Computational Models Using Multiple Machine Learning Algorithms for Predicting Drug Hepatotoxicity with the DILIrank Dataset

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

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

A Comparison of Machine Learning Approaches for predicting Hepatotoxicity potential using Chemical Structure and Targeted Transcriptomic Data

Animal toxicity testing is time and resource intensive, making it difficult to keep pace with the number of substances requiring assessment. Machine learning (ML) models that use chemical structure information and high-throughput experimental data can be helpful in predicting potential toxicity . However, much of the toxicity data used to train ML models is biased with an unequal balance of positives and negatives primarily since substances selected for in vivo testing are expected to elicit some toxicity effect. To investigate the impact this bias had on predictive performance, various sampling approaches were used to balance in vivo toxicity data as part of a supervised ML workflow to predict hepatotoxicity outcomes from chemical structure and/or targeted transcriptomic data. From the chronic, subchronic, developmental, multigenerational reproductive, and subacute repeat-dose testing toxicity outcomes with a minimum of 50 positive and 50 negative substances, 18 different study-toxicity outcome combinations were evaluated in up to 7 ML models. These included Artificial Neural Networks, Random Forests, Bernouilli Naïve Bayes, Gradient Boosting, and Support Vector classification algorithms which were compared with a local approach, Generalised Read-Across (GenRA), a similarity-weighted k-Nearest Neighbour (k-NN) method. The mean CV F1 performance for unbalanced data across all classifiers and descriptors for chronic liver effects was 0.735 (0.0395 SD). Mean CV F1 performance dropped to 0.639 (0.073 SD) with over-sampling approaches though the poorer performance of KNN approaches in some cases contributed to the observed decrease (mean CV F1 performance excluding KNN was 0.697 (0.072 SD)). With under-sampling approaches, the mean CV F1 was 0.523 (0.083 SD). For developmental liver effects, the mean CV F1 performance was much lower with 0.089 (0.111 SD) for unbalanced approaches and 0.149 (0.084 SD) for under-sampling. Over-sampling approaches led to an increase in mean CV F1 performance (0.234, (0.107 SD)) for developmental liver toxicity. Model performance was found to be dependent on dataset, model type, balancing approach and feature selection. Accordingly tailoring ML workflows for predicting toxicity should consider class imbalance and rely on simpler classifiers first.

Computational approaches for modeling and structural design of biological systems: A comprehensive review

The convergence of biology and computational science has ushered in a revolutionary era, revolutionizing our understanding of biological systems and providing novel solutions to global problems. The field of genetic engineering has facilitated the manipulation of genetic codes, thus providing opportunities for the advancement of innovative disease therapies and environmental enhancements. The emergence of bio-molecular simulation represents a significant advancement in this particular field, as it offers the ability to gain microscopic insights into molecular-level biological processes over extended periods. Biomolecular simulation plays a crucial role in advancing our comprehension of organismal mechanisms by establishing connections between molecular structures, interactions, and biological functions. The field of computational biology has demonstrated its significance in deciphering intricate biological enigmas through the utilization of mathematical models and algorithms. The process of decoding the human genome has resulted in the advancement of therapies for a wide range of genetic disorders, while the simulation of biological systems contributes to the identification of novel pharmaceutical compounds. The potential of biomolecular simulation and computational biology is vast and limitless. As the exploration of the underlying principles that govern living organisms progresses, the potential impact of this understanding on cancer treatment, environmental restoration, and other domains is anticipated to be transformative. This review examines the notable advancements achieved in the field of computational biology, emphasizing its potential to revolutionize the comprehension and enhancement of biological systems.

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).

Usage of model combination in computational toxicology

New Approach Methodologies (NAMs) have ushered in a new era in the field of toxicology, aiming to replace animal testing. However, despite these advancements, they are not exempt from the inherent complexities associated with the study's endpoint. In this review, we have identified three major groups of complexities: mechanistic, chemical space, and methodological. The mechanistic complexity arises from interconnected biological processes within a network that are challenging to model in a single step. In the second group, chemical space complexity exhibits significant dissimilarity between compounds in the training and test series. The third group encompasses algorithmic and molecular descriptor limitations and typical class imbalance problems. To address these complexities, this work provides a guide to the usage of a combination of predictive Quantitative Structure-Activity Relationship (QSAR) models, known as metamodels. This combination of low-level models (LLMs) enables a more precise approach to the problem by focusing on different sub-mechanisms or sub-processes. For mechanistic complexity, multiple Molecular Initiating Events (MIEs) or levels of information are combined to form a mechanistic-based metamodel. Regarding the complexity arising from chemical space, two types of approaches were reviewed to construct a fragment-based chemical space metamodel: those with and without structure sharing. Metamodels with structure sharing utilize unsupervised strategies to identify data patterns and build low-level models for each cluster, which are then combined. For situations without structure sharing due to pharmaceutical industry intellectual property, the use of prediction sharing, and federated learning approaches have been reviewed. Lastly, to tackle methodological complexity, various algorithms are combined to overcome their limitations, diverse descriptors are employed to enhance problem definition and balanced dataset combinations are used to address class imbalance issues (methodological-based metamodels). Remarkably, metamodels consistently outperformed classical QSAR models across all cases, highlighting the importance of alternatives to classical QSAR models when faced with such complexities.

