Feature Selection and Interpretation in Infrared Quantitative Models of Liquiritin and Glycyrrhizin in Radix Glycyrrhizae
ZHAN Xue-yan1, LIN Zhao-zhou1, SUN Yang1, YUAN Rui-juan1, YANG Zhan-lan2, DUAN Tian-xuan1*
1. School of Chinese Materia Medica, Beijing University of Chinese Medicine，Beijing 100102, China 2. College of Chemistry and Molecular Engineering, Peking University，Beijing 100871, China
Abstract：Feature selection can improve the interpretation of the modeling variables to a certain extent by selecting variables from the complex spectra backgrounds. However, the improvement of models interpretation does not mean that the modeling variables have the exact physical or chemical significance. In this paper, We explore the relation between the chemical characteristics of target components and the spectrum variables selected with 3 kinds of variables selection methods which are moving window partial least squares regression(mwPLS), synergy interval partial least squares regression(siPLS) and competitive adaptive reweighted sampling(CARS), and compare the interpretation difference of the variables selected with the above variables selection methods. The results show that the variables selected with mwPLS accord with ν(φ)CC of liquiritin and δCH3 or δCH2 of glycyrrhizin, which are the obvious spectra differences between the flavonoids and saponins in Radix Glycyrrhizae, and the variables selected with siPLS are the characteristic intervals combinations of the flavonoids or saponins in Radix Glycyrrhizae, which is the combination of ν()CC, ν()C—O, ν()C—H of flavonoids or the combination of νC—O, νC—H, νO—H of saponins while the variables selected with CARS can better accord with most of the characteristic peaks from 1 000 to 4 000 cm-1 of liquiritin or glycyrrhizin in Radix Glycyrrhizae, and the predict performance of the infrared quantitative model established on the spectroscopic variables selected with CARS can be improved. Therefore, most of the variables selected with CARS can be interpreted by the characteristic peaks in the infrared characteristic region of the target components, which is beneficial to improve the interpretation of the quantitative model.
詹雪艳1，林兆洲1，孙 杨1，袁瑞娟1，杨展澜2，段天璇1* . 甘草中甘草苷和甘草酸红外定量模型特征变量的筛选与解析 [J]. 光谱学与光谱分析, 2015, 35(09): 2530-2535.
ZHAN Xue-yan1, LIN Zhao-zhou1, SUN Yang1, YUAN Rui-juan1, YANG Zhan-lan2, DUAN Tian-xuan1* . Feature Selection and Interpretation in Infrared Quantitative Models of Liquiritin and Glycyrrhizin in Radix Glycyrrhizae . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2015, 35(09): 2530-2535.
[1] The State Pharmacopoeia Commission(国家药典委员会). The People’s Republic of China Pharmacopoeia (2010 Version A) (中华人民共和国药典2010版一部). Beijing：Chinese Medicine Science and Technology Press(北京：中国医药科技出版社)，2010. [2] Nrgaard A S L, Wagner J, Nielsen J P, et al. Applied Spectroscopy, 2000, 54(3)：413. [3] Kasemsumran S, Du Y P, Maruo K, et al. Chemometrics and Intelligent Laboratory Systems , 2006, 82：97. [4] Zou X, Zhao J, Malcolm J W P, et al. Analytica Chimica Acta 2010, 667：14. [5] Ferrao M F, Viera M D, Pazos R E P, et al. Fuel, 2011, 90(2)：701. [6] Shariati-Rad M, HasaniM. Journal of Chemometrics, 2010, 24(1-2)：45. [7] Li H, Liang Y, Xu Q, et al. Analytica Chimica Acta, 2009, 648(1)：77. [8] Yi Q X, Jiapaer G, Chen J M, et al. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 91：72. [9] Centner V, Massart D L. Analytical Chemistry, 1996, 68：3851. [10] Kirkpatrick S, Vecchi M P. Science, 1983, 220：671. [11] Lucasius C B, Beckers M L M, Kateman G. Analytica Chimica Acta, 1994, 286：135. [12] Kagarise R E. J. Phys. Chem., 1955, 59(3)：271.
