Computational Toxicology最新文献

AI-assisted QSAR framework for ecological risk assessment of pharmaceuticals: integrating experimental, mechanistic, and deep learning evidence 人工智能辅助的药品生态风险评估QSAR框架：整合实验、机制和深度学习证据

IF 2.9 Q2 TOXICOLOGY

Computational Toxicology

Pub Date : 2026-01-16 DOI: 10.1016/j.comtox.2026.100403

Vinicius Roveri , Alberto Teodorico Correia , Piter Gil dos Santos , Marcela Nascimento Ferreira Povoas , Walber Toma , Camilo Dias Seabra Pereira , Luciana Lopes Guimarães

Pharmaceutically active compounds (PhACs) are emerging pollutants of concern due to their bioactivity and potential to disrupt aquatic ecosystems. Although extensively studied in Europe and North America, knowledge of their occurrence and risks in Latin America and the Caribbean (LAC) remains limited. This study builds upon the harmonized dataset published by our group [1], which compiled and systematized 154 peer-reviewed studies addressing the presence of PhACs in LAC aquatic environments between 1990 and 2024, and pursued two objectives: (i) to map regional research activity through scientometric analysis, and (ii) to assess ecological risks (ERA) using a hierarchical framework integrating experimental and in silico ecotoxicological evidence. Predicted No-Effect Concentrations (PNECs) were derived from a structured evidence hierarchy comprising three tiers: validated experimental data (Tier 1), VEGA QSAR predictions within the applicability domain (ADI > 0.85; Tier 2), and ECOSAR–TRIDENT integrated outputs (Tier 3). In this tier, ECOSAR mechanistic predictions were cross-validated by TRIDENT artificial intelligence. The ERA integrated measured environmental concentrations from 58 studies conducted in Brazil, Mexico, Colombia, Argentina, and Bolivia, covering 24 compounds. Approximately 71 % of all exposure scenarios were classified as negligible or low risk, whereas 29 % exhibited moderate to high ecological concern. Psychotropic drugs (sertraline, citalopram, fluoxetine, carbamazepine), macrolide antibiotics (erythromycin, azithromycin, sulfamethoxazole), and the anti-inflammatory diclofenac emerged as regional priorities due to their persistence and bioactivity. Overall, this ERA framework provides a transparent and resource-efficient approach for prioritizing PhACs and managing ecological risks, suitable for regions with limited resources such as LAC and adaptable to other data-scarce areas worldwide.

药物活性化合物（PhACs）由于其生物活性和破坏水生生态系统的潜力而成为人们关注的新兴污染物。尽管在欧洲和北美进行了广泛的研究，但对其在拉丁美洲和加勒比（LAC）的发生和风险的了解仍然有限。本研究建立在[1]小组发布的统一数据集的基础上，该数据集汇编并系统化了154项同行评议的研究，讨论了1990年至2024年间LAC水生环境中PhACs的存在，并追求两个目标：(i)通过科学计量分析绘制区域研究活动图；（ii）使用整合实验和计算机生态毒理学证据的分层框架评估生态风险（ERA）。预测无效应浓度（PNECs）来自一个结构化的证据层次，包括三个层次：验证的实验数据（第1层），VEGA QSAR在适用性领域的预测（ADI > 0.85；第2层），以及ECOSAR-TRIDENT集成输出（第3层）。在这一层，ECOSAR的机制预测被TRIDENT人工智能交叉验证。ERA综合了在巴西、墨西哥、哥伦比亚、阿根廷和玻利维亚进行的58项研究中测量的环境浓度，涵盖了24种化合物。大约71%的暴露情景被归类为可忽略或低风险，而29%表现出中度至高度的生态问题。精神药物（舍曲林、西酞普兰、氟西汀、卡马西平）、大环内酯类抗生素（红霉素、阿奇霉素、磺胺甲恶唑）和抗炎药双氯芬酸因其持久性和生物活性而成为区域优先考虑的药物。总体而言，该ERA框架提供了一种透明和资源高效的方法，用于确定phac的优先顺序和管理生态风险，适用于LAC等资源有限的地区，也适用于全球其他数据匮乏地区。

