Jump to main content
Jump to site search

Issue 29, 2013
Previous Article Next Article

Successful combination of computationally inexpensive GIAO 13C NMR calculations and artificial neural network pattern recognition: a new strategy for simple and rapid detection of structural misassignments

Author affiliations

Abstract

GIAO NMR chemical shift calculations coupled with trained artificial neural networks (ANNs) have been shown to provide a powerful strategy for simple, rapid and reliable identification of structural misassignments of organic compounds using only one set of both computational and experimental data. The geometry optimization, usually the most time-consuming step in the overall procedure, was carried out using computationally inexpensive methods (MM+, AM1 or HF/3-21G) and the NMR shielding constants at the affordable mPW1PW91/6-31G(d) level of theory. As low quality NMR prediction is typically obtained with such protocols, the decision making was foreseen as a problem of pattern recognition. Thus, given a set of statistical parameters computed after correlation between experimental and calculated chemical shifts the classification was done using the knowledge derived from trained ANNs. The training process was carried out with a set of 200 molecules chosen to provide a wide array of chemical functionalities and molecular complexity, and the results were validated with a set of 26 natural products that had been incorrectly assigned along with their 26 revised structures. The high prediction effectiveness observed makes this method a suitable test for rapid identification of structural misassignments, preventing not only the publication of wrong structures but also avoiding the consequences of such a mistake.

Graphical abstract: Successful combination of computationally inexpensive GIAO 13C NMR calculations and artificial neural network pattern recognition: a new strategy for simple and rapid detection of structural misassignments

Back to tab navigation

Supplementary files

Publication details

The article was received on 24 Apr 2013, accepted on 28 May 2013 and first published on 29 May 2013


Article type: Paper
DOI: 10.1039/C3OB40843D
Org. Biomol. Chem., 2013,11, 4847-4859

  •   Request permissions

    Successful combination of computationally inexpensive GIAO 13C NMR calculations and artificial neural network pattern recognition: a new strategy for simple and rapid detection of structural misassignments

    A. M. Sarotti, Org. Biomol. Chem., 2013, 11, 4847
    DOI: 10.1039/C3OB40843D

Search articles by author

Spotlight

Advertisements