新型模型预测水生环境主要营养层次代表性物种的急性和慢性毒性。
New Models to Predict the Acute and Chronic Toxicities of Representative Species of the Main Trophic Levels of Aquatic Environments.
机构信息
Laboratory of Environmental Chemistry and Toxicology, Department of Environmental Health Science, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, Via Mario Negri 2, 20156 Milano, Italy.
Kode Chemoinformatics s.r.l.-Via Nino Pisano 14, 56122 Pisa, Italy.
出版信息
Molecules. 2021 Nov 19;26(22):6983. doi: 10.3390/molecules26226983.
Abstract
To assess the impact of chemicals on an aquatic environment, toxicological data for three trophic levels are needed to address the chronic and acute toxicities. The use of non-testing methods, such as predictive computational models, was proposed to avoid or reduce the need for animal models and speed up the process when there are many substances to be tested. We developed predictive models for , , and fish for acute and chronic toxicities. The random forest machine learning approach gave the best results. The models gave good statistical quality for all endpoints. These models are freely available for use as individual models in the VEGA platform and for prioritization in JANUS software.
摘要
为了评估化学物质对水生环境的影响，需要有三个营养级别的毒理学数据来解决慢性和急性毒性问题。因此，人们提出了使用非测试方法，如预测计算模型，以避免或减少对动物模型的需求，并在需要测试的物质很多时加快这一过程。我们开发了用于急性和慢性毒性的鱼类、藻类和水蚤的预测模型。随机森林机器学习方法给出了最好的结果。这些模型对于所有终点都具有良好的统计质量。这些模型可作为 VEGA 平台中的单独模型免费使用，并可在 JANUS 软件中进行优先级排序。
相似文献
1
New Models to Predict the Acute and Chronic Toxicities of Representative Species of the Main Trophic Levels of Aquatic Environments.新型模型预测水生环境主要营养层次代表性物种的急性和慢性毒性。
Molecules. 2021 Nov 19;26(22):6983. doi: 10.3390/molecules26226983.
2
Quantitative multi-species toxicity modeling: Does a multi-species, machine learning model provide better performance than a single-species model for the evaluation of acute aquatic toxicity by organic pollutants?定量多物种毒性建模：对于有机污染物急性水生毒性的评估，多物种机器学习模型的性能是否优于单物种模型？
Sci Total Environ. 2023 Feb 25;861:160590. doi: 10.1016/j.scitotenv.2022.160590. Epub 2022 Dec 5.
3
Comparing in vivo data and in silico predictions for acute effects assessment of biocidal active substances and metabolites for aquatic organisms.比较水生生物的杀菌活性物质及其代谢物的急性效应评估的体内数据和计算预测。
Ecotoxicol Environ Saf. 2020 Dec 1;205:111291. doi: 10.1016/j.ecoenv.2020.111291. Epub 2020 Sep 18.
4
Ecotoxicological study of six drugs in Aliivibrio fischeri, Daphnia magna and Raphidocelis subcapitata.六种药物对发光菌、大型蚤和水蚤的生态毒理学研究。
Environ Sci Pollut Res Int. 2020 Mar;27(9):9891-9900. doi: 10.1007/s11356-019-07592-8. Epub 2020 Jan 11.
5
Consensus QSAR modeling of toxicity of pharmaceuticals to different aquatic organisms: Ranking and prioritization of the DrugBank database compounds.共识定量构效关系模型在评估药物对不同水生生物的毒性方面的应用：对 DrugBank 数据库化合物进行排序和优先级划分。
Ecotoxicol Environ Saf. 2019 Jan 30;168:287-297. doi: 10.1016/j.ecoenv.2018.10.060. Epub 2018 Nov 1.
6
Multispecies QSAR modeling for predicting the aquatic toxicity of diverse organic chemicals for regulatory toxicology.用于预测多种有机化学品对监管毒理学的水生毒性的多物种定量构效关系建模。
Chem Res Toxicol. 2014 May 19;27(5):741-53. doi: 10.1021/tx400371w. Epub 2014 Apr 17.
7
Hazard of pharmaceuticals for aquatic environment: Prioritization by structural approaches and prediction of ecotoxicity.药品对水生环境的危害：基于结构方法的优先级排序和生态毒性预测。
Environ Int. 2016 Oct;95:131-43. doi: 10.1016/j.envint.2016.08.008. Epub 2016 Aug 26.
8
Development of classification models for predicting chronic toxicity of chemicals to Daphnia magna and Pseudokirchneriella subcapitata.建立预测化学品对大型溞和斜生栅藻慢性毒性的分类模型。
SAR QSAR Environ Res. 2019 Jan;30(1):39-50. doi: 10.1080/1062936X.2018.1545694. Epub 2018 Nov 27.
9
Developing random forest based QSAR models for predicting the mixture toxicity of TiO based nano-mixtures to Daphnia magna.建立基于随机森林的 QSAR 模型，预测 TiO2 基纳米混合物对大型溞的混合物毒性。
NanoImpact. 2022 Jan;25:100383. doi: 10.1016/j.impact.2022.100383. Epub 2022 Jan 21.
10
Identification and regulation of ecotoxicity of polychlorinated naphthalenes to aquatic food Chain (green algae-Daphnia magna-fish).多氯萘类对水生生食物链（绿藻-大型蚤-鱼）的生态毒性的鉴定和调控。
Aquat Toxicol. 2021 Apr;233:105774. doi: 10.1016/j.aquatox.2021.105774. Epub 2021 Feb 13.
