最小二乘支持向量机和偏最小二乘法在栀子中间体纯化工艺近红外定量分析中的应用

Application of least squares support vector machines and partial least squares in quantitation on purification of Gardenia jasminoides intermediate using NIR spectroscopy

目的应用近红外(NIR)光谱技术建立热毒宁注射液栀子中间体纯化工艺关键质控成分的定量分析模型。方法测定样品中山栀苷、京尼平苷酸、去乙酰车叶草酸甲酯、京尼平龙胆双糖苷、栀子苷、绿原酸和总酸的量,扫描NIR光谱,经过异常点的剔除、最佳光谱预处理方法的选择、最佳建模波段的选择,分别用偏最小二乘法(PLS)和最小二乘支持向量机法(LS-SVM)建立定量校正模型,并用此模型对18个未知样品进行预测。结果山栀苷、京尼平苷酸、去乙酰车叶草酸甲酯、京尼平龙胆双糖苷、栀子苷、绿原酸和总酸的PLS模型和LS-SVM模型对未知样品的预测相对偏差(RSEP)均小于3%,说明2种方法均产生较好的拟合效果和预测能力。但是山栀苷和总酸的LS-SVM模型预测误差明显小于PLS模型,京尼平苷酸、去乙酰车叶草酸甲酯、京尼平龙胆双糖苷、栀子苷和绿原酸的LS-SVM模型和PLS模型预测误差接近。结论LS-SVM法较PLS法预测性能更好,建立的模型可以用于热毒宁注射液栀子中间体纯化工艺关键质控成分的快速检测。

Objective To establish the quantitative models for analyzing the content of critical quality indicators in the purification process of Gardenia jasminoides intermediate in Reduning Injection using near-infrared（NIR） spectroscopy. Methods The contents of shanzhiside, geniposidic acid, deacetyl asperulosidic acid methyl ester, genipin-1-β-D-gentiobioside, geniposide, chlorogenic acid, and total acid were determined by the reference method and NIR spectra were acquired. After removing the outliers, selecting the optimal spectral preprocessing method and selecting the best spectral wavelength, partial least squares（PLS） and the least squares support vector machines（LS-SVM） were used to build the models for predicting the contents of the above quality indicators in 18 unknown samples. Results For shanzhiside, geniposidic acid, deacetyl asperulosidic acid methyl ester, genipin-1-β-D-gentiobioside, geniposide, chlorogenic acid, and total acid, the relative standard errors of prediction（RSEP） was lower than 3% for PLS models and LS-SVM models, indicating both methods could exhibit the satisfactory fitting results and predictive abilities. However, the LS-SVM models of shanzhiside and total acid showed lower predictive errors than PLS models. For geniposidic acid, deacetyl asperulosidic acid methyl ester, genipin-1-β-D-gentiobioside, geniposide, and chlorogenic acid, both models have the closer predictive errors. Conclusion S-SVM shows better predictive performance than PLS. The established NIR quantitative models can be used for rapidly measuring the content of critical quality indicators in the purification process of G. jasminoides intermediate in Reduning Injection.