Predicting drug-induced liver injury in human with Naïve Bayes classifier approach

HepatoToxicity Portal (HTP): an integrated database of drug-induced hepatotoxicity knowledgebase and graph neural network-based prediction model

Liver toxicity poses a critical challenge in drug development due to the liver's pivotal role in drug metabolism and detoxification. Accurately predicting liver toxicity is crucial but is hindered by scattered information sources, a lack of curation standards, and the heterogeneity of data perspectives. To address these challenges, we developed the HepatoToxicity Portal (HTP), which integrates an expert-curated knowledgebase (HTP-KB) and a state-of-the-art machine learning model for toxicity prediction (HTP-Pred). The HTP-KB consolidates hepatotoxicity data from nine major databases, carefully reviewed by hepatotoxicity experts and categorized into three levels: in vitro, in vivo, and clinical, using the Medical Dictionary for Regulatory Activities (MedDRA) terminology. The knowledgebase includes information on 8,306 chemicals. This curated dataset was used to build a hepatotoxicity prediction module by fine-tuning a GNN-based foundation model, which was pre-trained with approximately 10 million chemicals in the PubChem database. Our model demonstrated excellent performance, achieving an area under the ROC curve (AUROC) of 0.761, surpassing existing methods for hepatotoxicity prediction. The HTP is publicly accessible at https://kobic.re.kr/htp/ , offering both curated data and prediction services through an intuitive interface, thus effectively supporting drug development efforts.Scientific contributionsHTP-KB consolidates comprehensive curated information on liver toxicity gathered from nine sources. HTP-Pred utilizes advanced deep learning techniques, significantly enhancing predictive accuracy. Together, these tools provide valuable resources for researchers and practitioners in drug development, accessible through a user-friendly interface.

Deep Learning Prediction of Drug-Induced Liver Toxicity by Manifold Embedding of Quantum Information of Drug Molecules

PURPOSE

Drug-induced liver injury, or DILI, affects numerous patients and also presents significant challenges in drug development. It has been attempted to predict DILI of a chemical by in silico approaches, including data-driven machine learning models. Herein, we report a recent DILI deep-learning effort that utilized our molecular representation concept by manifold embedding electronic attributes on a molecular surface.

METHODS

Local electronic attributes on a molecular surface were mapped to a lower-dimensional embedding of the surface manifold. Such an embedding was featurized in a matrix form and used in a deep-learning model as molecular input. The model was trained by a well-curated dataset and tested through cross-validations.

RESULTS

Our DILI prediction yielded superior results to the literature-reported efforts, suggesting that manifold embedding of electronic quantities on a molecular surface enables machine learning of molecular properties, including DILI.

CONCLUSIONS

The concept encodes the quantum information of a molecule that governs intermolecular interactions, potentially facilitating the deep-learning model development and training.

Prospects of Electrocorticography in Neuropharmacological Studies in Small Laboratory Animals

Electrophysiological methods of research are widely used in neurobiology. To assess the bioelectrical activity of the brain in small laboratory animals, electrocorticography (ECoG) is most often used, which allows the recording of signals directly from the cerebral cortex. To date, a number of methodological approaches to the manufacture and implantation of ECoG electrodes have been proposed, the complexity of which is determined by experimental tasks and logistical capabilities. Existing methods for analyzing bioelectrical signals are used to assess the functional state of the nervous system in test animals, as well as to identify correlates of pathological changes or pharmacological effects. The review presents current areas of applications of ECoG in neuropharmacological studies in small laboratory animals. Traditionally, this method is actively used to study the antiepileptic activity of new molecules. However, the possibility of using ECoG to assess the neuroprotective activity of drugs in models of traumatic, vascular, metabolic, or neurodegenerative CNS damage remains clearly underestimated. Despite the fact that ECoG has a number of disadvantages and methodological difficulties, the recorded data can be a useful addition to traditional molecular and behavioral research methods. An analysis of the works in recent years indicates a growing interest in the method as a tool for assessing the pharmacological activity of psychoactive drugs, especially in combination with classification and prediction algorithms.

Machine Learning to Predict Drug-Induced Liver Injury and Its Validation on Failed Drug Candidates in Development

Drug-induced liver injury (DILI) poses a significant challenge for the pharmaceutical industry and regulatory bodies. Despite extensive toxicological research aimed at mitigating DILI risk, the effectiveness of these techniques in predicting DILI in humans remains limited. Consequently, researchers have explored novel approaches and procedures to enhance the accuracy of DILI risk prediction for drug candidates under development. In this study, we leveraged a large human dataset to develop machine learning models for assessing DILI risk. The performance of these prediction models was rigorously evaluated using a 10-fold cross-validation approach and an external test set. Notably, the random forest (RF) and multilayer perceptron (MLP) models emerged as the most effective in predicting DILI. During cross-validation, RF achieved an average prediction accuracy of 0.631, while MLP achieved the highest Matthews Correlation Coefficient (MCC) of 0.245. To validate the models externally, we applied them to a set of drug candidates that had failed in clinical development due to hepatotoxicity. Both RF and MLP accurately predicted the toxic drug candidates in this external validation. Our findings suggest that in silico machine learning approaches hold promise for identifying DILI liabilities associated with drug candidates during development.

