Computational Toxicology最新文献

{"title":"A novel deep learning framework for predicting protein-ligand interaction fingerprints from sequence data: integrating graph inductive bias transformer with Kolmogorov-Arnold networks","authors":"Lixin Lei,&nbsp;Qianjin Guo,&nbsp;Wu Liu,&nbsp;Zijun Wang,&nbsp;Kaitai Han,&nbsp;Chaojing Shi,&nbsp;Zhenxing Li,&nbsp;Sichao Lu,&nbsp;Mengqiu Wang,&nbsp;Zhiwei Zhang,&nbsp;Ruoyan Dai,&nbsp;Zhenghui Wang,&nbsp;Xingyu Liu","doi":"10.1016/j.comtox.2025.100386","DOIUrl":"10.1016/j.comtox.2025.100386","url":null,"abstract":"<div><div>Accurately modeling protein–ligand interactions is a central challenge in computational protein design and drug discovery. Traditional interaction fingerprint (IFP) approaches, while valuable, struggle to capture subtle binding features and adapt to diverse structural contexts. To address these limitations, we propose <strong>GITK</strong>, a deep learning framework that integrates a modified graph inductive bias transformer (GRIT) with Kolmogorov–Arnold networks (KANs) for interpretable interaction fingerprint prediction. GRIT introduces inductive bias to effectively represent both local and global graph structures of proteins and ligands, while KAN provides a principled functional decomposition that enhances nonlinear feature learning and interpretability. Benchmarking across multiple datasets demonstrates that GITK outperforms state-of-the-art models in binding affinity prediction, functional effect classification, and virtual screening. Moreover, GITK enables reliable selectivity analysis, successfully highlighting conformational differences and key residues in adenosine receptor subtypes, consistent with experimental findings such as the selectivity of the A1 antagonist DPCPX.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"36 ","pages":"Article 100386"},"PeriodicalIF":2.9,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling molecular level mechanisms of oxidative stress generation induced by agrochemicals in CKDu initiation","authors":"Samarawikcrama Wanni Arachchige Madushani Upamalika ,&nbsp;Champi Thusangi Wannige ,&nbsp;Sugandhima Mihirani Vidanagamachchi ,&nbsp;Don Kulasiri ,&nbsp;Mahesan Niranjan","doi":"10.1016/j.comtox.2025.100385","DOIUrl":"10.1016/j.comtox.2025.100385","url":null,"abstract":"<div><div>Oxidative stress is identified as a primary factor contributing to the failure of renal function. The excessive generation of oxidative stress is observed in CKDu patients in many experiments. Agrochemicals are identified as a major inducer of oxidative stress. Oxidative stress is induced mainly by direct generation of ROS through enzyme activation and by depleting antioxidant enzymes. To study how toxic exposure to agrochemicals alters the oxidative stress level in CKDu, a mathematical model of the body’s Redox system was developed and simulated how toxic exposure to agrochemicals, particularly arsenic toxicity, increases oxidative stress in cells. This model was employed to study how the molecular mechanisms of ROS generation are affected in CKDu. The study explores how arsenic concentration levels alter the oxidative stress levels and molecular interactions involved. The model indicates that the mitochondrial electron transport chain complex III is the primary contributor to ROS production, which needs to be validated through wet lab experiments. Sensitivity analyses on the model revealed that parameters associated with superoxide production are susceptible to perturbations. Further analysis shows that enzyme-driven reactions, especially those involving superoxide generation, catalase, and glutathione peroxidase, are crucial in governing oxidative stress generation in CKDu. According to the sensitivity analysis results, both NOX (NADPH oxidase) and SOD2 (superoxide dismutase 2) appear to be promising drug targets.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"36 ","pages":"Article 100385"},"PeriodicalIF":2.9,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational modeling of the hepatocytes reveals new insights into alterations in drug metabolism, oxidative stress response, and glutathione detoxification in acetaminophen-induced hepatotoxicity associated with MASLD","authors":"Yuki Miura ,&nbsp;Yasuyuki Sakai ,&nbsp;Masaki Nishikawa ,&nbsp;Eric Leclerc","doi":"10.1016/j.comtox.2025.100384","DOIUrl":"10.1016/j.comtox.2025.100384","url":null,"abstract":"<div><div>Metabolic dysfunction-associated steatotic liver disease (MASLD) is one of the most common liver diseases worldwide, originating from abnormal fat accumulation in the liver. Acetaminophen (APAP) is a common antipyretic, but its overdose is a leading cause of acute liver failure. Clinical studies suggest that APAP-induced hepatotoxicity can be more frequent and severe in obese patients with MASLD. To investigate this process, we have developed a new mathematical model that comprehensively incorporates lipid metabolism, APAP metabolism, and glutathione (GSH) detoxification. In MASLD patients, we found that CYP and GST activities have higher sensitivity to ROS production than UGT and SULT, which are highly effective in detoxifying