分子电性距离矢量用于稠环芳烃液相色谱保留值的QSPR研究

The Application of Molecular Electronegativity Distance Vector to the Quantitative Structure-Property Relationship Study on the Retention Index of Polycyclic Aromatic Hydrocarbons in Liquid Chromatography

采用分子电性距离矢量(Molecular Electronegativity Distance Vector,MEDV)表征稠环芳烃类化合物的分子结构。分别运用多元线性回归(Multiple Linear Regres-sion,MLR)和偏最小二乘回归(PLS)建立了稠环芳烃类化合物结构与其液相色谱(LC)保留值的定量结构-性质关系(QSPR)模型,同时采用内部及外部双重验证的办法对所建模型稳定性能进行分析和验证,建模计算值、留一法交互检验预测值和外部样本预测值的复相关系数Rcum、RLOO、Qext分别为0.9970,0.9950,0.9925(MLR);0.9930,0.9790,0.9917(PLS)。结果表明,MEDV能较好地表征该类分子结构信息,所建QSPR模型具有良好的稳定性和预测能力。为稠环芳烃类化合物分离、纯化、检测等方法的建立,提供有效的理论依据。

The molecular electronegativity-distance vector based on 4 atomic types （MEDV） was used to describe the chemical structure of Polycyclic Aromatic Hydrocarbons （PAHs）. With the help of multiple linear regression （MLR） and partial least square regression（PLS）, the quantitative structure-property relationship （QSPR） model was established. The estimation stability and generalization ability of the model was strictly analyzed by both internal and external validation. The correlation coefficient （R） for the established MLR, PLS models, including leave-one-out （LOO）, cross-validation （CV） and Qext were 0.9970, 0. 9950,0. 9925（MLR） ;0. 9930,0. 9790,0. 9917（PLS） ,respectively. The result shows that the MEDV can be used for the characterization of the structure information of PAHs, and the stability of the model is good. The propesed method provides an important support and is useful for chemical separation and identification of PAHs.