机器学习预测食品重金属检测中铜离子对汞离子荧光信号的干扰  

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

作　　者：宋方亮 梁盈[1,2] 董界 王雪洁 钱洁 SONG Fangliang;LIANG Ying;DONG Jie;WANG Xuejie;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;Xiangya School of Pharmaceutical Sciences,Central South University,Changsha,Hunan 410013,China)

机构地区：[1]中南林业科技大学食品科学与工程学院,湖南长沙410004 [2]水稻及副产物深加工国家工程研究中心分子营养分中心,湖南长沙410004 [3]中南大学湘雅药学院,湖南长沙410013

出　　处：《食品与机械》2024年第5期62-66,153,共6页Food and Machinery

基　　金：国家自然科学基金(编号:32372349);国家重点研发计划(编号:2022YFF1100203);湖南省科技创新人才项目(编号:2022RC3056)。

摘　　要：目的:构建一个人工智能预测模型,在存在Cu^(2+)干扰的复杂食品检测环境下预测荧光探针对Hg^(2+)的选择性。方法:采用荧光探针技术结合7种先进经典的机器学习模型,预测分析存在Cu^(2+)干扰时探针对Hg^(2+)的选择性,并比较各模型的预测效果,选择最优模型。结果:基于分子二维描述符(molecular 2D descriptors,Mol2D)和极端梯度提升算法成功建立了在交叉验证和测试集中准确度为0.786和0.810的高效模型,在Cu^(2+)干扰下准确预判Hg^(2+)的探针选择性。结论:该模型通过选择性预判对Hg^(2+)荧光分子探针的设计进行改进,使Hg^(2+)荧光探针的设计更加高效可靠。Objective:To construct an artificial intelligence prediction model to predict the selectivity of fluorescent probes for Hg^(2+)in a complex food testing environment in the presence of Cu^(2+)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 Hg^(2+)in the presence of Cu^(2+)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 Hg^(2+)under Cu^(2+)interference.Conclusion:The model is improved for the design of Hg^(2+)fluorescent molecular probes by selective prediction,which makes the design of Hg^(2+)fluorescent probes more efficient and reliable.

关 键 词：汞离子检测 荧光分子探针 探针选择性 机器学习 化学信息学 

分 类 号：O657.3[理学—分析化学] TS207.51[理学—化学] TP181[轻工技术与工程—食品科学]