APAP. We also highlighted that the upregulation of GPx poses an unanticipated risk during steatosis by inducing an increase in H₂O₂. This occurs due to a vicious circle in which increasing NAPQI adducts further elevate H₂O₂ levels. According to clinical reports, the toxicity of APAP varies depending on the progression of MASLD. We simulated that the pool of enzymatic alterations observed in steatotic patients exacerbates APAP-induced toxicity, which is thought to be due to a significant upregulation of CYP2E1. In contrast, the enzyme changes in MASH patients alleviate APAP-induced toxicity, likely due to decreased activity of CYPs and increased activity of UGT and GST. We believe that our strategy, which couples lipid and drug metabolism, offers valuable pharmacological insights for identifying enzymes that play a significant role in liver injury and for devising future therapeutic strategies in the context of MASLD.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"36 ","pages":"Article 100384"},"PeriodicalIF":2.9,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IoT integrated quantile principal component analysis based framework for toxic pesticides recognition and classification","authors":"Kanak Kumar ,&nbsp;Anshul Verma ,&nbsp;Pradeepika Verma","doi":"10.1016/j.comtox.2025.100375","DOIUrl":"10.1016/j.comtox.2025.100375","url":null,"abstract":"<div><div>Pesticides present significant concerns regarding environmental sustainability and global stability. This study investigates the types, benefits, and environmental challenges associated with pesticide use. To address these concerns, we developed an innovative Internet of Things (IoT) integrated quantile principal component analysis (QPCA) framework for the recognition of toxic pesticides in smart farming, termed IoT-TPR. The proposed IoT-TPR system is an intelligent electronic nose based on a tin-oxide sensor array, consisting of eight commercial metal–oxide–semiconductor gas sensors, which detect toxic pesticides and transmit the data to the Amazon Web Services cloud for further analysis. A two-stage QPCA preprocessing technique is employed to analyze sensor responses. Subsequently, four classifiers such as radial basis function (RBF), extreme learning machine (ELM), decision tree (DT), and k-nearest neighbor (KNN) are used for comparative performance evaluation. The results indicate that QPCA-KNN achieves the highest accuracy at 99.05%, outperforming other methods across all performance metrics and demonstrating superior classification capability. RBF (96.24%) and ELM (95.81%) also exhibit strong performance, though slightly lower than QPCA-KNN, while DT (92.35%) shows the lowest accuracy but still maintains reasonable performance. Overall, QPCA-KNN emerges as the most effective and robust classification model in this study.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"36 ","pages":"Article 100375"},"PeriodicalIF":2.9,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145098799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"“RapidTox”: A decision-support workflow to inform rapid toxicity and human health assessment","authors":"Jason C. Lambert ,&nbsp;Jason Brown ,&nbsp;Hui Gong ,&nbsp;Curtis Kilburn ,&nbsp;Jan Krysa ,&nbsp;Brad Kuntzelman ,&nbsp;Janet Lee ,&nbsp;April Luke ,&nbsp;Joshua Powell ,&nbsp;Asif Rashid ,&nbsp;James Renner ,&nbsp;Risa Sayre ,&nbsp;Jyothi Tumkur ,&nbsp;Carl F. Valone ,&nbsp;Chelsea Weitekamp ,&nbsp;Russell S. Thomas","doi":"10.1016/j.comtox.2025.100377","DOIUrl":"10.1016/j.comtox.2025.100377","url":null,"abstract":"<div><div>Regulatory bodies such as the U.S. Environmental Protection Agency are consistently faced with decisions pertaining to potential human health impacts of a diverse landscape of chemicals encountered in exposure matrices such as water, air, and soil. For legacy chemicals or those currently in commerce, decision contexts may range from emergency response to disasters where evaluation of potential threats to human health occurs on the order of hours to days, up to site- or media-specific assessment and remediation over the course of months to years. In addition, screening and prioritization of new chemicals or emerging contaminants represents an ever-present focus area for the regulatory community. A common theme across these overarching decision contexts is the need for assembling and integrating human health relevant data such as toxicity values and associated effects information. Various activities ranging from screening and prioritization to human health risk assessment of chemicals have historically been time and resource intensive, often requiring that practitioners consult and review a variety of disparate data streams to inform a given decision. In addition, many environmental chemicals are ‘data-poor’, lacking sufficient hazard data or toxicity values applicable to a given exposure scenario. In response, decision-based workflows have been developed and deployed in the RapidTox online platform wherein available toxicity values, hazard/effects data, physicochemical properties, and new approach methods-based data (e.g., read-across; cell-based bioactivity) have been assembled into data delivery modules. To date, the user interface design and expertly scoped content have been integrated in ‘screening human health assessment’ or ‘emergency response’ workflows to support decision-making.