Selpercatinib attenuates bleomycin-induced pulmonary fibrosis by inhibiting the TGF-ß1 signaling pathway.

IPF is a chronic, progressive, interstitial lung disease with high mortality. Current drugs have limited efficacy in curbing disease progression and improving quality of life. Selpercatinib, a highly selective inhibitor of receptor tyrosine kinase RET (rearranged during transfection), was approved in 2020 for the treatment of a variety of solid tumors with RET mutations. In this study, the action and mechanism of Selpercatinib in pulmonary fibrosis were evaluated in vivo and in vitro. In vivo experiments demonstrated that Selpercatinib significantly ameliorated bleomycin (BLM)-induced pulmonary fibrosis in mice. In vitro, Selpercatinib inhibited the proliferation, migration, activation and extracellular matrix deposition of fibroblasts by inhibiting TGF-ß1/Smad and TGF-ß1/non-Smad pathway, and suppressed epithelial-mesenchymal transition (EMT) like process of lung epithelial cells via inhibiting TGF-ß1/Smad pathway. The results of in vivo pharmacological tests corroborated the results obtained from the in vitro experiments. Further studies revealed that Selpercatinib inhibited abnormal phenotypes of lung fibroblasts and epithelial cells in part by regulating its target RET. In short, Selpercatinib inhibited the activation of fibroblasts and EMT-like process of lung epithelial cells by inhibiting TGF-ß1/Smad and TGF-ß1/non-Smad pathways, thus alleviating BLM-induced pulmonary fibrosis in mice.

Advances in the Experiments of Leaching in Cement-Based Materials and Dissolution in Rocks.

Leaching in cement-based materials and dissolution in rocks are important problems in civil engineering. In the past century, concrete damage caused by leaching have occurred worldwide. And, rock dissolution is usually the main cause of karst rock erosions. This paper provides a review of the causes, influencing factors, and effects on engineering properties of dissolution of rocks and leaching of cement-based materials. The applied experimental methods for leaching and dissolution have been sorted out and discussed. In situ field experiments can be used to study dissolution under natural conditions, while the laboratory experiments can effectively shorten the experiment time length (by changing pH, temperature, pressure or other factors that affect the leaching or dissolution) to quickly investigate the mechanism of dissolution and leaching. Micro tests including XRD, SEM, EDS, and other testing methods can obtain the changes in material properties and microstructures under leaching and dissolution. In addition, with the advances in technologies and updated instruments, more and more new testing methods are being used. The factors affecting the leaching and dissolution include environmental factors, materials, and solvent parameters. The mechanisms and deterioration processes of leaching and dissolution varies according to the types of material and the compositions.

A bibliometric systematic review of extracellular vesicles in eye diseases from 2003 to 2022.

BACKGROUND: Extracellular vesicles (EVs) have emerged as a valuable and promising research field in eye diseases. However, there are few bibliometric studies in this area. The purpose of this study was to employ bibliometric analysis to visualize the research hotspots and trends of EVs in eye diseases and provide researchers with new perspectives for further studies. METHODS: Articles and reviews on EVs in eye diseases published between January 1, 2003 and December 31, 2022 were retrieved from the Web of Science Core Collection. Qualitative and quantitative analysis was performed using Microsoft Excel and CiteSpace software. RESULTS: In total, 790 articles were included in the analysis. Over the past 2 decades, there has been a significant increase in the number of publications on the study of EVs in eye diseases. The United States, China, and Italy made the most significant contributions to this field. The Chinese Academy of Sciences was the most productive institution, and International Journal of Molecular Sciences published the most number of articles. Proceedings of the National Academy of Sciences of the United States of America had the highest citation frequency. Beit-Yannai E had the highest output and Thery C had the highest average citation frequency among authors. The analysis of keywords revealed that the neuroprotective effects of stem cell-derived EVs and biomarkers of eye diseases are current research hotspots and frontiers in this field. CONCLUSION: This study provides a scientific perspective on EVs in eye diseases and provides valuable information for researchers to detect current research conditions, hotspots, and emerging trends for further study.

Baricitinib Attenuates Bleomycin-Induced Pulmonary Fibrosis in Mice by Inhibiting TGF-ß1 Signaling Pathway.