引用本文的文献
1
Assessing the pharmaceutical residues as hotspots of the main rivers of Catalonia, Spain.评估西班牙加泰罗尼亚主要河流的药物残留热点。
Environ Sci Pollut Res Int. 2024 Jul;31(31):44080-44095. doi: 10.1007/s11356-024-33967-7. Epub 2024 Jun 26.
2
Models for the No-Observed-Effect Concentration (NOEC) and Maximal Half-Effective Concentration (EC50).未观察到效应浓度（NOEC）和半数最大效应浓度（EC50）的模型。
Toxics. 2024 Jun 12;12(6):425. doi: 10.3390/toxics12060425.
3
Ecotoxicological Evaluation of Bisphenol A and Alternatives: A Comprehensive In Silico Modelling Approach.双酚A及其替代品的生态毒理学评估：一种全面的计算机模拟方法。
J Xenobiot. 2023 Nov 23;13(4):719-739. doi: 10.3390/jox13040046.
4
A benchmark dataset for machine learning in ecotoxicology.用于生态毒理学机器学习的基准数据集。
Sci Data. 2023 Oct 18;10(1):718. doi: 10.1038/s41597-023-02612-2.
5
Integrated Approach for Synthetic Cathinone Drug Prioritization and Risk Assessment: In Silico Approach and Sub-Chronic Studies in and .综合方法用于合成卡西酮类药物的优先级排序和风险评估：计算机模拟方法和 在 和 中的亚慢性研究。
Molecules. 2023 Mar 23;28(7):2899. doi: 10.3390/molecules28072899.
6
Eco-toxicological effect of a commercial dye Rhodamine B on freshwater microalgae Chlorella vulgaris.Rhodamine B 商用染料对淡水微藻小球藻的生态毒理学效应。
Arch Microbiol. 2022 Oct 2;204(10):658. doi: 10.1007/s00203-022-03254-5.
本文引用的文献
1
Ecotoxicological QSAR modeling of organic compounds against fish: Application of fragment based descriptors in feature analysis.有机化合物对鱼类的生态毒理学定量构效关系模型研究：基于片段描述符的特征分析应用。
Aquat Toxicol. 2019 Jul;212:162-174. doi: 10.1016/j.aquatox.2019.05.011. Epub 2019 May 17.
2
QSAR modeling of Daphnia magna and fish toxicities of biocides using 2D descriptors.利用二维描述符对杀生物剂进行大型蚤和鱼类毒性的定量构效关系建模。
Chemosphere. 2019 Aug;229:8-17. doi: 10.1016/j.chemosphere.2019.04.204. Epub 2019 Apr 29.
3
Development of classification models for predicting chronic toxicity of chemicals to Daphnia magna and Pseudokirchneriella subcapitata.建立预测化学品对大型溞和斜生栅藻慢性毒性的分类模型。
SAR QSAR Environ Res. 2019 Jan;30(1):39-50. doi: 10.1080/1062936X.2018.1545694. Epub 2018 Nov 27.
4
Consensus QSAR modeling of toxicity of pharmaceuticals to different aquatic organisms: Ranking and prioritization of the DrugBank database compounds.共识定量构效关系模型在评估药物对不同水生生物的毒性方面的应用：对 DrugBank 数据库化合物进行排序和优先级划分。
Ecotoxicol Environ Saf. 2019 Jan 30;168:287-297. doi: 10.1016/j.ecoenv.2018.10.060. Epub 2018 Nov 1.
5
Development of thresholds of excess toxicity for environmental species and their application to identification of modes of acute toxic action.制定环境物种的毒性过剩阈值及其在鉴定急性毒性作用模式中的应用。
Sci Total Environ. 2018 Mar;616-617:491-499. doi: 10.1016/j.scitotenv.2017.10.308. Epub 2017 Nov 9.
6
Developing predictive models for toxicity of organic chemicals to green algae based on mode of action.基于作用机制开发有机化学品对绿藻毒性的预测模型。
Chemosphere. 2018 Jan;190:463-470. doi: 10.1016/j.chemosphere.2017.10.028. Epub 2017 Oct 5.
7
History of EPI Suite™ and future perspectives on chemical property estimation in US Toxic Substances Control Act new chemical risk assessments.EPI Suite™ 的历史以及美国《有毒物质控制法》新化学物质风险评估中化学性质估算的未来展望。
Environ Sci Process Impacts. 2017 Mar 22;19(3):203-212. doi: 10.1039/c7em00064b.
8
(Q)SARs to predict environmental toxicities: current status and future needs.用于预测环境毒性的（定量）构效关系：现状与未来需求
Environ Sci Process Impacts. 2017 Mar 22;19(3):213-220. doi: 10.1039/c6em00687f.
9
Prediction of acute toxicity of emerging contaminants on the water flea Daphnia magna by Ant Colony Optimization-Support Vector Machine QSTR models.基于蚁群算法-支持向量机 QSTR 模型预测新型污染物对水蚤的急性毒性。
Environ Sci Process Impacts. 2017 Mar 22;19(3):438-448. doi: 10.1039/c6em00679e.
10
An in silico algal toxicity model with a wide applicability potential for industrial chemicals and pharmaceuticals.一种对工业化学品和药物具有广泛潜在适用性的计算机模拟藻类毒性模型。
Environ Toxicol Chem. 2017 Apr;36(4):1012-1019. doi: 10.1002/etc.3620. Epub 2016 Oct 12.
Zotero 插件