The development and application of in silico models for drug induced liver injury

Roadmap to DILI research in Europe. A proposal from COST action ProEuroDILINet

In the current article the aims for a constructive way forward in Drug-Induced Liver Injury (DILI) are to highlight the most important priorities in research and clinical science, therefore supporting a more informed, focused, and better funded future for European DILI research. This Roadmap aims to identify key challenges, define a shared vision across all stakeholders for the opportunities to overcome these challenges and propose a high-quality research program to achieve progress on the prediction, prevention, diagnosis and management of this condition and impact on healthcare practice in the field of DILI. This will involve 1. Creation of a database encompassing optimised case report form for prospectively identified DILI cases with well-characterised controls with competing diagnoses, biological samples, and imaging data; 2. Establishing of preclinical models to improve the assessment and prediction of hepatotoxicity in humans to guide future drug safety testing; 3. Emphasis on implementation science and 4. Enhanced collaboration between drug-developers, clinicians and regulatory scientists. This proposed operational framework will advance DILI research and may bring together basic, applied, translational and clinical research in DILI.

InterDILI: interpretable prediction of drug-induced liver injury through permutation feature importance and attention mechanism

Safety is one of the important factors constraining the distribution of clinical drugs on the market. Drug-induced liver injury (DILI) is the leading cause of safety problems produced by drug side effects. Therefore, the DILI risk of approved drugs and potential drug candidates should be assessed. Currently, in vivo and in vitro methods are used to test DILI risk, but both methods are labor-intensive, time-consuming, and expensive. To overcome these problems, many in silico methods for DILI prediction have been suggested. Previous studies have shown that DILI prediction models can be utilized as prescreening tools, and they achieved a good performance. However, there are still limitations in interpreting the prediction results. Therefore, this study focused on interpreting the model prediction to analyze which features could potentially cause DILI. For this, five publicly available datasets were collected to train and test the model. Then, various machine learning methods were applied using substructure and physicochemical descriptors as inputs and the DILI label as the output. The interpretation of feature importance was analyzed by recognizing the following general-to-specific patterns: (i) identifying general important features of the overall DILI predictions, and (ii) highlighting specific molecular substructures which were highly related to the DILI prediction for each compound. The results indicated that the model not only captured the previously known properties to be related to DILI but also proposed a new DILI potential substructural of physicochemical properties. The models for the DILI prediction achieved an area under the receiver operating characteristic (AUROC) of 0.88-0.97 and an area under the Precision-Recall curve (AUPRC) of 0.81-0.95. From this, we hope the proposed models can help identify the potential DILI risk of drug candidates at an early stage and offer valuable insights for drug development.

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.

Machine Learning Toxicity Prediction: Latest Advances by Toxicity End Point

Machine learning (ML) models to predict the toxicity of small molecules have garnered great attention and have become widely used in recent years. Computational toxicity prediction is particularly advantageous in the early stages of drug discovery in order to filter out molecules with high probability of failing in clinical trials. This has been helped by the increase in the number of large toxicology databases available. However, being an area of recent application, a greater understanding of the scope and applicability of ML methods is still necessary. There are various kinds of toxic end points that have been predicted in silico. Acute oral toxicity, hepatotoxicity, cardiotoxicity, mutagenicity, and the 12 Tox21 data end points are among the most commonly investigated. Machine learning methods exhibit different performances on different data sets due to dissimilar complexity, class distributions, or chemical space covered, which makes it hard to compare the performance of algorithms over different toxic end points. The general pipeline to predict toxicity using ML has already been analyzed in various reviews. In this contribution, we focus on the recent progress in the area and the outstanding challenges, making a detailed description of the state-of-the-art models implemented for each toxic end point. The type of molecular representation, the algorithm, and the evaluation metric used in each research work are explained and analyzed. A detailed description of end points that are usually predicted, their clinical relevance, the available databases, and the challenges they bring to the field are also highlighted.