Idiopathic pulmonary fibrosis (IPF) is a chronic progressive interstitial lung disease with unknown etiology, high mortality and limited treatment options. It is characterized by myofibroblast proliferation and extensive deposition of extracellular matrix (ECM), which will lead to fibrous proliferation and the destruction of lung structure. Transforming growth factor-ß1 (TGF-ß1) is widely recognized as a central pathway of pulmonary fibrosis, and the suppression of TGF-ß1 or the TGF-ß1-regulated signaling pathway may thus offer potential antifibrotic therapies. JAK-STAT is a downstream signaling pathway regulated by TGF-ß1. JAK1/2 inhibitor baricitinib is a marketed drug for the treatment of rheumatoid arthritis, but its role in pulmonary fibrosis has not been reported. This study explored the potential effect and mechanism of baricitinib on pulmonary fibrosis in vivo and in vitro. The in vivo studies have shown that baricitinib can effectively attenuate bleomycin (BLM)-induced pulmonary fibrosis, and in vitro studies showed that baricitinib attenuates TGF-ß1-induced fibroblast activation and epithelial cell injury by inhibiting TGF-ß1/non-Smad and TGF-ß1/JAK/STAT signaling pathways, respectively. In conclusion, baricitinib, a JAK1/2 inhibitor, impedes myofibroblast activation and epithelial injury via targeting the TGF-ß1 signaling pathway and reduces BLM-induced pulmonary fibrosis in mice.

Antifibrotic mechanism of avitinib in bleomycin-induced pulmonary fibrosis in mice.

Idiopathic pulmonary fibrosis (IPF) is a chronic, progressive interstitial lung disease characterized by alveolar epithelial cell injury and lung fibroblast overactivation. At present, only two drugs are approved by the FDA for the treatment of IPF, including the synthetic pyridinone drug, pirfenidone, and the tyrosine kinase inhibitor, nintedanib. Avitinib (AVB) is a novel oral and potent third-generation tyrosine kinase inhibitor for treating non-small cell lung cancer (NSCLC). However, the role of avitinib in pulmonary fibrosis has not yet been established. In the present study, we used in vivo and in vitro models to evaluate the role of avitinib in pulmonary fibrosis. In vivo experiments first verified that avitinib significantly alleviated bleomycin-induced pulmonary fibrosis in mice. Further in vitro molecular studies indicated that avitinib inhibited myofibroblast activation, migration and extracellular matrix (ECM) production in NIH-3T3 cells, mainly by inhibiting the TGF-ß1/Smad3 signalling pathways. The cellular experiments also indicated that avitinib improved alveolar epithelial cell injury in A549 cells. In conclusion, the present findings demonstrated that avitinib attenuates bleomycin-induced pulmonary fibrosis in mice by inhibiting alveolar epithelial cell injury and myofibroblast activation.

Investigation of changes in proteomes of beef exudate and meat quality attributes during wet-aging.

This study was performed to evaluate the effects of wet-aging (3, 7, 14, 21, and 28 d at 2 °C) on beef (longissimus lumborum muscles) exudate proteome and meat quality changes. The pH, purge loss, and tenderness of beef increased with aging (P < 0.05), while color and lipid oxidative stabilities decreased, especially when long-term (14 and 21 d) aged meat were repackaged and displayed under retail condition (P < 0.05). Nineteen proteins changed significantly with aging (FDR < 0.05), in which most of them progressively accumulated in exudates over aging periods. Combined with partial least squares discriminant analysis, 16 proteins (including 9 structural proteins, 3 metabolic enzymes, 1 heat shock protein, 2 binding proteins, and KBTBD10 protein) were screened as characteristic proteins that could be used for potential meat quality indication. These findings offered novel insight into the utilization of exudates for meat quality assessment.

What affects musculoskeletal risk in nursing assistants and orderlies?

BACKGROUND: There are many musculoskeletal disorders in staff members at health centres, given the specific characteristics of their work. OBJECTIVE: The objective was to analyse the postural risk of patient handling tasks performed by nursing assistants and orderlies, as well as task factors, individual or organisational, that may be associated with increased postural risk. METHOD: This is a cross-sectional observational study. Analysis was done on 170 postures in five different tasks performed by 39 participants at three hospitals in Andalusia (Spain). The questionnaires collected sociodemographic variables, the task done, and REBA were used for assessment of postural risk. RESULTS: Overall the average REBA score was 9.0±2.4. Moving the patient to the head of the bed was the task with the highest risk (9.8). Handling involving more than two participants at once increased postural risk. Using mechanical aids were associated with high risk in the legs. Logistic regression analyses showed that age, stature, and not having adjustable beds available were associated with postural risk (p < 0.05). CONCLUSION: Health centre staff perform many tasks with high musculoskeletal disorder risk. Age, stature of the participants, and adjustment of bed height were associated with postural risk.

