摘要
应用近红外光谱(NIRS)技术结合偏最小二乘(PLS)和最小二乘支持向量机(LS-SVM)建立了附子中多指标成分的快速无损检测方法。选取38批样品建立了同时测定附子样品中6种成分含量的高效液相色谱(HPLC)方法;通过采集附子样品的NIRS图,分别采用PLS和LS-SVM建立了各个成分HPLC测定值与NIRS图的定量校正模型。所建立的苯甲酰新乌头原碱、苯甲酰乌头原碱、苯甲酰次乌头原碱、新乌头碱、次乌头碱、乌头碱、单酯型生物碱总量和双酯型生物碱总量LS-SVM模型的相对预测偏差(RPD)分别为3.3、3.2、4.1、7.7、8.8、7.6、4.0和8.6;验证集相关系数(rpre)分别为0.9486、0.9475、0.9668、0.9909、0.9946、0.9969、0.9669和0.9927,且LS-SVM模型优于PLS模型,说明NIRS模型验证集与HPLC测定值具有良好的非线性关系,模型预测效果良好。采用NIRS技术结合LS-SVM模型可以快速对附子中的上述6个生物碱含量以及单酯型生物碱总量和双酯型生物碱总量进行检测,方法操作简便,对控制附子中的生物碱含量具有一定的指导作用。
A rapid method was established for the nondestructive determination of multi-marker components in Aconiti Lateralis Radix Praeparata by near infrared spectroscopy(NIRS)combined with partial least squares(PLS)and least square-support vetor machine(LS-SVM).A total of 38 batches of samples were selected for the determination of six alkaloids,i.e.benzoylmesaconine,benzoylaconine,benzoylhypaconine,meaconitine,hypaconitine and aconitin in Aconiti Lateralis Radix Praeparata by high performance liquid chromatography(HPLC),and their NIR spectra were further collected.Two determination calibration models between the six components and NIRS were established by PLS and LS-SVM methods,respectively.The relative prediction deviations(RPDs)for the six components the total of monoester-type alkaloids and the total of diester-type alkaloid were 3.3,3.2,4.1,7.7,8.8,7.6,4.0 and 8.6,while the rpre for the 8 types were 0.9486,0.9475,0.9668,0.9909,0.9946,0.9969,0.9669 and 0.9927,respectively.Results showed that the LS-SVM model was better than PLS model,indicating that a good nonlinear relation existed between the predicted values of NIRS model and the measured values of HPLC.The established NIRS combined with LS-SVM could be applied to the rapid determination of six alkaloids in Aconiti Lateralis Radix Praeparata,and even to the prediction of the total of monoester-type alkaloids and the total of diester-type alkaloid,which is beneficial for the quality control of the Aconiti Lateralis Radix Praeparata.
作者
戴胜云
马青青
蒋双慧
刘杰
过立农
乔菲
周娟
乔延江
郑健
马双成
DAI Sheng-yun;MA Qing-qing;JIANG Shuang-hui;LIU Jie;GUO Li-nong;QIAO Fei;ZHOU Juan;QIAO Yan-jiang;ZHENG Jian;MA Shuang-cheng(National Institutes for Food and Drug Control,Beijing 100050,China;Qinghai Provincial Drug Inspection and Testing Institutes,Xi'ning 810016,China;School of Traditional Pharmacy,China Pharmaceutical University,Nanjing 210009,China;Sichuan Institute for Food and Drug Inspection and Detection,Chengdu 611730,China;Department of Chinese Medicine Information Science,Beijing University of Chinese Medicine,Beijing 102400,China)
出处
《分析测试学报》
CAS
CSCD
北大核心
2021年第1期57-64,共8页
Journal of Instrumental Analysis
基金
国家科技重大专项(2018ZX09735-006)。
关键词
近红外光谱
附子
最小二乘支持向量机
偏最小二乘
单酯型生物碱
双酯型生物碱
near infrared spectroscopy(NIRS)
Aconiti Lateralis Radix Praeparata
least square-support vetor machine(LS-SVM)
partial least squares(PLS)
monoester-type alkaloids
diester-type alkaloids