From Molecular Descriptors to Intrinsic Fish Toxicity of Chemicals: An Alternative Approach to Chemical Prioritization

Prediction of acute toxicity of organic contaminants to fish: Model development and a novel approach to identify reactive substructures

In this study, count-based Morgan fingerprints (CMF) were employed to represent the fundamental chemical structures of contaminants, and a neural network model (R² = 0.76) was developed to predict acute fish toxicity (AFT) of organic compounds. Models based on CMF consistently outperformed those based on binary Morgan fingerprints (BMF), likely due to the latter's inefficiency in describing homologous structures. The similarity of CMF was calculated using an improved method based on Tanimoto distance, which was used for calculation of dataset partition and application domain. The similarity-based dataset partitioning method ensured structural diversity within the training set and improved performance on the validation set, demonstrating its potential for toxicological structure analysis and priority screening. Toxic substructures identified by Shapley additive explanation (SHAP) method were substituted benzenes, long carbon chains, unsaturated carbons and halogen atoms. By incorporating Kow and monitoring shifts in feature importance, the influence of substructures on AFT was further delineated, revealing their roles in facilitating exposure (e.g.: long carbon chains) and reactive toxicity (e.g.: methyl). Additionally, we compared the toxicity of similar substructures and the same substructure in different chemical environments as well. To address SHAP's insensitivity to low-variance features, this study introduced a novel metric termed the toxicity index (TI), designed to pinpoint substructures that are present in minimal quantities yet potentially exhibit high toxicity. With TI, we identified several important substructures, such as parathion and polycyclic substituents. Finally, prevalent toxic substructures and potential highly toxic substances were identified in two external datasets.

Prioritization of Unknown LC-HRMS Features Based on Predicted Toxicity Categories

Complex environmental samples contain a diverse array of known and unknown constituents. While liquid chromatography coupled with high-resolution mass spectrometry (LC-HRMS) nontargeted analysis (NTA) has emerged as an essential tool for the comprehensive study of such samples, the identification of individual constituents remains a significant challenge, primarily due to the vast number of detected features in each sample. To address this, prioritization strategies are frequently employed to narrow the focus to the most relevant features for further analysis. In this study, we developed a novel prioritization strategy that directly links fragmentation and chromatographic data to aquatic toxicity categories, bypassing the need for identification of individual compounds. Given that features are not always well-characterized through fragmentation, we created two models: (1) a Random Forest Classification (RFC) model, which classifies fish toxicity categories based on MS1, retention, and fragmentation data─expressed as cumulative neutral losses (CNLs)─when fragmentation information is available, and (2) a Kernel Density Estimation (KDE) model that relies solely on retention time and MS1 data when fragmentation is absent. Both models demonstrated accuracy comparable to that of structure-based prediction methods. We further tested the models on a pesticide mixture in a tea extract measured by LC-HRMS, where the CNL-based RFC model achieved 0.76 accuracy and the KDE model reached 0.61, showcasing their robust performance in real-world applications.

Machine Learning-based Classification for the Prioritization of Potentially Hazardous Chemicals with Structural Alerts in Nontarget Screening

Nontarget screening (NTS) with liquid chromatography high-resolution mass spectrometry (LC-HRMS) is commonly used to detect unknown organic micropollutants in the environment. One of the main challenges in NTS is the prioritization of relevant LC-HRMS features. A novel prioritization strategy based on structural alerts to select NTS features that correspond to potentially hazardous chemicals is presented here. This strategy leverages raw tandem mass spectra (MS2) and machine learning models to predict the probability that NTS features correspond to chemicals with structural alerts. The models were trained on fragments and neutral losses from the experimental MS2 data. The feasibility of this approach is evaluated for two groups: aromatic amines and organophosphorus structural alerts. The neural network classification model for organophosphorus structural alerts achieved an Area Under the Curve of the Receiver Operating Characteristics (AUC-ROC) of 0.97 and a true positive rate of 0.65 on the test set. The random forest model for the classification of aromatic amines achieved an AUC-ROC value of 0.82 and a true positive rate of 0.58 on the test set. The models were successfully applied to prioritize LC-HRMS features in surface water samples, showcasing the high potential to develop and implement this approach further.