Visible-Light-Induced Palladium-Catalyzed Cross-Coupling of Iodocarboranes with (Hetero)Arenes.

This work describes a general method for the efficient production of a class of cage B-centered carboranyl radicals at the B3, B4, and B9 sites via a visible-light-promoted palladium(0)/palladium(I) pathway using readily available iodo-o-carboranes as the starting materials. The electrophilicities of these hypervalent boron-centered radicals decrease in the following order: B3 > B4 > B9. They are useful intermediates for the preparation of a family of cage B-(hetero)arylated o-carboranes at ambient temperature.

Zanubrutinib attenuates bleomycin-induced pulmonary fibrosis by inhibiting the TGF-ß1 signaling pathway.

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a chronic, progressive and fatal interstitial lung disease with high mortality and limited treatment. Only two drugs are currently approved for the treatment of IPF, but both have limitations and neither drug could prolong survival time of patients. The etiology of IPF is unclear, but there is growing evidence that B cells and B cell receptor signaling play important roles in the pathogenesis of IPF. Zanubrutinib is a small molecule inhibitor of Bruton's tyrosine kinase (BTK), which is a key enzyme downstream of B cell receptor signaling pathway, has approved for the treatment of mantle cell lymphoma (MCL) and chronic lymphocytic leukemia (CLL)/small lymphocytic lymphoma (SLL). While its role in pulmonary fibrosis remains unknown. In this study, we explored the potential effect and mechanisms of zanubrutinib on pulmonary fibrosis in vivo and in vitro. METHODS: In the in vivo experiments, different doses of zanubrutinib were administered in a mouse model of bleomycin-induced pulmonary fibrosis, and pathological manifestations and lung function indices were evaluated. In vitro experiments were performed using TGF-ß1-stimulated fibroblasts to evaluate the effect of zanubrutinib on the activation and autophagy phenotype of fibroblasts and to explore the underlying signaling pathway mechanism. RESULTS: In vivo experiments demonstrated that zanubrutinib effectively attenuated bleomycin (BLM)-induced pulmonary fibrosis in mice. An in vitro mechanistic study indicated that zanubrutinib suppresses collagen deposition and myofibroblast activation by inhibiting the TGF-ß1/Smad pathway and induces autophagy through the TGF-ß1/mTOR pathway. CONCLUSIONS: Zanubrutinib alleviated bleomycin-induced lung fibrosis in mice by inhibiting the TGF-ß1 signaling pathway.

Zanubrutinib ameliorates lipopolysaccharide-induced acute lung injury via regulating macrophage polarization.

Acute lung injury (ALI) is a disease characterized by pulmonary diffusion dysfunction and its exacerbation stage is acute respiratory distress syndrome (ARDS), which may develop to multiple organ failure and seriously threatens human health. ALI has high mortality rates and few effective treatments, thus effective protection measures for ALI are becoming increasingly important. Macrophages play a key regulatory role in the pathogenesis of ALI, and the degree of macrophage polarization is closely related to the severity and prognosis of ALI. In this study, we evaluated the effects of Zanubrutinib (ZB), a BTK small molecule inhibitor approved by the FDA for the treatment of cell lymphoma, on macrophage polarization and acute lung injury. In the in vivo study, we constructed a mouse model of Lipopolysaccharide (LPS)-induced acute lung injury and found that ZB could improve the acute injury of mouse lungs by inhibiting the secretion of proinflammatory factors and promoting the secretion of anti-inflammatory factors, reduce the number of inflammatory cells in alveolar lavage fluid, and then alleviate the inflammatory response. In vivo and in vitro studies have shown that ZB could inhibit the M1 macrophage polarization and promote the M2 macrophage polarization. Subsequent mechanistic studies revealed that ZB could inhibit the macrophage M1 polarization via targeting BTK activation and inhibiting JAK2/STAT1 and TLR4/MyD88/NF-κB signaling pathways, and promote the macrophage M2 polarization by promoting the activation of STAT6 and PI3K / Akt signaling pathways. In summary, ZB has shown therapeutic effect in LPS-induced acute lung injury in mice, which provides a potential candidate drug to treat acute lung injury.

