Artificial Intelligence and Machine Learning for Lead-to-Candidate Decision-Making and Beyond.

The use of artificial intelligence (AI) and machine learning (ML) in pharmaceutical research and development has to date focused on research: target identification; docking-, fragment-, and motif-based generation of compound libraries; modeling of synthesis feasibility; rank-ordering likely hits according to structural and chemometric similarity to compounds having known activity and affinity to the target(s); optimizing a smaller library for synthesis and high-throughput screening; and combining evidence from screening to support hit-to-lead decisions. Applying AI/ML methods to lead optimization and lead-to-candidate (L2C) decision-making has shown slower progress, especially regarding predicting absorption, distribution, metabolism, excretion, and toxicology properties. The present review surveys reasons why this is so, reports progress that has occurred in recent years, and summarizes some of the issues that remain. Effective AI/ML tools to derisk L2C and later phases of development are important to accelerate the pharmaceutical development process, ameliorate escalating development costs, and achieve greater success rates.

Application of the Biological Toxicity Effect Ratio (BER) Method for Advancing Water Quality Criteria Derivation.

Water quality criteria (WQC) serve as a scientific foundation for pollutant risk assessment and control in aquatic ecosystems. The development of regionally differentiated WQC tailored to specific regional characteristics has become an emerging trend. However, the current WQC is constrained by a lack of regional species toxicity data. To address these limitations, this study proposes the biological toxicity effect ratio (BER) method, which indirectly reflects the toxicity sensitivity of the overall aquatic ecosystem through the toxicity information on a limited number of species, enabling rapid WQC prediction. Using the established WQC in China and the USA as a case study, we combined mathematical derivation and data validation to evaluate the BER method. Among various species-taxon groups of freshwater organisms, planktonic crustaceans demonstrated the highest predictive accuracy. Our analysis further revealed that species toxicity sensitivity and regional variability jointly influence the prediction accuracy. Regardless of the evaluation indexes, planktonic crustaceans emerged as the most suitable species-taxon group for the BER method. Additionally, the BER method is particularly applicable to pollutants with conserved mechanisms across species. This study systematically explores the feasibility of using the BER method and offers new insights for deriving regionally differentiated WQC.

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.

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.

The prediction of hydrolysis and biodegradation of organophosphorus-based chemical warfare agents (G-series and V-series) using toxicology in silico methods.

Nerve agents (G- and V-series) are a group of extremely toxic organophosphorus chemical warfare agents that we have had the opportunity to encounter many times on a massive scale (Matsumoto City, Tokyo subway and Gulf War). The threat of using nerve agents in terrorist attacks or military operations is still present, even with establishing the Chemical Weapons Convention as the legal framework. Understanding their environmental sustainability and health risks is critical to social security. Due to the risk of contact with dangerous nerve agents and animal welfare considerations, in silico methods were used to assess hydrolysis and biodegradation safely. The environmental fate of the examined nerve agents was elucidated using QSAR models. The results indicate that the investigated compounds released into the environment hydrolyse at a different rate, from extremely fast (<1 day) to very slow (over a year); V-agents undergo slower hydrolysis compared to G-agents. V-agents turned out to be relatively challenging to biodegrade, the ultimate biodegradation time frame of which was predicted as weeks to months, while for G-agents, the overwhelming majority was classified as weeks. In silico methods for predicting various parameters are critical to preparing for the forthcoming application of nerve agents.

The investigation of the toxicity of organophosphorus flame retardants (OPFRs) by using in silico toxicity prediction platform ProTox- 3.0.

