Advancing Computational Toxicology by Interpretable Machine Learning

Incorporating new approach methods (NAMs) data in dose-response assessments: The future is now!

Regulatory dose-response assessments traditionally rely on in vivo data and default assumptions. New Approach Methods (NAMs) present considerable opportunities to both augment traditional dose-response assessments and accelerate the evaluation of new/data-poor chemicals. This review aimed to determine the potential utilization of NAMs through a unified conceptual framework that compartmentalizes derivation of toxicity values into five sequential Key Dose-response Modules (KDMs): (1) point-of-departure (POD) determination, (2) test system-to-human (e.g. inter-species) toxicokinetics and (3) toxicodynamics, (4) human population (intra-species) variability in toxicodynamics, and (5) toxicokinetics. After using several "traditional" dose-response assessments to illustrate this framework, a review is presented where existing NAMs, including in silico, in vitro, and in vivo approaches, might be applied across KDMs. Further, the false dichotomy between "traditional" and NAMs-derived data sources is broken down by organizing dose-response assessments into a matrix where each KDM has Tiers of increasing precision and confidence: Tier 0: Default/generic values, Tier 1: Computational predictions, Tier 2: Surrogate measurements, and Tier 3: Direct measurements. These findings demonstrated that although many publications promote the use of NAMs in KDMs (1) for POD determination and (5) for human population toxicokinetics, the proposed matrix of KDMs and Tiers reveals additional immediate opportunities for NAMs to be integrated across other KDMs. Further, critical needs were identified for developing NAMs to improve in vitro dosimetry and quantify test system and human population toxicodynamics. Overall, broadening the integration of NAMs across the steps of dose-response assessment promises to yield higher throughput, less animal-dependent, and more science-based toxicity values for protecting human health.

Elucidating per- and polyfluoroalkyl substances (PFASs) soil-water partitioning behavior through explainable machine learning models

In this study, an optimized random forest (RF) model was employed to better understand the soil-water partitioning behavior of per- and polyfluoroalkyl substances (PFASs). The model demonstrated strong predictive performance, achieving an R2 of 0.93 and an RMSE of 0.86. Moreover, it required only 11 easily obtainable features, with molecular weight and soil pH being the predominant factors. Using three-dimensional interaction analyses identified specific conditions associated with varying soil-water partitioning coefficients (Kd). Results showed that soils with high organic carbon (OC) content, cation exchange capacity (CEC), and lower soil pH, especially when combined with PFASs of higher molecular weight, were linked to higher Kd values, indicating stronger adsorption. Conversely, low Kd values (< 2.8 L/kg) typically observed in soils with higher pH (8.0), but lower CEC (8 cmol+/kg), lesser OC content (1 %), and lighter molecular weight (380 g/mol), suggested weaker adsorption capacities and a heightened potential for environmental migration. Furthermore, the model was used to predict Kd values for 142 novel PFASs in diverse soil conditions. Our research provides essential insights into the factors governing PFASs partitioning in soil and highlights the significant role of machine learning models in enhancing the understanding of environmental distribution and migration of PFASs.

Design optimization of bimetal-modified biochar for enhanced phosphate removal performance in livestock wastewater using machine learning

Mg-modified biochar shows high adsorption performance under weakly acidic and neutral water conditions. However, its phosphate removal efficiency markedly decreases in naturally alkaline wastewater, such as that released in livestock farming (anaerobic wastewater with a high phosphate concentration). This research employed six machine learning models to predict and optimize the phosphate removal performance of bimetal-modified biochar (i.e., Mg-Ca/Al/Fe/La) to develop material design strategies suitable for achieving high removal efficiency in alkaline wastewater. Random forest, gradient boosting regressor, and extreme gradient boosting models achieved high prediction accuracy (R2 > 0.98). Model predictions and experimental validations indicated that Mg-Ca-modified biochar still maintained high adsorption capacity under acidic conditions and could effectively realize phosphate adsorption under alkaline conditions, with a removal rate of 99.33 %. Overall, this research focuses on material performance optimization using machine learning, offering insights and methods for developing biochar materials for practical water-treatment applications.

