Citation: Ting Zeng, Yanshan Liang, Qingyuan Dai, Jinglin Tian, Jinyao Chen, Bo Lei, Zhu Yang, Zongwei Cai. Application of machine learning algorithms to screen potential biomarkers under cadmium exposure based on human urine metabolic profiles[J]. Chinese Chemical Letters, ;2022, 33(12): 5184-5188. doi: 10.1016/j.cclet.2022.03.020 shu

Application of machine learning algorithms to screen potential biomarkers under cadmium exposure based on human urine metabolic profiles

Ting Zeng ^{a, b} ,
Yanshan Liang ^{a, b} ,
Qingyuan Dai ^{a, b} ,
Jinglin Tian ^{a, b} ,
Jinyao Chen ^c ,
Bo Lei ^a ,
Zhu Yang ^b ,
Zongwei Cai ^{b, *,}

a.
Food Science and Technology Program, Beijing Normal University-Hong Kong Baptist University United International College, Zhuhai 519087, China
b.
State Key Laboratory of Environmental and Biological Analysis, Department of Chemistry, Hong Kong Baptist University, Hong Kong, China
c.
Department of Nutrition, Food Safety and Toxicology, West China School of Public Health, Sichuan University, Chengdu 610041, China

zwcai@hkbu.edu.hk

Received Date: 27 December 2021
Revised Date: 23 January 2022
Accepted Date: 4 March 2022
Available Online: 7 March 2022

Figures(3)