{"title":"AI-assisted QSAR framework for ecological risk assessment of pharmaceuticals: integrating experimental, mechanistic, and deep learning evidence","authors":"Vinicius Roveri , Alberto Teodorico Correia , Piter Gil dos Santos , Marcela Nascimento Ferreira Povoas , Walber Toma , Camilo Dias Seabra Pereira , Luciana Lopes Guimarães","doi":"10.1016/j.comtox.2026.100403","DOIUrl":"10.1016/j.comtox.2026.100403","url":null,"abstract":"<div><div>Pharmaceutically active compounds (PhACs) are emerging pollutants of concern due to their bioactivity and potential to disrupt aquatic ecosystems. Although extensively studied in Europe and North America, knowledge of their occurrence and risks in Latin America and the Caribbean (LAC) remains limited. This study builds upon the harmonized dataset published by our group [<span><span>1</span></span>], which compiled and systematized 154 peer-reviewed studies addressing the presence of PhACs in LAC aquatic environments between 1990 and 2024, and pursued two objectives: (i) to map regional research activity through scientometric analysis, and (ii) to assess ecological risks (ERA) using a hierarchical framework integrating experimental and in silico ecotoxicological evidence. Predicted No-Effect Concentrations (PNECs) were derived from a structured evidence hierarchy comprising three tiers: validated experimental data (Tier 1), VEGA QSAR predictions within the applicability domain (ADI > 0.85; Tier 2), and ECOSAR–TRIDENT integrated outputs (Tier 3). In this tier, ECOSAR mechanistic predictions were cross-validated by TRIDENT artificial intelligence. The ERA integrated measured environmental concentrations from 58 studies conducted in Brazil, Mexico, Colombia, Argentina, and Bolivia, covering 24 compounds. Approximately 71 % of all exposure scenarios were classified as negligible or low risk, whereas 29 % exhibited moderate to high ecological concern. Psychotropic drugs (sertraline, citalopram, fluoxetine, carbamazepine), macrolide antibiotics (erythromycin, azithromycin, sulfamethoxazole), and the anti-inflammatory diclofenac emerged as regional priorities due to their persistence and bioactivity. Overall, this ERA framework provides a transparent and resource-efficient approach for prioritizing PhACs and managing ecological risks, suitable for regions with limited resources such as LAC and adaptable to other data-scarce areas worldwide.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"37 ","pages":"Article 100403"},"PeriodicalIF":2.9,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977655","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}

引用次数: 0

Molecular dynamics insights into antibiotic–microplastic interactions: mechanisms, environmental risks, and predictive perspectives 分子动力学洞察抗生素-微塑料相互作用：机制，环境风险和预测观点

IF 2.9 Q2 TOXICOLOGY

Computational Toxicology

Pub Date : 2026-01-09 DOI: 10.1016/j.comtox.2026.100402

K. Shashikala , V. Sudheesh , Deepa Janardanan , Suja P Devipriya

Microplastics (MPs) have evolved from being viewed as inert pollutants to dynamic vectors that alter the environmental behaviour of antibiotics, intensifying their persistence, transport, and ecotoxicological impact. Despite a surge of experimental and computational studies, inconsistencies in methodology, polymer selection, and environmental realism continue to obscure the mechanistic understanding of antibiotic-MP interactions. This critical review re-evaluates the current evidence, contrasting adsorption kinetics, isotherm models, and desorption dynamics reported across different microplastic-antibiotic systems. We examine how polymer composition, environmental ageing, and biofilm colonisation jointly modulate the strength and nature of antibiotic adsorption, while also addressing inconsistencies in reported adsorption behaviours that stem from overly simplified laboratory conditions. Molecular dynamics (MD) and quantum–mechanical (DFT) simulations have provided unprecedented atomistic insights into these interactions; yet, their predictive potential remains underexploited due to inconsistent parameterisation, limited simulation time scales, and weak integration with environmental data. By synthesising empirical observations with simulation results, this review identifies dominant interaction pathways, including hydrophobic, electrostatic, hydrogen bonding, and π–π stacking, and examines how these mechanisms are modulated by environmental variables such as pH, salinity, and natural organic matter. We further assess the emerging role of machine-learning-accelerated MD, hybrid QM/MM approaches, and multiscale digital-twin frameworks that aim to bridge molecular-scale processes with ecosystem-level behaviour. Finally, this review proposes a unified framework for standardising simulation protocols, integrating MD-derived energetics into environmental fate and transport models, and translating atomistic insights into regulatory and risk-assessment contexts. Collectively, these critical perspectives reposition MD simulations not merely as interpretive tools but as predictive engines essential for managing the intertwined challenges of microplastic pollution and antimicrobial resistance.

微塑料（MPs）已从被视为惰性污染物演变为改变抗生素环境行为的动态载体，增强其持久性、运输和生态毒理学影响。尽管实验和计算研究激增，但方法、聚合物选择和环境现实主义方面的不一致继续模糊了抗生素- mp相互作用的机制理解。这篇重要的综述重新评估了目前的证据，对比了不同微塑料-抗生素系统的吸附动力学、等温线模型和解吸动力学。我们研究了聚合物组成、环境老化和生物膜定植如何共同调节抗生素吸附的强度和性质，同时也解决了由于过度简化的实验室条件而导致的报告中吸附行为的不一致。分子动力学（MD）和量子力学（DFT）模拟为这些相互作用提供了前所未有的原子性见解；然而，由于不一致的参数化、有限的模拟时间尺度以及与环境数据的弱集成，它们的预测潜力仍未得到充分利用。通过综合经验观察和模拟结果，本综述确定了主要的相互作用途径，包括疏水、静电、氢键和π -π堆叠，并研究了这些机制如何受到环境变量（如pH、盐度和天然有机物）的调节。我们进一步评估了机器学习加速MD、混合QM/MM方法和多尺度数字孪生框架的新兴作用，这些框架旨在将分子尺度过程与生态系统级行为联系起来。最后，本文提出了一个统一的框架，用于标准化模拟协议，将md衍生的能量学整合到环境命运和运输模型中，并将原子见解转化为监管和风险评估背景。总的来说，这些关键的观点重新定位了MD模拟，不仅是解释工具，而且是管理微塑料污染和抗菌素耐药性交织挑战所必需的预测引擎。