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"35 ","pages":"Article 100377"},"PeriodicalIF":2.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144932314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nanoinformatics: Emerging technology for prediction and controlling of biological performance of nanomedicines","authors":"Anjana Sharma ,&nbsp;Zubina Anjum ,&nbsp;Khalid Raza ,&nbsp;Nitin Sharma ,&nbsp;Balak Das Kurmi","doi":"10.1016/j.comtox.2025.100378","DOIUrl":"10.1016/j.comtox.2025.100378","url":null,"abstract":"<div><div>The nanoinformatics provides a platform to refine the nanotechnology approach by controlling the parameters based on the previous informations. Nanoinformatics helps the research community by leveraging sophisticated algorithms and complex computational modeling to predict the essential properties of nanomedicine and ensure their optimal biological interaction and performance. There are numerous potential roles of nanoinformatics in enhancing therapeutic value and preventing unpredictable toxicological pathways of nanomedicine. This review article delves into the pivotal applications of various computational tools to optimize the biological behavior of nanomedicine by controlling their physicochemical characteristics. This review thus offers an insight into adequately comprehending the <em>in silico</em> models such as nano-QSAR, MD simulations, CGMD and Brownian simulations to optimize nanomedicine. These tools help in product development by reducing the cost and time by controlling several biological responses of nanomedicines, including their protein interaction, mitigation, extravasation, receptor interaction and toxicological responses.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"35 ","pages":"Article 100378"},"PeriodicalIF":2.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of mathematical new approach methods to assess chemical mixtures","authors":"R. Broughton ,&nbsp;M. Feshuk ,&nbsp;Z. Stanfield ,&nbsp;K.K. Isaacs ,&nbsp;K. Paul Friedman","doi":"10.1016/j.comtox.2025.100376","DOIUrl":"10.1016/j.comtox.2025.100376","url":null,"abstract":"<div><div>The Toxicity Forecaster (ToxCast) program contains targeted bioactivity screening data for thousands of chemicals, but chemicals are often encountered as co-exposures. This work evaluated the feasibility of using single chemical ToxCast data to predict mixture bioactivity assuming chemical additivity. Twenty-one binary mixtures and their single components, inspired by consumer product chemical exposures, were screened in concentration–response using a multidimensional <em>in vitro</em> assay platform for transcription factor activity. Three models were applied to simulate mixtures’ concentration-responses: concentration addition (CA), independent action (IA), and a model that treats the mixture as the most potent single chemical component (MP). Uncertainty in the modeled and observed mixture points of departure and full concentration-responses was considered using bootstrap resampling and a Bayesian statistical framework. Approximately 80 % of the predicted mixture point of departure values were within ±0.5 on a log₁₀-micromolar scale of the observed concentrations; a majority of these predicted points of departure were protective (90–96 %), whether using CA, IA, or MP derived with the screened single components, when compared to the observed mixture. For most mixtures, ≥80 % of the observed mixture concentration–response data points fell within the modeled 95 % prediction interval, suggesting it would be difficult to observe deviations from additivity when accounting for experimental and mixtures modeling uncertainties. As it is resource-prohibitive to screen all mixtures, a case study to estimate bioactivity:exposure ratios for mixtures of per- and polyfluoroalkyl chemicals demonstrated the utility of operationalizing existing ToxCast data with mixtures modeling that includes uncertainty to predict potential risk from co-exposures.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"35 ","pages":"Article 100376"},"PeriodicalIF":2.9,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Conservative consensus QSAR approach for the prediction of rat acute oral toxicity","authors":"Jerry Achar ,&nbsp;James W. Firman ,&nbsp;Mark T.D. Cronin","doi":"10.1016/j.comtox.2025.100374","DOIUrl":"10.1016/j.comtox.2025.100374","url":null,"abstract":"<div><div>Consensus approaches are applied in different quantitative structure–activity relationship (QSAR) modeling contexts based on the assumption that combining individual model predictions will improve prediction reliability. This study evaluated the performance of TEST, CATMoS and VEGA models for prediction of oral rat LD₅₀, both individually and in consensus, across a dataset of 6,229 organic compounds. Predicted LD₅₀ values from the models were compared for each compound, and the lowest value was