Computational models for predicting liver toxicity in the deep learning era

Drug-induced liver injury (DILI) is a severe adverse reaction caused by drugs and may result in acute liver failure and even death. Many efforts have centered on mitigating risks associated with potential DILI in humans. Among these, quantitative structure-activity relationship (QSAR) was proven to be a valuable tool for early-stage hepatotoxicity screening. Its advantages include no requirement for physical substances and rapid delivery of results. Deep learning (DL) made rapid advancements recently and has been used for developing QSAR models. This review discusses the use of DL in predicting DILI, focusing on the development of QSAR models employing extensive chemical structure datasets alongside their corresponding DILI outcomes. We undertake a comprehensive evaluation of various DL methods, comparing with those of traditional machine learning (ML) approaches, and explore the strengths and limitations of DL techniques regarding their interpretability, scalability, and generalization. Overall, our review underscores the potential of DL methodologies to enhance DILI prediction and provides insights into future avenues for developing predictive models to mitigate DILI risk in humans.

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.

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).

Chemistry-Based Modeling on Phenotype-Based Drug-Induced Liver Injury Annotation: From Public to Proprietary Data

Drug-induced liver injury (DILI) is an important safety concern and a major reason to remove a drug from the market. Advancements in recent machine learning methods have led to a wide range of in silico models for DILI predictive methods based on molecule chemical structures (fingerprints). Existing publicly available DILI data sets used for model building are based on the interpretation of drug labels or patient case reports, resulting in a typical binary clinical DILI annotation. We developed a novel phenotype-based annotation to process hepatotoxicity information extracted from repeated dose in vivo preclinical toxicology studies using INHAND annotation to provide a more informative and reliable data set for machine learning algorithms. This work resulted in a data set of 430 unique compounds covering diverse liver pathology findings which were utilized to develop multiple DILI prediction models trained on the publicly available data (TG-GATEs) using the compound's fingerprint. We demonstrate that the TG-GATEs compounds DILI labels can be predicted well and how the differences between TG-GATEs and the external test compounds (Johnson & Johnson) impact the model generalization performance.

Machine-learning technique, QSAR and molecular dynamics for hERG-drug interactions

One of the most well-known anti-targets defining medication cardiotoxicity is the voltage-dependent hERG K + channel, which is well-known for its crucial involvement in cardiac action potential repolarization. Torsades de Pointes, QT prolongation, and sudden death are all caused by hERG (the human Ether-à-go-go-Related Gene) inhibition. There is great interest in creating predictive computational (in silico) tools to identify and weed out potential hERG blockers early in the drug discovery process because testing for hERG liability and the traditional experimental screening are complicated, expensive and time-consuming. This study used 2D descriptors of a large curated dataset of 6766 compounds and machine learning approaches to build robust descriptor-based QSAR and predictive classification models for KCNH2 liability. Decision Tree, Random Forest, Logistic Regression, Ada Boosting, kNN, SVM, Naïve Bayes, neural network and stochastic gradient classification classifier algorithms were used to build classification models. If a compound's IC50 value was between 10 μM and less, it was classified as a blocker (hERG-positive), and if it was more, it was classified as a non-blocker (hERG-negative). Matthew's correlation coefficient formula and F1score were applied to compare and track the developed models' performance. Molecular docking and dynamics studies were performed to understand the cardiotoxicity relating to the hERG-gene. The hERG residues interacting after 100 ns are LEU:697, THR:708, PHE:656, HIS:674, HIS:703, TRP:705 and ASN:709 and the hERG-ligand-16 complex trajectory showed stable behaviour with lesser fluctuations in the entire simulation of 200 ns.Communicated by Ramaswamy H. Sarma.

Applications of In Silico Models to Predict Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is a major cause of the withdrawal of pre-marketed drugs, typically attributed to oxidative stress, mitochondrial damage, disrupted bile acid homeostasis, and innate immune-related inflammation. DILI can be divided into intrinsic and idiosyncratic DILI with cholestatic liver injury as an important manifestation. The diagnosis of DILI remains a challenge today and relies on clinical judgment and knowledge of the insulting agent. Early prediction of hepatotoxicity is an important but still unfulfilled component of drug development. In response, in silico modeling has shown good potential to fill the missing puzzle. Computer algorithms, with machine learning and artificial intelligence as a representative, can be established to initiate a reaction on the given condition to predict DILI. DILIsym is a mechanistic approach that integrates physiologically based pharmacokinetic modeling with the mechanisms of hepatoxicity and has gained increasing popularity for DILI prediction. This article reviews existing in silico approaches utilized to predict DILI risks in clinical medication and provides an overview of the underlying principles and related practical applications.

