Molecular Screening and Toxicity Estimation of 260,000 Perfluoroalkyl and Polyfluoroalkyl Substances (PFASs) through Machine Learning

The oral acute toxicity of per- and polyfluoroalkyl compounds (PFASs) to Rat and Mouse: A mechanistic interpretation and prioritization analysis of untested PFASs by QSAR, q-RASAR and interspecies modelling methods

Per- and polyfluoroalkyl substances (PFASs) are widely used in modern industry, causing many adverse effects on both the environment and human health. In this study, for the first time, we followed OECD guidelines to systematically investigate the quantitative structure-activity relationship (QSAR) of the oral acute toxicity of PFASs to Rat and Mouse using simple 2D descriptors. The Read-Across similarity descriptors and 2D descriptors were also combined to develop the quantitative read-across structure-activity relationship (q-RASAR) models. Interspecies toxicity (iST) correlation was also explored between the two rodent species. All developed QSAR, q-RASAR and iST models met the state-of-the-art validation criteria and were applied for toxicity predictions of hundreds of untested PFASs in true external sets. Subsequently, we performed the priority ranking of the untested PFASs based on the model predictions, with the mechanistic interpretation of the top 20 most toxic PFASs predicted by both QSAR and q-RASAR models. The two univariate iST models were also used for filling the interspecies toxicity data gap. Overall, the developed QSAR, q-RASAR and iST models can be used as effective tools for predicting the oral acute toxicity of untested PFASs to Rat and Mouse, thus being important for risk assessment of PFASs in ecological environment.

Molecular designing of potential environmentally friendly PFAS based on deep learning and generative models

Perfluoroalkyl and polyfluoroalkyl substances (PFAS) are widely used across a spectrum of industrial and consumer goods. Nonetheless, their persistent nature and tendency to accumulate in biological systems pose substantial environmental and health threats. Consequently, striking a balance between maximizing product efficiency and minimizing environmental and health risks by tailoring the molecular structure of PFAS has become a pivotal challenge in the fields of environmental chemistry and sustainable development. To address this issue, a computational workflow was proposed for designing an environmentally friendly PFAS by incorporating deep learning (DL) and molecular generative models. The hybrid DL architecture MolHGT+ based on heterogeneous graph neural network with transformer-like attention was applied to predict the surface tension, bioaccumulation, and hepatotoxicity of the molecules. Through virtual screening of the PFAS master database using MolHGT+, the findings indicate that incorporating the siloxane group and betaine fragment can effectively decrease both the bioaccumulation and hepatotoxicity of PFAS while preserving low surface tension. In addition, molecular generative models were employed to create a structurally diverse pool of novel PFASs with the aforementioned hit molecules serving as the initial template structures. Overall, our study presents a promising AI-driven method for advancing the development of environmentally friendly PFAS.

Computational Tools to Facilitate Early Warning of New Emerging Risk Chemicals

Innovative tools suitable for chemical risk assessment are being developed in numerous domains, such as non-target chemical analysis, omics, and computational approaches. These methods will also be critical components in an efficient early warning system (EWS) for the identification of potentially hazardous chemicals. Much knowledge is missing for current use chemicals and thus computational methodologies complemented with fast screening techniques will be critical. This paper reviews current computational tools, emphasizing those that are accessible and suitable for the screening of new and emerging risk chemicals (NERCs). The initial step in a computational EWS is an automatic and systematic search for NERCs in literature and database sources including grey literature, patents, experimental data, and various inventories. This step aims at reaching curated molecular structure data along with existing exposure and hazard data. Next, a parallel assessment of exposure and effects will be performed, which will input information into the weighting of an overall hazard score and, finally, the identification of a potential NERC. Several challenges are identified and discussed, such as the integration and scoring of several types of hazard data, ranging from chemical fate and distribution to subtle impacts in specific species and tissues. To conclude, there are many computational systems, and these can be used as a basis for an integrated computational EWS workflow that identifies NERCs automatically.

