{"title":"用于预测传统和新兴芳香族污染物在植物根茎中生物利用率的机器学习模型。","authors":"Siyuan Li, Yuting Shen, Meng Gao, Huatai Song, Zhanpeng Ge, Qiuyue Zhang, Jiaping Xu, Yu Wang, Hongwen Sun","doi":"10.3390/toxics12100737","DOIUrl":null,"url":null,"abstract":"<p><p>To predict the behavior of aromatic contaminants (ACs) in complex soil-plant systems, this study developed machine learning (ML) models to estimate the root concentration factor (RCF) of both traditional (e.g., polycyclic aromatic hydrocarbons, polychlorinated biphenyls) and emerging ACs (e.g., phthalate acid esters, aryl organophosphate esters). Four ML algorithms were employed, trained on a unified RCF dataset comprising 878 data points, covering 6 features of soil-plant cultivation systems and 98 molecular descriptors of 55 chemicals, including 29 emerging ACs. The gradient-boosted regression tree (GBRT) model demonstrated strong predictive performance, with a coefficient of determination (R<sup>2</sup>) of 0.75, a mean absolute error (MAE) of 0.11, and a root mean square error (RMSE) of 0.22, as validated by five-fold cross-validation. Multiple explanatory analyses highlighted the significance of soil organic matter (SOM), plant protein and lipid content, exposure time, and molecular descriptors related to electronegativity distribution pattern (GATS8e) and double-ring structure (fr_bicyclic). An increase in SOM was found to decrease the overall RCF, while other variables showed strong correlations within specific ranges. This GBRT model provides an important tool for assessing the environmental behaviors of ACs in soil-plant systems, thereby supporting further investigations into their ecological and human exposure risks.</p>","PeriodicalId":23195,"journal":{"name":"Toxics","volume":null,"pages":null},"PeriodicalIF":3.9000,"publicationDate":"2024-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11511036/pdf/","citationCount":"0","resultStr":"{\"title\":\"Machine Learning Models for Predicting Bioavailability of Traditional and Emerging Aromatic Contaminants in Plant Roots.\",\"authors\":\"Siyuan Li, Yuting Shen, Meng Gao, Huatai Song, Zhanpeng Ge, Qiuyue Zhang, Jiaping Xu, Yu Wang, Hongwen Sun\",\"doi\":\"10.3390/toxics12100737\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>To predict the behavior of aromatic contaminants (ACs) in complex soil-plant systems, this study developed machine learning (ML) models to estimate the root concentration factor (RCF) of both traditional (e.g., polycyclic aromatic hydrocarbons, polychlorinated biphenyls) and emerging ACs (e.g., phthalate acid esters, aryl organophosphate esters). Four ML algorithms were employed, trained on a unified RCF dataset comprising 878 data points, covering 6 features of soil-plant cultivation systems and 98 molecular descriptors of 55 chemicals, including 29 emerging ACs. The gradient-boosted regression tree (GBRT) model demonstrated strong predictive performance, with a coefficient of determination (R<sup>2</sup>) of 0.75, a mean absolute error (MAE) of 0.11, and a root mean square error (RMSE) of 0.22, as validated by five-fold cross-validation. Multiple explanatory analyses highlighted the significance of soil organic matter (SOM), plant protein and lipid content, exposure time, and molecular descriptors related to electronegativity distribution pattern (GATS8e) and double-ring structure (fr_bicyclic). An increase in SOM was found to decrease the overall RCF, while other variables showed strong correlations within specific ranges. This GBRT model provides an important tool for assessing the environmental behaviors of ACs in soil-plant systems, thereby supporting further investigations into their ecological and human exposure risks.</p>\",\"PeriodicalId\":23195,\"journal\":{\"name\":\"Toxics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2024-10-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11511036/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Toxics\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://doi.org/10.3390/toxics12100737\",\"RegionNum\":3,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Toxics","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.3390/toxics12100737","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
Machine Learning Models for Predicting Bioavailability of Traditional and Emerging Aromatic Contaminants in Plant Roots.
To predict the behavior of aromatic contaminants (ACs) in complex soil-plant systems, this study developed machine learning (ML) models to estimate the root concentration factor (RCF) of both traditional (e.g., polycyclic aromatic hydrocarbons, polychlorinated biphenyls) and emerging ACs (e.g., phthalate acid esters, aryl organophosphate esters). Four ML algorithms were employed, trained on a unified RCF dataset comprising 878 data points, covering 6 features of soil-plant cultivation systems and 98 molecular descriptors of 55 chemicals, including 29 emerging ACs. The gradient-boosted regression tree (GBRT) model demonstrated strong predictive performance, with a coefficient of determination (R2) of 0.75, a mean absolute error (MAE) of 0.11, and a root mean square error (RMSE) of 0.22, as validated by five-fold cross-validation. Multiple explanatory analyses highlighted the significance of soil organic matter (SOM), plant protein and lipid content, exposure time, and molecular descriptors related to electronegativity distribution pattern (GATS8e) and double-ring structure (fr_bicyclic). An increase in SOM was found to decrease the overall RCF, while other variables showed strong correlations within specific ranges. This GBRT model provides an important tool for assessing the environmental behaviors of ACs in soil-plant systems, thereby supporting further investigations into their ecological and human exposure risks.
ToxicsChemical Engineering-Chemical Health and Safety
CiteScore
4.50
自引率
10.90%
发文量
681
审稿时长
6 weeks
期刊介绍:
The Journal accepts papers describing work that furthers our understanding of the exposure, effects, and risks of chemicals and materials in humans and the natural environment as well as approaches to assess and/or manage the toxicological and ecotoxicological risks of chemicals and materials. The journal covers a wide range of toxic substances, including metals, pesticides, pharmaceuticals, biocides, nanomaterials, and polymers such as micro- and mesoplastics. Toxics accepts papers covering:
The occurrence, transport, and fate of chemicals and materials in different systems (e.g., food, air, water, soil);
Exposure of humans and the environment to toxic chemicals and materials as well as modelling and experimental approaches for characterizing the exposure in, e.g., water, air, soil, food, and consumer products;
Uptake, metabolism, and effects of chemicals and materials in a wide range of systems including in-vitro toxicological assays, aquatic and terrestrial organisms and ecosystems, model mammalian systems, and humans;
Approaches to assess the risks of chemicals and materials to humans and the environment;
Methodologies to eliminate or reduce the exposure of humans and the environment to toxic chemicals and materials.