{"title":"Molecular dynamics insights into antibiotic–microplastic interactions: mechanisms, environmental risks, and predictive perspectives","authors":"K. Shashikala , V. Sudheesh , Deepa Janardanan , Suja P Devipriya","doi":"10.1016/j.comtox.2026.100402","DOIUrl":"10.1016/j.comtox.2026.100402","url":null,"abstract":"<div><div>Microplastics (MPs) have evolved from being viewed as inert pollutants to dynamic vectors that alter the environmental behaviour of antibiotics, intensifying their persistence, transport, and ecotoxicological impact. Despite a surge of experimental and computational studies, inconsistencies in methodology, polymer selection, and environmental realism continue to obscure the mechanistic understanding of antibiotic-MP interactions. This critical review re-evaluates the current evidence, contrasting adsorption kinetics, isotherm models, and desorption dynamics reported across different microplastic-antibiotic systems. We examine how polymer composition, environmental ageing, and biofilm colonisation jointly modulate the strength and nature of antibiotic adsorption, while also addressing inconsistencies in reported adsorption behaviours that stem from overly simplified laboratory conditions. Molecular dynamics (MD) and quantum–mechanical (DFT) simulations have provided unprecedented atomistic insights into these interactions; yet, their predictive potential remains underexploited due to inconsistent parameterisation, limited simulation time scales, and weak integration with environmental data. By synthesising empirical observations with simulation results, this review identifies dominant interaction pathways, including hydrophobic, electrostatic, hydrogen bonding, and π–π stacking, and examines how these mechanisms are modulated by environmental variables such as pH, salinity, and natural organic matter. We further assess the emerging role of machine-learning-accelerated MD, hybrid QM/MM approaches, and multiscale digital-twin frameworks that aim to bridge molecular-scale processes with ecosystem-level behaviour. Finally, this review proposes a unified framework for standardising simulation protocols, integrating MD-derived energetics into environmental fate and transport models, and translating atomistic insights into regulatory and risk-assessment contexts. Collectively, these critical perspectives reposition MD simulations not merely as interpretive tools but as predictive engines essential for managing the intertwined challenges of microplastic pollution and antimicrobial resistance.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"37 ","pages":"Article 100402"},"PeriodicalIF":2.9,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978245","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}

引用次数: 0

Nanoparticle in vitro dosimetry via supervised machine learning 基于监督机器学习的纳米颗粒体外剂量测定

IF 2.9 Q2 TOXICOLOGY

Computational Toxicology

Pub Date : 2026-01-08 DOI: 10.1016/j.comtox.2026.100401

Linard David Hoessly , Sandor Balog

To advance the dosimetry of nanoparticles in the context of in vitro cell culture experiments (assays), we propose an inferential machine learning approach realized by supervising a deep neural network trained for function approximation as a substitute for nonparametric regression. This study explicitly addresses the limitations of current PDE-based models by introducing a supervised machine learning framework for parameter inference, ensuring predictive accuracy and interpretability for computational toxicology applications. The approach—exhaustively tested via Monte Carlo simulations—can quantitatively estimate fundamental parameters, such as the particle diffusion coefficient, particle settling velocity, and the probability of particle association with cells, directly from the temporal progression of dosimetry data. The results demonstrate that accurate analyses can be obtained through supervised machine learning, which has the capacity to define a key domain in the interpretation of in vitro assays dedicated to hazard and risk assessment of nanoparticles.

为了在体外细胞培养实验（测定）的背景下推进纳米颗粒的剂量测定，我们提出了一种推理机器学习方法，该方法通过监督用于函数近似训练的深度神经网络来实现，以替代非参数回归。本研究通过引入有监督的机器学习框架进行参数推断，明确解决了当前基于pde的模型的局限性，确保了计算毒理学应用的预测准确性和可解释性。该方法通过蒙特卡罗模拟进行了详尽的测试，可以直接从剂量学数据的时间进展中定量估计基本参数，如颗粒扩散系数、颗粒沉降速度和颗粒与细胞关联的概率。结果表明，通过监督机器学习可以获得准确的分析，这有能力定义一个关键领域的解释，致力于纳米颗粒的危害和风险评估的体外分析。

引用次数: 0

A weighted-likelihood framework for class imbalance in Bayesian prediction models 贝叶斯预测模型中阶级不平衡的加权似然框架

IF 2.9 Q2 TOXICOLOGY

Computational Toxicology

Pub Date : 2026-01-07 DOI: 10.1016/j.comtox.2026.100400

Stanley E. Lazic

Class imbalance is a pervasive problem in predictive toxicology, where the number of non-toxic compounds often exceeds the number of toxic ones. Models trained on such data often perform well on the majority class but poorly on the minority class, which is most relevant for safety assessment. We propose a simple and general Bayesian framework that addresses class imbalance by modifying the likelihood function. Each observation’s likelihood is raised to a power inversely proportional to its class proportion, with the weights normalised to preserve the overall information content. This weighted-likelihood (or power-likelihood) approach embeds cost-sensitive learning directly into Bayesian updating. The method is demonstrated using simulated binary data and an ordered logistic model for drug-induced liver injury (DILI). Weighting alters parameter estimates and decision boundaries, improving balanced accuracy and sensitivity for the minority (toxic) class. The approach can be implemented with minimal changes in standard probabilistic programming languages such as Stan, PyMC, and Turing.jl. This framework provides an easily extensible foundation for developing Bayesian prediction models that better reflect the asymmetric costs of safety-critical decisions.