assigned as the output of the conservative consensus model (CCM). Predictive accuracy was then evaluated based on the agreement of predicted LD₅₀-based GHS category assignments with those derived experimentally. The aim was to allow for the most conservative value to be identified. Results showed that CCM had the highest over-prediction rate at 37 %, compared to TEST (24 %), CATMoS (25 %) and VEGA (8 %). Meanwhile, its under-prediction rate was lowest at 2 %, relative to TEST (20 %), CATMoS (10 %) and VEGA (5 %). Due to the method applied, CCM was the most conservative across all GHS categories. Further, structural analysis demonstrated that no specific chemical classes or functional groups were consistently underpredicted or overpredicted. The utility of CCM lies in its ability to establish a foundation for contextualizing the general use of consensus modeling, in order to derive health-protective oral rat LD₅₀ estimates under conditions of uncertainty, especially where experimental data are limited or absent.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"35 ","pages":"Article 100374"},"PeriodicalIF":2.9,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144879907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On the comparability between studies in predictive ecotoxicology","authors":"Christoph Schür ,&nbsp;Kristin Schirmer ,&nbsp;Marco Baity-Jesi","doi":"10.1016/j.comtox.2025.100367","DOIUrl":"10.1016/j.comtox.2025.100367","url":null,"abstract":"<div><div>Comparability across <em>in silico</em> predictive ecotoxicology studies remains a significant challenge, particularly when assessing model performance. In this work, we identify key criteria necessary for meaningful comparison between independent studies: (i) the use of identical datasets that represent the same chemical and/or taxonomic space; (ii) consistent data cleaning procedures; (iii) identical train/test splits; (iv) clearly defined evaluation metrics, as subtle differences — such as alternative formulations of <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> — can lead to misleading discrepancies; and (v) transparent reporting through code and dataset sharing. Our review of recent literature on fish acute toxicity prediction reveals a critical gap: no two studies fully meet these criteria, rendering cross-study comparisons unreliable. This lack of comparability hampers scientific progress in the field. To address this, we advocate for the adoption of benchmark datasets with standardized cleaning protocols, version control, and defined data splits. We further emphasize the importance of precise metric definitions and transparent reporting practices, including code availability and the use of structured reporting or data sheets, to foster reproducibility and advance the discipline.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"35 ","pages":"Article 100367"},"PeriodicalIF":2.9,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144866339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"In silico analyses as a tool for regulatory assessment of protein digestibility: Where are we?","authors":"Fernando Rivero-Pino,&nbsp;Caroline Idowu,&nbsp;Hannes Malfroy,&nbsp;Diana Rueda,&nbsp;Hannah Lester","doi":"10.1016/j.comtox.2025.100372","DOIUrl":"10.1016/j.comtox.2025.100372","url":null,"abstract":"<div><div><em>In silico</em> tools are emerging as a valuable resource for predicting the behaviour of proteins, not only for the assessment of toxicity and allergenicity, but also for modelling digestion to study protein digestibility. These methods offer cost-effective, high-throughput alternatives to traditional <em>in vitro</em> and <em>in vivo</em> methods. Computational models simulate enzymatic digestion, allowing the analysis of protein cleavage and peptide release. Complementary tools such as molecular docking have also been proposed as part of the <em>in silico</em> battery of tests. Given their efficiency, <em>in silico</em> approaches could ultimately be proposed to support regulated product applications, particularly in assessing protein digestibility for novel foods. However, their acceptance and use in risk assessment remains uncertain due to a lack of validation in part due to conflicting findings cited in the literature − while some studies report strong correlations between <em>in silico</em> and <em>in vitro</em> digestibility results, others indicate significant discrepancies. This review critically evaluates the potential regulatory application of <em>in silico</em> protein digestibility models for use in novel food risk assessment, highlighting key challenges such as model standardization, validation against experimental data, and the influence of protein structure and digestion conditions. Future research should focus on refining model accuracy and establishing clear validation frameworks to enhance regulatory confidence in <em>in silico</em> digestion tools.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"35 ","pages":"Article 100372"},"PeriodicalIF":2.9,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144780871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}