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.

A continuous challenge in nanotoxicology is the interaction of nanoparticles with the soil components. In the present study, we compare the toxicity of silver nanoparticles (AgNM300K) on earthworms across 4 different soils, exploring which among the total-, soil solution-, or worm tissue-Ag-concentrations that enables the best prediction of toxicity across the soils. We exposed the earthworm Eisenia fetida to AgNM300K for 56 days to assess survival, reproduction, and bioaccumulation. These endpoints were related to measurements of Ag-ions and -nanoparticles in soil, soil solution, and in the worm tissue. Tested soils included the standard OECD, LUFA 2.2, Hygum, and RefSol 01A soils. Toxicity was strongly dependent on the soil type, highly correlated with the organic matter, clay, and Cation Exchange Capacity (CEC). CEC provided the best correlation with the internal silver concentrations across the soils. The soil solution did not provide useful predictions across the soils.

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.

Drug-induced liver injury (DILI) has been significant challenge in drug discovery, often leading to clinical trial failures and necessitating drug withdrawals. The existing suite of in vitro proxy-DILI assays is generally effective at identifying compounds with hepatotoxicity. However, there is considerable interest in enhancing in silico prediction of DILI because it allows for the evaluation of large sets of compounds more quickly and cost-effectively, particularly in the early stages of projects. In this study, we aim to study ML models for DILI prediction that first predicts nine proxy-DILI labels and then uses them as features in addition to chemical structural features to predict DILI. The features include in vitro (e.g., mitochondrial toxicity, bile salt export pump inhibition) data, in vivo (e.g., preclinical rat hepatotoxicity studies) data, pharmacokinetic parameters of maximum concentration, structural fingerprints, and physicochemical parameters. We trained DILI-prediction models on 888 compounds from the DILIst dataset and tested on a held-out external test set of 223 compounds from DILIst dataset. The best model, DILIPredictor, attained an AUC-ROC of 0.79. This model enabled the detection of top 25 toxic compounds compared to models using only structural features (2.68 LR+ score). Using feature interpretation from DILIPredictor, we were able to identify the chemical substructures causing DILI as well as differentiate cases DILI is caused by compounds in animals but not in humans. For example, DILIPredictor correctly recognized 2-butoxyethanol as non-toxic in humans despite its hepatotoxicity in mice models. Overall, the DILIPredictor model improves the detection of compounds causing DILI with an improved differentiation between animal and human sensitivity as well as the potential for mechanism evaluation. DILIPredictor is publicly available at https://broad.io/DILIPredictor for use via web interface and with all code available for download and local implementation via https://pypi.org/project/dilipred/.

Surfactants as synergistic agents are necessary to improve the stability and utilization of pesticides, while their use is often accompanied by unexpected release into the environment. However, there are no efficient strategies available for screening low-toxicity surfactants, and traditional toxicity studies rely on extensive experimentation which are not predictive. Herein, a commonly used agricultural adjuvant Triton X (TX) series was selected to study the function of amphipathic structure to their toxicity in zebrafish. Molecular dynamics (MD) simulations, transcriptomics, metabolomics and machine learning (ML) were used to study the toxic effects and predict the toxicity of various TX. The results showed that TX with a relatively short hydrophilic chain was highly toxic to zebrafish with LC50 of 1.526 mg/L. However, TX with a longer hydrophilic chain was more likely to damage the heart, liver and gonads of zebrafish through the arachidonic acid metabolic network, suggesting that the effect of surfactants on membrane permeability is the key to determine toxic results. Moreover, biomarkers were screened through machine learning, and other hydrophilic chain lengths were predicted to affect zebrafish heart health potentially. Our study provides an advanced adjuvants screening method to improve the bioavailability of pesticides while reducing environmental impacts.

This study addresses the need for accurate structural data regarding the toxicity of fragrances in sanitizers and disinfectants. We compare the predictive and descriptive (model stability) potential of multiple linear regression (MLR) and partial least squares (PLS) models optimized through variable selection (VS). A novel hybrid chaotic neural network algorithm with competitive learning (CCLNNA)-PLS modeling strategy can offer specific optimization with satisfactory results, even for a limited dataset. While also exploring the preliminary comparative analysis, the goal is to introduce an adapted novel CCLNNA optimization strategy for VS, inspired by neural networks, along with exploring the influence of the percentage of significant descriptors in the optimization function to enhance the final model\'s capabilities. We analyzed an available dataset of 24 molecules, incorporating ADMET and PaDEL descriptors as predictor variables, to explore the relationship between the response/target variable (pLC50) and the meticulously optimized set of descriptors. The suitability of the selected PLS models (cross- and external-validated accuracy combined with percentage of significant descriptors at a level equal to or >80 %) underscores the importance of expanding the dataset to amplify the validation protocols, thus enhancing future model reliability and environmental impact.