AI and ML-based risk assessment of chemicals: predicting carcinogenic risk from chemical-induced genomic instability

Chemical risk assessment plays a pivotal role in safeguarding public health and environmental safety by evaluating the potential hazards and risks associated with chemical exposures. In recent years, the convergence of artificial intelligence (AI), machine learning (ML), and omics technologies has revolutionized the field of chemical risk assessment, offering new insights into toxicity mechanisms, predictive modeling, and risk management strategies. This perspective review explores the synergistic potential of AI/ML and omics in deciphering clastogen-induced genomic instability for carcinogenic risk prediction. We provide an overview of key findings, challenges, and opportunities in integrating AI/ML and omics technologies for chemical risk assessment, highlighting successful applications and case studies across diverse sectors. From predicting genotoxicity and mutagenicity to elucidating molecular pathways underlying carcinogenesis, integrative approaches offer a comprehensive framework for understanding chemical exposures and mitigating associated health risks. Future perspectives for advancing chemical risk assessment and cancer prevention through data integration, advanced machine learning techniques, translational research, and policy implementation are discussed. By implementing the predictive capabilities of AI/ML and omics technologies, researchers and policymakers can enhance public health protection, inform regulatory decisions, and promote sustainable development for a healthier future.

Construction of interpretable ensemble learning models for predicting bioaccumulation parameters of organic chemicals in fish

Accurate prediction of bioaccumulation parameters is essential for assessing exposure, hazards, and risks of chemicals. However, the majority of prediction models on bioaccumulation parameters are individual models based on a single algorithm and lack model interpretation, resulting in unsatisfactory prediction accuracy due to inherent constraints of the algorithm and weak interpretability. Ensemble learning (EL) that combine multiple algorithms, coupled with SHapley Additive exPlanation (SHAP) method, may overcome the limitations. Herein, EL models were constructed for three bioaccumulation parameters using datasets covering 2496 chemicals. The EL models demonstrated superior prediction accuracy compared to both individual models developed in this study and those from previous research, achieving a coefficient of determination of up to 0.861 on the validation sets. Applicability domains were characterized using a structure-activity landscape-based (abbreviated as ADSAL) methodology. The optimal EL models, together with the ADSAL, were successfully used to predict bioaccumulation parameters for 4374 chemicals included in the Inventory of Existing Chemical Substances of China. Model interpretation using the SHAP method offered insight into key features influencing bioaccumulation potential, including hydrophobicity, water solubility, polarizability, ionization potential, weight, and volume of molecules. Overall, the study provides data and models to support the sound management and risk assessment of chemicals.

Machine learning modeling of thermally assisted biodrying process for municipal sludge

Preparation of activated carbons is an important way to utilize municipal sludge (MS) resources, while drying is a pretreatment method for making activated carbons from MS. In this study, machine learning techniques were used to develop moisture ratio (MR) and composting temperature (CT) prediction models for the thermally assisted biodrying process of MS. First, six machine learning (ML) models were used to construct the MR and CT prediction models, respectively. Then the hyperparameters of the ML models were optimized using the Bayesian optimization algorithm, and the prediction performances of these models after optimization were compared. Finally, the effect of each input feature on the model was also evaluated using SHapley Additive exPlanations (SHAP) analysis and Partial Dependence Plots (PDPs) analysis. The results showed that Gaussian process regression (GPR) was the best model for predicting MR and CT, with R2 of 0.9967 and 0.9958, respectively, and root mean square errors (RMSE) of 0.0059 and 0.354 ℃. In addition, graphical user interface software was developed to facilitate the use of the GPR model for predicting MR and CT by researchers and engineers. This study contributes to the rapid prediction, improvement, and optimization of MR and CT during thermally assisted biodrying of MS, and also provides valuable guidance for the dynamic regulation of the drying process.

