Automated metabolite identification from biological fluid 1H NMR spectra

Abstract

Metabolite identification in biological samples using Nuclear Magnetic Resonance (NMR) spectra is a challenging task due to the complexity of the biological matrices. This paper introduces a new, automated computational scheme for the identification of metabolites in 1D 1H NMR spectra based on the Human Metabolome Database. The methodological scheme comprises of the sequential application of preprocessing, data reduction, metabolite screening and combination selection. The proposed scheme has been tested on the 1D 1H NMR spectra of: (a) an amino acid mixture, (b) a serum sample spiked with the amino acid mixture, (c) 20 blood serum, (d) 20 human amniotic fluid samples, (e) 160 serum samples from publicly available database. The methodological scheme was compared against widely used software tools, exhibiting good performance in terms of correct assignment of the metabolites. This new robust scheme accomplishes to automatically identify peak resonances in 1H-NMR spectra with high accuracy and less human intervention with a wide range of applications in metabolic profiling.