respectively. The relevance of 8 commonly used molecular properties and chemical-induced hematotoxicity was also investigated. Several molecular properties have an obvious differentiating effect on chemical-induced hematotoxicity. Besides, 12 structural alerts responsible for chemical hematotoxicity were identified using frequency analysis of substructures from Klekota-Roth fingerprint. These results should provide meaningful knowledge and useful tools for hematotoxicity evaluation in drug discovery and environmental risk assessment.

Trends in predictive biodegradation for sustainable mitigation of environmental pollutants: Recent progress and future outlook

The feasibility of in-silico techniques, together with the computational framework, has been applied to predictive bioremediation aiming to clean-up contaminants, toxicity evaluation, and possibilities for the degradation of complex recalcitrant compounds. Emerging contaminants from different industries have posed a significant hazard to the environment and public health. Given current bioremediation strategies, it is often a failure or inadequate for sustainable mitigation of hazardous pollutants. However, clear-cut vital information about biodegradation is quite incomplete from a conventional remediation techniques perspective. Lacking complete information on bio-transformed compounds leads to seeking alternative methods. Only scarce information about the transformed products and toxicity profile is available in the published literature. To fulfill this literature gap, various computational or in-silico technologies have emerged as alternating techniques, which are being recognized as in-silico approaches for bioremediation. Molecular docking, molecular dynamics simulation, and biodegradation pathways predictions are the vital part of predictive biodegradation, including the Quantitative Structure-Activity Relationship (QSAR), Quantitative structure-biodegradation relationship (QSBR) model system. Furthermore, machine learning (ML), artificial neural network (ANN), genetic algorithm (GA) based programs offer simultaneous biodegradation prediction along with toxicity and environmental fate prediction. Herein, we spotlight the feasibility of in-silico remediation approaches for various persistent, recalcitrant contaminants while traditional bioremediation fails to mitigate such pollutants. Such could be addressed by exploiting described model systems and algorithm-based programs. Furthermore, recent advances in QSAR modeling, algorithm, and dedicated biodegradation prediction system have been summarized with unique attributes.

Current opinion on risk assessment of cosmetics

Risk assessment of cosmetic ingredients is a useful scientific method to characterize potential adverse effects resulting from using cosmetics. The process of risk assessment consists of four steps: hazard identification, dose-response assessment, exposure assessment, and risk characterization. Hazard identification of chemicals refers to the initial stage of risk assessment and generally utilizes animal studies to evaluate toxicity. Since 2013, however, toxicity studies of cosmetic ingredients using animals have not been permitted in the EU and alternative toxicity test methods for animal studies have momentum to be developed for cosmetic ingredients. In this paper, we briefly review the alternative test methods that are available for cosmetic ingredients including read-across, in silico, in chemico, and invitro methods. In addition, new technologies such as omics and artificial intelligence (AI) have been discussed to expand or improve the knowledge and hazard identification of cosmetic ingredients. Aggregate exposure of cosmetic ingredients is another safety issue and methods for its improvement were reviewed. There have been concerns over the safety of nano-cosmetics for a long time, but the risk of nano-cosmetics remains unclear. Therefore, current issues of cosmetic risk assessment are discussed and expert opinion will be provided for the safety of cosmetics.

Discovery of Natural Products Targeting NQO1 via an Approach Combining Network-Based Inference and Identification of Privileged Substructures

NAD(P)H:quinone oxidoreductase 1 (NQO1) has been shown to be a potential therapeutic target for various human diseases, such as cancer and neurodegenerative disorders. Recent advances in computational methods, especially network-based methods, have made it possible to identify novel compounds for a target with high efficiency and low cost. In this study, we designed a workflow combining network-based methods and identification of privileged substructures to discover new compounds targeting NQO1 from a natural product library. According to the prediction results, we purchased 56 compounds for experimental validation. Without the assistance of privileged substructures, 31 compounds (31/56 = 55.4%) showed IC₅₀ < 100 μM, and 11 compounds (11/56 = 19.6%) showed IC₅₀ < 10 μM. With the assistance of privileged substructures, the two success rates were increased to 61.8 and 26.5%, respectively. Seven natural products further showed inhibitory activity on NQO1 at the cellular level, which may serve as lead compounds for further development. Moreover, network analysis revealed that osthole may exert anticancer effects against multiple cancer types by inhibiting not only carbonic anhydrases IX and XII but also NQO1. Our workflow and computational methods can be easily applied in other targets and become useful tools in drug discovery and development.

