Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Oct 12;12(10):737.
doi: 10.3390/toxics12100737.

Machine Learning Models for Predicting Bioavailability of Traditional and Emerging Aromatic Contaminants in Plant Roots

Siyuan Li  1 , Yuting Shen  1 , Meng Gao  1 , Huatai Song  1 , Zhanpeng Ge  1 , Qiuyue Zhang  1 , Jiaping Xu  1 , Yu Wang  1 , Hongwen Sun  1
Affiliations

Machine Learning Models for Predicting Bioavailability of Traditional and Emerging Aromatic Contaminants in Plant Roots

Siyuan Li et al. Toxics. .

Abstract

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.

Keywords: GBRT; RCF; aromatic contaminants; molecular descriptors; root concentration factor; root uptake.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Workflow of model construction and evaluation.
Figure 2
Figure 2
t-SNE visualization of RCF incorporating chemical, soil, and plant characteristics.
Figure 3
Figure 3
Performance of GBRT, RF, SVR, and LR models for predicting RCFs of traditional and emerging ACs.
Figure 4
Figure 4
Permutation feature importance of the GBRT model for predicting RCFs of traditional and emerging ACs.
Figure 5
Figure 5
SHAP analysis of the GBRT model for predicting RCFs of traditional and emerging ACs.
Figure 6
Figure 6
ICE analysis of key features of SOM, lipid content, protein content, xlogP, exposure time, and cultivation mode in the GBRT model for predicting RCFs of traditional and emerging ACs.
See this image and copyright information in PMC

References

    1. Vanwijnsberghe S., Peeters C., De Ridder E., Dumolin C., Wieme A.D., Boon N., Vandamme P. Genomic Aromatic Compound Degradation Potential of Novel Paraburkholderia Species: Paraburkholderia domus sp. nov., Paraburkholderia haematera sp. nov. and Paraburkholderia nemoris sp. nov. Int. J. Mol. Sci. 2021;22:7003. doi: 10.3390/ijms22137003. - DOI - PMC - PubMed
    1. Sakshi, Singh S.K., Haritash A.K. Polycyclic aromatic hydrocarbons: Soil pollution and remediation. Int. J. Environ. Sci. Technol. 2019;16:6489–6512. doi: 10.1007/s13762-019-02414-3. - DOI
    1. Przybysz A., Nersisyan G., Gawronski S.W. Removal of particulate matter and trace elements from ambient air by urban greenery in the winter season. Environ. Sci. Pollut. Res. 2019;26:473–482. doi: 10.1007/s11356-018-3628-0. - DOI - PMC - PubMed
    1. Primbs T., Piekarz A., Wilson G., Schmedding D., Higginbotham C., Field J., Simonich S.M. Influence of Asian and Western United States urban areas and fires on the atmospheric transport of polycyclic aromatic hydrocarbons, polychlorinated biphenyls, and fluorotelomer alcohols in the Western United States. Environ. Sci. Technol. 2008;42:6385–6391. doi: 10.1021/es702160d. - DOI - PMC - PubMed
    1. Shaul N.J., Dodder N.G., Aluwihare L.I., Mackintosh S.A., Maruya K.A., Chivers S.J., Danil K., Weller D.W., Hoh E. Nontargeted biomonitoring of halogenated organic compounds in two ecotypes of bottlenose dolphins (Tursiops truncatus) from the Southern California Bight. Environ. Sci. Technol. 2015;49:1328–1338. doi: 10.1021/es505156q. - DOI - PMC - PubMed