摘要
采用气相色谱-氢火焰离子化检测器(GC-FID),对常见的37种脂肪酸甲酯在Rtx-wax石英毛细管色谱柱上的分离条件进行了系统的研究,同时采用Steric and Electronic Descriptors(SEDs)表征其分子结构信息,运用多元线性回归(Multiple Linearregression,MLR)建立了脂肪酸甲酯分子结构参数与其气相色谱保留时间的定量结构-色谱保留相关(Quantitative Structure Retention Relationship,QSRR)模型。并采用留一法(Leave-One-Out,LOO)交互检验(Cross-Validation,CV)和外部验证的方法对该模型的稳定性和预测能力进行了评价,其预测值、留一法(Leave-One-Out,LOO)交互检验预测值和外部样本预测值的相关系数R、R CV、Q2ext分别为0.9990、0.9951、0.9995。结果表明,所建模型具有良好的稳定性和预测能力,为脂肪酸的分离、检测及结构表征提供了一条新途径。
Separation condition of the common 37 fatty acid methyl esters was researched in Rtx-wax quartz capillary chromatographic column by using gas chromatography- hydrogen flame ionization detector （ GC- FID）. Meanwhile,the Steric and Electronic Descriptors（SEDs）were used to characterize molecular structures of fatty acid methyl esters, and then the model of quantitative structure retention relationship（QSRR）for above-mentioned 37 compounds was established through multiple linear regression （MLR）.And the estimated stability and generalized ability of the model were strictly analyzed by both internal and external validation.The correlation coefficient（ R）, leave-one-out（LOQ） cross validation （CV） and Q8xt^2 for the established model were 0.9990,0.9951 and 0.9995, respectively.Results indicated that this model was good for stability and predictability.The proposed model could provide a new approach to separation,detection and structure characterization of fatty acids.
出处
《食品工业科技》
CAS
CSCD
北大核心
2013年第19期49-53,共5页
Science and Technology of Food Industry
基金
国家自然科学基金(31171748)
山西省研究生优秀创新项目(20123015)