The right tools for the job: the central role for next generation chemical probes and chemistry-based target deconvolution methods in phenotypic drug discovery

The reconnection of the scientific community with phenotypic drug discovery has created exciting new possibilities to develop therapies for diseases with highly complex biology. It promises to revolutionise fields such as neurodegenerative disease and regenerative medicine, where the development of new drugs has consistently proved elusive. Arguably, the greatest challenge in readopting the phenotypic drug discovery approach exists in establishing a crucial chain of translatability between phenotype and benefit to patients in the clinic. This remains a key stumbling block for the field which needs to be overcome in order to fully realise the potential of phenotypic drug discovery. Excellent quality chemical probes and chemistry-based target deconvolution techniques will be a crucial part of this process. In this review, we discuss the current capabilities of chemical probes and chemistry-based target deconvolution methods and evaluate the next advances necessary in order to fully support phenotypic screening approaches in drug discovery.

A Robust, Mechanistically Based In Silico Structural Profiler for Hepatic Cholestasis

Owing to the primary role which it holds within metabolism of xenobiotics, the liver stands at heightened risk of exposure to, and injury from, potentially hazardous substances. A principal manifestation of liver dysfunction is cholestasis-the impairment of physiological bile circulation from its point of origin within the organ to the site of action in the small intestine. The capacity for early identification of compounds liable to exert cholestatic effects is of particular utility within the field of pharmaceutical development, where contribution toward candidate attrition is great. Shortcomings associated with the present in vitro methodologies forecasting cholestasis render their predictivity questionable, permitting scope for the adoption of computational toxicology techniques. As such, the intention of this study has been to construct an in silico profiler, founded upon clinical data, highlighting structural motifs most reliably associated with the end point. Drawing upon a list of >1500 small molecular drugs, compiled and annotated by Kotsampasakou, E. and Ecker, G. F. (J. Chem. Inf. Model. 2017, 57, 608-615), we have formulated a series of 15 structural alerts. These describe fragments intrinsic within distinct pharmaceutical classes including psychoactive tricyclics, β-lactam antimicrobials, and estrogenic/androgenic steroids. Description of the coverage and selectivity of each are provided, alongside consideration of the underlying reactive mechanisms and relevant structure-activity concerns. Provision of mechanistic anchoring ensures that potential exists for framing within the adverse outcome pathway paradigm-the chemistry conveyed through the alert, in particular enabling rationalization at the level of the molecular initiating event.

The Influence of Structural Patterns on Acute Aquatic Toxicity of Organic Compounds

Investigation of the influence of molecular structure of different organic compounds on acute toxicity towards Fathead minnow, Daphnia magna, and Tetrahymena pyriformis has been carried out using 2D simplex representation of molecular structure and two modelling methods: Random Forest (RF) and Gradient Boosting Machine (GBM). Suitable QSAR (Quantitative Structure - Activity Relationships) models were obtained. The study was focused on QSAR models interpretation. The aim of the study was to develop a set of structural fragments that simultaneously consistently increase toxicity toward Fathead minnow, Daphnia magna, Tetrahymena pyriformis. The interpretation allowed to gain more details about known toxicophores and to propose new fragments. The results obtained made it possible to rank the contributions of molecular fragments to various types of toxicity to aquatic organisms. This information can be used for molecular optimization of chemicals. According to the results of structural interpretation, the most significant common mechanisms of the toxic effect of organic compounds on Fathead minnow, Daphnia magna and Tetrahymena pyriformis are reactions of nucleophilic substitution and inhibition of oxidative phosphorylation in mitochondria. In addition acetylcholinesterase and voltage-gated ion channel of Fathead minnow and Daphnia magna are important targets for toxicants. The on-line version of the OCHEM expert system (https://ochem.eu) were used for a comparative QSAR investigation. The proposed QSAR models comply with the OECD principles and can be used to reliably predict acute toxicity of organic compounds towards Fathead minnow, Daphnia magna and Tetrahymena pyriformis with allowance for applicability domain estimation.

Development of classification models for predicting inhibition of mitochondrial fusion and fission using machine learning methods

Mitochondrial fusion and fission are processes to maintain mitochondrial function when cells respond to environment stresses. Disruption of mitochondrial fusion and fission influences cell health and can cause adverse events such as neurodegenerative disorders. It is critical to identify environmental chemicals that can disrupt mitochondrial fusion and fission. However, experimentally testing all the chemicals is not practical because experimental methods are time-consuming and costly. Quantitative structure-activity relationship (QSAR) modeling is an attractive approach for evaluation of chemicals disrupting potential on mitochondrial fusion and fission. In this study, QSAR models were developed for differentiating chemicals capable of inhibition of mitochondrial fusion and fission using machine learning algorithms (i.e. random forest, logistic regression, Bernoulli naive Bayes, and deep neural network). One hundred iterations of five-fold cross validations and external validations showed that the best model on mitochondrial fusion had area under the receiver operating characteristic curve (AUC) of 82.8% and 78.1%, respectively; and the best model for mitochondrial fission yielded AUC of 84.3% and 97.5%, respectively. Furthermore, 45 and 56 structural alerts were identified for inhibition of mitochondrial fusion and fission, respectively. The results demonstrated that the models and the structural alerts could be useful for screening chemicals that inhibit mitochondrial fusion and fission.