药学学报, 2019, 54(1): 138-143
引用本文:
刘雪松, 张丝雨, 赵曼茜, 王钧, 李页瑞, 代军, 滕传震, 柯潇, 陈勇, 吴永江. 近红外光谱结合不同变量筛选方法用于黄芩提取过程中黄芩苷含量预测[J]. 药学学报, 2019, 54(1): 138-143.
LIU Xue-song, ZHANG Si-yu, ZHAO Man-qian, WANG Jun, LI Ye-rui, DAI Jun, TENG Chuan-zhen, KE Xiao, CHEN Yong, WU Yong-jiang. The prediction of baicalin content in the extraction process of Scutellaria baicalensis by near-infrared spectroscopy combined with different variable selection methods[J]. Acta Pharmaceutica Sinica, 2019, 54(1): 138-143.

近红外光谱结合不同变量筛选方法用于黄芩提取过程中黄芩苷含量预测
刘雪松1, 张丝雨1, 赵曼茜2, 王钧3, 李页瑞3, 代军2, 滕传震2, 柯潇2, 陈勇1, 吴永江1
1. 浙江大学药学院, 浙江 杭州 310058;
2. 成都康弘药业集团股份有限公司, 四川 成都 610036;
3. 苏州泽达兴邦医药科技有限公司, 江苏 苏州 215000
摘要:
近红外光谱技术(NIRS)结合化学计量学可以实现中药过程分析中的快速定量,变量筛选算法的应用可以有效去除光谱中的冗余信息并筛选出与成分信息相关的关键变量,与全光谱模型相比可以显著降低模型复杂度,并提高预测精度。本文将近红外光谱技术结合不同变量筛选算法用于黄芩提取过程黄芩苷含量的快速测定,基于SPXY法划分数据集,采用竞争自适应加权重采样法(CARS)、随机青蛙算法(RF)、连续投影算法(SPA)3种不同变量筛选方法,以偏最小二乘法(PLS)为基础,建立并比较了黄芩药材提取过程黄芩苷含量的定量校正模型。经CARS法、RF法和SPA法分别筛选出92、10、17个变量,CARS-PLS法建立的黄芩苷模型具有最佳性能,CARS法筛选的关健变量与指标成分黄芩苷的化学结构也有着较好的对应关系。模型的校正均方根误差(RMSEC)和预测均方根误差(RMSEP)分别为0.528 2和0.720 2,与全光谱模型相比,模型的校正集相关系数(Rc)从0.917 0上升到0.979 9,相对预测偏差(RSEP)从10.58%降低到5.59%。
关键词:    近红外光谱      变量筛选      黄芩苷      竞争自适应加权重采样      随机青蛙算法      连续投影算法      偏最小二乘法     
The prediction of baicalin content in the extraction process of Scutellaria baicalensis by near-infrared spectroscopy combined with different variable selection methods
LIU Xue-song1, ZHANG Si-yu1, ZHAO Man-qian2, WANG Jun3, LI Ye-rui3, DAI Jun2, TENG Chuan-zhen2, KE Xiao2, CHEN Yong1, WU Yong-jiang1
1. College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China;
2. Chengdu Kanghong Pharmaceutical Group Co., Ltd., Chengdu 610036, China;
3. Suzhou ZeDaXingBang Pharmaceutical Co., Ltd., Suzhou 215000, China
Abstract:
Near-infrared spectroscopy (NIRS) combined with chemometrics can achieve rapid detection in process analysis. After variable selection, the redundant information is effectively removed and the characteristic variables related to the response values are selected. Compared with global model, the complexity is significantly reduced and the prediction accuracy is also improved. In this study, near-infrared spectroscopy analysis combined with different variable selection methods was applied to achieve the rapid detection of baicalin in the extraction process of Scutellaria baicalensis. Data sets were divided based on sample set portioning based on joint x-y distance (SPXY) method. Competitive adaptive weighted resampling method (CARS), random frog (RF) and successive projections algorithm (SPA) were applied to variable selection. Partial least squares (PLS) models were constructed based on above three methods, and the prediction results were compared. After CARS, RF and SPA method, 92, 10 and 17 variables were screened out respectively. According to the performance of the models, CARS method is found to be more effective and suitable than RF and SPA. Furthermore, the characteristic variables selected by CARS method have a better correspondence with the chemical structure of baicalin. The root mean square error (RMSEC) of the calibration set and the root mean square error (RMSEP) of the prediction set are 0.528 2 and 0.720 2 respectively. Compared with the global PLS model, the correlation coefficient of the calibration set (Rc) is increased to 0.979 9 from 0.917 0, and the relative standard errors of prediction (RSEP) is reduced to 5.59% from 10.58%.