Review of machine learning and deep learning models for toxicity prediction

The ever-increasing number of chemicals has raised public concerns due to their adverse effects on human health and the environment. To protect public health and the environment, it is critical to assess the toxicity of these chemicals. Traditional in vitro and in vivo toxicity assays are complicated, costly, and time-consuming and may face ethical issues. These constraints raise the need for alternative methods for assessing the toxicity of chemicals. Recently, due to the advancement of machine learning algorithms and the increase in computational power, many toxicity prediction models have been developed using various machine learning and deep learning algorithms such as support vector machine, random forest, k-nearest neighbors, ensemble learning, and deep neural network. This review summarizes the machine learning- and deep learning-based toxicity prediction models developed in recent years. Support vector machine and random forest are the most popular machine learning algorithms, and hepatotoxicity, cardiotoxicity, and carcinogenicity are the frequently modeled toxicity endpoints in predictive toxicology. It is known that datasets impact model performance. The quality of datasets used in the development of toxicity prediction models using machine learning and deep learning is vital to the performance of the developed models. The different toxicity assignments for the same chemicals among different datasets of the same type of toxicity have been observed, indicating benchmarking datasets is needed for developing reliable toxicity prediction models using machine learning and deep learning algorithms. This review provides insights into current machine learning models in predictive toxicology, which are expected to promote the development and application of toxicity prediction models in the future.

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.

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.

Host Blood Gene Signatures Can Detect the Progression to Severe and Cerebral Malaria

Malaria is a major international public health problem that affects millions of patients worldwide especially in sub-Saharan Africa. Although many tests have been developed to diagnose malaria infections, we still lack reliable diagnostic biomarkers for the identification of disease severity, especially in endemic areas where the diagnosis of cerebral malaria is very difficult and requires the exclusion of all other possible causes. Previous host and pathogen transcriptomic studies have not yielded homogenous results that can be harnessed into a reliable diagnostic tool. Here we utilized a multi-cohort analysis approach using machine-learning algorithms to identify blood gene signatures that can distinguish severe and cerebral malaria from moderate and non-cerebral cases. Using a Regularized Random Forest model, we identified 28-gene and 32-gene signatures that can reliably distinguish severe and cerebral malaria, respectively. We tested the specificity of both signatures against other common infectious diseases to ensure the signatures reliability and suitability as diagnostic markers. The severe and cerebral malaria gene-signatures were further integrated through k-top scoring pairs classifiers into ten and nine gene pairs that could distinguish severe and cerebral malaria, respectively. These signatures have various implications that can be utilized as blood diagnostic tools for malaria severity in endemic countries.

Results of the Seventh Scientific Workshop of ECCO: Precision Medicine in IBD-What, Why, and How

Many diseases that affect modern humans fall in the category of complex diseases, thus called because they result from a combination of multiple aetiological and pathogenic factors. Regardless of the organ or system affected, complex diseases present major challenges in diagnosis, classification, and management. Current forms of therapy are usually applied in an indiscriminate fashion based on clinical information, but even the most advanced drugs only benefit a limited number of patients and to a variable and unpredictable degree. This 'one measure does not fit all' situation has spurred the notion that therapy for complex disease should be tailored to individual patients or groups of patients, giving rise to the notion of 'precision medicine' [PM]. Inflammatory bowel disease [IBD] is a prototypical complex disease where the need for PM has become increasingly clear. This prompted the European Crohn's and Colitis Organisation to focus the Seventh Scientific Workshop on this emerging theme. The articles in this special issue of the Journal address the various complementary aspects of PM in IBD, including what PM is; why it is needed and how it can be used; how PM can contribute to prediction and prevention of IBD; how IBD PM can aid in prognosis and improve response to therapy; and the challenges and future directions of PM in IBD. This first article of this series is structured on three simple concepts [what, why, and how] and addresses the definition of PM, discusses the rationale for the need of PM in IBD, and outlines the methodology required to implement PM in IBD in a correct and clinically meaningful way.