在预测毒理学中，类不平衡是一个普遍存在的问题，即无毒化合物的数量往往超过有毒化合物的数量。在这些数据上训练的模型通常在多数类别上表现良好，但在与安全评估最相关的少数类别上表现不佳。我们提出了一个简单而通用的贝叶斯框架，通过修改似然函数来解决类不平衡问题。每个观测值的似然被提高到与其类比例成反比的幂，权重归一化以保持整体信息内容。这种加权似然（或幂似然）方法将代价敏感学习直接嵌入到贝叶斯更新中。用模拟二值数据和药物性肝损伤的有序logistic模型对该方法进行了验证。加权改变了参数估计和决策边界，提高了少数（有毒）类的平衡准确性和灵敏度。这种方法可以在Stan、PyMC和Turing.jl等标准概率编程语言中进行最小的修改来实现。该框架为开发贝叶斯预测模型提供了一个易于扩展的基础，该模型可以更好地反映安全关键决策的不对称成本。

{"title":"A weighted-likelihood framework for class imbalance in Bayesian prediction models","authors":"Stanley E. Lazic","doi":"10.1016/j.comtox.2026.100400","DOIUrl":"10.1016/j.comtox.2026.100400","url":null,"abstract":"<div><div>Class imbalance is a pervasive problem in predictive toxicology, where the number of non-toxic compounds often exceeds the number of toxic ones. Models trained on such data often perform well on the majority class but poorly on the minority class, which is most relevant for safety assessment. We propose a simple and general Bayesian framework that addresses class imbalance by modifying the likelihood function. Each observation’s likelihood is raised to a power inversely proportional to its class proportion, with the weights normalised to preserve the overall information content. This weighted-likelihood (or power-likelihood) approach embeds cost-sensitive learning directly into Bayesian updating. The method is demonstrated using simulated binary data and an ordered logistic model for drug-induced liver injury (DILI). Weighting alters parameter estimates and decision boundaries, improving balanced accuracy and sensitivity for the minority (toxic) class. The approach can be implemented with minimal changes in standard probabilistic programming languages such as <span>Stan</span>, <span>PyMC</span>, and <span>Turing.jl</span>. This framework provides an easily extensible foundation for developing Bayesian prediction models that better reflect the asymmetric costs of safety-critical decisions.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"37 ","pages":"Article 100400"},"PeriodicalIF":2.9,"publicationDate":"2026-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145939538","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}

引用次数: 0

Development of machine learning-based multi-task quantitative structure–activity relationship models for predicting toxicities in six human organ systems 基于机器学习的多任务定量构效关系模型的开发，用于预测六种人体器官系统的毒性

IF 2.9 Q2 TOXICOLOGY

Computational Toxicology

Pub Date : 2025-12-24 DOI: 10.1016/j.comtox.2025.100399

Pei-Yu Wu , Wei-Chun Chou , Venkata N. Kamineni , Chi-Yun Chen , Jui-Hua Hsieh , Chris D. Vulpe , Zhoumeng Lin

Traditional toxicity assessment relies heavily on animal testing, particularly for chemicals lacking toxicity data. This study developed machine learning (ML)-driven quantitative structure–activity relationship (QSAR) models to predict human organ-specific toxicities, including cardiotoxicity, developmental toxicity, hepatotoxicity, neurotoxicity, nephrotoxicity, and reproductive toxicity. We collected in vivo data for 2,389 chemicals and Tox21 high-throughput screening data for 1,746 chemicals, resulting in 1,743 chemicals with matched datasets. Eighty-eight ML-based QSAR models were developed using three feature scenarios: (1) Tox21 data alone, (2) molecular descriptors alone, and (3) combined features. Five descriptor types and four ML algorithms (random forests, decision trees, support vector machines, and deep neural network [DNN]) were applied, with and without chi-square-based feature selection. Performance was evaluated using nested cross-validation and five metrics (recall, precision, balanced accuracy, F1 score, and ROC-AUC). DNN models in Scenario 2 performed best for developmental and neurotoxicity, while those in Scenario 3 outperformed others for the remaining toxicities. ROC-AUC values approached 0.8 across endpoints, and models without feature selection generally performed better. SHAP and contribution maps enhanced interpretability, highlighting key structural features of toxicity. This study demonstrates the potential of ML-assisted QSAR models for accurate multi-organ toxicity prediction, supporting drug development and chemical risk assessment.

传统的毒性评估严重依赖于动物试验，特别是对于缺乏毒性数据的化学品。本研究开发了机器学习（ML）驱动的定量构效关系（QSAR）模型来预测人类器官特异性毒性，包括心脏毒性、发育毒性、肝毒性、神经毒性、肾毒性和生殖毒性。我们收集了2389种化学物质的体内数据和1746种化学物质的Tox21高通量筛选数据，得到了1743种化学物质的匹配数据集。采用三种特征场景(1)单独使用Tox21数据，(2)单独使用分子描述符，(3)组合特征，开发了88个基于ml的QSAR模型。五种描述符类型和四种机器学习算法（随机森林、决策树、支持向量机和深度神经网络[DNN]）被应用，有和没有基于卡方的特征选择。使用嵌套交叉验证和五个指标（召回率、精度、平衡准确度、F1分数和ROC-AUC）评估性能。情景2中的DNN模型在发育和神经毒性方面表现最佳，而情景3中的DNN模型在其余毒性方面表现优于其他模型。各个端点的ROC-AUC值接近0.8，没有特征选择的模型通常表现更好。SHAP和贡献图增强了可解释性，突出了毒性的关键结构特征。该研究证明了ml辅助QSAR模型在准确预测多器官毒性、支持药物开发和化学品风险评估方面的潜力。