Multimodal Representation Learning via Graph Isomorphism Network for Toxicity Multitask Learning

Toxicity is paramount for comprehending compound properties, particularly in the early stages of drug design. Due to the diversity and complexity of toxic effects, it became a challenge to compute compound toxicity tasks. To address this issue, we propose a multimodal representation learning model, termed multimodal graph isomorphism network (MMGIN), to address this challenge for compound toxicity multitask learning. Based on fingerprints and molecular graphs of compounds, our MMGIN model incorporates a multimodal representation learning model to acquire a comprehensive compound representation. This model adopts a two-channel structure to independently learn fingerprint representation and molecular graph representation. Subsequently, two feedforward neural networks utilize the learned multimodal compound representation to perform multitask learning, encompassing compound toxicity classification and multiple compound category classification simultaneously. To test the effectiveness of our model, we constructed a novel data set, termed the compound toxicity multitask learning (CTMTL) data set, derived from the TOXRIC data set. We compare our MMGIN model with other representative machine learning and deep learning models on the CTMTL and Tox21 data sets. The experimental results demonstrate significant advancements achieved by our MMGIN model. Furthermore, the ablation study underscores the effectiveness of the introduced fingerprints, molecular graphs, the multimodal representation learning model, and the multitask learning model, showcasing the model's superior predictive capability and robustness.

The digital evolution in toxicology: pioneering computational education for emerging challenges

The educational landscape of toxicology is increasingly integrating computational methodologies due to ethical concerns about animal testing and advancements in biotechnological and data analysis tools. This paper examines the evolution and significance of the Toxicology in the 21st century (Tox21) initiative and its impact on computational toxicology education. It contrasts computational toxicology with traditional methods, highlighting the limitations of conventional approaches and the new perspectives offered by computational techniques. The study emphasizes the importance of incorporating computational toxicology into curricula, including case studies that demonstrate how this integration enhances students' problem-solving abilities, real-time data analysis skills, and innovation capabilities. Furthermore, it outlines effective teaching content and methods, including software tools, online resources, and academic literature. The paper also addresses the challenges and limitations faced in this educational shift and explores prospects for advancing computational toxicology education. By documenting these developments, the study aims to clarify the current advancements in toxicology education and the preparedness of students to address global chemical safety challenges with innovative solutions.

Inhalation Toxicity Screening of Consumer Products Chemicals using OECD Test Guideline Data-based Machine Learning Models

This study aimed to screen the inhalation toxicity of chemicals found in consumer products such as air fresheners, fragrances, and anti-fogging agents submitted to K-REACH using machine learning models. We manually curated inhalation toxicity data based on OECD test guideline 403 (Acute inhalation), 412 (Sub-acute inhalation), and 413 (Sub-chronic inhalation) for 1709 chemicals from the OECD eChemPortal database. Machine learning models were trained using ten algorithms, along with four molecular fingerprints (MACCS, Morgan, Topo, RDKit) and molecular descriptors, achieving F1 scores ranging from 51 % to 91 % in test dataset. Leveraging the high-performing models, we conducted a virtual screening of chemicals, initially applying them to data-rich chemicals generally used in occupational settings to determine the prediction uncertainty. Results showed high sensitivity (75 %) but low specificity (23 %), suggesting that our models can contribute to conservative screening of chemicals. Subsequently, we applied the models to consumer product chemicals, identifying 79 as of high concern. Most of the prioritized chemicals lacked GHS classifications related to inhalation toxicity, even though they were predicted to be used in many consumer products. This study highlights a potential regulatory blind spot concerning the inhalation risk of consumer product chemicals while also indicating the potential of artificial intelligence (AI) models to aid in prioritizing chemicals at the screening level.

Perspectives on Advancing Multimodal Learning in Environmental Science and Engineering Studies

The environment faces increasing anthropogenic impacts, resulting in a rapid increase in environmental issues that undermine the natural capital essential for human wellbeing. These issues are complex and often influenced by various factors represented by data with different modalities. While machine learning (ML) provides data-driven tools for addressing the environmental issues, the current ML models in environmental science and engineering (ES&E) often neglect the utilization of multimodal data. With the advancement in deep learning, multimodal learning (MML) holds promise for comprehensive descriptions of the environmental issues by harnessing data from diverse modalities. This advancement has the potential to significantly elevate the accuracy and robustness of prediction models in ES&E studies, providing enhanced solutions for various environmental modeling tasks. This perspective summarizes MML methodologies and proposes potential applications of MML models in ES&E studies, including environmental quality assessment, prediction of chemical hazards, and optimization of pollution control techniques. Additionally, we discuss the challenges associated with implementing MML in ES&E and propose future research directions in this domain.

