Ranking MOLGEN structure proposals by 13C NMR chemical shift prediction with ANALYZE

Artificial neural networks are capable of predicting the C-13 chemical shifts of organic molecules nearly as fast as incremental methods while maintaining the accuracy of database methods. In this article, we apply a recently developed neural network (Meiler et. al., J. Chem. Inf. Comput. Sci. 2000, 40, 1169-1176), to the screening of large sets of molecules obtained by structure generators in the process of automated structure elucidation. Specifically, we apply the network to sets of structures generated by MOLGEN (Benecke et. al., Anal. Chim. Acta 1995, 314, 141-147) for ten randomly selected molecules of less than 13 non-hydrogen atoms. The computed C-13 NMR spectra are compared to the experimental spectrum; in all cases, the computed spectrum belonging to the example molecule yields a significantly smaller deviation to the experimental data then all other predicted spectra. This result suggests that the approach is suitable for automated structure prediction for organic molecules with up to 12 non-hydrogen atoms.