Exposure to environmental cadmium increases the health risk of residents. Early urine metabolic detection using high-resolution mass spectrometry and machine learning algorithms would be advantageous to predict the adverse health effects. Here, we conducted machine learning approaches to screen potential biomarkers under cadmium exposure in 403 urine samples. In positive and negative ionization mode, 4207 and 3558 features were extracted, respectively. We compared seven machine learning algorithms and found that the extreme gradient boosting (XGBoost) and random forest (RF) classifiers showed better accuracy and predictive performance than others. Following 5-fold cross-validation, the value of area under curve (AUC) was both 0.93 for positive and negative ionization modes in XGBoost classifier. In the RF classifier, AUC were 0.80 and 0.84 for positive and negative ionization modes, respectively. We then identified a biomarker panel based on XGBoost and RF classifiers. The incorporation of machine learning models into urine analysis using high-resolution mass spectrometry could allow a convenient assessment of cadmium exposure.
- Human urine,
- High-resolution mass spectrometry,
- Cadmium exposure,
- Metabolic profiles,
- Machine learning
1. [1]
  S. Himeno, K. Aoshima, Cadmium Toxicity: New Aspects in Human Disease, Rice Contamination, and Cytotoxicity, Singapore, 2019.
2. [2]
  S. Satarug, Toxics. 6 (2018) 15. doi: 10.3390/toxics6010015
3. [3]
  E.D. Evans, C. Duvallet, N.D. Chu, et al., Sci. Rep. 10 (2020) 1–13. doi: 10.1038/s41598-019-56847-4
4. [4]
  A.S. Martinez-Vernon, J.A. Covington, R.P. Arasaradnam, et al., PLoS ONE 13 (2018) e0204425. doi: 10.1371/journal.pone.0204425
5. [5]
  Y. Gao, Y. Lu, S. Huang, et al., Environ. Sci. Technol. 48 (2014) 6409–6418. doi: 10.1021/es500750w
6. [6]
  H. Li, K. Huang, S. Jin, et al., Int. J. Hyg. Environ. Heal. 222 (2019) 556–562. doi: 10.1016/j.ijheh.2019.02.007
7. [7]
  T. Zeng, Y.S. Liang, J.Y. Chen, et al., Environ. Int. 154 (2021) 106646. doi: 10.1016/j.envint.2021.106646
8. [8]
  E.H. Wilkes, G. Rumsby, G.M. Woodward, Clin. Chem. 64 (2018) 1586–1595. doi: 10.1373/clinchem.2018.292201
9. [9]
  H.E. Anderson, T. Liden, B.K. Berger, et al., Anal. Chim. Acta 1172 (2021) 338668. doi: 10.1016/j.aca.2021.338668
10. [10]
  F. Roux-Dalvai, C. Gotti, M. Leclercq, et al., Mol. Cell Proteom. 18 (2019) 2492–2505. doi: 10.1074/mcp.tir119.001559
11. [11]
  G.L. Streun, A.E. Steuer, L.C. Ebert, A. Dobay, T. Kraemer, Clin. Chem. Lab. Med. 59 (2021) 1392–1399. doi: 10.1515/cclm-2021-0010
12. [12]
  Y.C. Huang, H.H. Chung, E.P. Dutkiewicz, et al., Anal. Chem. 92 (2019) 1653–1657. doi: 10.1002/cbic.201800814
13. [13]
  U.W. Liebal, A.N.T. Phan, M. Sudhakar, K. Raman, L.M. Blank, Metabolites 10 (2020) 243. doi: 10.3390/metabo10060243
14. [14]
  E.H. Wilkes, E. Emmett, L. Beltran, G.M. Woodward, R.S. Carling, Clin. Chem. 66 (2020) 1210–1218. doi: 10.1093/clinchem/hvaa134
15. [15]
  J. Huo, Z. Huang, R. Li, et al., PLoS ONE 13 (2018) e0201454. doi: 10.1371/journal.pone.0201454
16. [16]
  J.M. Mato, M.L. Martínez-Chantar, S.C. Lu, Ann. Hepatol. 12 (2015) 183–189.
17. [17]
  N.N. Pavlova, S. Hui, J.M. Ghergurovich, et al., Cell Metab. 27 (2018) 428–438. doi: 10.1016/j.cmet.2017.12.006
18. [18]
  J. Płonka, M. Babiuch, H. Barchanska, Chemosphere 286 (2022) 131592. doi: 10.1016/j.chemosphere.2021.131592
19. [19]
  M. Chen, B. Zhang, S. Cai, et al., J. Proteom. 200 (2019) 134–143. doi: 10.1016/j.jprot.2019.03.015
20. [20]
  J. Neunzig, R. Bernhardt, PLoS ONE 9 (2014) e89727. doi: 10.1371/journal.pone.0089727
21. [21]
  F.K. Abu Salem, M. Jurdi, M. Alkadri, F. Hachem, H.R. Dhaini, Environ. Sci. Pollut. Res. 29 (2022) 8253–8268. doi: 10.1007/s11356-021-15897-w
22. [22]
  X. Li, T. Geng, W. Shen, J. Zhang, Y. Zhou, Ecotoxicol. Environ. Saf. 209 (2021) 111773. doi: 10.1016/j.ecoenv.2020.111773
23. [23]