Integrated Transfer Learning and Multitask Learning Strategies to Construct Graph Neural Network Models for Predicting Bioaccumulation Parameters of Chemicals

Accurate prediction of parameters related to the environmental exposure of chemicals is crucial for the sound management of chemicals. However, the lack of large data sets for training models may result in poor prediction accuracy and robustness. Herein, integrated transfer learning (TL) and multitask learning (MTL) was proposed for constructing a graph neural network (GNN) model (abbreviated as TL-MTL-GNN model) using n-octanol/water partition coefficients as a source domain. The TL-MTL-GNN model was trained to predict three bioaccumulation parameters based on enlarged data sets that cover 2496 compounds with at least one bioaccumulation parameter. Results show that the TL-MTL-GNN model outperformed single-task GNN models with and without the TL, as well as conventional machine learning models trained with molecular descriptors or fingerprints. Applicability domains were characterized by a state-of-the-art structure-activity landscape-based (abbreviated as ADSAL) methodology. The TL-MTL-GNN model coupled with the optimal ADSAL was employed to predict bioaccumulation parameters for around 60,000 chemicals, with more than 13,000 compounds identified as bioaccumulative chemicals. The high predictive accuracy and robustness of the TL-MTL-GNN model demonstrate the feasibility of integrating the TL and MTL strategy in modeling small-sized data sets. The strategy holds significant potential for addressing small data challenges in modeling environmental chemicals.

Assessment of TGx-DDI genes for genotoxicity in a comprehensive panel of chemicals

BACKGROUND

The TGx-DDI biomarker identifies transcripts specifically induced by primary DNA damage. Profiling similarity of TGx-DDI signatures can allow clustering compounds by genotoxic mechanism. This transcriptomics-based approach complements conventional toxicology testing by enhancing mechanistic resolution.

METHODS

Unsupervised hierarchical clustering and t-distributed stochastic neighbor embedding (tSNE) were utilized to assess similarity of publicly-available per- and polyfluoroalkyl substances (PFAS) and ToxCast chemicals based on TGx-DDI modulation. TempO-seq transcriptomic data after highest chemical concentrations were analyzed.

RESULTS

Clustering discriminated between genotoxic and non-genotoxic compounds while drawing similarity among chemicals with shared mechanisms. PFAS largely clustered distinctly from classical mutagens. However, dynamic range across PFAS types and durations indicated variable potential for DNA damage. tSNE visualization reinforced phenotypic groupings, with genotoxins clustering separately from non-DNA damaging agents.

DISCUSSION

Unsupervised learning approaches applied to TGx-DDI profiles effectively categorizes chemical genotoxicity potential, aiding elucidation of biological response pathways. This transcriptomics-based strategy gives further insight into the role and effect of individual TGx-DDI biomarker genes and complements existing assays by enhancing mechanistic resolution. Overall, TGx-DDI biomarker profiling holds promise for predictive safety screening.

An Online Nanoinformatics Platform Empowering Computational Modeling of Nanomaterials by Nanostructure Annotations and Machine Learning Toolkits

Modern nanotechnology has generated numerous datasets from in vitro and in vivo studies on nanomaterials, with some available on nanoinformatics portals. However, these existing databases lack the digital data and tools suitable for machine learning studies. Here, we report a nanoinformatics platform that accurately annotates nanostructures into machine-readable data files and provides modeling toolkits. This platform, accessible to the public at https://vinas-toolbox.com/, has annotated nanostructures of 14 material types. The associated nanodescriptor data and assay test results are appropriate for modeling purposes. The modeling toolkits enable data standardization, data visualization, and machine learning model development to predict properties and bioactivities of new nanomaterials. Moreover, a library of virtual nanostructures with their predicted properties and bioactivities is available, directing the synthesis of new nanomaterials. This platform provides a data-driven computational modeling platform for the nanoscience community, significantly aiding in the development of safe and effective nanomaterials.

