Development of a QSAR model to predict hepatic steatosis using freely available machine learning tools

Systematic approaches to machine learning models for predicting pesticide toxicity

Pesticides play an important role in modern agriculture by protecting crops from pests and diseases. However, the negative consequences of pesticides, such as environmental contamination and adverse effects on human and ecological health, underscore the importance of accurate toxicity predictions. To address this issue, artificial intelligence models have emerged as valuable methods for predicting the toxicity of organic compounds. In this review article, we explore the application of machine learning (ML) for pesticide toxicity prediction. This review provides a detailed summary of recent developments, prediction models, and datasets used for pesticide toxicity prediction. In this analysis, we compared the results of several algorithms that predict the harmfulness of various classes of pesticides. Furthermore, this review article identified emerging trends and areas for future direction, showcasing the transformative potential of machine learning in promoting safer pesticide usage and sustainable agriculture.

Advancing chronic toxicity risk assessment in freshwater ecology by molecular characterization-based machine learning

The continuously increased production of various chemicals and their release into environments have raised potential negative effects on ecological health. However, traditional labor-intensive assessment methods cannot effectively and rapidly evaluate these hazards, especially for chronic risk. In this study, machine learning (ML) was employed to construct quantitative structure-activity relationship (QSAR) models, enabling the prediction of chronic toxicity to aquatic organisms by leveraging the molecular characteristics of pollutants, namely, the molecular descriptors, fingerprints, and graphs. The limited dataset size hindered the notable advantages of the graph attention network (GAT) model for the molecular graphs. Considering computational efficiency and performance (R2 = 0.78; RMSE = 0.77), XGBoost (XGB) was used for reliable QSAR-ML models predicting chronic toxicity using small- or medium-sized tabular data and the molecular descriptors. Further kernel density estimation analysis confirmed the high accuracy of the model for pollutant concentrations ranging from 10-3 to 102 mg/L, effectively aligning with most environmental scenarios. Model interpretation showed SlogP and exposure duration as the primary influential factors. SlogP, representing the distribution coefficient of a molecule between lipophilic and hydrophilic environments, had a negative effect on the toxicity outcomes. Additionally, the exposure duration played a crucial role in determining the chronic toxicity. Finally, the chronic toxicity data of bisphenol A validated the robustness and reliability of the model established in this research. Our study provided a robust and feasible methodology for chronic ecological risk evaluation of various types of pollutants and could facilitate and increase the use of ML applications in environmental fields.

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.

The application of artificial intelligence in hepatology: A systematic review

The integration of human and artificial intelligence (AI) in medicine has only recently begun but it has already become obvious that intelligent systems can dramatically improve the management of liver diseases. Big data made it possible to envisage transformative developments of the use of AI for diagnosing, predicting prognosis and treating liver diseases, but there is still a lot of work to do. If we want to achieve the 21^st century digital revolution, there is an urgent need for specific national and international rules, and to adhere to bioethical parameters when collecting data. Avoiding misleading results is essential for the effective use of AI. A crucial question is whether it is possible to sustain, technically and morally, the process of integration between man and machine. We present a systematic review on the applications of AI to hepatology, highlighting the current challenges and crucial issues related to the use of such technologies.

In Silico Methods for Environmental Risk Assessment: Principles, Tiered Approaches, Applications, and Future Perspectives

This chapter aims to introduce the reader to the basic principles of environmental risk assessment of chemicals and highlights the usefulness of tiered approaches within weight of evidence approaches in relation to problem formulation i.e., data availability, time and resource availability. In silico models are then introduced and include quantitative structure-activity relationship (QSAR) models, which support filling data gaps when no chemical property or ecotoxicological data are available. In addition, biologically-based models can be applied in more data rich situations and these include generic or species-specific models such as toxicokinetic-toxicodynamic models, dynamic energy budget models, physiologically based models, and models for ecosystem hazard assessment i.e. species sensitivity distributions and ultimately for landscape assessment i.e. landscape-based modeling approaches. Throughout this chapter, particular attention is given to provide practical examples supporting the application of such in silico models in real-world settings. Future perspectives are discussed to address environmental risk assessment in a more holistic manner particularly for relevant complex questions, such as the risk assessment of multiple stressors and the development of harmonized approaches to ultimately quantify the relative contribution and impact of single chemicals, multiple chemicals and multiple stressors on living organisms.