Multiple machine learning methods aided virtual screening of NaV 1.5 inhibitors

Na_v 1.5 sodium channels contribute to the generation of the rapid upstroke of the myocardial action potential and thereby play a central role in the excitability of myocardial cells. At present, the patch clamp method is the gold standard for ion channel inhibitor screening. However, this method has disadvantages such as high technical difficulty, high cost and low speed. In this study, novel machine learning models to screen chemical blockers were developed to overcome the above shortage. The data from the ChEMBL Database were employed to establish the machine learning models. Firstly, six molecular fingerprints together with five machine learning algorithms were used to develop 30 classification models to predict effective inhibitors. A validation and a test set were used to evaluate the performance of the models. Subsequently, the privileged substructures tightly associated with the inhibition of the Na_v 1.5 ion channel were extracted using the bioalerts Python package. In the validation set, the RF-Graph model performed best. Similarly, RF-Graph produced the best result in the test set in which the Prediction Accuracy (Q) was 0.9309 and Matthew's correlation coefficient was 0.8627, further indicating the model had high classification ability. The results of the privileged substructures indicated Sulfa structures and fragments with large Steric hindrance tend to block Na_v 1.5. In the unsupervised learning task of identifying sulfa drugs, MACCS and Graph fingerprints had good results. In summary, effective machine learning models have been constructed which help to screen potential inhibitors of the Na_v 1.5 ion channel and key privileged substructures with high affinity were also extracted.

Small Molecular Drug Screening Based on Clinical Therapeutic Effect

Virtual screening can significantly save experimental time and costs for early drug discovery. Drug multi-classification can speed up virtual screening and quickly predict the most likely class for a drug. In this study, 1019 drug molecules with actual therapeutic effects are collected from multiple databases and documents, and molecular sets are grouped according to therapeutic effect and mechanism of action. Molecular descriptors and molecular fingerprints are obtained through SMILES to quantify molecular structures. After using the Kennard–Stone method to divide the data set, a better combination can be obtained by comparing the combined results of five classification algorithms and a fusion method. Furthermore, for a specific data set, the model with the best performance is used to predict the validation data set. The test set shows that prediction accuracy can reach 0.862 and kappa coefficient can reach 0.808. The highest classification accuracy of the validation set is 0.873. The more reliable molecular set has been found, which could be used to predict potential attributes of unknown drug compounds and even to discover new use for old drugs. We hope this research can provide a reference for virtual screening of multiple classes of drugs at the same time in the future.

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.

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.

Recent research progress in galactose-based fluorescent probes for detection of biomarkers of liver diseases

This highlight illustrates the challenges and latest progress in galactose-based fluorescent probes for early diagnosis of liver diseases.

In Silico Models for Hepatotoxicity

In this chapter, we review the state of the art of predicting human hepatotoxicity using in silico techniques. There has been significant progress in this area over the past 20 years but there are still some challenges ahead. Principally, these challenges are our partial understanding of a very complex biochemical system and our ability to emulate that in a predictive capacity. Here, we provide an overview of the published modeling approaches in this area to date and discuss their design, strengths and weaknesses. It is interesting to note the diversity in modeling approaches, whether they be statistical algorithms or evidenced-based approaches including structural alerts and pharmacophore models. Irrespective of modeling approach, it appears a common theme of access to appropriate, relevant, and high-quality data is a limitation to all and is likely to continue to be the focus of future research.