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.

Construction of an explanatory model for predicting hepatotoxicity: a case study of the potentially hepatotoxic components of Gardenia jasminoides

It is well-known that the hepatotoxicity of drugs can significantly influence their clinical use. Despite their effective therapeutic efficacy, many drugs are severely limited in clinical applications due to significant hepatotoxicity. In response, researchers have created several machine learning-based hepatotoxicity prediction models for use in drug discovery and development. Researchers aim to predict the potential hepatotoxicity of drugs to enhance their utility. However, current hepatotoxicity prediction models often suffer from being unverified, and they fail to capture the detailed toxicological structures of predicted hepatotoxic compounds. Using the 56 chemical constituents of Gardenia jasminoides as examples, we validated the trained hepatotoxicity prediction model through literature reviews, principal component analysis (PCA), and structural comparison methods. Ultimately, we successfully developed a model with strong predictive performance and conducted visual validation. Interestingly, we discovered that the predicted hepatotoxic chemical constituents of Gardenia possess both toxic and therapeutic effects, which are likely dose-dependent. This discovery greatly contributes to our understanding of the dual nature of drug-induced hepatotoxicity.

Insights into PFAS environmental fate through computational chemistry: A review

Per- and polyfluoroalkyl substances (PFAS) are widely used chemicals that exhibit exceptional chemical and thermal stability. However, their resistance to degradation has led to their widespread environmental contamination. PFAS also negatively affect the environment and other organisms, highlighting the need for effective remediation methods to mitigate their presence and prevent further contamination. Computational chemistry methods, such as Density Functional Theory (DFT) and Molecular Dynamics (MD) offer valuable tools for studying PFAS and simulating their interactions with other molecules. This review explores how computational chemistry methods contribute to understanding and tackling PFAS in the environment. PFAS have been extensively studied using DFT and MD, each method offering unique advantages and computational limitations. MD simulates large macromolecules systems however it lacks the ability model chemical reactions, while DFT provides molecular insights however at a high computational cost. The integration of DFT with MD shows promise in predicting PFAS behavior in different environments. This work summarizes reported studies on PFAS compounds, focusing on adsorption, destruction, and bioaccumulation, highlighting contributions of computational methods while discussing the need for continued research. The findings emphasize the importance of computational chemistry in addressing PFAS contamination, guiding risk assessments, and informing future research and innovations in this field.

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.

An artificial intelligence platform for automated PFAS subgroup classification: A discovery tool for PFAS screening

Since structural analyses and toxicity assessments have not been able to keep up with the discovery of unknown per- and polyfluoroalkyl substances (PFAS), there is an urgent need for effective categorization and grouping of PFAS. In this study, we presented PFAS-Atlas, an artificial intelligence-based platform containing a rule-based automatic classification system and a machine learning-based grouping model. Compared with previously developed classification software, the platform's classification system follows the latest Organization for Economic Co-operation and Development (OECD) definition of PFAS and reduces the number of uncategorized PFAS. In addition, the platform incorporates deep unsupervised learning models to visualize the chemical space of PFAS by clustering similar structures and linking related classes. Through real-world use cases, we demonstrate that PFAS-Atlas can rapidly screen for relationships between chemical structure and persistence, bioaccumulation, or toxicity data for PFAS. The platform can also guide the planning of the PFAS testing strategy by showing which PFAS classes urgently require further attention. Ultimately, the release of PFAS-Atlas will benefit both the PFAS research and regulation communities.