Key words:    near infrared spectroscopy    variable selection    baicalin    competitive adaptive reweighted sampling method    random frog    successive projections algorithm    partial least squares   
收稿日期: 2018-08-06
DOI: 10.16438/j.0513-4870.2018-0712
基金项目: 重大新药创制科技重大专项(2018ZX09201010).
通讯作者: 吴永江,Tel:86-571-88208455,E-mail:yjwu@zju.edu.cn
Email: yjwu@zju.edu.cn
相关功能
PDF(417KB) Free
打印本文
0
作者相关文章
刘雪松  在本刊中的所有文章
张丝雨  在本刊中的所有文章
赵曼茜  在本刊中的所有文章
王钧  在本刊中的所有文章
李页瑞  在本刊中的所有文章
代军  在本刊中的所有文章
滕传震  在本刊中的所有文章
柯潇  在本刊中的所有文章
陈勇  在本刊中的所有文章
吴永江  在本刊中的所有文章

参考文献:
[1] Lu WZ, Chu XL. Near infrared spectroscopy and process analytical technology[J]. Mod Sci Instrum (现代科学仪器), 2007, (4):13-17.
[2] Liu XS, Sun FF, Jin Y, et al. Application of near infrared spectroscopy combined with particle swarm optimization based least square support vector machine to rapid quantitative analysis of Corni Fructus[J]. Acta Pharm Sin (药学学报), 2015, 50:1645-1651.
[3] Geng S, Chen Y, Jin Y, et al. Rapid quantitative determination of multi-indicators in Lonicerae Japonicae Flos by near-infrared spectroscopy[J]. Chin J Mod Appl Pharm (中国现代应用药学), 2016, 33:144-150.
[4] Jin Y, Ding HY, Wu YJ, et al. Near infrared spectroscopy on-line and real-time monitoring of extraction process of Xuebijing Injection[J]. Chin J Pharm Anal (药物分析杂志), 2012, 32:1214-1221, 1234.
[5] Liu XS, Chen JS, Chen GQ, et al. On-line detection of concentration process of Ganmaoling granules by near infrared spectroscopy combined with automatic control system[J]. Acta Pharm Sin (药学学报), 2017, 52:462-467.
[6] Zhang Y, Wu YJ, Wu CY, et al. Online monitor multi-component content of Danhong injection in the alcohol precipitation process using near-infrared spectroscopy[J]. Chin J Mod Appl Pharm (中国现代应用药学), 2015, 32:67-72.
[7] Bai G, Ding GY, Hou YY, et al. Rapid identification and evaluation of Chinese materia medica quality by near infrared spectroscopy[J]. China J Chin Mater Med (中国中药杂志), 2016, 41:3501-3505.
[8] Bin J, Fan W, Zhou JH, et al. Application of intelligent optimization algorithms to wavelength selection of near-infrared spectroscopy[J]. Spectrosc Spectr Anal (光谱学与光谱分析), 2017, 37:95-102.
[9] He J, He Y, Zhang AC. Determination and visualization of peimine and peiminine content in Fritillaria thunbergii Bulbi treated by sulfur fumigation using hyperspectral imaging with chemometrics[J]. Molecules, 2017, 22:1402.