From the past to the present, many chemicals have been used for the purpose of flame retardant. Due to PBDEs' (Polybrominated diphenyl ether) lipophilic and accumulative properties, some of them are banned from the market. As an alternative to these chemicals, OPFRs (organophosphorus flame retardants) have started to be used as flame retardants. In this article, acute toxicity profiles, mutagenicity, carcinogenicity, blood-brain barrier permeability, ecotoxicity and nutritional toxicity as also AHR, ER affinity and MMP, aromatase affinity, CYP2C9, CYP3A4 interaction of the of 16 different compounds of the OPFRs were investigated using a computational toxicology method; ProTox- 3.0. According to our results, eight compounds were found to be active in terms of carcinogenic effect, whereas two compounds were found to be active for mutagenicity. On the other hand, all compounds were found to be active in terms of blood-barrier permeability. Fourteen compounds and four compounds are found to have ecotoxic and nutritional toxic potency, respectively. Eight compounds were determined as active to AhR, and four chemicals were found to be active in Estrogen Receptor alpha. Eight chemicals were found to be active in terms of mitochondrial membrane potency. Lastly, three chemicals were found to be active in aromatase enzymes. In terms of CYP interaction potencies, eight compounds were found to be active in both CYP2C9 and CYP3A4. This research provided novel insights into the potential toxic effects of OPFRs. However, further studies are needed to evaluate their toxicity. Moreover, these findings lay the groundwork for in vitro and in vivo toxicity research.

DCAMCP: A deep learning model based on capsule network and attention mechanism for molecular carcinogenicity prediction.

The carcinogenicity of drugs can have a serious impact on human health, so carcinogenicity testing of new compounds is very necessary before being put on the market. Currently, many methods have been used to predict the carcinogenicity of compounds. However, most methods have limited predictive power and there is still much room for improvement. In this study, we construct a deep learning model based on capsule network and attention mechanism named DCAMCP to discriminate between carcinogenic and non-carcinogenic compounds. We train the DCAMCP on a dataset containing 1564 different compounds through their molecular fingerprints and molecular graph features. The trained model is validated by fivefold cross-validation and external validation. DCAMCP achieves an average accuracy (ACC) of 0.718 ± 0.009, sensitivity (SE) of 0.721 ± 0.006, specificity (SP) of 0.715 ± 0.014 and area under the receiver-operating characteristic curve (AUC) of 0.793 ± 0.012. Meanwhile, comparable results can be achieved on an external validation dataset containing 100 compounds, with an ACC of 0.750, SE of 0.778, SP of 0.727 and AUC of 0.811, which demonstrate the reliability of DCAMCP. The results indicate that our model has made progress in cancer risk assessment and could be used as an efficient tool in drug design.

Application of Cell Painting for chemical hazard evaluation in support of screening-level chemical assessments.

'Cell Painting' is an imaging-based high-throughput phenotypic profiling (HTPP) method in which cultured cells are fluorescently labeled to visualize subcellular structures (i.e., nucleus, nucleoli, endoplasmic reticulum, cytoskeleton, Golgi apparatus / plasma membrane and mitochondria) and to quantify morphological changes in response to chemicals or other perturbagens. HTPP is a high-throughput and cost-effective bioactivity screening method that detects effects associated with many different molecular mechanisms in an untargeted manner, enabling rapid in vitro hazard assessment for thousands of chemicals. Here, 1201 chemicals from the ToxCast library were screened in concentration-response up to ∼100 µM in human U-2 OS cells using HTPP. A phenotype altering concentration (PAC) was estimated for chemicals active in the tested range. PACs tended to be higher than lower bound potency values estimated from a broad collection of targeted high-throughput assays, but lower than the threshold for cytotoxicity. In vitro to in vivo extrapolation (IVIVE) was used to estimate administered equivalent doses (AEDs) based on PACs for comparison to human exposure predictions. AEDs for 18/412 chemicals overlapped with predicted human exposures. Phenotypic profile information was also leveraged to identify putative mechanisms of action and group chemicals. Of 58 known nuclear receptor modulators, only glucocorticoids and retinoids produced characteristic profiles; and both receptor types are expressed in U-2 OS cells. Thirteen chemicals with profile similarity to glucocorticoids were tested in a secondary screen and one chemical, pyrene, was confirmed by an orthogonal gene expression assay as a novel putative GR modulating chemical. Most active chemicals demonstrated profiles not associated with a known mechanism-of-action. However, many structurally related chemicals produced similar profiles, with exceptions such as diniconazole, whose profile differed from other active conazoles. Overall, the present study demonstrates how HTPP can be applied in screening-level chemical assessments through a series of examples and brief case studies.