Integration of Nontarget Screening and QSPR Models to Identify Novel Organophosphate Esters of High Priority in Aquatic Environment

With the development of large numbers of novel organophosphate esters (OPEs) alternatives, it is imperative to screen and identify those with high priority. In this study, surface water, biofilms, and freshwater snails were collected from the flow-in rivers of Taihu Lake Basin, China. Screened by target, suspect, and nontarget analysis, 11 traditional and 14 novel OPEs were identified, of which 5 OPEs were first discovered in Taihu Lake Basin. The OPE concentrations in surface water ranged from 196 to 2568 ng/L, with the primary homologue tris(2,4-ditert-butylphenyl) phosphate (TDtBPP) being newly identified, which was likely derived from the transformation of tris(2,4-ditert-butylphenyl) phosphite. The majority of the newly identified OPEs displayed substantially higher bioaccumulation and biomagnification potentials in the biofilm-snail food chain than the traditional ones. Quantitative structure-property relationship models revealed both hydrophobicity and polarity influenced the bioaccumulation and biomagnification of the OPEs, while electrostatic attraction also had a contribution to the bioaccumulation in the biofilm. TDtBPP was determined as the utmost priority by toxicological priority index scheme, which integrated concentration, bioaccumulation, biomagnification, acute toxicity, and endocrine disrupting potential of the identified OPEs. These findings provide novel insights into the behaviors of OPEs and scientific bases for better management of high-risk pollutants in aquatic ecosystem.

Identifying Driving Factors of Atmospheric N2O5 with Machine Learning

Dinitrogen pentoxide (N2O5) plays an essential role in tropospheric chemistry, serving as a nocturnal reservoir of reactive nitrogen and significantly promoting nitrate formations. However, identifying key environmental drivers of N2O5 formation remains challenging using traditional statistical methods, impeding effective emission control measures to mitigate NOx-induced air pollution. Here, we adopted machine learning assisted by steady-state analysis to elucidate the driving factors of N2O5 before and during the 2022 Winter Olympics (WO) in Beijing. Higher N2O5 concentrations were observed during the WO period compared to the Pre-Winter-Olympics (Pre-WO) period. The machine learning model accurately reproduced ambient N2O5 concentrations and showed that ozone (O3), nitrogen dioxide (NO2), and relative humidity (RH) were the most important driving factors of N2O5. Compared to the Pre-WO period, the variation in trace gases (i.e., NO2 and O3) along with the reduced N2O5 uptake coefficient was the main reason for higher N2O5 levels during the WO period. By predicting N2O5 under various control scenarios of NOx and calculating the nitrate formation potential from N2O5 uptake, we found that the progressive reduction of nitrogen oxides initially increases the nitrate formation potential before further decreasing it. The threshold of NOx was approximately 13 ppbv, below which NOx reduction effectively reduced the level of night-time nitrate formations. These results demonstrate the capacity of machine learning to provide insights into understanding atmospheric nitrogen chemistry and highlight the necessity of more stringent emission control of NOx to mitigate haze pollution.

Machine learning framework for predicting cytotoxicity and identifying toxicity drivers of disinfection byproducts

Drinking water disinfection can result in the formation disinfection byproducts (DBPs, > 700 have been identified to date), many of them are reportedly cytotoxic, genotoxic, or developmentally toxic. Analyzing the toxicity levels of these contaminants experimentally is challenging, however, a predictive model could rapidly and effectively assess their toxicity. In this study, machine learning models were developed to predict DBP cytotoxicity based on their chemical information and exposure experiments. The Random Forest model achieved the best performance (coefficient of determination of 0.62 and root mean square error of 0.63) among all the algorithms screened. Also, the results of a probabilistic model demonstrated reliable model predictions. According to the model interpretation, halogen atoms are the most prominent features for DBP cytotoxicity compared to other chemical substructures. The presence of iodine and bromine is associated with increased cytotoxicity levels, while the presence of chlorine is linked to a reduction in cytotoxicity levels. Other factors including chemical substructures (CC, N, CN, and 6-member ring), cell line, and exposure duration can significantly affect the cytotoxicity of DBPs. The similarity calculation indicated that the model has a large applicability domain and can provide reliable predictions for DBPs with unknown cytotoxicity. Finally, this study showed the effectiveness of data augmentation in the scenario of data scarcity.