Joint Decision-Making Model Based on Consensus Modeling Technology for the Prediction of Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is the major cause of clinical trial failure and postmarketing withdrawals of approved drugs. It is very expensive and time-consuming to evaluate hepatotoxicity using animal or cell-based experiments in the early stage of drug development. In this study, an in silico model based on the joint decision-making strategy was developed for DILI assessment using a relatively large dataset of 2608 compounds. Five consensus models were developed with PaDEL descriptors and PubChem, Substructure, Estate, and Klekota–Roth fingerprints, respectively. Submodels for each consensus model were obtained through joint optimization. The parameters and features of each submodel were optimized jointly based on the hybrid quantum particle swarm optimization (HQPSO) algorithm. The application domain (AD) based on the frequency-weighted and distance (FWD)-based method and Tanimoto similarity index showed the wide AD of the qualified consensus models. A joint decision-making model was integrated by the qualified consensus models, and the overwhelming majority principle was used to improve the performance of consensus models. The application scope narrowing caused by the overwhelming majority principle was successfully solved by joint decision-making. The proposed model successfully predicted 99.2% of the compounds in the test set, with an accuracy of 80.0%, a sensitivity of 83.9, and a specificity of 73.3%. For an external validation set containing 390 compounds collected from DILIrank, 98.2% of the compounds were successfully predicted with an accuracy of 79.9%, a sensitivity of 97.1%, and a specificity of 66.0%. Furthermore, 25 privileged substructures responsible for DILI were identified from Substructure, PubChem, and Klekota–Roth fingerprints. These privileged substructures can be regarded as structural alerts in hepatotoxicity evaluation. Compared with the main published studies, our method exhibits certain advantage in data size, transparency, and standardization of the modeling process and accuracy and credibility of prediction results. It is a promising tool for virtual screening in the early stage of drug development.

ResNet18DNN: prediction approach of drug-induced liver injury by deep neural network with ResNet18

Drug-induced liver injury (DILI) has always been the focus of clinicians and drug researchers. How to improve the performance of the DILI prediction model to accurately predict liver injury was an urgent problem for researchers in the field of medical research. In order to solve this scientific problem, this research collected a comprehensive and accurate dataset of DILI with high recognition and high quality based on clinically confirmed DILI compound datasets, including 1446 chemical compounds. Then, the residual neural network with 18-layer by using more 5-layer blocks (ResNet18) with deep neural network (ResNet18DNN) model was proposed to predict DILI, which was an improved model for DILI prediction through vectorization of compound structure image. In predicting DILI, the ResNet18DNN learned greatly and outperformed the existing state-of-the-art DILI predictors. The results of DILI prediction model based on ResNet18DNN showed that the AUC (area under the curve), accuracy, recall, precision, F1-score and specificity of the training set were 0.973, 0.992, 0.995, 0.994, 0.995 and 0.975; those of test set were, respectively, 0.958, 0.976, 0.935, 0.947, 0.926 and 0.913, which were better than the performance of previously published described DILI prediction models. This method adopted ResNet18 embedding method to vectorize molecular structure images and the evaluation indicators of Resnet18DNN were obtained after 10 000 iterations. This prediction approach will greatly improve the performance of the predictive model of DILI and provide an accurate and precise early warning method for DILI in drug development and clinical medication.

Preclinical models of idiosyncratic drug-induced liver injury (iDILI): Moving towards prediction

Idiosyncratic drug-induced liver injury (iDILI) encompasses the unexpected harms that prescription and non-prescription drugs, herbal and dietary supplements can cause to the liver. iDILI remains a major public health problem and a major cause of drug attrition. Given the lack of biomarkers for iDILI prediction, diagnosis and prognosis, searching new models to predict and study mechanisms of iDILI is necessary. One of the major limitations of iDILI preclinical assessment has been the lack of correlation between the markers of hepatotoxicity in animal toxicological studies and clinically significant iDILI. Thus, major advances in the understanding of iDILI susceptibility and pathogenesis have come from the study of well-phenotyped iDILI patients. However, there are many gaps for explaining all the complexity of iDILI susceptibility and mechanisms. Therefore, there is a need to optimize preclinical human in vitro models to reduce the risk of iDILI during drug development. Here, the current experimental models and the future directions in iDILI modelling are thoroughly discussed, focusing on the human cellular models available to study the pathophysiological mechanisms of the disease and the most used in vivo animal iDILI models. We also comment about in silico approaches and the increasing relevance of patient-derived cellular models.

