安全监测

机器学习算法在不同形态浙贝母与湖北贝母的干法REIMS指纹图谱鉴别分析中的应用研究

展开
  • 1.中国食品药品检定研究院,北京 102629;
    2.北京市药品检验研究院,北京 102206
第一作者 石 岩 Tel:(010)53852081;E-mail:shiyan@nifdc.org.cn
李 宁 Tel:13811671528;E-mail:642781540@qq.com
**Tel:(010)53852020;E-mail:weifeng@nifdc.org.cn

修回日期: 2023-11-17

  网络出版日期: 2024-06-21

Research of machine learning in the application of authenticity discrimination of Fritillariae Thunbergii Bulbus and Fritillariae Hupehensis Bulbus in different form with dry-process REIMS fingerpring

Expand
  • 1. National Institutes for Food and Drug Control, Beijing 102629, China;
    2. Beijing Institute for Drug Control, Beijing 102206, China

Revised date: 2023-11-17

  Online published: 2024-06-21

摘要

目的:使用快速蒸发离子化质谱(REIMS)指纹图谱与机器学习相关技术对不同形态的浙贝母和湖北贝母进行预测和判别。方法:通过干法灼烧使样品组分形成气溶胶,引入REIMS中,质谱扫描范围m/z 50~1 200,扫描模式为灵敏模式,扫描时间为0.2 s。正离子模式采集,数据记录为continuum模式,测得样品的REIMS指纹图谱数据。通过对数据进行聚类分析、相关性分析、相似度分析、主成分分析,得到数据分布的基本情况,最后建立逻辑回归模型,模型惩罚项参数选择岭回归(l2),优化算法选择拟牛顿法(lbfgs)。结果:测得样品的REIMS指纹图谱具有品种差异的特征性,逻辑回归模型交叉验证和测试集验证准确率均达到1.0,可以准确预测和判别样品的品种。结论:REIMS技术结合机器学习在中药领域的潜在应用前景十分广阔。

本文引用格式

石岩, 李宁, 魏锋 . 机器学习算法在不同形态浙贝母与湖北贝母的干法REIMS指纹图谱鉴别分析中的应用研究[J]. 药物分析杂志, 2024 , 44(1) : 134 -143 . DOI: 10.16155/j.0254-1793.2024.01.14

Abstract

Objective: To study and analyze rapid evaporative ionization mass spectrometry (REIMS) fingerprints of samples of Fritillariae Thunbergii Bulbus and Fritillariae Hupehensis Bulbus in different forms for authenticity discrimination with machine learning. Methods: Aerosol formations from the samples by high temperature of dry burning method were ionized and determined by REIMS with m/z 50-1 200 as scanning range in sensitive mode and positive ion mode. The scanning time was 0.2 s and data was recorded as continuous mode. Then the basic situation of REIMS data distribution was studied and analyzed through the methods of cluster analysis, correlation analysis, similarity analysis and principal component analysis. And then logistic regression model with ridge regression (l2) as penalty parameter and quasi-Newton method (lbfgs) as optimization algorithm was established. Results: The REIMS fingerprints of the samples showed the characteristics of variety differences. Both cross validation and test set validation had an accuracy of 1.0, and the logistic regression model could accurately predict and distinguish the varieties of the samples. Conclusion: The application prospect of REIMS technique combined with machine learning in the field of traditional Chinese medicine is very broad.

