Protein Content Determination of Shiitake Mushroom (Lentinus edodes) Using Mid-Infrared Spectroscopy and Chemometeics
ZHU Zhe-yan1, 2, LIU Fei2*, ZHANG Chu2, KONG Wen-wen2, HE Yong2*
1. Zhejiang Technical Institute of Economics, Hangzhou 310018, China 2. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China
摘要： 研究了中红外光谱预测香菇蛋白质含量的可行性。去掉明显噪声部分后，研究香菇3 581～689 cm-1中红外光谱与蛋白质含量的关系。以Savitzky-Golay(SG)5点平滑预处理光谱建立偏最小二乘法(partial least squares, PLS)的预测模型的效果不理想，模型的建模集和预测集的相关系数均高于0.85，但剩余预测偏差(residual prediction deviation, RPD)值仅为1.77。采用连续投影算法(successive projections algorithm, SPA)算法从3000个波数点中选择7个特征波数，并以七个特征波数分别建立PLS、多元线性回归(multiple linear regression, MLR)、反向传播神经网络(back-propagation neural network, BPNN)和极限学习机模型(extreme learning machine, ELM)。与全谱的PLS相比，以特征波数的PLS模型和MLR模型的预测效果相对较差，而以特征波数的BPNN和ELM模型的预测效果相对较好。其中SPA-ELM模型的预测效果最佳，预测集相关系数(correlation coefficient of prediction)Rp=0.899 5，预测集均方根误差(root mean square error of prediction)RMSEP=1.431 3，剩余预测偏差RPD=2.18。研究结果表明，中红外光谱分析技术可以用于预测香菇蛋白质含量，且SPA选取特征波数能用来代替原始光谱进行建模分析，为香菇蛋白质含量的检测提供了新的思路。
关键词：中红外光谱;香菇;蛋白质含量;连续投影算法
Abstract：The feasibility of protein determination of shiitake mushroom (Lentinus edodes) using mid-infrared spectroscopy (MIR) was studied in the present paper. Wavenumbers 3 581～689 cm-1 were used for quantitative analysis of protein content after removing of the part of obvious noises. Five points Savitzky-Golay smoothing was applied to pretreat the MIR spectra and partial least squares (PLS) model was built based on the pretreated spectra. The full spectra PLS model obtained poor performance with the ratio ofprediction to deviation (RPD) of only 1.77. Successive projections algorithm (SPA) was applied to select 7 sensitive wavenumbers from the full spectra, and PLS model, multiple linear regression (MLR), back-propagation neural network (BPNN) and extreme learning machine (ELM) model were built using the selected sensitive wavenumbers. SPA-PLS model and SPA-MLR model obtained relatively worse results than SPA-BPNN model and SPA-ELM model. SPA-ELM obtained the best results with correlation coefficient of prediction (Rp) of 0.899 5, root mean square error of prediction (RMSEP) of 1.431 3 and RPD of 2.18. The overall results indicated that MIR combined with chemometrics could be used for protein content determination of shiitake mushroom, and SPA could select sensitive wavenumbers to build more accurate models instead of the full spectra.
[1] LI Yue-mei (李月梅). Microbiology(微生物学通报), 2005, 32(4): 149. [2] BAI Lan(白 岚). Journalof Fungal Research(菌物研究), 2006, 4(2): 21. [3] Cozzolino D, Cynkar W, Shah N, et al. Food Analytical Methods, 2011, 5(3): 381. [4] De Marchi M, Penasa M, Cecchinato A, et al. Animal, 2011, 5(10): 1653. [5] Kanakis C D, Petrakis E A, Kimbaris, A C, et al. Phytochemical Analysis, 2012, 23(1): 34. [6] Bonfatti V, Di Martino G, Carnier P, et al. Journal of Dairy Science, 2011, 94(12): 5776. [7] Etzion Y, Linker R, Cogan U, et al. Journal of Dairy Science, 2004, 87(9): 2799. [8] Guo W L, Du Y P, Zhou Y C, et al. World Journal of Microbiology and Biotechnology, 2012, 28(3): 993. [9] Daszykowski M, Wrobel M S, Czarnik-Matusewicz H, et al. Analyst, 2008, 33(11): 1523. [10] RoggoY , Chalus P, Maurer L, et al. Journal of Pharmaceutical and Biomedical Analysis, 2007, 44(3): 683. [11] Liu F, He Y. Food Research International, 2008, 41(5): 562. [12] Huang G B, Zhu Q Y, Siew C K, et al. Neurocomputing, 2006, 70(1-3): 489. [13] Liu F, He Y. Food Chemistry, 2009, 115(4): 1430. [14] Gaston E, Frias J M, Cullen P J, et al. Journal of Agriculture and Food Chemistry, 2010, 58 (10): 6226.