ChemBioSim: Enhancing Conformal Prediction of In Vivo Toxicity by Use of Predicted Bioactivities

Computational methods such as machine learning approaches have a strong track record of success in predicting the outcomes of in vitro assays. In contrast, their ability to predict in vivo endpoints is more limited due to the high number of parameters and processes that may influence the outcome. Recent studies have shown that the combination of chemical and biological data can yield better models for in vivo endpoints. The ChemBioSim approach presented in this work aims to enhance the performance of conformal prediction models for in vivo endpoints by combining chemical information with (predicted) bioactivity assay outcomes. Three in vivo toxicological endpoints, capturing genotoxic (MNT), hepatic (DILI), and cardiological (DICC) issues, were selected for this study due to their high relevance for the registration and authorization of new compounds. Since the sparsity of available biological assay data is challenging for predictive modeling, predicted bioactivity descriptors were introduced instead. Thus, a machine learning model for each of the 373 collected biological assays was trained and applied on the compounds of the in vivo toxicity data sets. Besides the chemical descriptors (molecular fingerprints and physicochemical properties), these predicted bioactivities served as descriptors for the models of the three in vivo endpoints. For this study, a workflow based on a conformal prediction framework (a method for confidence estimation) built on random forest models was developed. Furthermore, the most relevant chemical and bioactivity descriptors for each in vivo endpoint were preselected with lasso models. The incorporation of bioactivity descriptors increased the mean F1 scores of the MNT model from 0.61 to 0.70 and for the DICC model from 0.72 to 0.82 while the mean efficiencies increased by roughly 0.10 for both endpoints. In contrast, for the DILI endpoint, no significant improvement in model performance was observed. Besides pure performance improvements, an analysis of the most important bioactivity features allowed detection of novel and less intuitive relationships between the predicted biological assay outcomes used as descriptors and the in vivo endpoints. This study presents how the prediction of in vivo toxicity endpoints can be improved by the incorporation of biological information-which is not necessarily captured by chemical descriptors-in an automated workflow without the need for adding experimental workload for the generation of bioactivity descriptors as predicted outcomes of bioactivity assays were utilized. All bioactivity CP models for deriving the predicted bioactivities, as well as the in vivo toxicity CP models, can be freely downloaded from https://doi.org/10.5281/zenodo.4761225.

Identification of average molecular weight (AMW) as a useful chemical descriptor to discriminate liver injury-inducing drugs

Drug-induced liver injury (DILI) is one of major causes of discontinuing drug development and withdrawing drugs from the market. In this study, we investigated chemical properties associated with DILI using in silico methods, to identify a physicochemical property useful for DILI screening at the early stages of drug development. Total of 652 drugs, including 432 DILI-positive drugs (DILI drugs) and 220 DILI-negative drugs (no-DILI drugs) were selected from Liver Toxicity Knowledge Base of US Food and Drug Administration. Decision tree models were constructed using 2,473 descriptors as explanatory variables. In the final model, the descriptor AMW, representing average molecular weight, was found to be at the first node and showed the highest importance value. With AMW alone, 276 DILI drugs (64%) and 156 no-DILI drugs (71%) were correctly classified. Discrimination with AMW was then performed using therapeutic category information. The performance of discrimination depended on the category and significantly high performance (>0.8 balanced accuracy) was obtained in some categories. Taken together, the present results suggest AMW as a novel descriptor useful for detecting drugs with DILI risk. The information presented may be valuable for the safety assessment of drug candidates at the early stage of drug development.

Artificial intelligence in drug design: algorithms, applications, challenges and ethics

The discovery paradigm of drugs is rapidly growing due to advances in machine learning (ML) and artificial intelligence (AI). This review covers myriad faces of AI and ML in drug design. There is a plethora of AI algorithms, the most common of which are summarized in this review. In addition, AI is fraught with challenges that are highlighted along with plausible solutions to them. Examples are provided to illustrate the use of AI and ML in drug discovery and in predicting drug properties such as binding affinities and interactions, solubility, toxicology, blood–brain barrier permeability and chemical properties. The review also includes examples depicting the implementation of AI and ML in tackling intractable diseases such as COVID-19, cancer and Alzheimer’s disease. Ethical considerations and future perspectives of AI are also covered in this review.