Comprehensive Mass Spectrometry Workflows to Systematically Elucidate Transformation Processes of Organic Micropollutants: A Case Study on the Photodegradation of Four Pharmaceuticals

Organic micropollutants (OMPs) in the aquatic environment challenge conventional water treatment processes. Advanced oxidation processes, such as UV photolysis, serve as effective strategies to remove OMPs. However, these often yield unknown transformation products (TPs). High-resolution mass spectrometry (HRMS)-based non-target analysis (NTA) is commonly used to screen large numbers of chemicals but faces specific challenges such as low concentrations of compounds of interest, lack of reference standards, and the need for sophisticated data analysis workflows when used for TP identification. This article describes comprehensive workflows to study UV photolysis-related processes and the resulting TPs, by combining an automated photodegradation setup and HRMS and advanced NTA approaches. Four pharmaceuticals were successfully degraded in a case study, and 38 NTA features were effectively prioritized from complex sample matrices and identified as TPs through complementary approaches developed in this work. The identified TPs were structurally diverse and mostly novel. Semi-quantitation suggested that the TPs explained a relevant part of the parent removal. The developed workflows are a step toward systematic comprehensive analysis of transformation processes in water and beyond. The openly available data-processing tools and data enhance transformation data repositories and algorithms and support NTA studies in general.

Effect-directed analysis and nontarget screening for identifying AhR-active substances in sediments of Gamcheon Harbor, South Korea

Gamcheon Harbor in Busan, the largest port city in South Korea, is contaminated with persistent toxic substances, including polycyclic aromatic hydrocarbons (92 to 1700 ng g-1 dry mass (dm)) and styrene oligomers (17 to 520 ng g-1 dm). This study applied effect-directed analysis and nontarget screening (NTS) to identify aryl hydrocarbon receptor (AhR)-active substances in Gamcheon harbor sediments. Relatively great AhR-mediated potencies were found in RP-HPLC fractions, F2.7-F2.8 (mid-polar, log KOW 6-8) and F3.6-F3.7 (polar, log KOW 5-7). Target AhR agonists comprised up to 43% of total AhR-mediated potencies. NTS using GC-QTOFMS and LC-QTOFMS identified daphnoretin and isorhamnetin as significant AhR agonists, with relative potency values of 0.4 × 10-3 and 6.5 × 10-5, respectively, compared to benzo[a]pyrene. The major AhR agonists in the coastal sediments of Korea appeared to be region-specific. This approach is useful for identifying and managing key toxic substances in coastal ecosystems.

Identifying the toxic mechanisms of emerging electronic contaminations liquid crystal monomers and the construction of a priority control list for graded control

Liquid crystal monomers (LCMs) are identified as emerging organic contaminations with largely unexplored health impacts. To elucidate their toxic mechanisms, support the establishment of environmental discharge and management standards, and promote effective LCMs control, this study constructs a database covering 20,545 potential targets of 1431 LCMs, highlighting 9 key toxic target proteins that disrupt the nervous system and metabolic functions. GO and KEGG pathway analysis suggests LCMs severely affect nervous system, linked to neurodegenerative diseases and mental health disorders, with toxicity variations driven by electronegativity and structural complexity of LCM terminal groups. To achieve tiered control of LCMs, construct toxicity risk control lists for 9 key toxic target proteins, suitable for the graded control of LCMs, management recommendations are provided based on toxicity levels. These lists were validated for reliability and offer reliable toxicity predictions for LCMs. SHAP analysis points to electronic properties, molecular shape, and structural characteristics of LCMs as primary health impact factors. As the first study integrating machine learning with computational toxicology to outline LCMs health impacts, it aims to enhance public understanding of LCM toxicity risks and support the development of environmental standards, effective management of LCM production and emissions, and reduction of public exposure risks.

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.

Computational modeling of air pollutants for aquatic risk: Prediction of ecological toxicity and exploring structural characteristics