Quantifying the Benefits of Imputation over QSAR Methods in Toxicology Data Modeling

Imputation machine learning (ML) surpasses traditional approaches in modeling toxicity data. The method was tested on an open-source data set comprising approximately 2500 ingredients with limited in vitro and in vivo data obtained from the OECD QSAR Toolbox. By leveraging the relationships between different toxicological end points, imputation extracts more valuable information from each data point compared to well-established single end point methods, such as ML-based Quantitative Structure Activity Relationship (QSAR) approaches, providing a final improvement of up to around 0.2 in the coefficient of determination. A significant aspect of this methodology is its resilience to the inclusion of extraneous chemical or experimental data. While additional data typically introduces a considerable level of noise and can hinder performance of single end point QSAR modeling, imputation models remain unaffected. This implies a reduction in the need for laborious manual preprocessing tasks such as feature selection, thereby making data preparation for ML analysis more efficient. This successful test, conducted on open-source data, validates the efficacy of imputation approaches in toxicity data analysis. This work opens the way for applying similar methods to other types of sparse toxicological data matrices, and so we discuss the development of regulatory authority guidelines to accept imputation models, a key aspect for the wider adoption of these methods.

Exploring pollutant joint effects in disease through interpretable machine learning

Identifying the impact of pollutants on diseases is crucial. However, assessing the health risks posed by the interplay of multiple pollutants is challenging. This study introduces the concept of Pollutants Outcome Disease, integrating multidisciplinary knowledge and employing explainable artificial intelligence (AI) to explore the joint effects of industrial pollutants on diseases. Using lung cancer as a representative case study, an extreme gradient boosting predictive model that integrates meteorological, socio-economic, pollutants, and lung cancer statistical data is developed. The joint effects of industrial pollutants on lung cancer are identified and analyzed by employing the SHAP (Shapley Additive exPlanations) interpretable machine learning technique. Results reveal substantial spatial heterogeneity in emissions from CPG and ILC, highlighting pronounced nonlinear relationships among variables. The model yielded strong predictions (an R of 0.954, an RMSE of 4283, and an R2 of 0.911) and emphasized the impact of pollutant emission amounts on lung cancer responses. Diverse joint effects patterns were observed, varying in terms of patterns, regions (frequency), and the extent of antagonistic and synergistic effects among pollutants. The study provides a new perspective for exploring the joint effects of pollutants on diseases and demonstrates the potential of AI technology to assist scientific discovery.

Bioavailability (BA)-based risk assessment of soil heavy metals in provinces of China through the predictive BA-models

The real biological effect is not generated by the total content of heavy metals (HMs), but rather by bioavailable content. A new bioavailability-based ecological risk assessment (BA-based ERA) framework was developed for deriving bioavailability-based soil quality criteria (BA-based SQC) and accurately assessing the ecological risk of soil HMs at a multi-regional scale in this study. Through the random forest (RF) models and BA-based ERA framework, the 217 BA-based SQC for HMs in 31 Chinese provinces were derived and the BA-based ERA was comprehensively assessed. This study found that bioavailable HMs extraction methods (BHEMs) and total HMs content play the predominant role in affecting HMs (As, Cd, Cr, Cu, Ni, Pb, and Zn) bioavailability by explaining 27.55-56.11% and 9.20-62.09% of the variation, respectively. The RF model had accurate and stable prediction ability for the bioavailability of soil HMs with the mean R2 and RMSE of 0.83 and 0.43 for the test set, respectively. The results of BA-based ERA showed that bioavailability could avoid the overestimation of ecological risks to some extent after reducing the uncertainty of soil differences. This study confirmed the feasibility of using bioavailability for ERA and will utilised to revise the soil environmental standards based on bioavailability for HMs.

