帮助 关于我们

返回检索结果

基于同步辐射X射线荧光光谱与机器学习的非靶标金属组学方法区分暴露于不同形态汞的水稻
Non-targeted metallomics based on synchrotron radiation X-ray fluorescence spectroscopy and machine learning for screening inorganic or methylmercury-exposed rice plants

查看参考文献53篇

敖飘雪 1   魏超杰 2   解宏鑫 3   费钰茜 4   崔丽巍 5   王伟 2   涂成龙 1 *   商立海 1,6 *   李柏 3   李玉锋 3 *  
文摘 [背景]汞是一种全球性污染物,严重威胁人类健康。不同形态汞的毒性不同,建立区分暴露于不同形态汞的样品的方法有助于针对性开展汞的治理,为降低人类汞暴露风险提供依据。 [目的]建立基于同步辐射X射线荧光(SRXRF)光谱与机器学习相结合的非靶标金属组学方法,从而区分暴露于无机汞(IHg)或甲基汞(MeHg)的水稻。 [方法]水稻种子分别暴露于超纯水(对照组)、0.1 mg·L~(-1)的IHg(IHg组)或MeHg(MeHg组)溶液中,种子发芽后继续培养21 d,收集水稻叶片、烘干、称重、压片。利用SRXRF测定各组水稻叶中金属组的含量。采用不同机器学习模型如软独立建模聚类分析(SIMCA)、最小二乘判别分析(PLS-DA)和逻辑回归(LR)对不同组叶片的SRXRF全光谱进行分类和识别,筛选出区分效果最优的模型以区分暴露于IHg或MeHg的水稻。进一步利用特征元素作为输入参数以提升运算速度,减少模型计算量,优化模型。 [结果] SRXRF显示,对照组、IHg组和MeHg组的SRXRF光谱强度各不相同,提示IHg或MeHg暴露可干扰水稻叶中金属组的稳态平衡。将SRXRF光谱进行主成分分析(PCA),发现对照组能与汞暴露组很好区分,但无法区分IHg组和MeHg组。利用PLS-DA、SIMCA和LR三个模型进行区分,发现训练集的准确率都高于98%,验证集的准确率都高于95%,交叉验证集的准确率都高于94%,其中LR模型的准确率均高于PLS-DA模型和SIMCA模型。以线性模型LR挑选出的K、Ca、Mn、Fe、Zn为特征元素区分IHg组和MeHg组的预测准确率为92.05%。与全光谱模型相比,利用特征光谱预测模型虽然预测准确率下降,但模型输入参数减少了99.51%,且精确度、召回率和F1得分在84.48%以上,同样可用于区分暴露于不同形态汞的水稻。 [结论]基于SRXRF和机器学习的非靶标金属组学方法可快速识别暴露于不同形态汞的水稻,减少人体摄入汞的风险。
其他语种文摘 [Background] Mercury, as a global heavy metal pollutant, poses a serious threat to human health. The toxicity of mercury depends on its chemical form. Distinguishing the forms of mercury in the environment is of great significance for mercury management and reducing human mercury exposure risks. [Objective] To establish a non-targeted metallomics method based on synchrotron radiation X-ray fluorescence (SRXRF) spectroscopy combined with machine learning to screen inorganic mercury (IHg) or methylmercury (MeHg) exposed rice plants. [Methods] Rice seeds were exposed to ultra-pure water (control group), 0.1 mg·L~(-1) IHg (IHg group) or MeHg (MeHg group) solutions, respectively. After germination, the seedlings were cultured for 21 d, and rice leaves were collected, dried, weighed, and pressed. The content of metallome in rice leaves was determined by SRXRF. Machine learning models including soft independent modeling cluster analysis (SIMCA), partial least squares discriminant analysis (PLS-DA), and logistic regression (LR) were used to classify the SRXRF full spectra of different groups and find the best model to distinguish rice exposed to IHg or MeHg. Besides, characteristic elements were selected as input parameters to optimize the model by improving computing speed and reducing model calculation. [Results] The SRXRF spectral intensities of the control group, IHg group, and MeHg group were different, indicating that exposure to IHg and MeHg can interfere the homeostasis of metallome in rice leaves. The results of principal component analysis (PCA) of SRXRF spectra showed that the control group could be well distinguished from the mercury exposed groups, but the IHg group and the MeHg group were mostly overlapped. The accuracy rates of the three models (PLS-DA, SIMCA, and LR) were higher than 98% for the training set, higher than 95% for the validation set, and higher than 94% for the cross-validation set. Besides, the accuracy of the LR model was higher than that of the PLS-DA model and the SIMCA model. Furthermore, the accuracy was 92.05% when using characteristic elements K, Ca, Mn, Fe, and Zn selected by LR to distinguish the IHg group and the MeHg group. Compared with the full spectra model, although the prediction accuracy of the characteristic spectral model decreased, the input parameters of the model decreased by 99.51%, and precision, recall, and F1 score were above 84.48%, indicating that the model could distinguish rice exposed to different mercury forms. [Conclusion] Non-targeted metallomics method based on SRXRF and machine learning can be applied for high-throughput screening of rice exposed to different forms of mercury and thus decrease the risks of people being exposed to mercury.
来源 环境与职业医学 ,2024,41(10):1095-1102 【核心库】
DOI 10.11836/JEOM24253
关键词 无机汞 ; 甲基汞 ; 水稻 ; 同步辐射X射线荧光光谱 ; 机器学习 ; 非靶标金属组学
地址