Traditional Chinese Medicine Injections for Diabetic Retinopathy: A Systematic Review and Network Meta-Analysis of Randomized Controlled Trials.

Background: The aim of this study was to compare the efficacy of different injected Traditional Chinese Medicines in the treatment of diabetic retinopathy (DR) and to provide a reference for the selection of adjuvant therapy for DR. Content: Related literature in multiple biological databases and websites was searched up to April 15, 2022, without language and publication time restrictions. A Bayesian network meta-analysis was used to analyze the included studies. Summary: Compared with conventional treatment, the combined use of injected Traditional Chinese Medicines, including astragalus, danhong, Ginkgo biloba extract powder, ginkgo leaf extract and dipyridamole (GLED), ligustrazine (LIG), mailuoning, puerarin, safflower, shuxuetong, safflower yellow sodium chloride, and xueshuantong (XST), can significantly improve the clinical effectiveness in patients with DR, while LIG, XST, and GLED can improve vision. The strength of the evidence ranged from high to very low. Outlook: In patients with DR, the combination of multiple injected Traditional Chinese Medicines is more effective than conventional treatment; some of these medicines may also improve visual acuity. This study may provide a good resource and reference for the selection of adjuvant therapy for DR.

Relationship between maternal heavy metal exposure and congenital heart defects: a systematic review and meta-analysis.

Congenital heart defects (CHDs) are one of the major causes of death in infants and young children, and heavy metal exposure during pregnancy is one of the possible risk factors. However, the effect of heavy metal exposure on CHDs is still controversial. We searched English (PubMed, Web of Science) and Chinese (CNKI and WanFang database) databases for relevant articles. The summarized effect sizes and 95% confidence intervals (CIs) were calculated by pooling estimates using the random-effects model. Egger's test was used to estimate publication bias. Heterogeneity among studies was indicated by p-values and I2. Finally, we conducted subgroup analyses to elucidate the causes of heterogeneity. Thirteen studies were included in this meta-analysis. A positive association between maternal exposure to heavy metals and CHDs was found. Pooling odds ratios (ORs) for arsenic, cadmium, mercury, and lead were 2.12, 1.30, 1.22, and 2.30, respectively for total CHDs. Regarding CHD subtypes, arsenic was associated with an increased risk of septal defects (OR: 1.82), barium with left ventricular outflow tract obstruction (LVOTO) (OR: 1.15) and septal defects (OR: 1.21), and lead with conotruncal defects (OR: 2.34) and LVOTO (OR: 1.93). A heterogeneous relationship was found between studies using different methods of measurement, which were mainly due to differences in actual exposure levels to heavy metals. This meta-analysis suggests significant associations between arsenic, cadmium, mercury, and lead exposure during pregnancy and an increased risk of specific CHDs in offspring. These findings underscore the importance of heavy metal exposure during pregnancy in the risk of CHDs in offspring.

De Novo design of potential inhibitors against SARS-CoV-2 Mpro.

The impact of the ravages of COVID-19 on people's lives is obvious, and the development of novel potential inhibitors against SARS-CoV-2 main protease (Mpro), which has been validated as a potential target for drug design, is urgently needed. This study developed a model named MproI-GEN, which can be used for the de novo design of potential Mpro inhibitors (MproIs) based on deep learning. The model was mainly composed of long-short term memory modules, and the last layer was re-trained with transfer learning. The validity (0.9248), novelty (0.9668), and uniqueness (0.0652) of the designed potential MproI library (PMproIL) were evaluated, and the results showed that MproI-GEN could be used to design structurally novel and reasonable molecules. Additionally, PMproIL was filtered based on machine learning models and molecular docking. After filtering, the potential MproIs were verified with molecular dynamics simulations to evaluate the binding stability levels of these MproIs and SARS-CoV-2 Mpro, thereby illustrating the inhibitory effects of the potential MproIs against Mpro. Two potential MproIs were proposed in this study. This study provides not only new possibilities for the development of COVID-19 drugs but also a complete pipeline for the discovery of novel lead compounds.

Visible-Light-Promoted Nickel-Catalyzed Cross-Coupling of Iodocarboranes with (Hetero)Arenes via Boron-Centered Carboranyl Radicals.