Predicting biochemical and physiological effects of natural products from molecular structures using machine learning

Covering: 2016 to 2021Discovery of novel natural products has been greatly facilitated by advances in genome sequencing, genome mining and analytical techniques. As a result, the volume of data for natural products has increased over the years, which started to serve as ingredients for developing machine learning models. In the past few years, a number of machine learning models have been developed to examine various aspects of a molecule by effectively processing its molecular structure. Understanding of the biological effects of natural products can benefit from such machine learning approaches. In this context, this Highlight reviews recent studies on machine learning models developed to infer various biological effects of molecules. A particular attention is paid to molecular featurization, or computational representation of a molecular structure, which is an essential process during the development of a machine learning model. Technical challenges associated with the use of machine learning for natural products are further discussed.

Support vector machine-based model for toxicity of organic compounds against fish

Predicting the toxicity of chemicals to various fish species through chemometric approach is crucial for ecotoxicological assessment of existing as well as not yet synthesized chemicals. This paper reports a quantitative structure-activity/toxicity relationship (QSAR/QSTR) model for the toxicity pLC₅₀ of organic chemicals against various fish species. Only six descriptors were used to develop the QSTR model, by applying support vector machine (SVM) together with genetic algorithm. The QSTR model was trained and established on a sufficiently large data set of 840 organic compounds and evaluated with a test set (281 compounds). Compared with other QSTRs reported in the literature, the optimal SVM model for fish toxicity produces better statistical results with determination coefficients R² above 0.70 for both the training set and test set, although the QSTR model in this work possesses fewer molecular descriptors. Applying SVM and genetic algorithm to develop the QSTR model for pLC₅₀ of organic compounds against various fish species is successful.

Polarizability and aromaticity index govern AhR-mediated potencies of PAHs: A QSAR with consideration of freely dissolved concentrations

Polycyclic aromatic hydrocarbons (PAHs) are ubiquitous environmental pollutants associated with adverse human effects including cancer, and the aryl hydrocarbon receptor (AhR) is a key ligand-activated transcription factor mediating their toxicity. However, there is presently a lack of data on AhR potencies of PAHs. Simple, transparent, interpretable and predictive quantitative structure-activity relationship (QSAR) models are helpful, especially with the consideration of freely dissolved concentrations linked to bioavailability. Here, QSAR models on AhR-mediated luciferase activity of PAHs were developed with nominal median effect concentrations (EC₅₀, _nom) and freely dissolved concentration (EC_{50, free}) as endpoints, and quantum chemical and Dragon descriptors as predictor variables. Results indicated that only the EC_{50, free} model met the acceptable criteria of QSAR model (determination coefficient (R²) > 0.600, leave-one-out cross validation (Q_LOO²) > 0.500, and external validation coefficient (Q_EXT²) > 0.500), implying that it has good goodness-of-fit, robustness and external predictive power. Molecular polarizability and aromaticity index reflecting the partition behavior and intermolecular interactions can effectively predict AhR-mediated potencies of PAHs. The results highlight the necessity of adoption of the freely dissolved concentration in the QSAR modeling and more in silico models need to be further developed for different animal models (in vivo or in vitro).

Combining In Vivo Data with In Silico Predictions for Modeling Hepatic Steatosis by Using Stratified Bagging and Conformal Prediction

Hepatic steatosis (fatty liver) is a severe liver disease induced by the excessive accumulation of fatty acids in hepatocytes. In this study, we developed reliable in silico models for predicting hepatic steatosis on the basis of an in vivo data set of 1041 compounds measured in rodent studies with repeated oral exposure. The imbalanced nature of the data set (1:8, with the "steatotic" compounds belonging to the minority class) required the use of meta-classifiers-bagging with stratified under-sampling and Mondrian conformal prediction-on top of the base classifier random forest. One major goal was the investigation of the influence of different descriptor combinations on model performance (tested by predicting an external validation set): physicochemical descriptors (RDKit), ToxPrint features, as well as predictions from in silico nuclear receptor and transporter models. All models based upon descriptor combinations including physicochemical features led to reasonable balanced accuracies (BAs between 0.65 and 0.69 for the respective models). Combining physicochemical features with transporter predictions and further with ToxPrint features gave the best performing model (BAs up to 0.7 and efficiencies of 0.82). Whereas both meta-classifiers proved useful for this highly imbalanced toxicity data set, the conformal prediction framework also guarantees the error level and thus might be favored for future studies in the field of predictive toxicology.