Advancing Computational Toxicology by Interpretable Machine Learning.

Chemical toxicity evaluations for drugs, consumer products, and environmental chemicals have a critical impact on human health. Traditional animal models to evaluate chemical toxicity are expensive, time-consuming, and often fail to detect toxicants in humans. Computational toxicology is a promising alternative approach that utilizes machine learning (ML) and deep learning (DL) techniques to predict the toxicity potentials of chemicals. Although the applications of ML- and DL-based computational models in chemical toxicity predictions are attractive, many toxicity models are "black boxes" in nature and difficult to interpret by toxicologists, which hampers the chemical risk assessments using these models. The recent progress of interpretable ML (IML) in the computer science field meets this urgent need to unveil the underlying toxicity mechanisms and elucidate the domain knowledge of toxicity models. In this review, we focused on the applications of IML in computational toxicology, including toxicity feature data, model interpretation methods, use of knowledge base frameworks in IML development, and recent applications. The challenges and future directions of IML modeling in toxicology are also discussed. We hope this review can encourage efforts in developing interpretable models with new IML algorithms that can assist new chemical assessments by illustrating toxicity mechanisms in humans.

A continuous in silico learning strategy to identify safety liabilities in compounds used in the leather and textile industry.

There is a widely recognized need to reduce human activity's impact on the environment. Many industries of the leather and textile sector (LTI), being aware of producing a significant amount of residues (Keßler et al. 2021; Liu et al. 2021), are adopting measures to reduce the impact of their processes on the environment, starting with a more comprehensive characterization of the chemical risk associated with the substances commonly used in LTI. The present work contributes to these efforts by compiling and toxicologically annotating the substances used in LTI, supporting a continuous learning strategy for characterizing their chemical safety. This strategy combines data collection from public sources, experimental methods and in silico predictions for characterizing four different endpoints: CMR, ED, PBT, and vPvB. We present the results of a prospective validation exercise in which we confirm that in silico methods can produce reasonably good hazard estimations and fill knowledge gaps in the LTI chemical space. The proposed protocol can speed the process and optimize the use of resources including the lives of experimental animals, contributing to identifying potentially harmful substances and their possible replacement by safer alternatives, thus reducing the environmental footprint and impact on human health.

Understanding and overcoming the technical challenges in using in silico predictions in regulatory decisions of complex toxicological endpoints - A pesticide perspective for regulatory toxicologists with a focus on machine learning models.

There are many challenges that must be overcome before in silico toxicity predictions are ripe for regulatory decision-making. Today, mandates in the United States of America and the European Union to avoid animal usage in toxicity testing is driving the need to consider alternative technologies, including Quantitative Structure Activity Relationship (QSAR) models, and read across approaches. However, when adopting new methods, it is critical that both new approach developers as well as regulatory users understand the strengths and challenges with these new approaches. In this paper, we identify potential sources of bias in machine learning methods specific to toxicity predictions, that may impact the overall performance of in silico models. We also discuss ways to mitigate these biases. Based on our experiences, the most prevalent sources of bias include class imbalance (differing numbers of "toxic" vs "nontoxic" compounds), limited numbers of chemicals within a particular chemistry, and biases within the studies that make up the database used for model building, as well as model evaluation biases. While this is already complex for repeated dose toxicity, in reproduction and developmental toxicity a further level of complexity is introduced by the need to evaluate effects on individual animal and litter basis (e.g., a hierarchal structure). We also discuss key considerations developers and regulators need to make when they use machine learning models to predict chemical safety. Our objective is for our paper to serve as a desk reference for model developers and regulators as they evaluate machine learning models and as they make decisions using these models.

2D-Quantitative structure-activity relationship modeling for risk assessment of pharmacotherapy applied during pregnancy.

