Prediction of developmental toxic effects of fine particulate matter (PM) water-soluble components via machine learning through observation of PM from diverse urban areas.

Journal: The Science of the total environment
PMID:

Abstract

The global health implications of fine particulate matter (PM) underscore the imperative need for research into its toxicity and chemical composition. In this study, zebrafish embryos exposed to the water-soluble components of PM from two cities (Harbin and Hangzhou) with differences in air quality, underwent microscopic examination to identify primary target organs. The Harbin PM induced dose-dependent organ malformation in zebrafish, indicating a higher level of toxicity than that of the Hangzhou sample. Harbin PM led to severe deformities such as pericardial edema and a high mortality rate, while the Hangzhou sample exhibited hepatotoxicity, causing delayed yolk sac absorption. The experimental determination of PM constituents was followed by the application of four algorithms for predictive toxicological assessment. The random forest algorithm correctly predicted each of the effect classes and showed the best performance, suggesting that zebrafish malformation rates were strongly correlated with water-soluble components of PM. Feature selection identified the water-soluble ions F and Cl and metallic elements Al, K, Mn, and Be as potential key components affecting zebrafish development. This study provides new insights into the developmental toxicity of PM and offers a new approach for predicting and exploring the health effects of PM.

Authors

  • Yang Fan
    Colby College, Waterville, Maine, United States of America.
  • Nannan Sun
    Hangzhou SanOmics Information Technology Co., Ltd., Hangzhou 310015, P. R. China.
  • Shenchong Lv
    Department of Medical Oncology of the Second Affiliated Hospital, Department of Toxicology, Zhejiang University School of Medicine, Hangzhou 310058, China.
  • Hui Jiang
    Queensland Alliance for Environmental Health Science (QAEHS), University of Queensland, 20 Cornwall Street, Woolloongabba, QLD 4012, Australia.
  • Ziqing Zhang
    Department of Medical Oncology of the Second Affiliated Hospital, Department of Toxicology, Zhejiang University School of Medicine, Hangzhou 310058, China.
  • Junjie Wang
    School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China.
  • Yiyi Xie
    Department of Medical Oncology of the Second Affiliated Hospital, Department of Toxicology, Zhejiang University School of Medicine, Hangzhou 310058, China.
  • Xiaomin Yue
    Department of Biophysics, Zhejiang University School of Medicine, Hangzhou 310058, China; Department of Neurology of the Fourth Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310058, China.
  • Baolan Hu
    College of Environmental Resource Sciences, Zhejiang University, Hangzhou 310058, China. Electronic address: blhu@zju.edu.cn.
  • Bin Ju
    Hangzhou Wowjoy Information Technology Co., Ltd, Hangzhou, China. bin.ju@wowjoy.cn.
  • Peilin Yu
    Department of Medical Oncology of the Second Affiliated Hospital, Department of Toxicology, Zhejiang University School of Medicine, Hangzhou 310058, China. Electronic address: yupeilin@zju.edu.cn.