药物的定量结构色谱保留关系研究
Study on the Quantitative Structure Chromatographic Retention Relationship of Drugs
何琴 1黄保军 1赵伟超 1徐可宣1
作者信息
- 1. 许昌学院 化工与材料学院,河南 许昌 461000
- 折叠
摘要
采用人工神经网络(ANN)建立了 110 种药物的结构与色谱保留之间的定量关系(QSRR)模型,并将其与偏最小二乘回归(PLSR)模型进行比对.110 种药物的ANN模型自相容能力的复相关系数(R2)为0.9191,泛化能力的复相关系数(R2)为 0.9365;而PLSR模型的复相关系数(R2)为0.8275 和0.8514.结果表明,ANN模型的自相容能力、泛化能力优于PLSR模型.采用集内集和集外集对模型进行检验时,ANN模型的复相关系数(R2)为 0.9105,也优于PLSR模型,且ANN预测精密度和准确度更高.
Abstract
The quantitative relationship(QSRR)model between the structure and the chromatographic re-tention of 110 drugs was established by the artificial neural network(ANN)and compared with the partial least squares regression(PLSR)model.The multiple correlation coefficient(R2)of the ANN model self-compatibility of 110 drugs was 0.9191.The multiple correlation coefficient(R2)of generalization ability was 0.9365.The multiple correlation coefficient(R2)of PLSR model was 0.8275,and the multiple correlation coefficient(R2)of generalization ability was 0.8514.The results showed that ANN model has better self-compatibility and gener-alization ability than PLSR model.In addition,when using the in-set and the out-of-set to test the model,the complex correlation coefficient(R2)of ANN model is 0.9105,which is better than PLSR model,and the preci-sion and accuracy of ANN prediction are higher.
关键词
定量结构色谱保留相关/人工神经网络/药物/保留因子Key words
quantitative structure retention relationship/artificial neural network/drugs/retention factor引用本文复制引用
出版年
2024
NETL
NSTL
万方数据