The risk evaluation for pharmacological therapy during pregnancy is critical for maternal and fetal health. The initial risk assessment stage, the risk measurement, begins with pregnancy-labeling categories (A, B, C, D, and X) for pharmaceuticals defined by the US Food and Drug Administration (FDA). Recently, in silico methods have been preferred in toxicology studies to eliminate ethical issues before conducting clinical toxicology studies and animal experiments. Quantitative structure-activity relationship (QSAR) modeling is one of the in silico methodologies. The research focuses on creating a QSAR model that predicts the five FDA pregnancy categories of medications. Our dataset included 868 pharmaceuticals, containing nearly every pharmacological group collected from the FDA. 2D-molecular descriptors were calculated using PaDEL software. Twenty-four QSAR models were developed, and the best four models were discussed. The results of the models were compared according to sensitivity, accuracy, F-score, specificity, receiver operating characteristic (ROC) values, and Matthews correlation coefficient. Considering the statistical results, random forest is the best model for determining the pregnancy risk category of drugs. The accuracy of the model was 76.49% for internal and 93.58% for external validation. According to the kappa statistics, there is an average agreement of 0.583 for internal validation and a perfect agreement of 0.893 for external validation. Because the error rates of the model are very close to 0, the model is highly accurate. Consequently, our novel QSAR model gives guidance on the safe use of pharmaceuticals during pregnancy without requiring animal tests or clinical trials on pregnant women.

Predicting binding between 55 cannabinoids and 4,799 biological targets by in silico methods.

Recently, there has been an increase in cannabis-derived products being marketed as foods, dietary supplements, and other consumer products. Cannabis contains over a hundred cannabinoids, many of which have unknown physiological effects. Since there are large numbers of cannabinoids, and many are not commercially available for in vitro testing, an in silico tool (Chemotargets Clarity software) was used to predict binding between 55 cannabinoids and 4,799 biological targets (enzymes, ion channels, receptors, and transporters). This tool relied on quantitative structure activity relationships (QSAR), structural similarity, and other approaches to predict binding. From this screening, 827 cannabinoid-target binding pairs were predicted, which included 143 unique targets. Many cannabinoids sharing core structures (cannabinoid "types") had similar binding profiles, whereas most cannabinoids containing carboxylic acid groups were similar without regards to their core structure. For some of the binding predictions (43), in vitro binding data were available, and they agreed well with in silico binding data (median fourfold difference in binding concentrations). Finally, clinical adverse effects associated with 22 predicted targets were identified from an online database (Clarivate Off-X), providing important insights on potential human health hazards. Overall, in silico biological target predictions are a rapid means to identify potential hazards due to cannabinoid-target interactions, and the data can be used to prioritize subsequent in vitro and in vivo testing.

In Silico Prediction of Eye Irritation Using Hansen Solubility Parameters and Predicted pKa Values.

An in silico method has been developed that permits the binary differentiation between pure liquids causing serious eye damage or eye irritation, and pure liquids with no need for such classification, according to the UN GHS system. The method is based on the finding that the Hansen Solubility Parameters (HSP) of a liquid are collectively important predictors for eye irritation. Thus, by applying a two-tier approach in which in silico-predicted pKa values (firstly) and a trained model based solely on in silico-predicted HSP data (secondly) were used, we have developed, and validated, a fully in silico approach for predicting the outcome of a Draize test (in terms of UN GHS Cat. 1/Cat. 2A/Cat. 2B or UN GHS No Cat.) with high validation set performance (sensitivity = 0.846, specificity = 0.818, balanced accuracy = 0.832) using SMILES only. The method is applicable to pure non-ionic liquids with molecular weight below 500 g/mol, fewer than six hydrogen bond donors (e.g. nitrogen-hydrogen or oxygen-hydrogen bonds) and fewer than eleven hydrogen bond acceptors (e.g. nitrogen or oxygen atoms). Due to its fully in silico characteristics, this method can be applied to pure liquids that are still at the desktop design stage and not yet in production.

A dynamic inventory database for assessing age-, gender-, and route-specific chronic internal exposure to chemicals in support of human exposome research.

