Nuclear Magnetic Resonance (NMR) allows the molecular structure of a material to be analyzed by observing and measuring the interaction of nuclear spins via a powerful magnetic field. NMR can be used to determine molecular conformation in solution and physical properties at the molecular level such as conformational exchange, phase changes, solubility, and diffusion and is used in many industries, including quality control, food production, drug development, and many others.

The Need

Analyzing NMR spectra is inherently challenging for the comprehensive and explicit identification and characterization of peaks. In addition, data often include a large number of cross-peaks, and analysis is tedious, time-consuming, and requires highly-trained specialists to interpret. New software that can allow the broader scientific community to rapidly analyze NMR spectra would significantly enhance its applicability in many fields.

The Technology

This technology describes a software called “DEEP Picker” and “Voigt Fitter”” that uses a deep neural network for automating the analysis of 1-D and 2-D NMR spectra. It uses seven convolutional layers and is trained on an extensive database of known spectra. The inventors have created a software prototype and showed it identifies overlapping peaks accurately belonging to proteins or small molecules, such as metabolites, in complex mixtures.

Commercial Applications

This invention can be used for drug development, basic research, quality control, water treatment, food processing facilities, etc.

Benefits/Advantages

Compared to existing NMR products, this technology facilitates rapid and improved analysis of NMR spectra, when necessary, with full quantitation, thereby accelerating research and quality for the evaluation of complex materials.

Patents

PCT application pending