[10] Xia Z, Zhang C, Weng H, et al. Sensitive wavelengths selection in identification of Ophiopogon japonicus based on near-infrared hyperspectral imaging technology[J]. Int J Anal Chem, 2017:6018769.
[11] Zhan BA, Ni JH, Li J. Hyperspectral technology combined with CARS algorithm to quantitatively determine the SSC in Korla fragant pear[J]. Spectrosc Spectr Anal (光谱学与光谱分析), 2014, 34:2752-2757.
[12] Zheng J, Zhou Z, Zhong SM, et al. Chestnut browning detected with near-infrared spectroscopy and a random-frog algorithm[J]. J Zhejiang A F Univ (浙江农林大学学报), 2016, 33:322-329.
[13] Li JB, Guo ZM, Hung WQ, et al. Near-infrared spectra combining with CARS and SPA algorithms to screen the variables and samples for quantitatively determining the soluble solids content in strawberry[J]. Spectrosc Spectr Anal (光谱学与光谱分析), 2015, 35:372-378.
[14] Chinese Pharmacopoeia Commission. Pharmacopoeia of People's Republic of China (中华人民共和国药典)[S]. Vol 1. 2015 ed. Beijing:China Medical Science Press, 2015:301.
[15] Jin Y, Wu ZZ, Liu XS, et al. Near infrared spectroscopy in combination with chemometrics as a process analytical technology (PAT) tool for on-line quantitative monitoring of alcohol precipitation[J]. J Pharm Biomed Anal, 2013, 77:32-39.
[16] Zhan XY, Zhao N, Lin ZZ, et al. Effect of algorithms for calibration set selection on quantitatively determining asiaticoside content in Centella total glucosides by near infrared spectroscopy[J]. Spectrosc Spectr Anal (光谱学与光谱分析), 2014, 34:3267-3272.
[17] Suo T, Wang H, Shi X, et al. Combining near infrared spectroscopy with predictive model and expertise to monitor herb extraction processes[J]. J Pharm Biomed Anal, 2018, 148:214-223.
[18] Li TT, Hu T, Nie L, et al. Rapid monitoring five components of ethanol precipitation process of Shenzhiling oral solution using near infrared spectroscopy[J]. China J Chin Mater Med (中国中药杂志), 2016, 41:3543-3550.
[19] Jin Y, Yang K, Wu YJ, et al. Application of particle swarm optimization based least square support vector machine in quantitative analysis of extraction solution of safflower using near-infrared spectroscopy[J]. Chin J Anal Chem (分析化学), 2012, 40:925-931.
[20] Wang Y, Jiang F, Gupta BB, et al. Variable selection and optimization in rapid detection of soybean straw biomass based on CARS[J]. IEEE Access, 2018, 6:5290-5299.
[21] Hu M, Zhai G, Zhao Y, et al. Uses of selection strategies in both spectral and sample spaces for classifying hard and soft blueberry using near infrared data[J]. Sci Rep, 2018, 8:6671.
[22] Zhang C, Kong W, Liu F. Measurement of aspartic acid in oilseed rape leaves under herbicide stress using near infrared spectroscopy and chemometrics[J]. Heliyon, 2016, 2:e00064
[23] Chen LY, Zhao ZG, Liu F. mRMR-based wavelength selection for quantitative detection of Chinese yellow wine using NIRS[J]. Anal Methods, 2018, 10:667-675.
[24] Lacy JH. Interpretation of infrared vibration vibration-rotation spectra of interstellar and circumstellar molecules[J]. Astrophys J, 2013, 765:1035-1045.
[25] Nishimura Y, Lee YP, Irle S, et al. Critical interpretation of CH-and OH-stretching regions for infrared spectra of methanol clusters (CH3OH)n (n=2-5) using self-consistent-charge density functional tight-binding molecular dynamics simulations[J]. J Chem Phys, 2014, 141:094303.