Using machine learning to classify the immunosuppressive activity of per- and polyfluoroalkyl substances

被引:0
作者
Xuan, Yuxin [1 ]
Wang, Yulu [1 ]
Li, Rui [1 ]
Zhong, Yuyan [1 ]
Wang, Na [1 ]
Zhang, Lingyin [1 ]
Chen, Qian [1 ]
Yu, Shuling [2 ]
Yuan, Jintao [1 ]
机构
[1] Zhengzhou Univ, Coll Publ Hlth, Zhengzhou, Peoples R China
[2] Henan Univ, Key Lab Nat Med & Immune Engn Henan Prov, Kaifeng, Henan, Peoples R China
关键词
Per- and polyfluoroalkyl substances; machine learning; random forest; immunosuppression; extreme gradient boosting machine; PERFLUOROALKYL SUBSTANCES; FEATURE-SELECTION;
D O I
10.1080/15376516.2024.2387733
中图分类号
R99 [毒物学(毒理学)];
学科分类号
100405 ;
摘要
Per- and polyfluoroalkyl substances (PFASs), one of the persistent organic pollutants, have immunosuppressive effects. The evaluation of this effect has been the focus of regulatory toxicology. In this investigation, 146 PFASs (immunosuppressive or nonimmunosuppressive) and corresponding concentration gradients were collected from literature, and their structures were characterized by using Dragon descriptors. Feature importance analysis and stepwise feature elimination are used for feature selection. Three machine learning (ML) methods, namely Random Forest (RF), Extreme Gradient Boosting Machine (XGB), and Categorical Boosting Machine (CB), were utilized for model development. The model interpretability was explored by feature importance analysis and correlation analysis. The findings indicated that the three models developed have exhibited excellent performance. Among them, the best-performing RF model has an average AUC score of 0.9720 for the testing set. The results of the feature importance analysis demonstrated that concentration, SpPosA_X, IVDE, R2s, and SIC2 were the crucial molecular features. Applicability domain analysis was also performed to determine reliable prediction boundaries for the model. In conclusion, this study is the first application of ML models to investigate the immunosuppressive activity of PFASs. The variables used in the models can help understand the mechanism of the immunosuppressive activity of PFASs, allow researchers to more effectively assess the immunosuppressive potential of a large number of PFASs, and thus better guide environmental and health risk assessment efforts.
引用
收藏
页码:72 / 80
页数:9
相关论文
共 50 条
[41]   Preferential Partitioning of Per- and Polyfluoroalkyl Substances in Freshwater Ice [J].
Sherman-Bertinetti, Summer L. ;
Gruber, Kaitlyn J. ;
Remucal, Christina K. .
ENVIRONMENTAL SCIENCE & TECHNOLOGY, 2024, 58 (34) :15214-15223
[42]   Consideration of pathways for immunotoxicity of per- and polyfluoroalkyl substances (PFAS) [J].
Veronika Ehrlich ;
Wieneke Bil ;
Rob Vandebriel ;
Berit Granum ;
Mirjam Luijten ;
Birgitte Lindeman ;
Philippe Grandjean ;
Andreas-Marius Kaiser ;
Ingrid Hauzenberger ;
Christina Hartmann ;
Claudia Gundacker ;
Maria Uhl .
Environmental Health, 22
[43]   Per- and polyfluoroalkyl substances in the Western Mediterranean Sea waters [J].
Brumovsky, Miroslav ;
Karaskova, Pavlina ;
Borghini, Mireno ;
Nizzetto, Luca .
CHEMOSPHERE, 2016, 159 :308-316
[44]   Prediction of critical micelle concentration for per- and polyfluoroalkyl substances [J].
Creton, B. ;
Barraud, E. ;
Nieto-Draghi, C. .
SAR AND QSAR IN ENVIRONMENTAL RESEARCH, 2024, 35 (04) :309-324
[45]   Electrothermal mineralization of per- and polyfluoroalkyl substances for soil remediation [J].
Cheng, Yi ;
Deng, Bing ;
Scotland, Phelecia ;
Eddy, Lucas ;
Hassan, Arman ;
Wang, Bo ;
Silva, Karla J. ;
Li, Bowen ;
Wyss, Kevin M. ;
Ucak-Astarlioglu, Mine G. ;
Chen, Jinhang ;
Liu, Qiming ;
Si, Tengda ;
Xu, Shichen ;
Gao, Xiaodong ;
JeBailey, Khalil ;
Jana, Debadrita ;
Torres, Mark Albert ;
Wong, Michael S. ;
Yakobson, Boris I. ;
Griggs, Christopher ;
McCary, Matthew A. ;
Zhao, Yufeng ;
Tour, James M. .
NATURE COMMUNICATIONS, 2024, 15 (01)
[46]   Biodegradation of per- and polyfluoroalkyl substances: microbes, enzymes and their interactions [J].
Ye, Dongyun ;
Wang, Zeyu ;
Qian, Xiaofei ;
Kai, Ouyang ;
Wu, Dizhi ;
Tang, Fan ;
Hrynsphan, Dzmitry ;
Savitskaya, Tatsiana ;
Chen, Jun .
REVIEWS IN ENVIRONMENTAL SCIENCE AND BIO-TECHNOLOGY, 2025, 24 (01) :43-62
[47]   Associations of per-/polyfluoroalkyl substances with glucocorticoids and progestogens in newborns [J].
Liu, Hongxiu ;
Pan, Yitao ;
Jin, Shuna ;
Li, Yuanyuan ;
Zhao, Liuqing ;
Sun, Xiaojie ;
Cui, Qianqian ;
Zhang, Bin ;
Zheng, Tongzhang ;
Xia, Wei ;
Zhou, Aifen ;
Campana, Anna Maria ;
Dai, Jiayin ;
Xu, Shunqing .
ENVIRONMENT INTERNATIONAL, 2020, 140
[48]   Per- and polyfluoroalkyl substances in foam and dewatering streams at wastewater treatment plants [J].
Schaefer, Charles E. ;
Hooper, Jennifer L. ;
Strom, Laurel E. ;
Wu, Ke ;
Guelfo, Jennifer L. .
AWWA WATER SCIENCE, 2023, 5 (04)
[49]   Per- and polyfluoroalkyl substances (PFAS) in sediment: a source of PFAS to the food web? [J].
Endicott, Douglas ;
Silva-Wilkinson, Robin ;
Mccauley, Dennis ;
Armstrong, Brandon .
INTEGRATED ENVIRONMENTAL ASSESSMENT AND MANAGEMENT, 2025, 21 (04) :810-822
[50]   Mechanism for the adsorption of Per- and polyfluoroalkyl substances on kaolinite: Molecular dynamics modeling [J].
Ke, Ze-Wei ;
Wei, Sheng-Jie ;
Shen, Peng ;
Chen, Yun-Min ;
Li, Yu-Chao .
APPLIED CLAY SCIENCE, 2023, 232