  K. Nakamura, T. Yasutaka, T. Kuwatani, T. Komai, Chemosphere 186 (2017) 501–509. doi: 10.1016/j.chemosphere.2017.07.131
24. [24]
  Z. Xin, S. Jun, T. Yan, et al., Chemometr. Intell. Lab. Syst. 200 (2020) 103996. doi: 10.1016/j.chemolab.2020.103996
25. [25]
  L. Wei, Y. Huang, Z. Chen, et al., Front. Oncol. 11 (2021) 4148.
26. [26]
  X. Zhu, X. Wang, Y.S. Ok, J. Hazard. Mater. 378 (2019) 120727. doi: 10.1016/j.jhazmat.2019.06.004
27. [27]
  V. Cantoni, R. Green, C. Ricciardi, et al., Comput. Math Methods Med. 16 (2021) 5288844.
28. [28]
  X. Jia, B. Hu, B.P. Marchant, et al., Environ. Pollut. 250 (2019) 601–609. doi: 10.1016/j.envpol.2019.04.047
29. [29]
  M. Hussain, Z. Chen, M. Lv, et al., Chin. Chem. Lett. 31 (2020) 3163–3167. doi: 10.1016/j.cclet.2020.04.038
30. [30]
  Y. Guo, A. Graber, R.N. McBurney, R. Balasubramanian, BMC Bioinform. 11 (2010) 1–19.
31. [31]
  S.K. Park, Z. Zhao, B. Mukherjee, Environ. Health 16 (2017) 1–17. doi: 10.1186/s12940-016-0208-y
32. [32]
  T. Guan, Y. Xin, K. Zheng, et al., BioMetals 34 (2021) 33–48. doi: 10.1007/s10534-020-00260-2
33. [33]
  X. He, Z. Qi, H. Hou, J. Gao, X.X. Zhang, J. Hazard. Mater. 388 (2020) 121791. doi: 10.1016/j.jhazmat.2019.121791
34. [34]
  M.Y. Xu, Y.J. Sun, P. Wang, L. Yang, Y.J. Wu, Ecotoxicol. Environ. Saf. 195 (2020) 110467. doi: 10.1016/j.ecoenv.2020.110467
35. [35]
  L. Zong, J. Xing, L. Shu, et al., Ecotoxicol. Environ. Saf. 147 (2018) 26–33. doi: 10.1016/j.ecoenv.2017.08.028
36. [36]
  G. Xun, C. Yang, Y. Hong, et al., Sci. Total Environ. 676 (2019) 72–86. doi: 10.1016/j.scitotenv.2019.04.208
37. [37]
  L. Xie, Y. Zhao, J. Duan, et al., Chem. Res. Toxicol. 33 (2020) 1897–1906. doi: 10.1021/acs.chemrestox.0c00091
38. [38]
  Y. Liang, T. Zeng, J. Tian, et al., Sci. Total Environ. 798 (2021) 149379. doi: 10.1016/j.scitotenv.2021.149379
39. [39]
  M. Valcke, N. Ouellet, M. Dubé, et al., Toxicol. Lett. 312 (2019) 148–156. doi: 10.1016/j.toxlet.2019.05.014
40. [40]
  M.Y. Xu, P. Wang, Y.J. Sun, Y.J. Wu, Toxicology 384 (2017) 50–58. doi: 10.1016/j.tox.2017.04.008
41. [41]
  T. Zeng, W. Guo, L. Jiang, et al., Sci. Total Environ. 801 (2021) 149803. doi: 10.1016/j.scitotenv.2021.149803
42. [42]
  L. Xiang, J. Nie, L. Wang, et al., Chin. Chem. Lett. 32 (2021) 2197–2202. doi: 10.1016/j.cclet.2020.12.042
43. [43]
  H. Luan, W. Gu, H. Li, et al., J. Transl. Med. 19 (2021) 1–10. doi: 10.1186/s12967-020-02683-4
1. [1]
  Zhang Jiawei , Chen Jianfu , Hu Peijun , Wang Haifeng . Identifying the composition and atomic distribution of Pt-Au bimetallic nanoparticle with machine learning and genetic algorithm. Chinese Chemical Letters, 2020, 31(3): 890-896. doi: 10.1016/j.cclet.2019.12.006
2. [2]
  Lv Yiwei , Li Tiegang , Guo Chengan , Sun Chenglong , Tang Fei , Huang Luojiao , Luo Zhigang , Li Xin , Zhang Ruiping , Zang Qingce , He Jiuming , Abliz Zeper . A high-performance bio-tissue imaging method using air flow-assisted desorption electrospray ionization coupled with a high-resolution mass spectrometer. Chinese Chemical Letters, 2019, 30(2): 461-464. doi: 10.1016/j.cclet.2018.06.006
3. [3]
  Zhao Hongzhi , Li Jiufeng , Ma Xinli , Huo Wenqian , Xu Shunqing , Cai Zongwei . Simultaneous determination of bisphenols, benzophenones and parabens in human urine by using UHPLC-TQMS. Chinese Chemical Letters, 2018, 29(1): 102-106. doi: 10.1016/j.cclet.2017.06.013
4. [4]
  Hongzhi Zhao , Yuanyuan Zheng , Lin Zhu , Li Xiang , Shunqing Xu , Zongwei Cai . Trimester-specific urinary metabolome alterations associated with gestational diabetes mellitus: A study in different pregnancy stages. Chinese Chemical Letters, 2022, 33(6): 3139-3143. doi: 10.1016/j.cclet.2021.10.001
5. [5]
  Zhang Lin , Xu Tengfei , Pi Zifeng , Zheng Meizhu , Song Fengrui , Liu Zhiqiang . Effects of the ambient fine particulate matter (PM2.5) exposure on urinary metabolic profiles in rats using UPLC-Q-TOF-MS. Chinese Chemical Letters, 2019, 30(1): 90-94. doi: 10.1016/j.cclet.2017.11.019