Elucidating Key Characteristics of PFAS Binding to Human Peroxisome Proliferator-Activated Receptor Alpha: An Explainable Machine Learning Approach

Per- and polyfluoroalkyl substances (PFAS) are widely employed anthropogenic fluorinated chemicals known to disrupt hepatic lipid metabolism by binding to human peroxisome proliferator-activated receptor alpha (PPARα). Therefore, screening for PFAS that bind to PPARα is of critical importance. Machine learning approaches are promising techniques for rapid screening of PFAS. However, traditional machine learning approaches lack interpretability, posing challenges in investigating the relationship between molecular descriptors and PPARα binding. In this study, we aimed to develop a novel, explainable machine learning approach to rapidly screen for PFAS that bind to PPARα. We calculated the PPARα-PFAS binding score and 206 molecular descriptors for PFAS. Through systematic and objective selection of important molecular descriptors, we developed a machine learning model with good predictive performance using only three descriptors. The molecular size (b_single) and electrostatic properties (BCUT_PEOE_3 and PEOE_VSA_PPOS) are important for PPARα-PFAS binding. Alternative PFAS are considered safer than their legacy predecessors. However, we found that alternative PFAS with many carbon atoms and ether groups exhibited a higher affinity for PPARα. Therefore, confirming the toxicity of these alternative PFAS compounds with such characteristics through biological experiments is important.

Binding of Per- and Polyfluoroalkyl Substances (PFAS) to the PPARγ/RXRα-DNA Complex

Nuclear receptors are the fundamental building blocks of gene expression regulation and the focus of many drug targets. While binding to DNA, nuclear receptors act as transcription factors, governing a multitude of functions in the human body. Peroxisome proliferator-activator receptor γ (PPARγ) and the retinoid X receptor α (RXRα) form heterodimers with unique properties and have a primordial role in insulin sensitization. This PPARγ/RXRα heterodimer has been shown to be impacted by per- and polyfluoroalkyl substances (PFAS) and linked to a variety of significant health conditions in humans. Herein, a selection of the most common PFAS (legacy and emerging) was studied utilizing molecular dynamics simulations for PPARγ/RXRα. The local and global structural effects of PFAS binding on the known ligand binding pockets of PPARγ and RXRα as well as the DNA binding domain (DBD) of RXRα were inspected. The binding free energies were predicted computationally and were compared between the different binding pockets. In addition, two electronic structure approaches were utilized to model the interaction of PFAS within the DNA binding domain, density functional theory (DFT) and domain-based pair natural orbital coupled cluster with perturbative triples (DLPNO-CCSD(T)) approaches, with implicit solvation. Residue decomposition and hydrogen-bonding analysis were also performed, detailing the role of prominent residues in molecular recognition. The role of l-carnitine is explored as a potential in vivo remediation strategy for PFAS interaction with the PPARγ/RXRα heterodimer. In this work, it was found that PFAS can bind and act as agonists for all of the investigated pockets. For the first time in the literature, PFAS are postulated to bind to the DNA binding domain in a nonspecific manner. In addition, for the PPARγ ligand binding domain, l-carnitine shows promise in replacing smaller PFAS from the pocket.

Building Chemical Intuition about Physicochemical Properties of C8-Per-/Polyfluoroalkyl Carboxylic Acids through Computational Means

We have predicted acid dissociation constants (pK a), octanol-water partition coefficients (K OW), and DMPC lipid membrane-water partition coefficients (K lipid-w) of 150 different eight-carbon-containing poly-/perfluoroalkyl carboxylic acids (C8-PFCAs) utilizing the COnductor-like Screening MOdel for Realistic Solvents (COSMO-RS) theory. Different trends associated with functionalization, degree of fluorination, degree of saturation, degree of chlorination, and branching are discussed on the basis of the predicted values for the partition coefficients. In general, functionalization closest to the carboxylic headgroup had the greatest impact on the value of the predicted physicochemical properties.

