Discovery of metabolite features for the modelling and analysis of high-resolution NMR spectra. (30th June 2008)

• Record Type: Journal Article
• Authors: Cho, Hyun-Woo; Kim, Seoung Bum; Jeong, Myong K.; Park, Youngja; Miller, Nana; Ziegler, Thomas; Jones, Dean
• Is Part Of: International journal of data mining and bioinformatics. Volume 2:Number 2(2008)
• Page Start: 176
• Page End: 192
• Publication Date: 2008-06-30
• Subjects: nuclear magnetic resonance -- NMR spectra -- feature selection -- metabolomics -- multivariate statistical analysis -- orthogonal signal correction -- OSC -- data mining -- bioinformatics -- metabolite features -- classification; Data mining -- Periodicals; Bioinformatics -- Periodicals; 006.312
• Languages: English
• ISSNs: 1748-5673

Abstract

This study presents three feature selection methods for identifying the metabolite features in nuclear magnetic resonance spectra that contribute to the distinction of samples among varying nutritional conditions. Principal component analysis, Fisher discriminant analysis, and Partial Least Square Discriminant Analysis (PLS-DA) were used to calculate the importance of individual metabolite feature in spectra. Moreover, an Orthogonal Signal Correction (OSC) filter was used to eliminate unnecessary variations in spectra. We evaluated the presented methods by comparing the ability of classification based on the features selected by each method. The result showed that the best classification was achieved from an OSC-PLS-DA model.