{"title":"Development of machine learning-based multi-task quantitative structure–activity relationship models for predicting toxicities in six human organ systems","authors":"Pei-Yu Wu , Wei-Chun Chou , Venkata N. Kamineni , Chi-Yun Chen , Jui-Hua Hsieh , Chris D. Vulpe , Zhoumeng Lin","doi":"10.1016/j.comtox.2025.100399","DOIUrl":"10.1016/j.comtox.2025.100399","url":null,"abstract":"<div><div>Traditional toxicity assessment relies heavily on animal testing, particularly for chemicals lacking toxicity data. This study developed machine learning (ML)-driven quantitative structure–activity relationship (QSAR) models to predict human organ-specific toxicities, including cardiotoxicity, developmental toxicity, hepatotoxicity, neurotoxicity, nephrotoxicity, and reproductive toxicity. We collected in vivo data for 2,389 chemicals and Tox21 high-throughput screening data for 1,746 chemicals, resulting in 1,743 chemicals with matched datasets. Eighty-eight ML-based QSAR models were developed using three feature scenarios: (1) Tox21 data alone, (2) molecular descriptors alone, and (3) combined features. Five descriptor types and four ML algorithms (random forests, decision trees, support vector machines, and deep neural network [DNN]) were applied, with and without chi-square-based feature selection. Performance was evaluated using nested cross-validation and five metrics (recall, precision, balanced accuracy, F1 score, and ROC-AUC). DNN models in Scenario 2 performed best for developmental and neurotoxicity, while those in Scenario 3 outperformed others for the remaining toxicities. ROC-AUC values approached 0.8 across endpoints, and models without feature selection generally performed better. SHAP and contribution maps enhanced interpretability, highlighting key structural features of toxicity. This study demonstrates the potential of ML-assisted QSAR models for accurate multi-organ toxicity prediction, supporting drug development and chemical risk assessment.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"37 ","pages":"Article 100399"},"PeriodicalIF":2.9,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884618","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}

引用次数: 0

A comparative assessment of predictive methods for ready biodegradation using REACH experimental data 利用REACH实验数据对现成生物降解预测方法进行比较评估

IF 2.9 Q2 TOXICOLOGY

Computational Toxicology

Pub Date : 2025-12-18 DOI: 10.1016/j.comtox.2025.100398

Panagiotis G. Karamertzanis, Heidi Ekholm, Aliisa Yli-Tuomola, Romanas Cesnaitis, Kostas Andreou, Anna-Maija Nyman, Wim De Coen

This study presents a comparative assessment of predictive methods for ready biodegradation using a curated dataset with REACH experimental information for 2684 industrial chemicals. A large part of these structures is not present in the training and validation sets of the models allowing for their unbiased external validation. We evaluated various QSAR models that can be readily used, including Biowin, Opera, Vega, Catalogic, and a recent model by Körner et al. The models were compared based on how well their training sets span the industrial chemical space, their predictive performance and applicability domain coverage. The balanced accuracy ranged from 0.600 to 0.771, while the sensitivity for identifying non-readily biodegradable substances varied between 0.217 and 0.848, reflecting the expected trade-off with specificity. The applicability domain coverage ranged from 28.5% to nearly the entire chemical space. Consensus models were developed using majority voting to explore the sensitivity and specificity interplay by combining model predictions, but did not yield appreciable increases in balanced accuracy or F1 score, although they increased the reliability of non-readily biodegradable predictions at the detriment of applicability domain coverage. This work underscores the potential of in silico methods for predicting the fate properties of substances, even before they are synthesised or commercialised, thereby fulfilling regulatory information requirements and prioritizing substances for testing. However, further developments are needed to achieve predictive performance that is comparable to the variability in the experimental test. The curated dataset has been made publicly available as supporting information, facilitating the further development and validation of predictive methods.

本研究使用2684种工业化学品的REACH实验信息整理数据集，对现成生物降解的预测方法进行了比较评估。这些结构的很大一部分不存在于模型的训练和验证集中，允许它们的无偏外部验证。我们评估了各种可以随时使用的QSAR模型，包括Biowin、Opera、Vega、catalog和Körner等人最近的模型。对这些模型进行比较的依据是它们的训练集跨越工业化学空间的程度、它们的预测性能和适用性领域覆盖范围。平衡精度范围为0.600 ~ 0.771，而识别不易生物降解物质的灵敏度范围为0.217 ~ 0.848，反映了期望与特异性之间的权衡。适用范围从28.5%到几乎整个化学领域。共识模型使用多数投票通过结合模型预测来探索敏感性和特异性的相互作用，但没有产生明显的平衡准确性或F1分数的增加，尽管它们在损害适用性领域覆盖的情况下增加了不易生物降解预测的可靠性。这项工作强调了计算机方法在预测物质命运特性方面的潜力，甚至在它们被合成或商业化之前，从而满足监管信息要求并优先考虑物质进行测试。然而，需要进一步的发展来实现与实验测试中的可变性相媲美的预测性能。整理的数据集已作为辅助信息公开提供，促进了预测方法的进一步发展和验证。

{"title":"A comparative assessment of predictive methods for ready biodegradation using REACH experimental data","authors":"Panagiotis G. Karamertzanis, Heidi Ekholm, Aliisa Yli-Tuomola, Romanas Cesnaitis, Kostas Andreou, Anna-Maija Nyman, Wim De Coen","doi":"10.1016/j.comtox.2025.100398","DOIUrl":"10.1016/j.comtox.2025.100398","url":null,"abstract":"<div><div>This study presents a comparative assessment of predictive methods for ready biodegradation using a curated dataset with REACH experimental information for 2684 industrial chemicals. A large part of these structures is not present in the training and validation sets of the models allowing for their unbiased external validation. We evaluated various QSAR models that can be readily used, including Biowin, Opera, Vega, Catalogic, and a recent model by Körner et al. The models were compared based on how well their training sets span the industrial chemical space, their predictive performance and applicability domain coverage. The balanced accuracy ranged from 0.600 to 0.771, while the sensitivity for identifying non-readily biodegradable substances varied between 0.217 and 0.848, reflecting the expected trade-off with specificity. The applicability domain coverage ranged from 28.5% to nearly the entire chemical space. Consensus models were developed using majority voting to explore the sensitivity and specificity interplay by combining model predictions, but did not yield appreciable increases in balanced accuracy or F1 score, although they increased the reliability of non-readily biodegradable predictions at the detriment of applicability domain coverage. This work underscores the potential of <em>in silico</em> methods for predicting the fate properties of substances, even before they are synthesised or commercialised, thereby fulfilling regulatory information requirements and prioritizing substances for testing. However, further developments are needed to achieve predictive performance that is comparable to the variability in the experimental test. The curated dataset has been made publicly available as supporting information, facilitating the further development and validation of predictive methods.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"37 ","pages":"Article 100398"},"PeriodicalIF":2.9,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841034","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}

引用次数: 0

Modeling metabolism: Evolution of toxicodynamic and toxicokinetic considerations. Adding a new kinetics layer 代谢建模：毒性动力学和毒性动力学考虑的演变。增加一个新的动力学层

IF 2.9 Q2 TOXICOLOGY

Computational Toxicology

Pub Date : 2025-12-02 DOI: 10.1016/j.comtox.2025.100394

A. Chapkanov , H. Ivanova , G. Poryazova , I. Todorova , T.W. Schultz , O.G. Mekenyan

Modern metabolic simulation encompasses five key attributes that align with a typical data matrix, enabling accurate predictions of metabolism. These attributes are 1) the structural features of the parent molecule (S), 2) the metabolic transformations, both individual and grouped standard types (T), 3) the probability that a specific reaction will occur (P), especially if a particular structural fragment is present nearby, 4) reaction rate (R) (such as the depletion rate of a parent structure), and 5) the quantity of reaction products generated at a given time (Q). The thermodynamically informed phase of metabolism includes STP. Here, the previously described kinetic phase is expanded to include the R and Q attributes. Specifically, a proof-of-concept is described that shows how 2D, 3D, or local parameters can be aligned through regression analysis with hydroxylation and hydrolysis to explicitly simulate metabolic kinetics. In this approach, the amount of metabolite formed depends on the substrate reaction rate via chemical half-lives.

现代代谢模拟包含与典型数据矩阵一致的五个关键属性，从而能够准确预测代谢。这些属性是1)母体分子的结构特征（S), 2)个体和分组标准类型的代谢转化（T), 3）特定反应发生的概率(P)，特别是如果附近存在特定的结构片段，4）反应速率（R)（如母体结构的损耗率），以及5）在给定时间产生的反应生成物的数量(Q)。代谢的热力学信息阶段包括STP。在这里，先前描述的动力学相被扩展到包括R和Q属性。具体来说，描述了一个概念验证，显示了如何通过羟基化和水解的回归分析来对齐2D， 3D或局部参数，以明确模拟代谢动力学。在这种方法中，形成的代谢物的数量取决于通过化学半衰期的底物反应速率。

{"title":"Modeling metabolism: Evolution of toxicodynamic and toxicokinetic considerations. Adding a new kinetics layer","authors":"A. Chapkanov , H. Ivanova , G. Poryazova , I. Todorova , T.W. Schultz , O.G. Mekenyan","doi":"10.1016/j.comtox.2025.100394","DOIUrl":"10.1016/j.comtox.2025.100394","url":null,"abstract":"<div><div>Modern metabolic simulation encompasses five key attributes that align with a typical data matrix, enabling accurate predictions of metabolism. These attributes are 1) the structural features of the parent molecule (S), 2) the metabolic transformations, both individual and grouped standard types (T), 3) the probability that a specific reaction will occur (P), especially if a particular structural fragment is present nearby, 4) reaction rate (R) (such as the depletion rate of a parent structure), and 5) the quantity of reaction products generated at a given time (Q). The thermodynamically informed phase of metabolism includes STP. Here, the previously described kinetic phase is expanded to include the R and Q attributes. Specifically, a proof-of-concept is described that shows how 2D, 3D, or local parameters can be aligned through regression analysis with hydroxylation and hydrolysis to explicitly simulate metabolic kinetics. In this approach, the amount of metabolite formed depends on the substrate reaction rate via chemical half-lives.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"37 ","pages":"Article 100394"},"PeriodicalIF":2.9,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145749932","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}