A general strategy for the generation of hypervalent boron-centered carboranyl radicals at the B(3), B(4), and B(9) positions has been developed for the first time via visible-light-promoted iodine atom abstraction from iodo-o-carboranes by low-valent nickel complex. These radicals react with various (hetero)arenes to afford a wide range of cage B-arylated carborane derivatives at room temperature in very good to excellent yields with a broad substrate scope. Their electrophilicities are dependent on the vertex charges of the cage and follow the order B(3) > B(4) > B(9). Both visible light and nickel catalyst are proved critical to the generation of boron-centered carboranyl radicals. The involvement of boron radicals is supported by control experiments. A reaction mechanism associated with these reactions is also proposed. This strategy offers a new protocol for the generation of boron-centered carboranyl radicals at the selected boron vertex, leading to a facile synthesis of a large class of cage boron substituted carborane molecules.

Cabozantinib ameliorates lipopolysaccharide-induced lung inflammation and bleomycin--induced early pulmonary fibrosis in mice.

The lung, as the primary organ for gas exchange in mammals, is the main target organ for many pathogens and allergens, which may cause acute lung injury. A certain proportion of acute lung injury may progress into irreversible pulmonary fibrosis. Both acute lung injury and pulmonary fibrosis have high mortality rates and few effective treatments. Cabozantinib is a multi-target small molecule tyrosine kinase inhibitor and has been approved for the treatment of multiple malignant solid tumors. In this study, we explored the role of cabozantinib in acute lung injury and pulmonary fibrosis in vivo and in vitro. In the lipopolysaccharide and bleomycin induced mouse lung injury models, cabozantinib significantly improved the pathological state and reduced the infiltration of inflammatory cells in the lung tissues. In the bleomycin induced pulmonary fibrosis model, cabozantinib significantly reduced the area of pulmonary fibrosis and improved lung function in mice. The results of in vitro studies showed that cabozantinib could inhibit the inflammatory response and apoptosis of alveolar epithelial cells by inhibiting the activation of TLR4/NF-κB and NLRP3 inflammasome pathways. At the same time, cabozantinib could inhibit the activation of lung fibroblasts through suppressing the TGF-ß1/Smad pathway, and promote the apoptosis of fibroblasts. In summary, cabozantinib could alleviate lung injury through regulating the TLR4 /NF-κB/NLRP3 inflammasome pathway, and alleviate pulmonary fibrosis by inhibiting the TGF-ß1/Smad3 signaling pathway.

TSSF-hERG: A machine-learning-based hERG potassium channel-specific scoring function for chemical cardiotoxicity prediction.

The human ether-à-go-go-related gene (hERG) encodes the Kv11.1 voltage-gated potassium ion (K+) channel that conducts the rapidly activating delayed rectifier current (IKr) in cardiomyocytes to regulate the repolarization process. Some drugs, as blockers of hERG potassium channels, cannot be marketed due to prolonged QT intervals, as well known as cardiotoxicity. Predetermining the binding affinity values between drugs and hERG through in silico methods can greatly reduce the time and cost required for experimental verification. In this study, we collected 9,215 compounds with AutoDock Vina's docking structures as training set, and collected compounds from four references as test sets. A series of models for predicting the binding affinities of hERG blockers were built based on five machine learning algorithms and combinations of interaction features and ligand features. The model built by support vector regression (SVR) using the combination of all features achieved the best performance on both tenfold cross-validation and external verification, which was selected and named as TSSF-hERG (target-specific scoring function for hERG). TSSF-hERG is more accurate than the classic scoring function of AutoDock Vina and the machine-learning-based generic scoring function RF-Score, with a Pearson's correlation coefficient (Rp) of 0.765, a Spearman's rank correlation coefficient (Rs) of 0.757, a root-mean-square error (RMSE) of 0.585 in a tenfold cross-validation study. All results demonstrated that TSSF-hERG would be useful for improving the power of binding affinity prediction between hERG and compounds, which can be further used for prediction or virtual screening of the hERG-related cardiotoxicity of drug candidates.

Protective Effect of Remdesivir Against Pulmonary Fibrosis in Mice.

