Abstract:  The assignment of the 1H spectrum of a protein or a polypeptide is the prerequisite for advanced NMR studies.  We present here an assignment tool based on the artificial neural network technology, which determines the type of amino acid from the chemical shift values observed in the ¹H spectrum.  Two artificial neural networks have been trained and extensively tested against a non-redundant subset of the BMRB chemical shift databank [Seavey, B.R. et al. (1991) J. Biolmol. NMR, 1, 217-236 PubMed PMID: 1841696].   The most promising of the two accomplishes the analysis in two steps, grouping related amino acids together.  It presents a mean rate of success above 80% on the the test set.  The second network tested separates down to the single amino acid; it presents a mean success rate of 63%.  This tool has been used to assist in the manual assignment of peptides and proteins and can also be used tas a block in an automated approach to assignment.  The program has been called RESCUE and is made publicly available at the following URL: ftp://www.cbs.univ-montp1.fr/pub/RESCUE/

J Biomol NMR 2000 Sep;15(1):15-26.
[PubMed PMID: 10549132]

The following table lists the proteins and polypeptides along with their BMRB accession codes,  that were used to develop and test RESCUE.