In this study, we proposed a dynamic inventory database to evaluate chronic internal exposure to chemicals at a population level, which enables users to perform modeling exercises specific to a particular chemical, route of exposure, age group, and gender. The database was built based on the steady-state solution of physiologically based kinetic (PBK) models. The biotransfer factors [BTF, the steady-state ratio between the chemical concentration in human tissues and the average daily dose (ADD) of the chemical] of 931 organic chemicals in major organs and tissues were simulated for a total of 14 population age groups for males and females. The results indicated that infants and children had the highest simulated BTFs of chemicals, and middle-aged adults had the lowest simulated BTFs. The route-specific analysis of the simulated BTFs indicated that the biotransformation half-life and octanol-water partition coefficient of chemicals had a profound impact on the BTFs. Organ- and chemical-specific results indicated that the biotransfer potential of chemicals in human bodies was primarily determined by bio-thermodynamic variables (e.g., lipid contents). In conclusion, the proposed inventory database can be conveniently used to access chronic internal exposure doses of chemicals by multiplying the route-specific ADD values for different population groups. In future studies, we recommend incorporating human biotransformation data, partition coefficients of ionizable chemicals, age-specific vulnerable indicators (e.g., the degree of maturation of immune systems), physiological variations within the same age group (e.g., intensity of daily physical activities), growth rates (i.e., the dilution effect on chemical biotransfer), and all possible target organs of carcinogenicity (e.g., bladder) into the proposed dynamic inventory database to help promote human exposome research.

Use of clinical chemistry health outcomes and PFAS chain length to predict 28-day rodent oral toxicity.

Current literature suggests PFAS carbon chain length may be a predictive variable of toxicity. If so, statistical modeling may be used to help predict toxicity, thus improving the efficiency of PFAS regulation development. Data were analyzed using one-way ANOVAs, Tukey's HSD post hoc tests, and simple linear regressions. A dataset was predicted using modeling from this data. Analysis indicated that 11 of 15 health outcomes showed significant differences in mean values. Two of 15 health outcomes were analyzed using simple linear regressions, with statistically significant results. After predictive modeling generated a theoretical dataset, unpaired t-tests comparing the results of an actual dataset indicated no significant differences among the mean values of the two health outcomes. Therefore, predictive statistical modeling may be used to predict health outcomes for PFAS exposure.

Combining phenotypic profiling and targeted RNA-Seq reveals linkages between transcriptional perturbations and chemical effects on cell morphology: Retinoic acid as an example.

The United States Environmental Protection Agency has proposed a tiered testing strategy for chemical hazard evaluation based on new approach methods (NAMs). The first tier includes in vitro profiling assays applicable to many (human) cell types, such as high-throughput transcriptomics (HTTr) and high-throughput phenotypic profiling (HTPP). The goals of this study were to: (1) harmonize the seeding density of U-2 OS human osteosarcoma cells for use in both assays; (2) compare HTTr- versus HTPP-derived potency estimates for 11 mechanistically diverse chemicals; (3) identify candidate reference chemicals for monitoring assay performance in future screens; and (4) characterize the transcriptional and phenotypic changes in detail for all-trans retinoic acid (ATRA) as a model compound known for its adverse effects on osteoblast differentiation. The results of this evaluation showed that (1) HTPP conducted at low (400 cells/well) and high (3000 cells/well) seeding densities yielded comparable potency estimates and similar phenotypic profiles for the tested chemicals; (2) HTPP and HTTr resulted in comparable potency estimates for changes in cellular morphology and gene expression, respectively; (3) three test chemicals (etoposide, ATRA, dexamethasone) produced concentration-dependent effects on cellular morphology and gene expression that were consistent with known modes-of-action, demonstrating their suitability for use as reference chemicals for monitoring assay performance; and (4) ATRA produced phenotypic changes that were highly similar to other retinoic acid receptor activators (AM580, arotinoid acid) and some retinoid X receptor activators (bexarotene, methoprene acid). This phenotype was observed concurrently with autoregulation of the RARB gene. Both effects were prevented by pre-treating U-2 OS cells with pharmacological antagonists of their respective receptors. Thus, the observed phenotype could be considered characteristic of retinoic acid pathway activation in U-2 OS cells. These findings lay the groundwork for combinatorial screening of chemicals using HTTr and HTPP to generate complementary information for the first tier of a NAM-based chemical hazard evaluation strategy.