Assessing the aquatic toxicity originating from air pollutants is essential in sustaining water resources and maintaining the ecosystem's safety. Quantitative structure-activity relationship (QSAR) models provide a computational tool for predicting pollutant toxicity, facilitating the identification/evaluation of the contaminants and identifying responsible structural fragments. One-vs-all (OvA) QSAR is a tailored approach to address multi-class QSAR problems. The study aims to determine five distinct levels of aquatic hazard categories for airborne pollutants using OvA-QSAR modeling containing 254 air contaminants. This QSAR analysis reveals the critical descriptors of air pollutants to target for molecular modification. Various factors, including the selection of relevant mechanistic descriptors, data quality, and outliers, determine the reliability of QSAR models. By employing feature selection and outlier identification approaches, the robustness and accuracy of our QSAR models were significantly increased, leading to more reliable predictions in chemical hazard assessment. The results revealed that models using the Random Forest algorithm performed the best based on the selected descriptors, with internal and external validation accuracy ranging from 71.90% to 97.53% and 76.47%-98.03%, respectively. This study indicated that the aquatic risk of air contaminants might be attributed predominantly to their sp3/sp2 carbon ratio, hydrogen-bond acceptor capability, hydrophilicity/lipophilicity, and van der Waals volumes. These structures can be critical in developing innovative strategies to mitigate or avoid the chemicals' harmful effects. Supporting air quality improvement, this study contributes to the rapid implementation of measures to protect aquatic ecosystems affected by air pollution.

Non-target analysis of Danish wastewater treatment plant effluent: Statistical analysis of chemical fingerprinting as a step toward a future monitoring tool

In an attempt to discover and characterize the plethora of xenobiotic substances, this study investigates chemical compounds released into the environment with wastewater effluents. A novel non-targeted screening methodology based on ultra-high resolution Orbitrap mass spectrometry and nanoflow ultra-high performance liquid chromatography together with a newly optimized data-processing pipeline were applied to effluent samples from two state-of-the-art and one small wastewater treatment facility. In total, 785 molecular structures were obtained, of which 38 were identified as single compounds, while 480 structures were identified at a putative level. Most of these substances were therapeutics and drugs, present as parent compounds and metabolites. Using R packages Phyloseq and MetacodeR, originally developed for bioinformatics, significant differences in xenobiotic presence in the wastewater effluents between the three sites were demonstrated.

Exploring the chemical subspace of RPLC: A data driven approach

BACKGROUND

The chemical space is comprised of a vast number of possible structures, of which an unknown portion comprises the human and environmental exposome. Such samples are frequently analyzed using non-targeted analysis via liquid chromatography (LC) coupled to high-resolution mass spectrometry often employing a reversed phase (RP) column. However, prior to analysis, the contents of these samples are unknown and could be comprised of thousands of known and unknown chemical constituents. Moreover, it is unknown which part of the chemical space is sufficiently retained and eluted using RPLC.

RESULTS

We present a generic framework that uses a data driven approach to predict whether molecules fall 'inside', 'maybe' inside, or 'outside' of the RPLC subspace. Firstly, three retention index random forest (RF) regression models were constructed that showed that molecular fingerprints are able to predict RPLC retention behavior. Secondly, these models were used to set up the dataset for building an RPLC RF classification model. The RPLC classification model was able to correctly predict whether a chemical belonged to the RPLC subspace with an accuracy of 92% for the testing set. Finally, applying this model to the 91 737 small molecules (i.e., ≤1 000 Da) in NORMAN SusDat showed that 19.1% fall 'outside' of the RPLC subspace.

SIGNIFICANCE AND NOVELTY

The RPLC chemical space model provides a major step towards mapping the chemical space and is able to assess whether chemicals can potentially be measured with an RPLC method (i.e., not every RPLC method) or if a different selectivity should be considered. Moreover, knowing which chemicals are outside of the RPLC subspace can assist in reducing potential candidates for library searching and avoid screening for chemicals that will not be present in RPLC data.

Quinolone Antibiotics Inhibit the Rice Photosynthesis by Targeting Photosystem II Center Protein: Generational Differences and Mechanistic Insights

Soil antibiotic pollution profoundly influences plant growth and photosynthetic performance, yet the main disturbed processes and the underlying mechanisms remain elusive. This study explored the photosynthetic toxicity of quinolone antibiotics across three generations on rice plants and clarified the mechanisms through experimental and computational studies. Marked variations across antibiotic generations were noted in their impact on rice photosynthesis with the level of inhibition intensifying from the second to the fourth generation. Omics analyses consistently targeted the light reaction phase of photosynthesis as the primary process impacted, emphasizing the particular vulnerability of photosystem II (PS II) to the antibiotic stress, as manifested by significant interruptions in the photon-mediated electron transport and O2 production. PS II center D2 protein (psbD) was identified as the primary target of the tested antibiotics, with the fourth-generation quinolones displaying the highest binding affinity to psbD. A predictive machine learning method was constructed to pinpoint antibiotic substructures that conferred enhanced affinity. As antibiotic generations evolve, the positive contribution of the carbonyl and carboxyl groups on the 4-quinolone core ring in the affinity interaction gradually intensified. This research illuminates the photosynthetic toxicities of antibiotics across generations, offering insights for the risk assessment of antibiotics and highlighting their potential threats to carbon fixation of agroecosystems.

