Toward More Reliable 13C and 1H Chemical Shift Prediction: A Systematic Comparison of Neural-Network and Least-Squares Regression Based Approaches
- 5 December 2007
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 48 (1) , 128-134
Abstract
The efficacy of neural network (NN) and partial least-squares (PLS) methods is compared for the prediction of NMR chemical shifts for both 1H and 13C nuclei using very large databases containing millions of chemical shifts. The chemical structure description scheme used in this work is based on individual atoms rather than functional groups. The performances of each of the methods were optimized in a systematic manner described in this work. Both of the methods, least-squares and neural network analyses, produce results of a very similar quality, but the least-squares algorithm is approximately 2−3 times faster.Keywords
This publication has 17 references indexed in Scilit:
- Are Deterministic Expert Systems for Computer-Assisted Structure Elucidation Obsolete?Journal of Chemical Information and Modeling, 2006
- Structure Elucidator: A Versatile Expert System for Molecular Structure Elucidation from 1D and 2D NMR Data and Molecular FragmentsJournal of Chemical Information and Computer Sciences, 2004
- Nonlinear Multivariate Regression Outperforms Several Concisely Designed Neural Networks on Three QSPR Data SetsJournal of Chemical Information and Computer Sciences, 2000
- Simulation of the 13C Nuclear Magnetic Resonance Spectra of Ribonucleosides Using Multiple Linear Regression Analysis and Neural NetworksJournal of Chemical Information and Computer Sciences, 1996
- New parameters for predicting 1H NMR chemical shifts of protons attached to carbon atomsAnalytica Chimica Acta, 1995
- C13Shift: a computer program for the prediction of carbon-13 NMR spectra based on an open set of additivity rulesJournal of Chemical Information and Computer Sciences, 1992
- SpecInfo?A multidimensional spectroscopic interpretation systemMicrochimica Acta, 1991
- A computer program for the prediction of 13-C-NMR chemical shifts of organic compoundsAnalytica Chimica Acta, 1990
- Tables of Spectral Data for Structure Determination of Organic Compounds1989
- Nuclear Magnetic Resonance Studies of Hydrogen Bonding. II. Calculation of the Shift upon Complex FormationJournal of the American Chemical Society, 1964