Prediction of Drug-Induced Liver Toxicity Using SVM and Optimal Descriptor Sets

Drug-induced liver toxicity is one of the significant safety challenges for the patient's health and the pharmaceutical industry. It causes termination of drug candidates in clinical trials and also the retractions of approved drugs from the market. Thus, it is essential to identify hepatotoxic compounds in the initial stages of drug development process. The purpose of this study is to construct quantitative structure activity relationship models using machine learning algorithms and systematical feature selection methods for molecular descriptor sets. The models were built from a large and diverse set of 1253 drug compounds and were validated internally with 10-fold cross-validation. In this study, we applied a variety of feature selection techniques to extract the optimal subset of descriptors as modeling features to improve the prediction performance. Experimental results suggested that the support vector machine-based classifier had achieved a better classification accuracy with reduced molecular descriptors. The final optimal model provides an accuracy of 0.811, a sensitivity of 0.840, a specificity of 0.783 and Mathew's correlation coefficient of 0.623 with an internal validation set. Furthermore, this model outperformed the prior studies while evaluated in both the internal and external test sets. The utilization of distinct optimal molecular descriptors as modeling features produce an in silico model with a superior performance.

In silico prediction of drug-induced ototoxicity using machine learning and deep learning methods

Drug-induced ototoxicity has become a serious global problem, because of leading to deafness in hundreds of thousands of people every year. It always results from exposure to drugs or environmental chemicals that cause the impairment and degeneration of the inner ear. Herein, we focused on the in silico modeling of drug-induced ototoxicity of chemicals. We collected 1,102 ototoxic medications and 1,705 non-ototoxic drugs. Based on the data set, a series of computational models were developed with different traditional machine learning and deep learning algorithms implemented on an online chemical database and modeling environment. Six ML models performed best on 5-fold cross-validation and test set. A consensus model was developed with the best individual models. These models were further validated with an external validation. The consensus model showed best predictive ability, with high accuracy of 0.95 on test set and 0.90 on validation set. The consensus model and the data sets used for model development are available at https://ochem.eu/model/46566321. Besides, 16 structural alerts responsible for drug-induced ototoxicity were identified. We hope the results could provide meaningful knowledge and useful tools for ototoxicity evaluation in drug discovery and environmental risk assessment.

Machine Learning in Predictive Toxicology: Recent Applications and Future Directions for Classification Models

In recent times, machine learning has become increasingly prominent in predictive toxicology as it has shifted from in vivo studies toward in silico studies. Currently, in vitro methods together with other computational methods such as quantitative structure-activity relationship modeling and absorption, distribution, metabolism, and excretion calculations are being used. An overview of machine learning and its applications in predictive toxicology is presented here, including support vector machines (SVMs), random forest (RF) and decision trees (DTs), neural networks, regression models, naïve Bayes, k-nearest neighbors, and ensemble learning. The recent successes of these machine learning methods in predictive toxicology are summarized, and a comparison of some models used in predictive toxicology is presented. In predictive toxicology, SVMs, RF, and DTs are the dominant machine learning methods due to the characteristics of the data available. Lastly, this review describes the current challenges facing the use of machine learning in predictive toxicology and offers insights into the possible areas of improvement in the field.

Neural network activation similarity: a new measure to assist decision making in chemical toxicology

Deep learning neural networks, constructed for the prediction of chemical binding at 79 pharmacologically important human biological targets, show extremely high performance on test data (accuracy 92.2 ± 4.2%, MCC 0.814 ± 0.093 and ROC-AUC 0.96 ± 0.04). A new molecular similarity measure, Neural Network Activation Similarity, has been developed, based on signal propagation through the network. This is complementary to standard Tanimoto similarity, and the combined use increases confidence in the computer's prediction of activity for new chemicals by providing a greater understanding of the underlying justification. The in silico prediction of these human molecular initiating events is central to the future of chemical safety risk assessment and improves the efficiency of safety decision making.

