Developing random forest based QSAR models for predicting the mixture toxicity of TiO2 based nano-mixtures to Daphnia magna

An artificial intelligence-based model for predicting reproductive toxicity of bisphenol analogues mixtures to the rotifer Brachionus calyciflorus

The joint toxicity effects of mixtures, particularly reproductive toxicity, one of the main causes of aquatic ecosystem degradation, are often overlooked as it is impractical to test all mixtures. This study developed and evaluated the following models to predict the concentration response curve concerning the joint reproductive toxicity of mixtures of three bisphenol analogues (BPA, BPF, BPAF) on the rotifer Brachionus calyciflorus: concentration addition (CA), independent action (IA), and two deep neural network (DNN) models. One applied mixture molecular descriptors as input variables (DNN-QSAR), while the other applied the ratios of chemicals in the mixtures (DNN-Ratio). Descriptors related to molecular mass were found to be of greater importance and exhibited a proportional relationship with toxic effects. The results indicate that the range of correlation coefficients (R2) between predicted and measured values for various mixture rays by CA and IA models is 0.372 to 0.974 and - 0.970 to 0.586, respectively. The R2 values for DNN-Ratio and DNN-QSAR were 0.841 to 0.984 and 0.834 to 0.991, respectively, demonstrating that models developed by DNN significantly outperform traditional models in predicting the joint toxicity of mixtures. Furthermore, DNN-QSAR not only predicts mixture toxicity but also provides accurate toxicity predictions for BPA, BPF, and BPAF, with R2 values of 0.990, 0.616, and 0.887, respectively, while DNN-Ratio yields values of 0.920, 0.355, and - 0.495. The study also found that the joint effects of mixtures are primarily influenced by the total concentration of the mixtures, and an increase in total concentration shifts the joint effects towards addition. This study introduces a novel approach to predict joint toxicity and analyze the influencing factors of joint effects, providing a more comprehensive assessment of the ecological risk posed by mixtures.

Computational modeling approaches for developing a synergistic effect prediction model of estrogen agonistic activity

The concerns regarding the potential health threats caused by estrogenic endocrine-disrupting chemicals (EDCs) and their mixtures manufactured by the chemical industry are increasing worldwide. Conventional experimental tests for understanding the estrogenic activity of mixtures are expensive and time-consuming. Although non-testing methods using computational modeling approaches have been developed to reduce the number of traditional tests, they are unsuitable for predicting synergistic effects because current prediction models consider only a single chemical. Thus, the development of predictive models is essential for predicting the mixture toxicity, including chemical interactions. However, selecting suitable computational modeling approaches to develop a high-performance prediction model requires considerable time and effort. In this study, we provide a suitable computational approach to develop a predictive model for the synergistic effects of estrogenic activity. We collected datasets on mixture toxicity based on the synergistic effect of estrogen agonistic activity in binary mixtures. Using the model deviation ratio approach, we classified the labels of the binary mixtures as synergistic or non-synergistic effects. We assessed five molecular descriptors, four machine learning-based algorithms, and a deep learning-based algorithm to provide a suitable computational modeling approach. Compared with other modeling approaches, the prediction model using the deep learning-based algorithm and chemical-protein network descriptors exhibited the best performance in predicting the synergistic effects. In conclusion, we developed a new high-performance binary classification model using a deep neural network and chemical-protein network-based descriptors. The developed model will be helpful for the preliminary screening of the synergistic effects of binary mixtures during the development process of chemical products.

Global classification models for predicting acute toxicity of chemicals towards Daphnia magna

Molecular descriptors reflecting structural information on hydrophobicity, reactivity, polarizability, hydrogen bond and charged groups, were used to predict the toxicity (pLC50) of chemicals towards Daphnia magna with global quantitative structure-activity/toxicity relationship (QSAR/QSTR) models. A sufficiently large dataset including 1517 chemical toxicity to Daphnia magna was divided into a training set (758 pLC50) and a test set (759 pLC50). By applying random forest algorithm, two classification models, Class Model A and Class Model B were developed, having prediction accuracy, sensitivity and specificity above 85% for Class 1 (with pLC50 ≤ 4.48) and Class 2 (with pLC50 > 4.48). The Class Model A was based on nine molecular descriptors and RF parameters of nodesize = 1, ntree = 80 and mtry = 2, and yielded accuracy of 92.3% (training set), 85.6% (test set) and 88.9% (total data set). Class Model B was based on ten descriptors and parameters, nodesize = 1, ntree = 90 and mtry = 2, produced accuracy of 88.3% (training set), 86.8% (test set) and 87.5% (total data set). The two classification models were satisfactory compared with other classification model reported in the literature, although classification models in this work dealt with more samples. Thus, the two classification models with a larger applicability domain provided efficient tools for assessing chemical aquatic toxicity towards Daphnia magna.

Using Machine Learning to Predict Adverse Effects of Metallic Nanomaterials to Various Aquatic Organisms

The wide production and use of metallic nanomaterials (MNMs) leads to increased emissions into the aquatic environments and induces high potential risks. Experimentally evaluating the (eco)toxicity of MNMs is time-consuming and expensive due to the multiple environmental factors, the complexity of material properties, and the species diversity. Machine learning (ML) models provide an option to deal with heterogeneous data sets and complex relationships. The present study established an in silico model based on a machine learning properties-environmental conditions-multi species-toxicity prediction model (ML-PEMST) that can be applied to predict the toxicity of different MNMs toward multiple aquatic species. Feature importance and interaction analysis based on the random forest method indicated that exposure duration, illumination, primary size, and hydrodynamic diameter were the main factors affecting the ecotoxicity of MNMs to a variety of aquatic organisms. Illumination was demonstrated to have the most interaction with the other features. Moreover, incorporating additional detailed information on the ecological traits of the test species will allow us to further optimize and improve the predictive performance of the model. This study provides a new approach for ecotoxicity predictions for organisms in the aquatic environment and will help us to further explore exposure pathways and the risk assessment of MNMs.

A structure-activity approach towards the toxicity assessment of multicomponent metal oxide nanomaterials

The increase of human and environmental exposure to engineered nanomaterials (ENMs) due to the emergence of nanotechnology has raised concerns over their safety. The challenging nature of in vivo and in vitro toxicity assessment methods for ENMs, has led to emerging in silico techniques for ENM toxicity assessment, such as structure-activity relationship (SAR) models. Although such approaches have been extensively developed for the case of single-component nanomaterials, the case of multicomponent nanomaterials (MCNMs) has not been thoroughly addressed. In this paper, we present a SAR approach for the case metal and metal oxide MCNMs. The developed SAR framework is built using a dataset of 796 individual toxicity measurements for 340 different MCNMs, towards human cells, mammalian cells, and bacteria. The novelty of the approach lies in the multicomponent nature of the nanomaterials, as well as the size, diversity and heterogeneous nature of the dataset used. Furthermore, the approach used to calculate descriptors for surface loaded MCNMs, and the mechanistic insight provided by the model results can assist the understanding of MCNM toxicity. The developed models are able to correctly predict the toxic class of the MCNMs in the heterogeneous dataset, towards a wide range of human cells, mammalian cells and bacteria. Using the abovementioned approach, the principal toxicity pathways and mechanisms are identified, allowing a more holistic understanding of metal oxide MCNM toxicity.

Machine learning-driven QSAR models for predicting the mixture toxicity of nanoparticles

Research on theoretical prediction methods for the mixture toxicity of engineered nanoparticles (ENPs) faces significant challenges. The application of in silico methods based on machine learning is emerging as an effective strategy to address the toxicity prediction of chemical mixtures. Herein, we combined toxicity data generated in our lab with experimental data reported in the literature to predict the combined toxicity of seven metallic ENPs for Escherichia coli at different mixing ratios (22 binary combinations). We thereafter applied two machine learning (ML) techniques, support vector machine (SVM) and neural network (NN), and compared the differences in the ability to predict the combined toxicity by means of the ML-based methods and two component-based mixture models: independent action and concentration addition. Among 72 developed quantitative structure-activity relationship (QSAR) models by the ML methods, two SVM-QSAR models and two NN-QSAR models showed good performance. Moreover, an NN-based QSAR model combined with two molecular descriptors, namely enthalpy of formation of a gaseous cation and metal oxide standard molar enthalpy of formation, showed the best predictive power for the internal dataset (R²_test = 0.911, adjusted R²_test = 0.733, RMSE_test = 0.091, and MAE_test = 0.067) and for the combination of internal and external datasets (R²_test = 0.908, adjusted R²_test = 0.871, RMSE_test = 0.255, and MAE_test = 0.181). In addition, the developed QSAR models performed better than the component-based models. The estimation of the applicability domain of the selected QSAR models showed that all the binary mixtures in training and test sets were in the applicability domain. This study approach could provide a methodological and theoretical basis for the ecological risk assessment of mixtures of ENPs.