Development of binary classification models for assessment of drug-induced liver injury in humans using a large set of FDA-approved drugs

Drug-induced liver injury (DILI) has been identified as one of the major causes for drugs withdrawn from the market, and even termination during the late stages of development. Therefore, it is imperative to evaluate the DILI potential of lead compounds during the research and development process. Although various computational models have been developed to predict DILI, most of which applied the DILI data were extracted from preclinical sources. In this investigation, the in silico prediction models for DILI were constructed based on 1140 FDA-approved drugs by using naïve Bayes classifier approach. The genetic algorithm method was applied for the molecular descriptors selection. Among these established prediction models, the NB-11 model based on eight molecular descriptors combined with ECFP_18 showed the best prediction performance for DILI, which gave 91.7% overall prediction accuracy for the training set, and 68.9% concordance for the external test set. Therefore, the established NB-11 prediction model can be used as a reliable virtual screening tool to predict DILI adverse effect in the early stages of drug design. In addition, some new structural alters for DILI were identified, which could be used for structural optimization in the future drug design by medicinal chemists.

Relationships between the Structure and Severe Drug-Induced Liver Injury for Low, Medium, and High Doses of Drugs

Assessment of structure-activity relationships (SARs) for predicting severe drug-induced liver injury (DILI) is essential since in vivo and in vitro preclinical methods cannot detect many druglike compounds disrupting liver functions. To date, plenty of SAR models for the prediction of DILI have been developed; however, none of them considered the route of drug administration and daily dose, which may introduce significant bias into prediction results. We have created a dataset of 617 drugs with parenteral and oral administration routes and consistent information on DILI severity. We have found a clear relationship between route, dose, and DILI severity. According to SAR, nearly 40% of moderate- and non-DILI-causing drugs would cause severe DILI if they were administered at high oral doses. We have proposed the following approach to predict severe DILI. New compounds recommended to be used at low oral doses (<∼10 mg daily), or parenterally, can be considered not causing severe DILI. DILI for compounds administered at medium oral doses (∼10-100 mg daily; 22.2% of drugs under consideration) can be considered unpredictable because reasonable SAR models were not obtained due to the small size and heterogeneity of the corresponding dataset. The DILI potential of the compounds recommended to be used at high oral doses (more than ∼100 mg daily) can be estimated using SAR modeling. The balanced accuracy of the approach calculated by a 10-fold cross-validation procedure is 0.803. The developed approach can be used to estimate severe DILI for druglike compounds proposed to use at low and high oral doses or parenterally at the early stages of drug development.

Machine Learning Models for Predicting Liver Toxicity

Liver toxicity is a major adverse drug reaction that accounts for drug failure in clinical trials and withdrawal from the market. Therefore, predicting potential liver toxicity at an early stage in drug discovery is crucial to reduce costs and the potential for drug failure. However, current in vivo animal toxicity testing is very expensive and time consuming. As an alternative approach, various machine learning models have been developed to predict potential liver toxicity in humans. This chapter reviews current advances in the development and application of machine learning models for prediction of potential liver toxicity in humans and discusses possible improvements to liver toxicity prediction.

Insight into the structural requirement of aryl sulphonamide based gelatinases (MMP-2 and MMP-9) inhibitors - Part I: 2D-QSAR, 3D-QSAR topomer CoMFA and Naïve Bayes studies - First report of 3D-QSAR Topomer CoMFA analysis for MMP-9 inhibitors and jointly inhibitors of gelatinases together

Gelatinases [gelatinase A - matrix metalloproteinase-2 (MMP-2), gelatinase B - matrix metalloproteinase-9 (MMP-9)] play key roles in many disease conditions including cancer. Despite some research work on gelatinases inhibitors both jointly and individually had been reported, challenges still exist in achieving potency as well as selectivity. Here in part I of a series of work, we have reported the structural requirement of some arylsulfonamides. In particular, regression-based 2D-QSARs, topomer CoMFA (comparative molecular field analysis) and Bayesian classification models were constructed to refine structural features for attaining better gelatinase inhibitory activity. The 2D-QSAR models exhibited good statistical significance. The descriptors nsssN, SHBint6, SHBint7, PubchemFP629 were directly correlated with the MMP-2 binding affinities whereas nsssN, SHBint10 and AATS2i were directly proportional to MMP-9 binding affinities. The topomer CoMFA results indicated that the steric and electrostatic fields play key roles in gelatinase inhibition. The established Naïve Bayes prediction models were evaluated by fivefold cross validation and an external test set. Furthermore, important molecular descriptors related to MMP-2 and MMP-9 binding affinities and some active/inactive fragments were identified. Thus, these observations may be helpful for further work of aryl sulphonamide based gelatinase inhibitors in future.

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.

Predicting rifampicin resistance mutations in bacterial RNA polymerase subunit beta based on majority consensus

BACKGROUND

Mutations in an enzyme target are one of the most common mechanisms whereby antibiotic resistance arises. Identification of the resistance mutations in bacteria is essential for understanding the structural basis of antibiotic resistance and design of new drugs. However, the traditionally used experimental approaches to identify resistance mutations were usually labor-intensive and costly.