引用次数: 0

In vitro transcriptomic points of departure derived from human whole transcriptome and reduced S1500+ gene panel are highly comparable 人类全转录组和减少的S1500+基因组的体外转录组出发点具有高度可比性

IF 2.9 Q2 TOXICOLOGY

Computational Toxicology

Pub Date : 2025-12-01 DOI: 10.1016/j.comtox.2025.100392

James Johnson , Joseph L. Bundy , Joshua A. Harrill , Logan J. Everett

Previous high-throughput transcriptomic screening of over 1,300 chemicals in three different human cell lines relied on a whole transcriptome targeted RNA-seq assay that measures the expression of over 19,000 genes and a signature-based concentration–response analysis method to derive an overall transcriptomic point of departure (tPOD) for each chemical. To explore the impacts of switching to a reduced representation version of the assay (“S1500+”) measuring only 2730 genes, we re-analyzed the existing data using only the S1500+ gene panel, and performed concentration–response modeling using the same methodology previously applied to the whole transcriptome data. The tPODs derived from the S1500+ genes were highly concordant with the tPODs derived from the whole transcriptome expression data regardless of cell line, with over 93 % of the corresponding tPODs falling within 1 order of magnitude of each other. The overall root mean squared deviation between tPODs derived from the two gene sets was less than what was observed between duplicate samples of the same chemical within screening studies. Importantly, the total number of active gene signatures shrunk by only 13–17 % (depending on cell line) when reducing the analysis to the S1500+ genes. However, examination of the individual active gene signatures showed systematic differences between the two TempO-Seq gene panels as a function of source database or associated protein target. Overall, our analysis suggests that switching to the reduced representation assay in the context of high-throughput transcriptomic screening would likely have minimal impacts on the inference of overall tPODs, but could impact inference of specific mechanisms-of-action.

之前对三种不同人类细胞系中超过1300种化学物质的高通量转录组筛选依赖于测量超过19,000个基因表达的全转录组靶向RNA-seq测定和基于特征的浓度-反应分析方法，以获得每种化学物质的总体转录组出发点（tPOD）。为了探索切换到仅测量2730个基因的减少表示版本的检测（“S1500+”）的影响，我们仅使用S1500+基因面板重新分析了现有数据，并使用先前应用于整个转录组数据的相同方法进行了浓度响应建模。来自S1500+基因的tpod与来自整个转录组表达数据的tpod高度一致，无论细胞系如何，超过93%的tpod相互之间的差异在1个数量级以内。从两个基因组衍生的tpod之间的总体均方根偏差小于在筛选研究中相同化学物质的重复样本之间观察到的偏差。重要的是，当减少对S1500+基因的分析时，活性基因签名的总数仅减少了13 - 17%（取决于细胞系）。然而，对单个活性基因特征的检查显示，两个TempO-Seq基因面板之间存在系统差异，这是源数据库或相关蛋白靶点的功能。总的来说，我们的分析表明，在高通量转录组学筛选的背景下，切换到减少代表性的分析可能对总体tpod的推断影响最小，但可能会影响对特定作用机制的推断。

{"title":"In vitro transcriptomic points of departure derived from human whole transcriptome and reduced S1500+ gene panel are highly comparable","authors":"James Johnson , Joseph L. Bundy , Joshua A. Harrill , Logan J. Everett","doi":"10.1016/j.comtox.2025.100392","DOIUrl":"10.1016/j.comtox.2025.100392","url":null,"abstract":"<div><div>Previous high-throughput transcriptomic screening of over 1,300 chemicals in three different human cell lines relied on a whole transcriptome targeted RNA-seq assay that measures the expression of over 19,000 genes and a signature-based concentration–response analysis method to derive an overall transcriptomic point of departure (tPOD) for each chemical. To explore the impacts of switching to a reduced representation version of the assay (“S1500+”) measuring only 2730 genes, we re-analyzed the existing data using only the S1500+ gene panel, and performed concentration–response modeling using the same methodology previously applied to the whole transcriptome data. The tPODs derived from the S1500+ genes were highly concordant with the tPODs derived from the whole transcriptome expression data regardless of cell line, with over 93 % of the corresponding tPODs falling within 1 order of magnitude of each other. The overall root mean squared deviation between tPODs derived from the two gene sets was less than what was observed between duplicate samples of the same chemical within screening studies. Importantly, the total number of active gene signatures shrunk by only 13–17 % (depending on cell line) when reducing the analysis to the S1500+ genes. However, examination of the individual active gene signatures showed systematic differences between the two TempO-Seq gene panels as a function of source database or associated protein target. Overall, our analysis suggests that switching to the reduced representation assay in the context of high-throughput transcriptomic screening would likely have minimal impacts on the inference of overall tPODs, but could impact inference of specific mechanisms-of-action.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"36 ","pages":"Article 100392"},"PeriodicalIF":2.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145614427","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}