Converting Nanotoxicity Data to Information Using Artificial Intelligence and Simulation

Decades of nanotoxicology research have generated extensive and diverse data sets. However, data is not equal to information. The question is how to extract critical information buried in vast data streams. Here we show that artificial intelligence (AI) and molecular simulation play key roles in transforming nanotoxicity data into critical information, i.e., constructing the quantitative nanostructure (physicochemical properties)-toxicity relationships, and elucidating the toxicity-related molecular mechanisms. For AI and molecular simulation to realize their full impacts in this mission, several obstacles must be overcome. These include the paucity of high-quality nanomaterials (NMs) and standardized nanotoxicity data, the lack of model-friendly databases, the scarcity of specific and universal nanodescriptors, and the inability to simulate NMs at realistic spatial and temporal scales. This review provides a comprehensive and representative, but not exhaustive, summary of the current capability gaps and tools required to fill these formidable gaps. Specifically, we discuss the applications of AI and molecular simulation, which can address the large-scale data challenge for nanotoxicology research. The need for model-friendly nanotoxicity databases, powerful nanodescriptors, new modeling approaches, molecular mechanism analysis, and design of the next-generation NMs are also critically discussed. Finally, we provide a perspective on future trends and challenges.

Review and Prospects on the Ecotoxicity of Mixtures of Nanoparticles and Hybrid Nanomaterials

The rapid development of nanomaterials (NMs) and the emergence of new multicomponent NMs will inevitably lead to simultaneous exposure of organisms to multiple engineered nanoparticles (ENPs) at varying exposure levels. Understanding the joint impacts of multiple ENPs and predicting the toxicity of mixtures of ENPs are therefore evidently of importance. We reviewed the toxicity of mixtures of ENPs to a variety of different species, covering algae, bacteria, daphnia, fish, fungi, insects, and plants. Most studies used the independent-action (IA)-based model to assess the type of joint effects. Using co-occurrence networks, it was revealed that 53% of the cases with specific joint response showed antagonistic, 25% synergistic, and 22% additive effects. The combination of nCuO and nZnO exhibited the strongest interactions in each type of joint interaction. Compared with other species, plants exposed to multiple ENPs were more likely to experience antagonistic effects. The main factors influencing the joint response type of the mixtures were (1) the chemical composition of individual components in mixtures, (2) the stability of suspensions of mixed ENPs, (3) the type and trophic level of the individual organisms tested, (4) the biological level of organization (population, communities, ecosystems), (5) the exposure concentrations and time, (6) the endpoint of toxicity, and (7) the abiotic field conditions (e.g., pH, ionic strength, natural organic matter). This knowledge is critical in developing efficient strategies for the assessment of the hazards induced by combined exposure to multiple ENPs in complex environments. In addition, this knowledge of the joint effects of multiple ENPs assists in the effective prediction of hybrid NMs.

Quasi-SMILES for predicting toxicity of Nano-mixtures to Daphnia Magna

Quasi-SMILES is an extension of the traditional SMILES. The classic SMILES is a way to represent the molecular structure. The quasi-SMILES is a way to describe all eclectic conditions that are able to affect the activity of a substance or a mixture. Nano-QSAR for prediction of toxicity of Nano-mixtures built up using the database on the corresponding experimental data. Models built up for five random splits of available data in training and validation sets are suggested. The Monte Carlo method of optimization is applied to calculate so-called optimal descriptors. The optimization was carried out with two criteria of predictive potential. These are the so-called index of ideality of correlation (IIC) and correlation intensity index (CII). Applying CII gives the better statistical quality of models for toxicity Nano-mixtures towards Daphnia Magna. The statistical quality of the best model follows the determination coefficients 0.987 (training set) and 0.980 (validation set).