RESULTS

We present a machine learning (ML)-based classifier for predicting rifampicin (Rif) resistance mutations in bacterial RNA Polymerase subunit β (RpoB). A total of 186 mutations were gathered from the literature for developing the classifier, using 80% of the data as the training set and the rest as the test set. The features of the mutated RpoB and their binding energies with Rif were calculated through computational methods, and used as the mutation attributes for modeling. Classifiers based on five ML algorithms, i.e. decision tree, k nearest neighbors, naïve Bayes, probabilistic neural network and support vector machine, were first built, and a majority consensus (MC) approach was then used to obtain a new classifier based on the classifications of the five individual ML algorithms. The MC classifier comprehensively improved the predictive performance, with accuracy, F-measure and AUC of 0.78, 0.83 and 0.81for training set whilst 0.84, 0.87 and 0.83 for test set, respectively.

CONCLUSION

The MC classifier provides an alternative methodology for rapid identification of resistance mutations in bacteria, which may help with early detection of antibiotic resistance and new drug discovery.

In-Vitro Approaches to Predict and Study T-Cell Mediated Hypersensitivity to Drugs

Mitigating the risk of drug hypersensitivity reactions is an important facet of a given pharmaceutical, with poor performance in this area of safety often leading to warnings, restrictions and withdrawals. In the last 50 years, efforts to diagnose, manage, and circumvent these obscure, iatrogenic diseases have resulted in the development of assays at all stages of a drugs lifespan. Indeed, this begins with intelligent lead compound selection/design to minimize the existence of deleterious chemical reactivity through exclusion of ominous structural moieties. Preclinical studies then investigate how compounds interact with biological systems, with emphasis placed on modeling immunological/toxicological liabilities. During clinical use, competent and accurate diagnoses are sought to effectively manage patients with such ailments, and pharmacovigilance datasets can be used for stratification of patient populations in order to optimise safety profiles. Herein, an overview of some of the in-vitro approaches to predict intrinsic immunogenicity of drugs and diagnose culprit drugs in allergic patients after exposure is detailed, with current perspectives and opportunities provided.

Prediction and mechanistic analysis of drug-induced liver injury (DILI) based on chemical structure

BACKGROUND

Drug-induced liver injury (DILI) is a major safety concern characterized by a complex and diverse pathogenesis. In order to identify DILI early in drug development, a better understanding of the injury and models with better predictivity are urgently needed. One approach in this regard are in silico models which aim at predicting the risk of DILI based on the compound structure. However, these models do not yet show sufficient predictive performance or interpretability to be useful for decision making by themselves, the former partially stemming from the underlying problem of labeling the in vivo DILI risk of compounds in a meaningful way for generating machine learning models.

RESULTS

As part of the Critical Assessment of Massive Data Analysis (CAMDA) "CMap Drug Safety Challenge" 2019 ( http://camda2019.bioinf.jku.at ), chemical structure-based models were generated using the binarized DILIrank annotations. Support Vector Machine (SVM) and Random Forest (RF) classifiers showed comparable performance to previously published models with a mean balanced accuracy over models generated using 5-fold LOCO-CV inside a 10-fold training scheme of 0.759 ± 0.027 when predicting an external test set. In the models which used predicted protein targets as compound descriptors, we identified the most information-rich proteins which agreed with the mechanisms of action and toxicity of nonsteroidal anti-inflammatory drugs (NSAIDs), one of the most important drug classes causing DILI, stress response via TP53 and biotransformation. In addition, we identified multiple proteins involved in xenobiotic metabolism which could be novel DILI-related off-targets, such as CLK1 and DYRK2. Moreover, we derived potential structural alerts for DILI with high precision, including furan and hydrazine derivatives; however, all derived alerts were present in approved drugs and were over specific indicating the need to consider quantitative variables such as dose.

CONCLUSION

Using chemical structure-based descriptors such as structural fingerprints and predicted protein targets, DILI prediction models were built with a predictive performance comparable to previous literature. In addition, we derived insights on proteins and pathways statistically (and potentially causally) linked to DILI from these models and inferred new structural alerts related to this adverse endpoint.

An ensemble learning approach for modeling the systems biology of drug-induced injury

BACKGROUND

Drug-induced liver injury (DILI) is an adverse reaction caused by the intake of drugs of common use that produces liver damage. The impact of DILI is estimated to affect around 20 in 100,000 inhabitants worldwide each year. Despite being one of the main causes of liver failure, the pathophysiology and mechanisms of DILI are poorly understood. In the present study, we developed an ensemble learning approach based on different features (CMap gene expression, chemical structures, drug targets) to predict drugs that might cause DILI and gain a better understanding of the mechanisms linked to the adverse reaction.

RESULTS

We searched for gene signatures in CMap gene expression data by using two approaches: phenotype-gene associations data from DisGeNET, and a non-parametric test comparing gene expression of DILI-Concern and No-DILI-Concern drugs (as per DILIrank definitions). The average accuracy of the classifiers in both approaches was 69%. We used chemical structures as features, obtaining an accuracy of 65%. The combination of both types of features produced an accuracy around 63%, but improved the independent hold-out test up to 67%. The use of drug-target associations as feature obtained the best accuracy (70%) in the independent hold-out test.