引用次数: 0

Corrigendum to “Screening for genotoxicants in food: A data-driven approach using food composition data and machine learning based in silico models” [Comput. Toxicol. 35 (2025) 100370] “筛选食品中的基因毒物：使用食品成分数据和基于计算机模型的机器学习的数据驱动方法”的勘误表。毒物，35 (2025)100370]

IF 2.9 Q2 TOXICOLOGY

Computational Toxicology

Pub Date : 2025-12-01 DOI: 10.1016/j.comtox.2025.100387

Jakob Menz, Bernd Schäfer

引用次数: 0

A computational framework for modeling VX skin penetration and RSDL-based neutralization 模拟VX皮肤穿透和基于rsdl的中和的计算框架

IF 2.9 Q2 TOXICOLOGY

Computational Toxicology

Pub Date : 2025-12-01 DOI: 10.1016/j.comtox.2025.100393

Laurent Simon

VX is one of the most toxic organophosphorus nerve agents, capable of causing severe harm after dermal exposure. Rapid removal or neutralization is therefore essential in both military and civilian contexts. This study developed and validated a mechanistic skin-treatment model to evaluate the effect of delayed application of Reactive Skin Decontamination Lotion (RSDL). The model included diffusion through the stratum corneum, neutralization within the tissue, and systemic uptake. The VX diffusion coefficient in the stratum corneum was estimated at 4.3 × 10⁻¹⁰ cm²/s, while the first-order decontamination rate constant was derived from 120-minute treatment data as 2.1 × 10⁻⁴ s⁻¹. Key performance metrics included the area under the curve for the average VX concentration in the skin, the cumulative amount released, the reacted mass, the remaining amount in the dermal layer and the protection factor. Without further parameter fitting, the model predicted that RSDL applied within 5–10 min nearly eliminated penetration (cumulative absorption 155.7 µg/cm² vs. 2877.0 µg/cm² for the control), whereas treatments at 30–60 min delayed but did not prevent absorption, and treatment at 120 min provided only limited protection. These results underscore the importance of early intervention while showing that delayed action still reduces systemic uptake. The framework provides occupational and environmental hygienists with a quantitative tool for assessing dermal risk, optimizing intervention timing, and guiding response strategies in industrial or accidental exposures.

VX是毒性最强的有机磷神经毒剂之一，皮肤接触后可造成严重伤害。因此，在军事和民用情况下，迅速清除或消除是至关重要的。本研究建立并验证了一个机械性皮肤治疗模型，以评估延迟应用反应性皮肤去污洗剂（RSDL）的效果。该模型包括通过角质层扩散、组织内中和和全身摄取。角质层中的VX扩散系数估计为4.3 × 10−10 cm2/s，而120分钟处理数据的一级去污速率常数为2.1 × 10−4 s−1。关键性能指标包括皮肤中VX平均浓度的曲线下面积、累积释放量、反应质量、真皮层剩余量和保护系数。在没有进一步参数拟合的情况下，该模型预测5-10分钟内使用RSDL几乎消除了渗透（累积吸收155.7µg/cm2，对照组为2877.0µg/cm2），而30-60分钟处理延迟但不阻止吸收，120分钟处理仅提供有限的保护。这些结果强调了早期干预的重要性，同时表明延迟行动仍然会减少全身摄取。该框架为职业和环境卫生学家提供了一种定量工具，用于评估皮肤风险，优化干预时机，并指导工业或意外暴露的反应策略。

{"title":"A computational framework for modeling VX skin penetration and RSDL-based neutralization","authors":"Laurent Simon","doi":"10.1016/j.comtox.2025.100393","DOIUrl":"10.1016/j.comtox.2025.100393","url":null,"abstract":"<div><div>VX is one of the most toxic organophosphorus nerve agents, capable of causing severe harm after dermal exposure. Rapid removal or neutralization is therefore essential in both military and civilian contexts. This study developed and validated a mechanistic skin-treatment model to evaluate the effect of delayed application of Reactive Skin Decontamination Lotion (RSDL). The model included diffusion through the stratum corneum, neutralization within the tissue, and systemic uptake. The VX diffusion coefficient in the stratum corneum was estimated at 4.3 × 10<sup>−10</sup> cm<sup>2</sup>/s, while the first-order decontamination rate constant was derived from 120-minute treatment data as 2.1 × 10<sup>−4</sup> s<sup>−1</sup>. Key performance metrics included the area under the curve for the average VX concentration in the skin, the cumulative amount released, the reacted mass, the remaining amount in the dermal layer and the protection factor. Without further parameter fitting, the model predicted that RSDL applied within 5–10 min nearly eliminated penetration (cumulative absorption 155.7 µg/cm<sup>2</sup> vs. 2877.0 µg/cm<sup>2</sup> for the control), whereas treatments at 30–60 min delayed but did not prevent absorption, and treatment at 120 min provided only limited protection. These results underscore the importance of early intervention while showing that delayed action still reduces systemic uptake. The framework provides occupational and environmental hygienists with a quantitative tool for assessing dermal risk, optimizing intervention timing, and guiding response strategies in industrial or accidental exposures.</div></div>","PeriodicalId":37651,"journal":{"name":"Computational Toxicology","volume":"36 ","pages":"Article 100393"},"PeriodicalIF":2.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145681480","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}

引用次数: 0