Metabolic profiling using principal component analysis, discriminant partial least squares, and genetic algorithms

• Published in: Talanta (Oxford) Vol. 68; no. 5; pp. 1683 - 1691
• Main Authors: Ramadan, Z., Jacobs, D., Grigorov, M., Kochhar, S.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 28.02.2006; Oxford Elsevier
• Subjects: Analytical chemistry; Chemistry; Exact sciences and technology; Genetic algorithms; Metabonomics; NMR; PCA; PLS-DA; Spectrometric and optical methods; NMR; PLS-DA; Metabonomics; PCA; Genetic algorithms; Performance evaluation; Human; Urine; Discriminant analysis; Metabolite; NMR spectrometry; Pattern recognition; PLS regression; Genetic algorithm; Principal component analysis
• ISSN: 0039-9140; 1873-3573; 1873-3573
• DOI: 10.1016/j.talanta.2005.08.042

The aim of this study was to evaluate evolutionary variable selection methods in improving the classification of 1H nuclear magnetic resonance (NMR) metabonomic profiles, and to identify the metabolites that are responsible for the classification. Human plasma, urine, and saliva from a group of 150 healthy male and female subjects were subjected to 1H NMR-based metabonomic analysis. The 1H NMR spectra were analyzed using two pattern recognition methods, principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA), to identify metabolites responsible for gender differences. The use of genetic algorithms (GA) for variable selection methods was found to enhance the classification performance of the PLS-DA models. The loading plots obtained by PCA and PLS-DA were compared and various metabolites were identified that are responsible for the observed separations. These results demonstrated that our approach is capable of identifying the metabolites that are important for the discrimination of classes of individuals of similar physiological conditions.