期刊
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES
卷 41, 期 1, 页码 225-232出版社
AMER CHEMICAL SOC
DOI: 10.1021/ci000458k
关键词
-
Quantitative structure-property relationships (QSPR) on a large set of descriptors are developed for the P-31 NMR chemical shifts of a large set of phosphines. The data set was composed of 291 primary, secondary, and tertiary phosphines, PH3-nRn, including substituents with different steric and electronic characteristics. Multiple linear regression and computational neural networks (CNN) were employed to create the models best suited for the prediction of P-31 NMR chemical shifts. A correlation equation including seven descriptors (R-2 = 0.8619) is reported. A 7-5-1 CNN was developed that produced a root-mean-error of 9.6 ppm (R-2 = 0.9513) for the training set, of 11.7 ppm (R-2 = 0.8986) for the cross-validation set, and of 11.3 ppm (R-2 = 0.9527) for an external prediction set. The CNN methods give significantly better predictions of P-31 NMR chemical shifts for phosphines than the multiple linear regression approach.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据