Ensemble Models Based on QuBiLS-MAS Features and Shallow Learning for the Prediction of Drug-Induced Liver Toxicity: Improving Deep Learning and Traditional Approaches

Drug-induced liver injury (DILI) is a key safety issue in the drug discovery pipeline and a regulatory concern. Thus, many in silico tools have been proposed to improve the hepatotoxicity prediction of organic-type chemicals. Here, classifiers for the prediction of DILI were developed by using QuBiLS-MAS 0-2.5D molecular descriptors and shallow machine learning techniques, on a training set composed of 1075 molecules. The best ensemble model build, E13, was obtained with good statistical parameters for the learning series, namely, the following: accuracy = 0.840, sensibility = 0.890, specificity = 0.761, Matthew's correlation coefficient = 0.660, and area under the ROC curve = 0.904. The model was also satisfactorily evaluated with Y-scrambling test, and repeated k-fold cross-validation and repeated k-holdout validation. In addition, an exhaustive external validation was also carried out by using two test sets and five external test sets, with an average accuracy value equal to 0.854 (±0.062) and a coverage equal to 98.4% according to its applicability domain. A statistical comparison of the performance of the E13 model, with regard to results and tools (e.g., Padel DDPredictor Software, Deep Learning DILIserver, and Vslead) reported in the literature, was also performed. In general, E13 presented the best global performance in all experiments. The sum of the ranking differences procedure provided a very similar grouping pattern to that of the M-ANOVA statistical analysis, where E13 was identified as the best model for DILI predictions. A noncommercial and fully cross-platform software for the DILI prediction was also developed, which is freely available at http://tomocomd.com/apps/ptoxra. This software was used for the screening of seven data sets, containing natural products, leads, toxic materials, and FDA approved drugs, to assess the usefulness of the QSAR models in the DILI labeling of organic substances; it was found that 50-92% of the evaluated molecules are positive-DILI compounds. All in all, it can be stated that the E13 model is a relevant method for the prediction of DILI risk in humans, as it shows the best results among all of the methods analyzed.

Modeling and insights into molecular basis of low molecular weight respiratory sensitizers

Respiratory sensitization has been considered an important toxicological endpoint, because of the severe risk to human health. A great part of sensitization events were caused by low molecular weight (< 1000) respiratory sensitizers in the past decades. However, there is currently no widely accepted test method that can identify prospective low molecular weight respiratory sensitisers. Herein, we performed the study of modeling and insights into molecular basis of low molecular weight respiratory sensitizers with a high-quality data set containing 136 respiratory sensitizers and 518 nonsensitizers. We built a number of classification models by using OCHEM tools, and a consensus model was developed based on the ten best individual models. The consensus model showed good predictive ability with a balanced accuracy of 0.78 and 0.85 on fivefold cross-validation and external validation, respectively. The readers can predict the respiratory sensitization of organic compounds via https://ochem.eu/article/114857 . The effect of several molecular properties on respiratory sensitization was also evaluated. The results indicated that these properties differ significantly between respiratory sensitizers and nonsensitizers. Furthermore, 14 privileged substructures responsible for respiratory sensitization were identified. We hope the models and the findings could provide useful help for environmental risk assessment.

In-silico approach for drug induced liver injury prediction: Recent advances

Drug induced liver injury (DILI) is the prime cause of liver disfunction which may lead to mild non-specific symptoms to more severe signs like hepatitis, cholestasis, cirrhosis and jaundice. Not only the prescription medications, but the consumption of herbs and health supplements have also been reported to cause these adverse reactions resulting into high mortality rates and post marketing withdrawal of drugs. Due to the continuously increasing DILI incidences in recent years, robust prediction methods with high accuracy, specificity and sensitivity are of priority. Bioinformatics is the emerging field of science that has been used in the past few years to explore the mechanisms of DILI. The major emphasis of this review is the recent advances of in silico tools for the diagnostic and therapeutic interventions of DILI. These tools have been developed and widely used in the past few years for the prediction of pathways induced from both hepatotoxic as well as hepatoprotective Chinese drugs and for the identification of DILI specific biomarkers for prognostic purpose. In addition to this, advanced machine learning models have been developed for the classification of drugs into DILI causing and non-DILI causing. Moreover, development of 3 class models over 2 class offers better understanding of multi-class DILI risks and at the same time providing authentic prediction of toxicity during drug designing before clinical trials.