CONCLUSIONS

When using CMap gene expression data, searching for a specific gene signature among the landmark genes improves the quality of the classifiers, but it is still limited by the intrinsic noise of the dataset. When using chemical structures as a feature, the structural diversity of the known DILI-causing drugs hampers the prediction, which is a similar problem as for the use of gene expression information. The combination of both features did not improve the quality of the classifiers but increased the robustness as shown on independent hold-out tests. The use of drug-target associations as feature improved the prediction, specially the specificity, and the results were comparable to previous research studies.

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.

DeepDILI: Deep Learning-Powered Drug-Induced Liver Injury Prediction Using Model-Level Representation

Drug-induced liver injury (DILI) is the most frequently reported single cause of safety-related withdrawal of marketed drugs. It is essential to identify drugs with DILI potential at the early stages of drug development. In this study, we describe a deep learning-powered DILI (DeepDILI) prediction model created by combining model-level representation generated by conventional machine learning (ML) algorithms with a deep learning framework based on Mold2 descriptors. We conducted a comprehensive evaluation of the proposed DeepDILI model performance by posing several critical questions: (1) Could the DILI potential of newly approved drugs be predicted by accumulated knowledge of early approved ones? (2) is model-level representation more informative than molecule-based representation for DILI prediction? and (3) could improved model explainability be established? For question 1, we developed the DeepDILI model using drugs approved before 1997 to predict the DILI potential of those approved thereafter. As a result, the DeepDILI model outperformed the five conventional ML algorithms and two state-of-the-art ensemble methods with a Matthews correlation coefficient (MCC) value of 0.331. For question 2, we demonstrated that the DeepDILI model's performance was significantly improved (i.e., a MCC improvement of 25.86% in test set) compared with deep neural networks based on molecule-based representation. For question 3, we found 21 chemical descriptors that were enriched, suggesting a strong association with DILI outcome. Furthermore, we found that the DeepDILI model has more discrimination power to identify the DILI potential of drugs belonging to the World Health Organization therapeutic category of 'alimentary tract and metabolism'. Moreover, the DeepDILI model based on Mold2 descriptors outperformed the ones with Mol2vec and MACCS descriptors. Finally, the DeepDILI model was applied to the recent real-world problem of predicting any DILI concern for potential COVID-19 treatments from repositioning drug candidates. Altogether, this developed DeepDILI model could serve as a promising tool for screening for DILI risk of compounds in the preclinical setting, and the DeepDILI model is publicly available through https://github.com/TingLi2016/DeepDILI.

Predicting Drug-Induced Liver Injury Using Convolutional Neural Network and Molecular Fingerprint-Embedded Features

As a critical issue in drug development and postmarketing safety surveillance, drug-induced liver injury (DILI) leads to failures in clinical trials as well as retractions of on-market approved drugs. Therefore, it is important to identify DILI compounds in the early-stages through in silico and in vivo studies. It is difficult using conventional safety testing methods, since the predictive power of most of the existing frameworks is insufficiently effective to address this pharmacological issue. In our study, we employ a natural language processing (NLP) inspired computational framework using convolutional neural networks and molecular fingerprint-embedded features. Our development set and independent test set have 1597 and 322 compounds, respectively. These samples were collected from previous studies and matched with established chemical databases for structural validity. Our study comes up with an average accuracy of 0.89, Matthews's correlation coefficient (MCC) of 0.80, and an AUC of 0.96. Our results show a significant improvement in the AUC values compared to the recent best model with a boost of 6.67%, from 0.90 to 0.96. Also, based on our findings, molecular fingerprint-embedded featurizer is an effective molecular representation for future biological and biochemical studies besides the application of classic molecular fingerprints.

Developing novel computational prediction models for assessing chemical-induced neurotoxicity using naïve Bayes classifier technique

Development of reliable and efficient alternative in vivo methods for evaluation of the chemicals with potential neurotoxicity is an urgent need in the early stages of drug design. In this investigation, the computational prediction models for drug-induced neurotoxicity were developed by using the classical naïve Bayes classifier. Eight molecular properties closely relevant to neurotoxicity were selected. Then, 110 classification models were developed with using the eight important molecular descriptors and 10 types of fingerprints with 11 different maximum diameters. Among these 110 prediction models, the prediction model (NB-03) based on eight molecular descriptors combined with ECFP_10 fingerprints showed the best prediction performance, which gave 90.5% overall prediction accuracy for the training set and 82.1% concordance for the external test set. In addition, compared to naïve Bayes classifier, the recursive partitioning classifier displayed worse predictive performance for neurotoxicity. Therefore, the established NB-03 prediction model can be used as a reliable virtual screening tool to predict neurotoxicity in the early stages of drug design. Moreover, some structure alerts for characterizing neurotoxicity were identified in this research, which could give an important guidance for the chemists in structural modification and optimization to reduce the chemicals with potential neurotoxicity.

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.