Artificial intelligence (AI)-it's the end of the tox as we know it (and I feel fine)

The rapid progress of AI impacts diverse scientific disciplines, including toxicology, and has the potential to transform chemical safety evaluation. Toxicology has evolved from an empirical science focused on observing apical outcomes of chemical exposure, to a data-rich field ripe for AI integration. The volume, variety and velocity of toxicological data from legacy studies, literature, high-throughput assays, sensor technologies and omics approaches create opportunities but also complexities that AI can help address. In particular, machine learning is well suited to handle and integrate large, heterogeneous datasets that are both structured and unstructured-a key challenge in modern toxicology. AI methods like deep neural networks, large language models, and natural language processing have successfully predicted toxicity endpoints, analyzed high-throughput data, extracted facts from literature, and generated synthetic data. Beyond automating data capture, analysis, and prediction, AI techniques show promise for accelerating quantitative risk assessment by providing probabilistic outputs to capture uncertainties. AI also enables explanation methods to unravel mechanisms and increase trust in modeled predictions. However, issues like model interpretability, data biases, and transparency currently limit regulatory endorsement of AI. Multidisciplinary collaboration is needed to ensure development of interpretable, robust, and human-centered AI systems. Rather than just automating human tasks at scale, transformative AI can catalyze innovation in how evidence is gathered, data are generated, hypotheses are formed and tested, and tasks are performed to usher new paradigms in chemical safety assessment. Used judiciously, AI has immense potential to advance toxicology into a more predictive, mechanism-based, and evidence-integrated scientific discipline to better safeguard human and environmental wellbeing across diverse populations.

Comparative Study of Machine Learning-Based QSAR Modeling of Anti-inflammatory Compounds from Durian Extraction

Quantitative structure-activity relationship (QSAR) analysis, an in silico methodology, offers enhanced efficiency and cost effectiveness in investigating anti-inflammatory activity. In this study, a comprehensive comparative analysis employing four machine learning algorithms (random forest (RF), gradient boosting regression (GBR), support vector regression (SVR), and artificial neural networks (ANNs)) was conducted to elucidate the activities of naturally derived compounds from durian extraction. The analysis was grounded in the exploration of structural attributes encompassing steric and electrostatic properties. Notably, the nonlinear SVR model, utilizing five key features, exhibited superior performance compared to the other models. It demonstrated exceptional predictive accuracy for both the training and external test datasets, yielding R2 values of 0.907 and 0.812, respectively; in addition, their RMSE resulted in 0.123 and 0.097, respectively. The study outcomes underscore the significance of specific structural factors (denoted as shadow ratio, dipole z, methyl, ellipsoidal volume, and methoxy) in determining anti-inflammatory efficacy. Thus, the findings highlight the potential of molecular simulations and machine learning as alternative avenues for the rational design of novel anti-inflammatory agents.

Identifying the drivers of chlorophyll-a dynamics in a landscape lake recharged by reclaimed water using interpretable machine learning

The water quality of lakes recharged by reclaimed water is affected by both the fluctuation of reclaimed water quality and the biochemical processes in the lakes, and therefore the main controlling factors of algal blooms are difficult to identify. Taking a typical landscape lake recharged by reclaimed water as an example and using the spatiotemporal distribution characteristics and correlation analysis of water quality indexes, we propose an interpretable machine learning framework based on random forest to predict chlorophyll-a (Chl-a). The model considered nutrient difference indexes between reclaimed water and lake water, and further used feature importance ranking and partial dependence plot to identify nutrient drivers. Results show that the NO3--N input from reclaimed water is the dominant nutrient driver for algal bloom especially at high temperatures, and the negative correlation between NO3--N and Chl-a in the lake water is the consequence of algal bloom rather than the cause. Our study provides new insights into the identification of eutrophication factors for lakes recharged by reclaimed water.

Advances and applications of machine learning and deep learning in environmental ecology and health

Machine learning (ML) and deep learning (DL) possess excellent advantages in data analysis (e.g., feature extraction, clustering, classification, regression, image recognition and prediction) and risk assessment and management in environmental ecology and health (EEH). Considering the rapid growth and increasing complexity of data in EEH, it is of significance to summarize recent advances and applications of ML and DL in EEH. This review summarized the basic processes and fundamental algorithms of the ML and DL modeling, and indicated the urgent needs of ML and DL in EEH. Recent research hotspots such as environmental ecology and restoration, environmental fate of new pollutants, chemical exposures and risks, chemical hazard identification and control were highlighted. Various applications of ML and DL in EEH demonstrate their versatility and technological revolution, and present some challenges. The perspective of ML and DL in EEH were further outlined to promote the innovative analysis and cultivation of the ML-driven research paradigm.