Machine learning prediction of copper ion interference with mercury ion fluorescence signals in food heavy metal detection

Authors

SONG Fangliang, College of Food Science and Engineering, Central South University of Forestry and Technology, Changsha, Hunan 410004, China;Molecular Nutrition Branch, National Engineering Research Center of Rice and By-Product Deep Processing, Changsha, Hunan 410004, China
LIANG Ying, College of Food Science and Engineering, Central South University of Forestry and Technology, Changsha, Hunan 410004, China;Molecular Nutrition Branch, National Engineering Research Center of Rice and By-Product Deep Processing, Changsha, Hunan 410004, ChinaFollow
DONG Jie, Xiangya School of Pharmaceutical Sciences, Central South University, Changsha, Hunan 410013, China
WANG Xuejie, College of Food Science and Engineering, Central South University of Forestry and Technology, Changsha, Hunan 410004, China;Molecular Nutrition Branch, National Engineering Research Center of Rice and By-Product Deep Processing, Changsha, Hunan 410004, China
QIAN Jie, College of Food Science and Engineering, Central South University of Forestry and Technology, Changsha, Hunan 410004, China;Molecular Nutrition Branch, National Engineering Research Center of Rice and By-Product Deep Processing, Changsha, Hunan 410004, China

Corresponding Author(s)

梁盈（1981—），女，中南林业科技大学教授，博士。E-mail：liangying498@163.com董界（1989—），男，中南大学副教授，博士。E-mail：jiedong@csu.edu.cn

Abstract

Objective: To construct an artificial intelligence prediction model to predict the selectivity of fluorescent probes for Hg²⁺ in a complex food testing environment in the presence of Cu²⁺ interference. Methods: Fluorescent probe technology combined with seven advanced classical machine learning models was used to predict and analyze the selectivity of the probe for Hg²⁺ in the presence of Cu²⁺ interference, and to compare the prediction effect of each model and select the optimal model. Results: Efficient models with accuracies of 0.786 and 0.810 in the cross-validation and test sets were successfully established based on Molecular 2D Descriptors （Mol2D） and extreme gradient boosting algorithms to accurately predict the probe selectivity of Hg²⁺ under Cu²⁺ interference. Conclusion: The model is improved for the design of Hg²⁺ fluorescent molecular probes by selective prediction, which makes the design of Hg²⁺ fluorescent probes more efficient and reliable.

Publication Date

7-22-2024

First Page

62

Last Page

66,153

DOI

10.13652/j.spjx.1003.5788.2024.60045

Recommended Citation

Fangliang, SONG; Ying, LIANG; Jie, DONG; Xuejie, WANG; and Jie, QIAN (2024) "Machine learning prediction of copper ion interference with mercury ion fluorescence signals in food heavy metal detection," Food and Machinery: Vol. 40: Iss. 5, Article 8.
DOI: 10.13652/j.spjx.1003.5788.2024.60045
Available at: https://www.ifoodmm.cn/journal/vol40/iss5/8