Quantitative structure-activity relationship model development for estimating the predicted No-effect concentration of petroleum hydrocarbon and derivatives in the ecological risk assessment

Quantitative structure-activity relationship (QSAR) is a cost-effective solution to directly and accurately estimating the environmental safety thresholds (ESTs) of pollutants in the ecological risk assessment due to the lack of toxicity data. In this study, QSAR models were developed for estimating the Predicted No-Effect Concentrations (PNECs) of petroleum hydrocarbons and their derivatives (PHDs) under dietary exposure, based on the quantified molecular descriptors and the obtained PNECs of 51 PHDs with given acute or chronic toxicity concentrations. Three high-reliable QSAR models were respectively developed for PHDs, aromatic hydrocarbons and their derivatives (AHDs), and alkanes, alkenes and their derivatives (ALKDs), with excellent fitting performance evidenced by high correlation coefficient (0.89-0.95) and low root mean square error (0.13-0.2 mg/kg), and high stability and predictive performance reflected by high internal and external verification coefficient (Q2LOO, 0.66-0.89; Q2F1, 0.62-0.78; Q2F2, 0.60-0.73). The investigated quantitative relationships between molecular structure and PNECs indicated that 18 autocorrelation descriptors, 3 information index descriptors, 4 barysz matrix descriptors, 6 burden modified eigenvalues descriptors, and 1 BCUT descriptor were important molecular descriptors affecting the PNECs of PHDs. The obtained results supported that PNECs of PHDs can be accurately estimated by the influencing molecular descriptors and the quantitative relationship from the developed QSAR models, that provided a new feasible solution for ESTs derivation in the ecological risk assessment.

Integrated predictive QSAR, Read Across, and q-RASAR analysis for diverse agrochemical phytotoxicity in oat and corn: A consensus-based approach for risk assessment and prioritization

In the modern fast-paced lifestyle, time-efficient and nutritionally rich foods like corn and oat have gained popularity for their amino acids and antioxidant contents. The increasing demand for these cereals necessitates higher production which leads to dependency on agrochemicals, which can pose health risks through residual present in the plant products. To first report the phytotoxicity for corn and oat, our study employs QSAR, quantitative Read-Across and quantitative RASAR (q-RASAR). All developed QSAR and q-RASAR models were equally robust (R2 = 0.680-0.762, Q2Loo = 0.593-0.693, Q2F1 = 0.680-0.860) and find their superiority in either oat or corn model, respectively, based on MAE criteria. AD and PRI had been performed which confirm the reliability and predictability of the models. The mechanistic interpretation reveals that the symmetrical arrangement of electronegative atoms and polar groups directly influences the toxicity of compounds. The final phytotoxicity and prioritization are performed by the consensus approach which results into selection of 15 most toxic compounds for both species.

Machine Learning-Based Hazard-Driven Prioritization of Features in Nontarget Screening of Environmental High-Resolution Mass Spectrometry Data

Nontarget high-resolution mass spectrometry screening (NTS HRMS/MS) can detect thousands of organic substances in environmental samples. However, new strategies are needed to focus time-intensive identification efforts on features with the highest potential to cause adverse effects instead of the most abundant ones. To address this challenge, we developed MLinvitroTox, a machine learning framework that uses molecular fingerprints derived from fragmentation spectra (MS2) for a rapid classification of thousands of unidentified HRMS/MS features as toxic/nontoxic based on nearly 400 target-specific and over 100 cytotoxic endpoints from ToxCast/Tox21. Model development results demonstrated that using customized molecular fingerprints and models, over a quarter of toxic endpoints and the majority of the associated mechanistic targets could be accurately predicted with sensitivities exceeding 0.95. Notably, SIRIUS molecular fingerprints and xboost (Extreme Gradient Boosting) models with SMOTE (Synthetic Minority Oversampling Technique) for handling data imbalance were a universally successful and robust modeling configuration. Validation of MLinvitroTox on MassBank spectra showed that toxicity could be predicted from molecular fingerprints derived from MS2 with an average balanced accuracy of 0.75. By applying MLinvitroTox to environmental HRMS/MS data, we confirmed the experimental results obtained with target analysis and narrowed the analytical focus from tens of thousands of detected signals to 783 features linked to potential toxicity, including 109 spectral matches and 30 compounds with confirmed toxic activity.

