Machine learning for predicting chemical migration from food packaging materials to foods

被引:8
作者
Wang, Shan -Shan [1 ,2 ,3 ,7 ]
Lin, Pinpin [4 ]
Wang, Chia-Chi [5 ]
Lin, Ying-Chi [6 ]
Tung, Chun-Wei [3 ,7 ]
机构
[1] Kaohsiung Med Univ, Coll Med, PhD Program Environm & Occupat Med, Kaohsiung 80756, Taiwan
[2] Natl Hlth Res Inst, Kaohsiung 80756, Taiwan
[3] Natl Hlth Res Inst, Inst Biotechnol & Pharmaceut Res, Miaoli Cty 35053, Taiwan
[4] Natl Hlth Res Inst, Natl Inst Environm Hlth Sci, Miaoli Cty 35053, Taiwan
[5] Natl Taiwan Univ, Dept & Grad Inst Vet Med, Sch Vet Med, Taipei 10617, Taiwan
[6] Kaohsiung Med Univ, Coll Pharm, Kaohsiung 80756, Taiwan
[7] Kaohsiung Med Univ, Coll Pharm, Sch Pharm, Kaohsiung 80756, Taiwan
关键词
Chemical migration; Food contact chemical; Ensemble learning; Quantitative structure-activity relationship; MIGRANTS; EXPOSURE; DIETARY;
D O I
10.1016/j.fct.2023.113942
中图分类号
TS2 [食品工业];
学科分类号
0832 ;
摘要
Food contact chemicals (FCCs) can migrate from packaging materials to food posing an issue of exposure to FCCs of toxicity concern. Compared to costly experiments, computational methods can be utilized to assess the migration potentials for various migration scenarios for further experimental investigation that can potentially accelerate the migration assessment. This study developed a nonlinear machine learning method utilizing chemical properties, material type, food type and temperature to predict chemical migration from package to food. Nine nonlinear algorithms were evaluated for their prediction performance. The ensemble model leveraging multiple algorithms provides state-of-the-art performance that is much better than previous linear regression models. The developed prediction models were subsequently applied to profile the migration potential of FCCs of high toxicity concern. The models are expected to be useful for accelerating the assessment of migration of FCCs from package to foods.
引用
收藏
页数:9
相关论文
共 36 条
[1]   Chemicals of concern in plastic toys [J].
Aurisano, Nicolo ;
Huang, Lei ;
Canals, Llorenc Mila i ;
Jolliet, Olivier ;
Fantke, Peter .
ENVIRONMENT INTERNATIONAL, 2021, 146
[2]  
Baner III A.L., 1993, PARTITION COEFFICIEN, VII
[3]  
Baner III A.L., 1993, PARTITION COEFFICIEN, VI
[4]   High-throughput dietary exposure predictions for chemical migrants from food contact substances for use in chemical prioritization [J].
Biryol, Derya ;
Nicolas, Chantel I. ;
Wambaugh, John ;
Phillips, Katherine ;
Isaacs, Kristin .
ENVIRONMENT INTERNATIONAL, 2017, 108 :185-194
[5]   The role of packaging on the flavor of fluid milk [J].
Cadwallader, D. C. ;
Gerard, P. D. ;
Drake, M. A. .
JOURNAL OF DAIRY SCIENCE, 2023, 106 (01) :151-167
[6]  
Caruana R., 2004, Proceedings of The Twenty-First Interna-tional Conference on Machine Learning, P18, DOI [10.1145/1015330.1015432, DOI 10.1145/1015330.1015432]
[7]   Ensemble learning for predicting ex vivo human placental barrier permeability [J].
Chou, Che-Yu ;
Lin, Pinpin ;
Kim, Jongwoon ;
Wang, Shan-Shan ;
Wang, Chia-Chi ;
Tung, Chun-Wei .
BMC BIOINFORMATICS, 2022, 22 (SUPPL 10)
[8]   Computational methods on food contact chemicals: Big data and in silico screening on nuclear receptors family [J].
Cozzini, Pietro ;
Cavaliere, Francesca ;
Spaggiari, Giulia ;
Morelli, Gianluca ;
Riani, Marco .
CHEMOSPHERE, 2022, 292
[9]   A regression-based model to predict chemical migration from packaging to food [J].
Douziech, Melanie ;
Benitez-Lopez, Ana ;
Ernstoff, Alexi ;
Askham, Cecilia ;
Hendriks, A. Jan ;
King, Henry ;
Huijbregts, Mark A. J. .
JOURNAL OF EXPOSURE SCIENCE AND ENVIRONMENTAL EPIDEMIOLOGY, 2020, 30 (03) :469-477
[10]  
Erickson N, 2020, Arxiv, DOI arXiv:2003.06505