1. 贵州医科大学公共卫生与健康学院, 环境污染与疾病监控教育部重点实验室, 贵州, 贵阳, 561113  

2. 中国农业大学工学院, 全国金属组学创新研究中心, 北京, 100083  

3. 中国科学院高能物理研究所/中国科学院-香港大学金属组学与健康和环境联合实验室/北京金属组学平台, 中国科学院纳米生物效应与安全性重点实验室;;全国金属组学创新研究中心, 北京, 100049  

4. 河南农业大学国际教育学院, 河南, 郑州, 450002  

5. 中国科学院大学资源与环境学院, 北京, 100049  

6. 中国科学院地球化学研究所, 环境地球化学国家重点实验室, 贵州, 贵阳, 550081

语种 中文
文献类型 研究性论文
ISSN 2095-9982
学科 预防医学、卫生学
基金 国家自然科学基金 ;  中国科学院大学生创新实践训练计划
文献收藏号 CSCD:7842596

参考文献 共 53 共3页

1.  Beckers F. Cycling of mercury in the environment: sources, fate, and human health implications: a review. Crit Rev Environ Sci Technol,2017,47(9):693-794 CSCD被引 23 次    
2.  Mahbub K R. Mercury toxicity to terrestrial biota. Ecol Indic,2017,74:451-462 CSCD被引 3 次    
3.  冯琳. 食用大米人群甲基汞暴露健康风险及摄入量限值研究进展. 安全与环境工程,2022,29(5):5-12 CSCD被引 2 次    
4.  Feng L. Research progress on health risk and intake limit of methylmercury exposure among rice consumption population. Saf Environ Eng,2022,29(5):5-12 CSCD被引 1 次    
5.  Chen B. Mercury contamination in fish and its effects on the health of pregnant women and their fetuses, and guidance for fish consumption-a narrative review. Int J Environ Res Public Health,2022,19(23):15929 CSCD被引 1 次    
6.  Wang W. Neurotransmitter disturbances caused by methylmercury exposure: microbiota-gut-brain interaction. Sci Total Environ,2023,873:162358 CSCD被引 2 次    
7.  Zhang H. In inland China, rice, rather than fish, is the major pathway for methylmercury exposure. Environ Health Perspect,2010,118(9):1183-1188 CSCD被引 81 次    
8.  Meng M. Accumulation of total mercury and methylmercury in rice plants collected from different mining areas in China. Environ Pollut,2014,184:179-186 CSCD被引 21 次    
9.  Feng L. Methylmercury bioaccumulation in rice and health effects: a systematic review. Curr Opin Environ Sci Health,2021,23:100285 CSCD被引 1 次    
10.  Liu M. Rice life cycle-based global mercury biotransport and human methylmercury exposure. Nat Commun,2019,10(1):5164 CSCD被引 3 次    
11.  Abdullah-Zawawi M R. Genome-wide analysis of sulfur-encoding biosynthetic genes in rice (Oryza sativa L.) with Arabidopsis as the sulfur-dependent model plant. Sci Rep,2022,12(1):13829 CSCD被引 1 次    
12.  瞿爱权. 汞对水稻、油菜影响的研究初报. 环境科学,1980(6):50-52,13 CSCD被引 16 次    
13.  Qu A Q. Preliminary study on the effects of mercury on rice and rapeseed. Environ Sci,1980(6):50-52,13 CSCD被引 1 次    
14.  何丽娜. 金属组学方法识别水中络合态重金属形态及其吸附净化技术研究进展. 中国无机分析化学,2024,14(1):46-55 CSCD被引 1 次    
15.  He L N. Research progress on identification of heavy metal complexes in water by metallomics and its purification technologies by adsorption. Chin J Inorg Anal Chem,2024,14(1):46-55 CSCD被引 1 次    
16.  Xie H. Size characterization of nanomaterials in environmental and biological matrices through non-electron microscopic techniques. Sci Total Environ,2022,835:155399 CSCD被引 1 次    
17.  李玉锋. 金属组学,2016:1-5 CSCD被引 1 次    
18.  Li Y F. Metallomics,2016:1-5 CSCD被引 1 次    
19.  解宏鑫. 纳米聚对苯二甲酸乙二醇酯对水稻幼苗光合作用系统和金属组稳态平衡的影响. 中国无机分析化学,2024,14(8):1058-1065 CSCD被引 1 次    
20.  Xie H X. Effects of nano poly(ethylene terephthalate) on photosynthesis system and metallome homeostasis of rice seedlings. Chin J Inorg Anal Chem,2024,14(8):1058-1065 CSCD被引 1 次    
引证文献 1 篇

1 张夏男 环境健康效应研究的新技术与新方法 环境与职业医学,2024,41(10):1083-1086
CSCD被引 0 次

显示所有1篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号