Abstract：Partial least squares (PLS) and radial basis function neural network (RBFNN) combined with near infrared spectroscopy (NIR) were applied to develop models for cordycepic acid, polysaccharide and adenosine analysis in Paecilomyces hepialid fermentation mycelium. The developed models possess well generalization and predictive ability which can be applied for crude drugs and related productions determination. During the experiment, 214 Paecilomyces hepialid mycelium samples were obtained via chemical mutagenesis combined with submerged fermentation. The contents of cordycepic acid, polysaccharide and adenosine were determined via traditional methods and the near infrared spectroscopy data were collected. The outliers were removed and the numbers of calibration set were confirmed via Monte Carlo partial least square (MCPLS) method. Based on the values of degree of approach (Da), both moving window partial least squares (MWPLS) and moving window radial basis function neural network (MWRBFNN) were applied to optimize characteristic wavelength variables, optimum preprocessing methods and other important variables in the models. After comparison, the RBFNN, RBFNN and PLS models were developed successfully for cordycepic acid, polysaccharide and adenosine detection, and the correlation between reference values and predictive values in both calibration set (R2c) and validation set (R2p) of optimum models was 0.941 7 and 0.966 3, 0.980 3 and 0.985 0, and 0.976 1 and 0.972 8, respectively. All the data suggest that these models possess well fitness and predictive ability.
Key words：Near Infrared spectroscopy;Partial least square;Radial basis function neural network;Paecilomyces hepialid
滕伟卓1，宋 佳1，孟凡欣2，孟庆繁1，逯家辉1，胡 爽1，滕利荣1，2，王 迪1*，谢 晶1* . 采用近红外漫反射光谱进行蝙蝠蛾拟青霉菌丝体组分检测的研究 [J]. 光谱学与光谱分析, 2014, 34(10): 2645-2651.
TENG Wei-zhuo1, SONG Jia1, MENG Fan-xin2, MENG Qing-fan1, LU Jia-hui1, HU Shuang1, TENG Li-rong1,2, WANG Di1*, XIE Jing1*. Study on the Detection of Active Ingredient Contents of Paecilomyces hepiali Mycelium via Near Infrared Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(10): 2645-2651.
[1] Hsu T H, Shiao L H, Hsieh C Y, et al. Food Chemistry, 2002, 78: 463. [2] Li S P, Su Z R, Dong T T, et al. Phytomedicine, 2002, 9: 319. [3] Li S P, Su Z R, Dong T T, et al. Electrophoresis, 2001, 22(1): 144. [4] Yoshikawa N, Nakamura K, Yamaguchi Y, et al. Clin Exp Pharmacol Physiol, 2004, 2: S51. [5] DENG Yue-yi, CHEN Yi-ping, HE Xue-lin, et al(邓跃毅，陈以平，贺学林，等). Chinese Journal of Integrated Traditional and Western Nephrology(中国中西医结合肾病杂志), 2001, 2(7): 381. [6] Koh J H, Yu K W, Suh H J, et al. Biosci. Biotechnol. Biochem., 2002, 66(2): 407. [7] Restaino E, Fassio A, Cozzolino D, et al. Cyta-Journal of Food, 2011, 9: 210. [8] Martelo M, Vazquez M. Czech Journal of Food Science, 2014, 32: 37. [9] Guo Weiliang, Du Yiping, Zhou Yongcan, et al. World Journal of Microbiology & Biotechnology, 2012, 3(28): 993. [10] DING Chang-chun, FANG Xiang-jing, ZHAO Yan-li, et al(丁长春，方向京，赵艳丽，等). Spectroscopy and Spectral Analysis (光谱学与光谱分析), 2014, 34(1): 82. [11] Ko Chia-Nan. Applied Mathematics and Computation, 2013, 221: 503. [12] Swierenga H, Groot P J, Weijer A P. Chemometrics and Intelligent Laboratory Systems，1998, 41: 237. [13] Chinese Pharmacopoeia Commission(中华人民共和国药典委员会). Pharmacopoeia of the People’s Republic of China(中华人民共和国药典), Part One(第一部). Beijing：Chinese Medical Science and Technology Press(北京：中国医药科技出版社)，2010，106. [14] WANG Li-ming，XIA Wen-shui(王黎明，夏文水). Food Science(食品科学). 2005, 26(7)：185. [15] CAI You-hua, FAN Wen-xia, LIU Xue-ming, et al(蔡友华, 范文霞, 刘学铭, 等). Modern Food Science and Technology(现代食品科技), 2008, 24(1): 76. [16] Koseki S, Noda T, Yokoyama S. J. Affect Disord, 2013, 151: 352.