Developing novel in silico prediction models for assessing chemical reproductive toxicity using the naïve Bayes classifier method

Assessment of reproductive toxicity is one of the important safety considerations in drug development. Thus, in the present research, the naïve Bayes (NB)-classifier method was applied to develop binary classification models. Six important molecular descriptors for reproductive toxicity were selected by the genetic algorithm. Then, 110 classification models were developed using six molecular descriptors and10 types of fingerprints with 11 different maximum diameters. Among these established models, the model based on six molecular descriptors and the SciTegic extended-connectivity fingerprints with 20 maximum diameters (LCFC_20) displayed the best prediction performance for reproductive toxicity (NB-1), which gave a 0.884 receiver operating characteristic (ROC) score and 91.8% overall prediction accuracy for the Training Set, and produced a 0.888 ROC score and 83.0% overall accuracy for the external Test Set I. In addition, for the external rat multi-generation reproductive toxicity dataset (Test Set II), the NB-1 model generated a 0.806 ROC score and 85.1% concordance. The generated prediction results indicated that the NB-1 model could give robust and reliable predictions for a reproductive toxicity potential of chemicals. Thus, the established model could be applied to filter early-stage molecules for potential reproductive adverse effects. In addition, six important molecular descriptors and new structural alerts for reproductive toxicity were identified, which could help medicinal chemists rationally guide the optimization of lead compounds and select chemicals with the best prospects of being safe and effective.

Understanding Idiosyncratic Toxicity: Lessons Learned from Drug-Induced Liver Injury

Idiosyncratic adverse drug reactions (IADRs) encompass a diverse group of toxicities that can vary by drug and patient. The complex and unpredictable nature of IADRs combined with the fact that they are rare makes them particularly difficult to predict, diagnose, and treat. Common clinical characteristics, the identification of human leukocyte antigen risk alleles, and drug-induced proliferation of lymphocytes isolated from patients support a role for the adaptive immune system in the pathogenesis of IADRs. Significant evidence also suggests a requirement for direct, drug-induced stress, neoantigen formation, and stimulation of an innate response, which can be influenced by properties intrinsic to both the drug and the patient. This Perspective will provide an overview of the clinical profile, mechanisms, and risk factors underlying IADRs as well as new approaches to study these reactions, focusing on idiosyncratic drug-induced liver injury.

Drug-induced liver injury severity and toxicity (DILIst): binary classification of 1279 drugs by human hepatotoxicity

Drug-induced liver injury (DILI) is of significant concern to drug development and regulatory review because of the limited success with existing preclinical models. For developing alternative methods, a large drug list is needed with known DILI severity and toxicity. We augmented the DILIrank data set [annotated using US Food and Drug Administration (FDA) drug labeling)] with four literature datasets (N >350 drugs) to generate the largest drug list with DILI classification, called DILIst (DILI severity and toxicity). DILIst comprises 1279 drugs, of which 768 were DILI positives (increase of 65% from DILIrank), whereas 511 were DILI negatives (increase of 65%). The investigation of DILI positive-negative distribution across various therapeutic categories revealed the most and least frequent DILI categories. Thus, we consider DILIst to be an invaluable resource for the community to improve DILI research.

Predicting Drug-Induced Liver Injury with Bayesian Machine Learning

Drug induced liver injury (DILI) can require significant risk management in drug development and on occasion can cause morbidity or mortality, leading to drug attrition. Optimizing candidates preclinically can minimize hepatotoxicity risk, but it is difficult to predict due to multiple etiologies encompassing DILI, often with multifactorial and overlapping mechanisms. In addition to epidemiological risk factors, physicochemical properties, dose, disposition, lipophilicity, and hepatic metabolic function are also relevant for DILI risk. Better human-relevant, predictive models are required to improve hepatotoxicity risk assessment in drug discovery. Our hypothesis is that integrating mechanistically relevant hepatic safety assays with Bayesian machine learning will improve hepatic safety risk prediction. We present a quantitative and mechanistic risk assessment for candidate nomination using data from in vitro assays (hepatic spheroids, BSEP, mitochondrial toxicity, and bioactivation), together with physicochemical (cLogP) and exposure (Cmax_total) variables from a chemically diverse compound set (33 no/low-, 40 medium-, and 23 high-severity DILI compounds). The Bayesian model predicts the continuous underlying DILI severity and uses a data-driven prior distribution over the parameters to prevent overfitting. The model quantifies the probability that a compound falls into either no/low-, medium-, or high-severity categories, with a balanced accuracy of 63% on held-out samples, and a continuous prediction of DILI severity along with uncertainty in the prediction. For a binary yes/no DILI prediction, the model has a balanced accuracy of 86%, a sensitivity of 87%, a specificity of 85%, a positive predictive value of 92%, and a negative predictive value of 78%. Combining physiologically relevant assays, improved alignment with FDA recommendations, and optimal statistical integration of assay data leads to improved DILI risk prediction.

Predicting Drug-Induced Liver Injury Using Ensemble Learning Methods and Molecular Fingerprints

Drug-induced liver injury (DILI) is a major safety concern in the drug-development process, and various methods have been proposed to predict the hepatotoxicity of compounds during the early stages of drug trials. In this study, we developed an ensemble model using 3 machine learning algorithms and 12 molecular fingerprints from a dataset containing 1241 diverse compounds. The ensemble model achieved an average accuracy of 71.1 ± 2.6%, sensitivity (SE) of 79.9 ± 3.6%, specificity (SP) of 60.3 ± 4.8%, and area under the receiver-operating characteristic curve (AUC) of 0.764 ± 0.026 in 5-fold cross-validation and an accuracy of 84.3%, SE of 86.9%, SP of 75.4%, and AUC of 0.904 in an external validation dataset of 286 compounds collected from the Liver Toxicity Knowledge Base. Compared with previous methods, the ensemble model achieved relatively high accuracy and SE. We also identified several substructures related to DILI. In addition, we provide a web server offering access to our models (http://ccsipb.lnu.edu.cn/toxicity/HepatoPred-EL/).

In Silico Prediction of Drug-Induced Liver Injury Based on Ensemble Classifier Method

Drug-induced liver injury (DILI) is a major factor in the development of drugs and the safety of drugs. If the DILI cannot be effectively predicted during the development of the drug, it will cause the drug to be withdrawn from markets. Therefore, DILI is crucial at the early stages of drug research. This work presents a 2-class ensemble classifier model for predicting DILI, with 2D molecular descriptors and fingerprints on a dataset of 450 compounds. The purpose of our study is to investigate which are the key molecular fingerprints that may cause DILI risk, and then to obtain a reliable ensemble model to predict DILI risk with these key factors. Experimental results suggested that 8 molecular fingerprints are very critical for predicting DILI, and also obtained the best ratio of molecular fingerprints to molecular descriptors. The result of the 5-fold cross-validation of the ensemble vote classifier method obtain an accuracy of 77.25%, and the accuracy of the test set was 81.67%. This model could be used for drug-induced liver injury prediction.

Herb-Induced Liver Injury: Phylogenetic Relationship, Structure-Toxicity Relationship, and Herb-Ingredient Network Analysis

Currently, hundreds of herbal products with potential hepatotoxicity were available in the literature. A comprehensive summary and analysis focused on these potential hepatotoxic herbal products may assist in understanding herb-induced liver injury (HILI). In this work, we collected 335 hepatotoxic medicinal plants, 296 hepatotoxic ingredients, and 584 hepatoprotective ingredients through a systematic literature retrieval. Then we analyzed these data from the perspectives of phylogenetic relationship and structure-toxicity relationship. Phylogenetic analysis indicated that hepatotoxic medicinal plants tended to have a closer taxonomic relationship. By investigating the structures of the hepatotoxic ingredients, we found that alkaloids and terpenoids were the two major groups of hepatotoxicity. We also identified eight major skeletons of hepatotoxicity and reviewed their hepatotoxic mechanisms. Additionally, 15 structural alerts (SAs) for hepatotoxicity were identified based on SARpy software. These SAs will help to estimate the hepatotoxic risk of ingredients from herbs. Finally, a herb-ingredient network was constructed by integrating multiple datasets, which will assist to identify the hepatotoxic ingredients of herb/herb-formula quickly. In summary, a systemic analysis focused on HILI was conducted which will not only assist to identify the toxic molecular basis of hepatotoxic herbs but also contribute to decipher the mechanisms of HILI.

Three-Level Hepatotoxicity Prediction System Based on Adverse Hepatic Effects

Hepatotoxicity is a major cause of drug withdrawal from the market. To reduce the drug attrition induced by hepatotoxicity, an accurate and efficient hepatotoxicity prediction system must be constructed. In the present study, we constructed a three-level hepatotoxicity prediction system based on different levels of adverse hepatic effects (AHEs) combined with machine learning, using (1) an end point, hepatotoxicity; (2) four hepatotoxicity severity degrees; and (3) specific AHEs. After collecting and curing 15 873 compound-AHE pairs associated with 2017 compounds and 403 AHEs, we constructed 27 models with three end point levels with the random forest algorithm, and obtained accuracies ranging from 67.0 to 78.2% and the area under receiver operating characteristic curves (AUCs) of 0.715-0.875. The 27 models were fully integrated into a tiered hepatotoxicity prediction system. The existence of hepatotoxicity existence, severity degree, and potential AHEs for a given compound could be inferred simultaneously and systematically. Thus, the tiered hepatotoxicity prediction system allows researchers to have significant confidence in confirming compound hepatotoxicity, analyzing hepatotoxicity from multiple perspectives, obtaining warnings for the potential hepatotoxicity severity, and even rapidly selecting the proper in vitro experiments for hepatotoxicity verification. We also applied three external sets (11 drugs or candidates that failed in clinical trials or were withdrawn from the market, the PharmGKB (offsides) database, and an herbal hepatotoxicity data set) to test and validate the prediction ability of our system. Furthermore, the hepatotoxicity prediction system was adapted into a flow framework based on the Konstanz Information Miner, which was made available for researchers.

