基于数据融合的生物毒素及生物调节剂快速识别研究

引用本文: 南迪娜, 刘卫卫, 傅文翔, 李宝强, 孔景临. 基于数据融合的生物毒素及生物调节剂快速识别研究[J]. 分析化学, 2020, 48(10): 1343-1350. doi: 10.19756/j.issn.0253-3820.201137 shu

Citation: NAN Di-Na, LIU Wei-Wei, FU Wen-Xiang, LI Bao-Qiang, KONG Jing-Lin. Study on Fast Recognition of Biotoxins and Biological Modifiers Using Data Fusion Algorithm[J]. Chinese Journal of Analytical Chemistry, 2020, 48(10): 1343-1350. doi: 10.19756/j.issn.0253-3820.201137 shu

基于数据融合的生物毒素及生物调节剂快速识别研究

国民核生化灾害防护国家重点实验室, 北京 102205
基金项目:
本文系国家自然科学基金项目（No.61775017）资助

摘要: 建立了多种生物毒素和生物调节剂的电喷雾离子迁移谱和拉曼光谱分析方法，构建了几类代表性生物毒素、生物调节剂及常见无毒白色粉末共26种物质的离子迁移谱和拉曼光谱数据库，其中包括乌头碱、河豚毒素等生物碱，缓激肽、P物质等生物调节剂及其同分异构体等结构类似物，芋螺毒素、α-银环蛇毒素、蓖麻毒素等多肽和蛋白质毒素和食盐、面粉、蛋白粉等常见无毒物。在此基础上，利用线性判别分析、二次判别分析、k近邻、朴素贝叶斯模型、分类决策树、Sigmoid核函数支持向量机共6种模式识别算法对单一和融合数据进行识别归类，不同方法的识别准确率在76.0%~97.2%范围内，并分析了方法识别准确率差异原因。研究发现，以支持向量机模型建立的融合识别算法准确率高达97.2%。本方法能区分两种生物调节剂的多个结构类似物，可用于不明白色粉末的识别归类。

关键词:

English

Study on Fast Recognition of Biotoxins and Biological Modifiers Using Data Fusion Algorithm

State Key Laboratory of NBC Protection for Civilian, Beijing 102205, China
Received Date: 17 March 2020
Revised Date: 02 July 2020
Fund Project:
This work was supported by the National Natural Science Foundation of China (No. 61775017).

Abstract: A method for analysis of various biotoxins and biological modifiers based on electrospray ionization-ion mobility spectrometry (ESI-IMS) and Raman spectroscopy was established. A database of 26 kinds of white powders, including alkaloids such as aconitine and tetrodotoxin, biological modifiers such as bradykinin, substance P and their structural analogs, biotoxins such as conotoxins, α-bungarotoxin and ricin, and common white powder such as salt, flour and bovine serum albumin was constructed. Six pattern recognition algorithms, including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), k-nearest neighbor (kNN), naive bayesian (NB), classification tree (CT) and support vector machine (SVM), were used to classify the single spectrum and the fusion data with this database. The results showed that the recognition accuracy of different methods was 76.0%-97.2%, and among which, the fusion recognition algorithm based on the support vector machine model achieved a high recognition accuracy of 97.2%. Meanwhile, the difference of recognition accuracy was analyzed in this study. This method could also distinguish multiple structural analogues of the two biological modifiers, which could be used in rapid distinguish of unknown white powder.

Key words:

1. [1]
  Baucum M, John R. Risk Anal., 2019, 40(2):399-407
2. [2]
  Berger T,Eisenkraft A, Bar-Haim E, Kassirer M, Aran A A, Fogel I. Disaster Mil. Med., 2016, 2:7
3. [3]
  Zhao L, Huang Y, Dong Y, Han X, Wang S, Liang X. Toxins, 2018, 10(11):427
4. [4]
  Banerjee P,Kintzios S, Prabhakarpandian B. Toxins, 2013, 5(12):2366-2383
5. [5]
  Liu X, Fan X, Matsumoto H,Nie Y, Sha Z, Yi K, Pan J, Qian Y, Cao M, Wang Y, Zhu G, Wang M. Environ. Sci. Technol., 2018, 52(9):5105-5114
6. [6]
  McNamee S E, Medlin L K, Kegel J,Mccoy G R, Raine R, Barra L, Ruggiero M V, Kooistra W H C F, Montresor M, Hagstrom J A, Blanco E P, Graneli E, Rodriguez F J, Escalera L, Reguera B, Dittami S M, Edvardsen B, Taylor J D, Lewis J, Pazos Y, Elliott C T, Campbell K. Harmful Algae, 2016, 55:112-120
7. [7]
  Stipić F, Burić P, Jakšić Ž, Pletikapic G, Sikiric M D, Zgrablic G, Frkanec L, Lyons D M. Colloids Surf. B, 2015, 135:481-489
8. [8]
  Pan Y, Wei X, Liang T, Zhou J, Wan H, Hu N, Wang P. Biomed. Microdevices, 2018, 20(3):60
9. [9]
  Warth B, Parich A, Atehnkeng J, Bandyopadhyay R, Schuhmacher R, Sulyok M, Krska R. J. Agric. Food Chem., 2012, 60:9352-9363
10. [10]
  Valea P, Gomesa S S, Lameirasa J, Rodrigues S M, Botelho M J, Laycock M V. Food Addit. Contam. A, 2009, 26:214-220
11. [11]
  Tsai C, Tipple C A, Yost R A. Rapid Commun. Mass Spectrom., 2018, 32(7):552-560
12. [12]
  Nousiainen M, Holopainen S, Puton J, Sillanpaa M. Talanta, 2011, 84(3):738-744
13. [13]
  Satoh T, Kishi S, Nagashima H, Tachikawa M, Kanamori-Kataoka M, Nakagawa T, Kitagawa N, Tokita K, Yamamoto S, Seto Y. Anal. Chim. Acta, 2015, 865(1):39-52
14. [14]
  Guo Z, Wang M, Wu J, Tao F, Chen Q, Wang Q, Ouyang Q, Shi J, Zou X. Food Chem., 2019, 286:282-288
15. [15]
  Chao K, Dhakal S, Qin J, Peng Y, Schmidt W F, Kim M S, Chan D E. Sensors, 2017, 17(3):618
16. [16]
  JIANG Lin-Hua, SHEN Jun, YU Zhi-Hao, SHAO Yong-Ni, CHEN Xiao-Wan, CHEN Xiao-Dong. Chinese J. Opt. Instrum., 2018, 40(02):31-37 蒋林华, 沈俊, 余治昊, 邵咏妮, 陈小婉, 陈晓东. 光学仪器, 2018, 40(02):31-37
17. [17]
  List of Human and Animal Pathogens and Toxins for Export Control. https://australiagroup.net/en/human_animal_pathogens.html,2017-07
18. [18]
  Annex on Chemicals Schedule 1. https://www.opcw.org/chemical-weapons-convention/annexes/annex-chemicals/schedule-1,1997-04-29
19. [19]
  Eiceman G A, Karpas Z. Ion Mobility Spectrometry^© 2005 CRC Press. Taylor & Francis Group

扫一扫看文章

计量

PDF下载量: 8
文章访问数: 1055
HTML全文浏览量: 75

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

基于数据融合的生物毒素及生物调节剂快速识别研究

English

Study on Fast Recognition of Biotoxins and Biological Modifiers Using Data Fusion Algorithm

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

基于数据融合的生物毒素及生物调节剂快速识别研究

English

Study on Fast Recognition of Biotoxins and Biological Modifiers Using Data Fusion Algorithm

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南： 你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

文章相关

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs