Discovery of metabolite features for the modelling and analysis of high-resolution NMR spectra

Hyun Woo Cho; Seoung Bum Kim; Myong K. Jeong; Youngja Park; Nana Gletsu Miller; Thomas R. Ziegler; Dean P. Jones

doi:10.1504/IJDMB.2008.019097

Discovery of metabolite features for the modelling and analysis of high-resolution NMR spectra

Hyun Woo Cho, Seoung Bum Kim, Myong K. Jeong, Youngja Park, Nana Gletsu Miller, Thomas R. Ziegler, Dean P. Jones

Research output: Contribution to journal › Article › peer-review

67 Citations (Scopus)

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.

Original language	English
Pages (from-to)	176-192
Number of pages	17
Journal	International Journal of Data Mining and Bioinformatics
Volume	2
Issue number	2
DOIs	https://doi.org/10.1504/IJDMB.2008.019097
Publication status	Published - 2008 Jun
Externally published	Yes

Keywords

Bioinformatics
Data mining
Feature selection
Metabolomics
Multivariate statistical analysis
NMR
Nuclear magnetic resonance
OSC
Orthogonal signal correction

ASJC Scopus subject areas

Information Systems
Biochemistry, Genetics and Molecular Biology(all)
Library and Information Sciences

Access to Document

10.1504/IJDMB.2008.019097

Cite this

@article{b5b4f76855964be8a6d9992edf725559,

title = "Discovery of metabolite features for the modelling and analysis of high-resolution NMR spectra",

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.",

keywords = "Bioinformatics, Data mining, Feature selection, Metabolomics, Multivariate statistical analysis, NMR, Nuclear magnetic resonance, OSC, Orthogonal signal correction",

author = "Cho, {Hyun Woo} and Kim, {Seoung Bum} and Jeong, {Myong K.} and Youngja Park and Miller, {Nana Gletsu} and Ziegler, {Thomas R.} and Jones, {Dean P.}",

year = "2008",

month = jun,

doi = "10.1504/IJDMB.2008.019097",

language = "English",

volume = "2",

pages = "176--192",

journal = "International Journal of Data Mining and Bioinformatics",

issn = "1748-5673",

publisher = "Inderscience Enterprises Ltd",

number = "2",

}

TY - JOUR

T1 - Discovery of metabolite features for the modelling and analysis of high-resolution NMR spectra

AU - Cho, Hyun Woo

AU - Kim, Seoung Bum

AU - Jeong, Myong K.

AU - Park, Youngja

AU - Miller, Nana Gletsu

AU - Ziegler, Thomas R.

AU - Jones, Dean P.

PY - 2008/6

Y1 - 2008/6

N2 - 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.

AB - 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.

KW - Bioinformatics

KW - Data mining

KW - Feature selection

KW - Metabolomics

KW - Multivariate statistical analysis

KW - NMR

KW - Nuclear magnetic resonance

KW - OSC

KW - Orthogonal signal correction

UR - http://www.scopus.com/inward/record.url?scp=47149086566&partnerID=8YFLogxK

U2 - 10.1504/IJDMB.2008.019097

DO - 10.1504/IJDMB.2008.019097

M3 - Article

C2 - 18767354

AN - SCOPUS:47149086566

SN - 1748-5673

VL - 2

SP - 176

EP - 192

JO - International Journal of Data Mining and Bioinformatics

JF - International Journal of Data Mining and Bioinformatics

IS - 2

ER -

Discovery of metabolite features for the modelling and analysis of high-resolution NMR spectra

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this