Diverse classes of HDAC8 inhibitors: in search of molecular fingerprints that regulate activity

AIM

HDAC8 is one of the crucial enzymes involved in malignancy. Structural explorations of HDAC8 inhibitory activity and selectivity are required.

MATERIALS & METHODS

A mathematical framework was constructed to explore important molecular fragments responsible for HDAC8 inhibition. Bayesian classification models were developed on a large set of structurally diverse HDAC8 inhibitors.

RESULTS

This study helps to understand the structural importance of HDAC8 inhibitors. The hydrophobic aryl cap function is important for HDAC8 inhibition whereas benzamide moiety shows a negative impact on HDAC8 inhibition.

CONCLUSION

This work validates our previously proposed structural features for better HDAC8 inhibition. The comparative learning between the statistical and intelligent methods will surely enrich future drug design aspects of HDAC8 inhibitors.

Impact of Physicochemical Properties on Dose and Hepatotoxicity of Oral Drugs

A database containing maximum daily doses of 1841 marketed oral drugs was used to examine the influence of physicochemical properties on dose and hepatotoxicity (drug induced liver injury, DILI). Drugs in the highest ∼20% dose range had significantly reduced mean lipophilicity and molecular weight, increased fractional surface area, increased % of acids, and decreased % of bases versus drugs in the lower ∼60% dose range. Drugs in the ∼20-40% dose range had intermediate mean properties, similar to the mean values for the full drug set. Drugs that are both large and highly lipophilic almost invariably do not have doses in the upper ∼20% range. The results show that oral druglike physicochemical properties are different according to these dose ranges, and this is consistent with maintenance of acceptable safety profiles as efficacious exposure increases. Verified DILI annotations from a compilation of >1000 approved drugs (Chen, M.; et al. Drug Discov. Today, 2016, 21, 648 ) were used. The drugs classified as "No DILI" ( n = 163) had significantly lower dose and lipophilicity, and higher Fsp3 (fraction of carbon atoms that are sp³ hybridized) versus the "Most DILI" ( n = 163) drugs. The percentages of acids were reduced and bases increased in the "No DILI" versus the "Most DILI" groups. Drugs classified as "Less DILI" or "Ambiguous DILI" had intermediate mean values of dose, lipophilicity, Fsp3, and % acids and bases. The impact of lipophilicity and Fsp3 on DILI increases in the upper 20% versus the lower 80% dose range, and a simple decision tree model predicted "No DILI" versus "Most DILI" outcomes with 82% accuracy. The model correctly classified 19 of 22 drugs (86%) that failed in development due to human hepatotoxicity. Because many oral drugs lacking DILI annotations are predicted to be "Most DILI", the model is best used preclinically in conjunction with experimental DILI mitigation.

Development of Decision Forest Models for Prediction of Drug-Induced Liver Injury in Humans Using A Large Set of FDA-approved Drugs

Drug-induced liver injury (DILI) presents a significant challenge to drug development and regulatory science. The FDA’s Liver Toxicity Knowledge Base (LTKB) evaluated >1000 drugs for their likelihood of causing DILI in humans, of which >700 drugs were classified into three categories (most-DILI, less-DILI, and no-DILI). Based on this dataset, we developed and compared 2-class and 3-class DILI prediction models using the machine learning algorithm of Decision Forest (DF) with Mold2 structural descriptors. The models were evaluated through 1000 iterations of 5-fold cross-validations, 1000 bootstrapping validations and 1000 permutation tests (that assessed the chance correlation). Furthermore, prediction confidence analysis was conducted, which provides an additional parameter for proper interpretation of prediction results. We revealed that the 3-class model not only had a higher resolution to estimate DILI risk but also showed an improved capability to differentiate most-DILI drugs from no-DILI drugs in comparison with the 2-class DILI model. We demonstrated the utility of the models for drug ingredients with warnings very recently issued by the FDA. Moreover, we identified informative molecular features important for assessing DILI risk. Our results suggested that the 3-class model presents a better option than the binary model (which most publications are focused on) for drug safety evaluation.

Development of novel prediction model for drug-induced mitochondrial toxicity by using naïve Bayes classifier method

Mitochondrial dysfunction has been considered as an important contributing factor in the etiology of drug-induced organ toxicity, and even plays an important role in the pathogenesis of some diseases. The objective of this investigation was to develop a novel prediction model of drug-induced mitochondrial toxicity by using a naïve Bayes classifier. For comparison, the recursive partitioning classifier prediction model was also constructed. Among these methods, the prediction performance of naïve Bayes classifier established here showed best, which yielded average overall prediction accuracies for the internal 5-fold cross validation of the training set and external test set were 95 ± 0.6% and 81 ± 1.1%, respectively. In addition, four important molecular descriptors and some representative substructures of toxicants produced by ECFP_6 fingerprints were identified. We hope the established naïve Bayes prediction model can be employed for the mitochondrial toxicity assessment, and these obtained important information of mitochondrial toxicants can provide guidance for medicinal chemists working in drug discovery and lead optimization.