References

[1] PRAJAPATI S, CHALLIS J K, JARDINE T D, et al. Levels of pesticides and trace metals in water, sediment, and fish of a large, agriculturally-dominated river[J]. Chemosphere, 2022, 308: 136236.
[2] ULLAH N, UR REHMAN M, AHMAD B, et al. Assessment of heavy metals accumulation in agricultural soil, vegetables and associated health risks[J]. PLoS One, 2022, 17（6）: e0267719.
[3] 王丽, 许华杰, 李海丽, 等. 茂名地区主要水产品汞含量分析与风险评估[J]. 食品与机械, 2021, 37（9）: 73-77. WANG L, XU H J, LI H L, et al. Mercury content analysis and risk assessment of the major aquatic products in Maoming[J]. Food & Machinery, 2021, 37（9）: 73-77.
[4] LIAQUAT H, IMRAN M, LATIF S, et al. Multifunctional nanomaterials and nanocomposites for sensing and monitoring of environmentally hazardous heavy metal contaminants[J]. Environmental Research, 2022, 214: 113795.
[5] MICHALSKI R, JABONSKA M, SZOPA S, et al. Application of ion chromatography with ICP-MS or MS detection to the determination of selected halides and metal/metalloids species[J]. Critical Reviews in Analytical Chemistry, 2011, 41（2）: 133-150.
[6] BOLSHOV M A, KOLOSHNIKOV V G, RUDNEV S N, et al. Detection of trace amounts of toxic metals in environmental samples by laser-excited atomic fluorescence spectrometry[J]. Journal of Analytical Atomic Spectrometry, 1992, 7（2）: 99-104.
[7] DONG H, GIRMATSION M, WANG R Y, et al. Construction of fluorescent logic gates for the detection of mercury（II） and ciprofloxacin based on phycocyanin[J]. Methods and Applications in Fluorescence, 2022, 10（3）: 035008.
[8] GONG L D, ZHANG L X, SHEN R, et al. A novel conjugated polymer fluorescence probe for the detection of copper ions in aqueous media[J]. Methods and Applications in Fluorescence, 2022, 11（1）: 015001.
[9] 武玲, 韦庆益, 蒲洪彬. 黄绿色碳量子点的热合成荧光探针及其在白皮杉醇促氧化作用中的研究[J]. 现代食品科技, 2019, 35（10）: 174-181. WU L, WEI Q Y, PU H B. A thermal synthesis of yellow-green carbon dots as a fluorescent probe for the study of the pro-oxidation of piceatannol[J]. Modern Food Science and Technology, 2019, 35（10）: 174-181.
[10] LI G C, GAO G Q, CHENG J Y, et al. Two new reversible naphthalimide-based fluorescent chemosensors for Hg²⁺[J]. Luminescence, 2016, 31（4）: 992-996.
[11] HUANG M X, LU C H, HUANG Q D, et al. A novel and fast responsive turn-on fluorescent probe for the highly selective detection of Cd²⁺ based on photo-induced electron transfer[J]. RSC Advances, 2019, 9（62）: 36 011-36 019.
[12] SURESH M, SHRIVASTAV A, MISHRA S, et al. A rhodamine-based chemosensor that works in the biological system[J]. Organic Letters, 2008, 10（14）: 3 013-3 016.
[13] KAUR P, KAUR S, SINGH K. Bis（N-methylindolyl）methane-based chemical probes for Hg²⁺ and Cu²⁺ and molecular IMPLICATION gate operating in fluorescence mode[J]. Organic & Biomolecular Chemistry, 2012, 10（8）: 1 497-1 501.
[14] KAUR M, AHN Y H, CHOI K, et al. A bifunctional colorimetric fluorescent probe for Hg²⁺ and Cu²⁺ based on a carbazole-pyrimidine conjugate: Chromogenic and fluorogenic recognition on TLC, silica-gel and filter paper[J]. Organic & Biomolecular Chemistry, 2015, 13（26）: 7 149-7 153.
[15] HE T, LIN C L, GU Z Y, et al. Sensing behavior and logic operation of a colorimetric fluorescence sensor for Hg²⁺/Cu²⁺ ions[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2016, 167: 66-71.
[16] JOLLIFFE I T, CADIMA J. Principal component analysis: A review and recent developments[J]. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2016, 374（2 065）: 20150202.
[17] DONG J, YAO Z J, ZHANG L, et al. PyBioMed: A python library for various molecular representations of chemicals, proteins and DNAs and their interactions[J]. Journal of Cheminformatics, 2018, 10: 1-11.
[18] QUINLAN J R. Induction of decision trees[J]. Machine Learning, 1986, 1（1）: 81-106.
[19] PETERSON L. K-nearest neighbor[J]. Scholarpedia, 2009, 4（2）: 1 883.
[20] HESS A S, HESS J R. Logistic regression[J]. Transfusion, 2019, 59（7）: 2 197-2 198.
[21] BREIMAN L. Random forests[J]. Machine Learning, 2001, 45: 5-32.
[22] MAMMONE A, TURCHI M, CRISTIANINI N. Support vector machines[J]. WIREs Computational Statistics, 2009, 1（3）: 283-289.
[23] SHERIDAN R P, WANG W M, LIAW A, et al. Extreme gradient boosting as a method for quantitative structure-activity relationships[J]. Journal of Chemical Information and Modeling, 2016, 56（12）: 2 353-2 360.
[24] GARDNER M, DORLING S. Artificial neural networks （the multilayer perceptron）: A review of applications in the atmospheric sciences[J]. Atmospheric Environment, 1998, 32（14/15）: 2 627-2 636.
[25] CHICCO D, JURMAN G. The advantages of the Matthews correlation coefficient （MCC） over F₁ score and accuracy in binary classification evaluation[J]. BMC Genomics, 2020, 21: 1-13.
[26] NARKHEDE S. Understanding auc-roc curve[J]. Towards data science, 2018, 26（1）: 220-227.