High-Level Quantum Chemical Prediction of C-F Bond Dissociation Energies of Perfluoroalkyl Substances

In this study, 550 C-F bond dissociation energies (BDEs) of a variety of per- and polyfluoroalkyl substances (PFASs) obtained from high-level DLPNO-CCSD(T)/CBS calculations were used to assess the accuracy of contemporary density functional theory (DFT) and semiempirical methods. DLPNO-CCSD(T)/CBS gas phase C-F BDEs fall between 404.9-550.7 kJ mol-1 and M06-2X and ωB97M-V in conjunction with the aug-cc-pVTZ basis set predicted BDEs closest to the benchmark level with a mean absolute deviation (MAD) of 7.3 and 8.3 kJ mol-1, respectively. It was observed that DFT prediction errors increase with the degree of fluorination and system size. As such, previous model chemistry recommendations based on smaller nonfluorinated systems may not be carried over to modeling the energetics of PFASs and related systems.

Associations between exposure to a mixture of perfluoroalkyl and polyfluoroalkyl substances and age at menarche in adolescent girls utilizing three statistical models

Exposure to perfluoroalkyl and polyfluoroalkyl substances (PFAS) is suggested to interfere with endocrine function and may affect female pubertal development. However, the epidemiological evidence on age at menarche associated with PFAS exposure is still inconsistent. Our objective was to investigate association of serum PFAS concentrations with age at menarche among 12-19 years old girls. We used data on 432 girls from National Health and Nutrition Examination Survey (NHANES) 2007-2012 cycles. NHANES reported serum concentrations of perfluorooctanoic acid (PFOA), perfluorooctanesulfonic acid (PFOS), perfluorohexane sulfonate (PFHxS), perfluorononanoic acid (PFNA) and perfluorodecanoic acid (PFDA) as quantified by liquid chromatography tandem mass spectrometry (LC-MS/MS). Age at menarche was self-reported by girls or their guardians. Multivariable linear regression models were applied to estimate the association of individual PFAS exposure with age at menarche. The combined effects of PFAS mixture exposures on age at menarche were assessed using three statistical methods, including Bayesian kernel machine regression (BKMR), weighted quantile sum regression (WQS), and elastic net regression (ENR). In the single-chemical model, girls in the middle tertile of serum PFOA concentration had a lower age at menarche [regression coefficient (β) = -0.73 years, 95% confidence interval (CI): 1.44, -0.01; P = 0.047], compared with those in the lower tertile. Girls in the higher tertile of PFNA exposure were associated with older age at menarche (β = 0.36 years, 95% CI: 0.03, 0.80; P = 0.027), compared with those in the lower tertile. In the multiple-chemical models using BKMR and ENR approaches, higher PFNA exposure was significantly associated with older age at menarche among girls, after adjusting for other PFAS. We found suggestive evidence that higher PFAS mixture exposures may be related to an increase in age at menarche using the BKMR model. In conclusion, exposure to PFNA was associated with the later timing of menarche among girls.

A Review on Per- and Polyfluoroalkyl Substances in Pregnant Women: Maternal Exposure, Placental Transfer, and Relevant Model Simulation

Per- and polyfluoroalkyl substances (PFASs) are important and ubiquitous environmental contaminants worldwide. These novel contaminants can enter human bodies via various pathways, subsequently posing risks to the ecosystem and human health. The exposure of pregnant women to PFASs might pose risks to the health of mothers and the growth and development of fetuses. However, little information is available about the placental transfer of PFASs from mothers to fetuses and the related mechanisms through model simulation. In the present study, based upon a review of previously published literature, we initially summarized the exposure pathways of PFASs in pregnant women, factors affecting the efficiency of placental transfer, and mechanisms associated with placental transfer; outlined simulation analysis approaches using molecular docking and machine learning to reveal the mechanisms of placental transfer; and finally highlighted future research emphases that need to be focused on. Consequently, it was notable that the binding of PFASs to proteins during placental transfer could be simulated by molecular docking and that the placental transfer efficiency of PFASs could also be predicted by machine learning. Therefore, future research on the maternal-fetal transfer mechanisms of PFASs with the benefit of simulation analysis approaches is warranted to provide a scientific basis for the health effects of PFASs on newborns.