6. [6]
  Ji ZHANG , Chun Sheng LIU , Yi Zhong ZHANG , Chang Jiu ZHANG , Li YE , Tong Hui ZHOU . GAS CHROMATOGRAPHIC-MASS SPECTROMETRIC ANALYSIS OF ANABOLIC STEROIDS IN HUMAN URINE. Chinese Chemical Letters, 1990, 1(2): 143-146.
7. [7]
  Mohammad ASADI , Ali Mohammad HAJI SHABANI , Shayessteh DADFARNIA , Bijan ABBASI . Solidified floating organic drop microextraction combined with high performance liquid chromatography for the determination of carbamazepine in human plasma and urine samples. Chinese Journal of Chromatography, 2015, 33(6): 634-641. doi: 10.3724/SP.J.1123.2015.02072
8. [8]
  Hongyu Liu , Gang Meng , Zanhong Deng , Meng Li , Junqing Chang , Tiantian Dai , Xiaodong Fang . Progress in Research on VOC Molecule Recognition by Semiconductor Sensors. Acta Physico-Chimica Sinica, 2022, 38(5): 2008018-0. doi: 10.3866/PKU.WHXB202008018
9. [9]
  Li Ming DU , Zhe Feng FAN , Jin Li QIAO , Jing Ping WANG . Determination of Sparfloxacin in Human Urine by Reversed-Phase High Performance Liquid Chromatography With Nitrous Acid and Hydroiodic Pre-Column Derivatization. Chinese Chemical Letters, 2001, 12(11): 1007-1010.
10. [10]
  Mubashir Hussain , Xiaolong Liu , Jun Zou , Jian Yang , Zeeshan Ali , Hamood Ur Rehman , Nongyue He , Jianguo Dai , Yongjun Tang . On-chip classification of micro-particles using laser light scattering and machine learning. Chinese Chemical Letters, 2022, 33(4): 1885-1888. doi: 10.1016/j.cclet.2021.09.044
11. [11]
  Ya Wei LI , Xiu Yuan ZHU . IDENTIFICATION OF A METABOLITE OF BIPHENYLDIMETHYLDICARBOXYLE IN HUMAN URINE. Chinese Chemical Letters, 1996, 7(4): 345-346.
12. [12]
  Chenhang Chao , Ping Lu , Xin Hong . AI化学狂想曲. University Chemistry, 2022, 37(9): 2207027-0. doi: 10.3866/PKU.DXHX202207027
13. [13]
  CAO Jie , GU Zhen , LIU Ming-Feng , DANG Li-Hong , DU Qiu-Xiang , LI Yu , SUN Jun-Hong . Study on Postmortem Interval Estimation by Proton Nuclear Magnetic Resonance Spectroscopy-based Metabolomics. Chinese Journal of Analytical Chemistry, 2022, 50(10): 1551-1559. doi: 10.19756/j.issn.0253-3820.221049
14. [14]
  Yang QIN , Chang Jiu ZHANG , You Xuan XU , Shao Tang ZHU . GC/MS CONFIRMATORY METHOD OF BENZTHIAZIDE IN HUMAN URINE. Chinese Chemical Letters, 1995, 6(6): 497-500.
15. [15]
  Xiao Bai XU , Surinder KAUR , David MALTBY , Alma BURLINGAME . XENOBIOTICALLY MODIFIED HUMAN HEMOGLOBIN STUDIED BY ELECTROSPRAY MASS SPECTROMETRY. Chinese Chemical Letters, 1995, 6(5): 399-402.
16. [16]
  Meng-Yuan Chen , Zhu Gui , Ke-Ke Chen , Jiang-Hui Ding , Jin-Gang He , Jun Xiong , Jia-Le Li , Jie Wang , Bi-Feng Yuan , Yu-Qi Feng . Adolescent alcohol exposure alters DNA and RNA modifications in peripheral blood by liquid chromatography-tandem mass spectrometry analysis. Chinese Chemical Letters, 2022, 33(4): 2086-2090. doi: 10.1016/j.cclet.2021.08.094
17. [17]
  Hua Lin XIE , Xi Du NIE , You Gen TANG . Quantification of Trace Amounts of Impurities in High Purity Cobalt by High Resolution Inductively Coupled Plasma Mass Spectrometry. Chinese Chemical Letters, 2006, 17(8): 1077-1080.
18. [18]
  Fu Yong Zhao , Zong Hua Wang , Hui Wang , Rui Zhao , Ming Yu Ding . Determination of uric acid in human urine by ion chromatography with conductivity detector. Chinese Chemical Letters, 2011, 22(3): 342-345. doi: 10.1016/j.cclet.2010.10.008
19. [19]
  Ke Jun TAN , Yuan Fang LI , Cheng Zhi HUANG , Xue Lian LIU . Determination of Chlorine in Human Urine by Detecting Backscattering Signals with a New Optical Assembly. Chinese Chemical Letters, 2006, 17(5): 679-682.
20. [20]
  Cheng Quan Wang , Hui Wang , Yan Ming Liu . Capillary electrophoresis with direct chemiluminescence detection for the analysis of catecholamines in human urine. Chinese Chemical Letters, 2007, 18(4): 452-454. doi: 10.1016/j.cclet.2007.02.009

Get Citation

PDF

XML

Metrics

PDF Downloads(0)
Abstract views(83)
HTML views(5)

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142