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.

Read-across-based intelligent learning: development of a global q-RASAR model for the efficient quantitative predictions of skin sensitization potential of diverse organic chemicals

Environmental chemicals and contaminants cause a wide array of harmful implications to terrestrial and aquatic life which ranges from skin sensitization to acute oral toxicity. The current study aims to assess the quantitative skin sensitization potential of a large set of industrial and environmental chemicals acting through different mechanisms using the novel quantitative Read-Across Structure-Activity Relationship (q-RASAR) approach. Based on the identified important set of structural and physicochemical features, Read-Across-based hyperparameters were optimized using the training set compounds followed by the calculation of similarity and error-based RASAR descriptors. Data fusion, further feature selection, and removal of prediction confidence outliers were performed to generate a partial least squares (PLS) q-RASAR model, followed by the application of various Machine Learning (ML) tools to check the quality of predictions. The PLS model was found to be the best among different models. A simple user-friendly Java-based software tool was developed based on the PLS model, which efficiently predicts the toxicity value(s) of query compound(s) along with their status of Applicability Domain (AD) in terms of leverage values. This model has been developed using structurally diverse compounds and is expected to predict efficiently and quantitatively the skin sensitization potential of environmental chemicals to estimate their occupational and health hazards.

Critical Assessment of the Chemical Space Covered by LC-HRMS Non-Targeted Analysis

Non-targeted analysis (NTA) has emerged as a valuable approach for the comprehensive monitoring of chemicals of emerging concern (CECs) in the exposome. The NTA approach can theoretically identify compounds with diverse physicochemical properties and sources. Even though they are generic and have a wide scope, non-targeted analysis methods have been shown to have limitations in terms of their coverage of the chemical space, as the number of identified chemicals in each sample is very low (e.g., ≤5%). Investigating the chemical space that is covered by each NTA assay is crucial for understanding the limitations and challenges associated with the workflow, from the experimental methods to the data acquisition and data processing techniques. In this review, we examined recent NTA studies published between 2017 and 2023 that employed liquid chromatography-high-resolution mass spectrometry. The parameters used in each study were documented, and the reported chemicals at confidence levels 1 and 2 were retrieved. The chosen experimental setups and the quality of the reporting were critically evaluated and discussed. Our findings reveal that only around 2% of the estimated chemical space was covered by the NTA studies investigated for this review. Little to no trend was found between the experimental setup and the observed coverage due to the generic and wide scope of the NTA studies. The limited coverage of the chemical space by the reviewed NTA studies highlights the necessity for a more comprehensive approach in the experimental and data processing setups in order to enable the exploration of a broader range of chemical space, with the ultimate goal of protecting human and environmental health. Recommendations for further exploring a wider range of the chemical space are given.

In silico assessment of risks associated with pesticides exposure during pregnancy

Novel Quantitative Structure-Activity Relationship (QSAR) models of compounds' placenta (PL) permeability expressed as their log FM (fetus-to-mother blood concentration) values or binary PL1/0 (crossing/non-crossing) score were generated using a number of statistical tools: Multiple Linear Regression, Boosted Trees, Principal Component Analysis and Artificial Neural Networks, on the basis of molecular descriptors calculated by Mordred software and selected using Partial Least Squares (PLS) analysis. It was established that the most important predictor of both log FM and the binary PL1/0 score is Lipinski - a binary variable reflecting the compounds' ability to satisfy the criteria of drug-likeness according to the Lipinski's "Rule of 5". The quantitative (log FM) and qualitative (PL1/0) models of PL permeability were applied to 345 pesticides from different chemical families (triazines, carbamates, pyrethroids, organochlorine, organophosphorus and miscellaneous compounds). The ability of studied pesticides to cross the placenta was assessed; the basic physico-chemical parameters responsible for good or poor placenta transport of pesticides were identified and the relationships between the pesticides' PL permeability, blood-brain barrier (BBB) transfer and gastro-intestinal (GI) absorption were investigated. It was found (on the basis of logistic regression analysis) that the probability of a compound crossing the placenta (PL1) is inversely correlated with its lipophilicity and molar refractivity and positively correlated with the total count of oxygen and nitrogen atoms.