Pulmonary fibrosis is a known sequela of severe or persistent lung damage. Existing clinical, imaging and autopsy studies have shown that the lungs exhibit a pathological pulmonary fibrosis phenotype after infection with coronaviruses, including severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Pulmonary fibrosis may be one of the most serious sequelae associated with coronavirus disease 2019 (COVID-19). In this study, we aimed to examine the preventative effects of the antiviral drug remdesivir on pulmonary fibrosis. We used a mouse model of bleomycin-induced pulmonary fibrosis to evaluate the effects of remdesivir on pulmonary fibrosis in vivo and further explored the potential pharmacological mechanisms of remdesivir in lung fibroblasts and alveolar epithelial cells in vitro. The preventive remdesivir treatment was started on the day of bleomycin installation, and the results showed that remdesivir significantly alleviated bleomycin-induced collagen deposition and improved pulmonary function. In vitro experiments showed that remdesivir dose-dependently suppressed TGF-ß1-induced lung fibroblast activation and improved TGF-ß1-induced alveolar epithelial to mesenchymal transition. Our results indicate that remdesivir can preventatively alleviate the severity of pulmonary fibrosis and provide some reference for the prevention of pulmonary fibrosis in patients with COVID-19.

A building information modeling-based tool for estimating building demolition waste and evaluating its environmental impacts.

The amount of building demolition waste produced in China is large, and waste treatment processes discharge many pollutants. Pre-evaluating waste's environmental damage at the design stage of building projects could provide an opportunity to understand and minimize potential environmental impacts. Tools that can conveniently estimate the amount of demolition waste and quantify its impacts are lacking. This study combines building information modeling (BIM), geographic information system (GIS), and life cycle assessment (LCA) to develop an estimation and evaluation system for building demolition waste. In this system, BIM digitizes the specific characteristics of the evaluated buildings and provides geometric and semantic information for waste estimation. GIS offers geographic information regarding waste treatment plants and landfill site, and is used to design waste transportation routes. LCA provides an environmental impact assessment framework and quantifies ecological damage impacts and resource depletion impacts due to demolition waste. The system includes five modules, which form the basis of an automated calculation tool. The evaluation tool can quickly quantify the amount of waste and assess its impacts, while achieving automated waste estimation and impact evaluation after a building is designed. A building in a middle school is taken as a case study to demonstrate and verify the system. This study provides an operable tool for waste evaluation and management at the design stage. With the increasing application of BIM technology in the construction industry, this tool is expected to gain popularity and promote efficient waste management.

Prediction of the Blood-Brain Barrier (BBB) Permeability of Chemicals Based on Machine-Learning and Ensemble Methods.

The ability of chemicals to enter the blood-brain barrier (BBB) is a key factor for central nervous system (CNS) drug development. Although many models for BBB permeability prediction have been developed, they have insufficient accuracy (ACC) and sensitivity (SEN). To improve performance, ensemble models were built to predict the BBB permeability of compounds. In this study, in silico ensemble-learning models were developed using 3 machine-learning algorithms and 9 molecular fingerprints from 1757 chemicals (integrated from 2 published data sets) to predict BBB permeability. The best prediction performance of the base classifier models was achieved by a prediction model based on an random forest (RF) and a MACCS molecular fingerprint with an ACC of 0.910, an area under the receiver-operating characteristic (ROC) curve (AUC) of 0.957, a SEN of 0.927, and a specificity of 0.867 in 5-fold cross-validation. The prediction performance of the ensemble models is better than that of most of the base classifiers. The final ensemble model has also demonstrated good accuracy for an external validation and can be used for the early screening of CNS drugs.

MutagenPred-GCNNs: A Graph Convolutional Neural Network-Based Classification Model for Mutagenicity Prediction with Data-Driven Molecular Fingerprints.

An important task in the early stage of drug discovery is the identification of mutagenic compounds. Mutagenicity prediction models that can interpret relationships between toxicological endpoints and compound structures are especially favorable. In this research, we used an advanced graph convolutional neural network (GCNN) architecture to identify the molecular representation and develop predictive models based on these representations. The predictive model based on features extracted by GCNNs can not only predict the mutagenicity of compounds but also identify the structure alerts in compounds. In fivefold cross-validation and external validation, the highest area under the curve was 0.8782 and 0.8382, respectively; the highest accuracy (Q) was 80.98% and 76.63%, respectively; the highest sensitivity was 83.27% and 78.92%, respectively; and the highest specificity was 78.83% and 76.32%, respectively. Additionally, our model also identified some toxicophores, such as aromatic nitro, three-membered heterocycles, quinones, and nitrogen and sulfur mustard. These results indicate that GCNNs could learn the features of mutagens effectively. In summary, we developed a mutagenicity classification model with high predictive performance and interpretability based on a data-driven molecular representation trained through GCNNs.