Decachlorobiphenyl (PCB-209) can be widely detected in suspended particles and sediments due to its large hydrophobicity, and some of its transformation products may potentially threaten organisms through the food chain. Here we investigate the photochemical transformation of PCB-209 on suspended particles from the Yellow River. It was found that the suspended particles had an obvious shielding effect to largely inhibit the photodegradation of PCB-209. Meanwhile, the presence of inorganic ions (e.g. Mg2+ and NO3-) and organic matters (e.g. humic acid, HA) in the Yellow River water inhibited the reaction. The main transformation products of PCB-209 were lower-chlorinated and hydroxylated polychlorinated biphenyls (OH-PCBs), and small amounts of pentachlorophenol (PCP) and polychlorinated dibenzofurans (PCDFs) were also observed. The mechanisms of PCP formation by double •OH attacking carbon bridge and PCDFs formation by elimination reaction of ionic state OH-PCBs were proposed using theoretical calculations, which provided some new insights into the inter-transformations between persistent organic pollutants. In combination with VEGA and EPI Suite software, some intermediates such as PCDFs were more toxic to organisms than PCB-209. This study deepens the understanding of the transformation behavior of PCB-209 on suspended particles under sunlight.

Black phosphorus nanosheets (BPNs)/CdS heterostructure was successfully synthesized via hydrothermal method. The experimental results indicated that BPNs modified the surface of CdS nanoparticles uniformly. Meanwhile, the BPNs/CdS heterostructure exhibited a distinguished high rate of photocatalytic activity for Tetrabromobisphenol A (TBBPA) degradation under visible light irradiation (λ > 420 nm), the kinetic constant of TBBPA degradation reached 0.0261 min-1 was approximately 5.68 and 9.67 times higher than that of CdS and P25, respectively. Moreover, superoxide radical (•O2-) is the main active component in the degradation process of TBBPA (the relative contribution is 91.57%). The photocatalytic mechanism and intermediates of the TBBPA was clarified, and a suitable model and pathway for the degradation of TBBPA were proposed. The results indicated that the toxicities of some intermediates were higher than the parent pollutant. This research provided an efficient approach by a novel photocatalyst for the removal of TBBPA from wastewater, and the appraisal methods for the latent risks from the intermediates were reported in this paper.

This research delves into the exploration of the potential of tocopherol-based nanoemulsion as a therapeutic agent for cardiovascular diseases (CVD) through an in-depth molecular docking analysis. The study focuses on elucidating the molecular interactions between tocopherol and seven key proteins (1O8a, 4YAY, 4DLI, 1HW9, 2YCW, 1BO9 and 1CX2) that play pivotal roles in CVD development. Through rigorous in silico docking investigations, assessment was conducted on the binding affinities, inhibitory potentials and interaction patterns of tocopherol with these target proteins. The findings revealed significant interactions, particularly with 4YAY, displaying a robust binding energy of -6.39 kcal/mol and a promising Ki value of 20.84 μM. Notable interactions were also observed with 1HW9, 4DLI, 2YCW and 1CX2, further indicating tocopherol\'s potential therapeutic relevance. In contrast, no interaction was observed with 1BO9. Furthermore, an examination of the common residues of 4YAY bound to tocopherol was carried out, highlighting key intermolecular hydrophobic bonds that contribute to the interaction\'s stability. Tocopherol complies with pharmacokinetics (Lipinski\'s and Veber\'s) rules for oral bioavailability and proves safety non-toxic and non-carcinogenic. Thus, deep learning-based protein language models ESM1-b and ProtT5 were leveraged for input encodings to predict interaction sites between the 4YAY protein and tocopherol. Hence, highly accurate predictions of these critical protein-ligand interactions were achieved. This study not only advances the understanding of these interactions but also highlights deep learning\'s immense potential in molecular biology and drug discovery. It underscores tocopherol\'s promise as a cardiovascular disease management candidate, shedding light on its molecular interactions and compatibility with biomolecule-like characteristics.

Drug-induced liver injury (DILI) is one of the major concerns during drug development. Wide acceptance of the 3 R principles and the innovation of in-vitro techniques have introduced various novel model options, among which the three-dimensional (3D) cell spheroid cultures have shown a promising prospect in DILI prediction. The present study developed a 3D quadruple cell co-culture liver spheroid model for DILI prediction via self-assembly. Induction by phorbol 12-myristate 13-acetate at the concentration of 15.42 ng/mL for 48 hours with a following 24-hour rest period was used for THP-1 cell differentiation, resulting in credible macrophagic phenotypes. HepG2 cells, PUMC-HUVEC-T1 cells, THP-1-originated macrophages, and human hepatic stellate cells were selected as the components, which exhibited adaptability in the designated spheroid culture conditions. Following establishment, the characterization demonstrated the competence of the model in long-term stability reflected by the maintenance of morphology, viability, cellular integration, and cell-cell junctions for at least six days, as well as the reliable liver-specific functions including superior albumin and urea secretion, improved drug metabolic enzyme expression and CYP3A4 activity, and the expression of MRP2, BSEP, and P-GP accompanied by the bile acid efflux transport function. In the comparative testing using 22 DILI-positive and 5 DILI-negative compounds among the novel 3D co-culture model, 3D HepG2 spheroids, and 2D HepG2 monolayers, the 3D culture method significantly enhanced the model sensitivity to compound cytotoxicity compared to the 2D form. The novel co-culture liver spheroid model exhibited higher overall predictive power with margin of safety as the classifying tool. In addition, the non-parenchymal cell components could amplify the toxicity of isoniazid in the 3D model, suggesting their potential mediating role in immune-mediated toxicity. The proof-of-concept experiments demonstrated the capability of the model in replicating drug-induced lipid dysregulation, bile acid efflux inhibition, and α-SMA upregulation, which are the key features of liver steatosis and phospholipidosis, cholestasis, and fibrosis, respectively. Overall, the novel 3D quadruple cell co-culture spheroid model is a reliable and readily available option for DILI prediction.