Current trends in read-across applications for chemical risk assessments and chemical registrations in the Republic of Korea.

Read-across, an alternative approach for hazard assessment, has been widely adopted when in vivo data are unavailable for chemicals of interest. Read-across is enabled via in silico tools such as quantitative structure activity relationship (QSAR) modeling. In this study, the current status of structure activity relationship (SAR)-based read-across applications in the Republic of Korea (ROK) was examined considering both chemical risk assessments and chemical registrations from different sectors, including regulatory agencies, industry, and academia. From the regulatory perspective, the Ministry of Environment (MOE) established the Act on Registration and Evaluation of Chemicals (AREC) in 2019 to enable registrants to submit alternative data such as information from read-across instead of in vivo data to support hazard assessment and determine chemical-specific risks. Further, the Ministry of Food and Drug Safety (MFDS) began to consider read-across approaches for establishing acceptable intake (AI) limits of impurities occurring during pharmaceutical manufacturing processes under the ICH M7 guideline. Although read-across has its advantages, this approach also has limitations including (1) lack of standardized criteria for regulatory acceptance, (2) inconsistencies in the robustness of scientific evidence, and (3) deficiencies in the objective reliability of read-across data. The application and acceptance rate of read-across may vary among regulatory agencies. Therefore, sufficient data need to be prepared to verify the hypothesis that structural similarities might lead to similarities in properties of substances (between source and target chemicals) prior to adopting a read-across approach. In some cases, additional tests may be required during the registration process to clarify long-term effects on human health or the environment for certain substances that are data deficient. To improve the quality of read-across data for regulatory acceptance, cooperative efforts from regulatory agencies, academia, and industry are needed to minimize limitations of read-across applications.

Graph Attention Network Model with Defined Applicability Domains for Screening PBT Chemicals.

In silico models for screening environmentally persistent, bio-accumulative, and toxic (PBT) substances are necessary for sound management of chemicals. Due to the complex structure-activity landscapes (SALs) on the PBT attributes, previous models for screening PBT chemicals lack either applicability domain (AD) characterizations or interpretability, restricting their applications. Herein, graph attention networks (GATs), a novel neural network architecture, were introduced to construct models for screening PBT chemicals. Results show that the GAT model not only outperformed those in previous studies but also exhibited interpretability since it optimizes attention weight parameters (PAW) that indicate contributions of each atom to the PBT attributes. An AD characterization termed ADFP-AC, which considers both molecular fingerprint (FP) similarities and compounds at activity cliffs (ACs) of SALs, was proposed to describe the ADs, which further assured the performance of the GAT model. Eight previously unidentified classes of compounds were identified as PBT chemicals from the Inventory of Existing Chemical Substances in China. The GAT model together with the ADFP-AC characterization may serve as efficient tools for screening PBT chemicals, and the modeling methodology can be applied to other physicochemical, environmental, behavioral, and toxicological parameters of chemicals that are necessary for their risk assessment and management.

Potential Application of Machine-Learning-Based Quantum Chemical Methods in Environmental Chemistry.

It is an important topic in environmental sciences to understand the behavior and toxicology of chemical pollutants. Quantum chemical methodologies have served as useful tools for probing behavior and toxicology of chemical pollutants in recent decades. In recent years, machine learning (ML) techniques have brought revolutionary developments to the field of quantum chemistry, which may be beneficial for investigating environmental behavior and toxicology of chemical pollutants. However, the ML-based quantum chemical methods (ML-QCMs) have only scarcely been used in environmental chemical studies so far. To promote applications of the promising methods, this Perspective summarizes recent progress in the ML-QCMs and focuses on their potential applications in environmental chemical studies that could hardly be achieved by the conventional quantum chemical methods. Potential applications and challenges of the ML-QCMs in predicting degradation networks of chemical pollutants, searching global minima for atmospheric nanoclusters, discovering heterogeneous or photochemical transformation pathways of pollutants, as well as predicting environmentally relevant end points with wave functions as descriptors are introduced and discussed.