Treasuring the computational approach in medicinal plant research

Medicinal plants serve as a valuable source of secondary metabolites since time immemorial. Computational Research in 21st century is giving more attention to medicinal plants for new drug design as pharmacological screening of bioactive compound was time consuming and expensive. Computational methods such as Molecular Docking, Molecular Dynamic Simulation and Artificial intelligence are significant Insilico tools in medicinal plant research. Molecular docking approach exploits the mechanism of potential phytochemicals into the target active site to elucidate its interactions and biological therapeutic properties. MD simulation illuminates the dynamic behavior of biomolecules at atomic level with fine quality representation of biomolecules. Dramatical advancement in computer science is illustrating the biological mechanism via these tools in different diseases treatment. The advancement comprises speed, the system configuration, and other software upgradation to insights into the structural explanation and optimization of biomolecules. A probable shift from simulation to artificial intelligence has in fact accelerated the art of scientific study to a sky high. The most upgraded algorithm in artificial intelligence such as Artificial Neural Networks, Deep Neural Networks, Neuro-fuzzy Logic has provided a wide opportunity in easing the time required in classical experimental strategy. The notable progress in computer science technology has paved a pathway for understanding the pharmacological functions and creating a roadmap for drug design and development and other achievement in the field of medicinal plants research. This review focus on the development and overview in computational research moving from static molecular docking method to a range of dynamic simulation and an advanced artificial intelligence such as machine learning.

Partitioning Pattern of Natural Products Based on Molecular Properties Descriptors Representing Drug-Likeness

A cheminformatics procedure for a partitioning model based on 135 natural compounds including Flavonoids, Saponins, Alkaloids, Terpenes and Triterpenes with drug-like features based on a descriptors pool was developed. The knowledge about the applicability of natural products as a unique source for the development of new candidates towards deadly infectious disease is a contemporary challenge for drug discovery. We propose a partitioning scheme for unveiling drug-likeness candidates with properties that are important for a prompt and efficient drug discovery process. In the present study, the vantage point is about the matching of descriptors to build the partitioning model applied to natural compounds with diversity in structures and complexity of action towards the severe diseases, as the actual SARS-CoV-2 virus. In the times of the de novo design techniques, such tools based on a chemometric and symmetrical effect by the implied descriptors represent another noticeable sign for the power and level of the descriptors applicability in drug discovery in establishing activity and target prediction pipeline for unknown drugs properties.

Deep Graph Learning with Property Augmentation for Predicting Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is a crucial factor in determining the qualification of potential drugs. However, the DILI property is excessively difficult to obtain due to the complex testing process. Consequently, an in silico screening in the early stage of drug discovery would help to reduce the total development cost by filtering those drug candidates with a high risk to cause DILI. To serve the screening goal, we apply several computational techniques to predict the DILI property, including traditional machine learning methods and graph-based deep learning techniques. While deep learning models require large training data to tune huge model parameters, the DILI data set only contains a few hundred annotated molecules. To alleviate the data scarcity problem, we propose a property augmentation strategy to include massive training data with other property information. Extensive experiments demonstrate that our proposed method significantly outperforms all existing baselines on the DILI data set by obtaining a 81.4% accuracy using cross-validation with random splitting, 78.7% using leave-one-out cross-validation, and 76.5% using cross-validation with scaffold splitting.

Fast Identification of Adverse Drug Reactions (ADRs) of Digestive and Nervous Systems of Organic Drugs by In Silico Models

This study aimed to discover concurrences of adverse drug reactions (ADRs) and derive models of the most frequent items of ADRs based on the SIDER database, which included 1430 marketed drugs and 5868 ADRs. First, common ADRs of organic drugs were manually reclassified according to side effects in the human system and followed by an association rule analysis, which found ADRs of digestive and nervous systems often occurred at the same time with a good association rule. Then, three algorithms, linear discriminant analysis (LDA), support vector machine (SVM) and deep learning, were used to derive models of ADRs of digestive and nervous systems based on 497 organic monomer drugs and to identify key structural features in defining these ADRs. The statistical results indicated that these kinds of QSAR models were good tools for screening ADRs of digestive and nervous systems, which gave the ROC AUC values of 81.5%, 98.9%, 91.5%, 69.5%, 78.4% and 78.8%, respectively. Then, these models were applied to investigate ADRs of 1536 organic compounds with four phase and zero rule-of-five (RO5) violations from the ChEMBL database. Based on the consensus ADRs’ predictions of models, 58.1% and 42.6% of compounds were predicted to cause these two ADRs, respectively, indicating the significance of initial assessment of ADRs in early drug discovery.