Diffusion coefficient distribution from NMR-DOSY experiments using Hopfield neural network

• DOI: 10.1016/j.jmr.2006.06.005
• Publication Date: 2006-07-26T02:57:51Z
• Authors: Rita C.O. Sebastião; Carlos N. Pacheco; J.P. Braga; Dorila Piló-Veloso
• Keywords: Diffusion; Bridged Bicyclo Compounds; Neural Networks, Computer; Strychnine; Propionates; Nuclear Magnetic Resonance, Biomolecular; 01 natural sciences; 0104 chemical sciences

Diffusion ordered spectroscopy (DOSY) is a powerful two-dimensional NMR method to study molecular translation in various systems. The diffusion coefficients are usually retrieved, at each frequency, from a fit procedure on the experimental data, considering a unique coefficient for each molecule or mixture. However, the fit can be improved if one regards the decaying curve as a multiexponential function and the diffusion coefficient as a distribution. This work presents a computer code based on the Hopfield neural network to invert the data. One small-molecule binary mixture with close diffusion coefficients is treated with this approach, demonstrating the effectiveness of the method.