参考文献

[1] 王书军, 高文远, 于琳, 等. 百合科贝母属药用植物分类研究进展[J]. 中国中药杂志, 2007, 32(16): 1609
WANG SJ, GAO WY, YU L, et al. Progress of taxonomic study on Fritillaria (Liliaceae) medicinal plant[J]. China J Chin Mater Med, 2007, 32(16): 1609
[2] 肖培根. 湖北贝母的研究进展[J]. 中国中药杂志, 2002, 27(10): 726
XIAO PG. A review on the study of Hubeibeimu[J]. China J Chin Mater Med, 2002, 27(10): 726
[3] YU M, WANG S, CAI R, et al. Discrimination and content analysis of Fritillaria using near infrared spectroscopy[J]. J Anal Methods Chem, 2015:752162
[4] ZHOU M, MA X, DING G, et al. Comparison and evaluation of antimuscarinic and anti-inflammatory effects of five Bulbus Fritillariae species based on UPLC-Q/TOF integrated dual-luciferase reporter assay, PCA and ANN analysis[J]. J Chromatogr B Analyt Technol Biomed Life Sci, 2017, 1041-1042: 60
[5] 中华人民共和国药典2020年版. 一部[S]. 2020: 304
ChP 2020. Vol Ⅰ[S]. 2020: 304
[6] 马秀芹, 秦伟华, 李学斌, 等. 浙贝母与其混淆品湖北贝母的鉴别[J]. 时珍国药研究, 1997, 8(1): 37
MA XQ, QIN WH, LI XB, et al. Identification of Fritillaria thunbergii and its adulterant Fritillaria hupehensis[J]. Lishizhen Med Mater Med Res, 1997, 8(1): 37
[7] 周建良, 刘伟, 郭增喜, 等. 基于快速液相色谱-四极杆飞行时间串联质谱的浙贝母特征图谱研究[J]. 中国中药杂志, 2013, 38(17): 2832
ZHOU JL, LIU W, GUO ZX, et al. Fingerprint analysis of Fritillaria thunbergii using rapid resolution liquid chromatography coupled with electrospray ionization quadrupole time-of-flight tandem mass spectrometry[J]. China J Chin Mater Med, 2013, 38(17): 2832
[8] ZHANG ZF, LU LY, LIU Y. Comparing major alkaloids of Fritillariae Hupehensis Bulbs (FHB) and congeneric plants by HPLC-ELSD and HPLC-ESI-MSn[J]. Nat Prod Res, 2014, 28(15): 1171
[9] WANG Z, XIE H, REN J, et al. Metabolomic approach for rapid differentiation of Fritillaria bulbs by matrix-assisted laser desorption/ionization mass spectrometry and multivariate statistical analysis[J]. J Pharm Biomed Anal, 2020, 185: 113177
[10] SCHÄFERFER KC, DÉNES J, ALBRECHT K, et al. In vivo, in situ tissue analysis using rapid evaporative ionization mass spectrometry[J]. Angew Chem Int Ed, 2009, 48(44): 8240
[11] BALOG J, SZANISZLO T, SCHAEFER KC, et al. Identification of biological tissues by rapid evaporative ionization mass spectrometry[J]. Anal Chem, 2010, 82(17): 7343
[12] STRITTMATTER N, REBEC M, JONES EA, et al. Characterization and identification of clinically relevant microorganisms using rapid evaporative ionization mass spectrometry[J]. Anal Chem, 2014, 86(13): 6555
[13] BALOG J, KUMAR S, ALEXANDER J, et al. In vivo endoscopic tissue identification by rapid evaporative ionization mass spectrometry (REIMS)[J]. Angew Chem Int Ed, 2015, 54(38): 11059
[14] 高海燕, 孟宪双, 付珺珺, 等. 快速蒸发电离质谱技术及其应用研究进展[J]. 分析测试学报, 2021, 40(2): 159
GAO HY, MENG XS, FU JJ, et al. Research progress on rapid evaporative ionization mass spectrometry and its applications[J]. J Instrum Anal, 2021, 40(2):159
[15] SONG G, CHEN K, WANG H, et al. In situ and real-time authentication of Thunnus species by iKnife rapid evaporative ionization mass spectrometry based lipidomics without sample pretreatment[J]. Food Chem, 2020, 318: 126504
[16] CUI Y, WANG H, ZHAO Q, et al. Real-time detection of authenticity and adulteration of krill phospholipids with soybean phospholipids using rapid evaporative ionization mass spectrometry: application on commercial samples[J]. Food Control, 2021, 121: 107680
[17] MANOLI E, MASON S, FORD L, et al. Validation of ultrasonic harmonic scalpel for real-time tissue identification using rapid evaporative ionization mass spectrometry[J]. Anal Chem, 2021, 93: 5906
[18] 刘鸣畅, 林继红, 刘哲硕, 等. 快速蒸发电离质谱技术(REIMS)鉴别肉品[J]. 质谱学报, 2020, 41(5): 470
LIU MC, LIN JH, LIU ZS, et al. Identification of meat by rapid evaporation ionization mass spectrometry (REIMS)[J]. J Chin Mass Spectrom Soc, 2020, 41(5): 470
[19] 张燕平, 王海星, 陈康, 等. 实时质谱新技术分析南极磷虾油的脂质组学轮廓[J]. 中国食品学报, 2020, 20(9): 226
ZHANG YP, WANG HX, CHEN K, et al. Novel real-time mass spectrometry for detecting the lipidomics profile of antarctic krill oil[J]. J Chin Inst Food Sci Technol, 2020, 20(9): 226
[20] 石岩, 姚令文, 魏锋, 等. 基于干法快速蒸发离子化质谱(REIMS)指纹图谱与机器学习算法联用的白头翁真伪判别研究[J]. 中国中药杂志, 2023, 48(4): 921
SHI Y, YAO LW, WEI F, et al. Authenticity discrimination of Pulsatillae Radix based on dry-process REIMS fingerprinting combined with machine learning[J]. China J Chin Mater Med, 2023, 48(4): 921
[21] SANDUSKY P, RAFTERY D. Use of semiselective TOCSY and the pearson correlation for the metabonomic analysis of biofluid mixtures: application to urine[J]. Anal Chem, 2005, 77(23): 7717
[22] WANG Z, LUO P, CHENG L, et al. Hapten-antibody recognition studies in competitive immunoassay of α-zearalanol analogs by computational chemistry and pearson correlation analysis[J]. J Mol Recognit, 2011, 24(5): 815
[23] LUNSFORD R, GILLIS D, GRUN J. Automated identification of components in a chemical mixture utilizing multi-wavelength resonant-Raman spectroscopy and a Pearson correlation algorithm[J]. J Raman Spectrosc, 2012, 43(10): 1472
[24] GÉRON A. Hands-on Machine Learning with Sciket-Learn, Keras & Tensorflow: Concepts, Tools, and Techniques to Build Intelligent Systems[M]. 2nd Ed. Sebastopol: Reilly Media, 2019
文章导航

/