Feature selection and classification of high-resolution NMR spectra in the complex wavelet transform domain

Seoung Bum Kim, Zhou Wang, Soontorn Oraintara, Chivalai Temiyasathit, Yodchanan Wongsawat

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Successful identification of the important metabolite features in high-resolution nuclear magnetic resonance (NMR) spectra is a crucial task for the discovery of biomarkers that have the potential for early diagnosis of disease and subsequent monitoring of its progression. Although a number of traditional features extraction/selection methods are available, most of them have been conducted in the original frequency domain and disregarded the fact that an NMR spectrum comprises a number of local bumps and peaks with different scales. In the present study a complex wavelet transform that can handle multiscale information efficiently and has an energy shift-insensitive property is proposed as a method to improve feature extraction and classification in NMR spectra. Furthermore, a multiple testing procedure based on a false discovery rate (FDR) was used to identify important metabolite features in the complex wavelet domain. Experimental results with real NMR spectra showed that classification models constructed with the complex wavelet coefficients selected by the FDR-based procedure yield lower rates of misclassification than models constructed with original features and conventional wavelet coefficients.

Original languageEnglish
Pages (from-to)161-168
Number of pages8
JournalChemometrics and Intelligent Laboratory Systems
Volume90
Issue number2
DOIs
Publication statusPublished - 2008 Feb 15
Externally publishedYes

Fingerprint

Nuclear Magnetic Resonance
Feature Selection
Wavelet transforms
Wavelet Transform
Feature extraction
High Resolution
Nuclear magnetic resonance
Wavelet Coefficients
Metabolites
Feature Extraction
Multiple Testing
Misclassification
Biomarkers
Progression
Frequency Domain
Wavelets
Monitoring
Testing
Experimental Results
Energy

Keywords

  • Classification tree
  • Complex wavelet transforms
  • False discovery rates
  • Gabor coefficients
  • High-resolution NMR spectra
  • Metabolomics

ASJC Scopus subject areas

  • Analytical Chemistry
  • Spectroscopy
  • Statistics and Probability

Cite this

Feature selection and classification of high-resolution NMR spectra in the complex wavelet transform domain. / Kim, Seoung Bum; Wang, Zhou; Oraintara, Soontorn; Temiyasathit, Chivalai; Wongsawat, Yodchanan.

In: Chemometrics and Intelligent Laboratory Systems, Vol. 90, No. 2, 15.02.2008, p. 161-168.

Research output: Contribution to journalArticle

Kim, Seoung Bum ; Wang, Zhou ; Oraintara, Soontorn ; Temiyasathit, Chivalai ; Wongsawat, Yodchanan. / Feature selection and classification of high-resolution NMR spectra in the complex wavelet transform domain. In: Chemometrics and Intelligent Laboratory Systems. 2008 ; Vol. 90, No. 2. pp. 161-168.
@article{cf53ca7d551346af935dd9785e7adfe3,
title = "Feature selection and classification of high-resolution NMR spectra in the complex wavelet transform domain",
abstract = "Successful identification of the important metabolite features in high-resolution nuclear magnetic resonance (NMR) spectra is a crucial task for the discovery of biomarkers that have the potential for early diagnosis of disease and subsequent monitoring of its progression. Although a number of traditional features extraction/selection methods are available, most of them have been conducted in the original frequency domain and disregarded the fact that an NMR spectrum comprises a number of local bumps and peaks with different scales. In the present study a complex wavelet transform that can handle multiscale information efficiently and has an energy shift-insensitive property is proposed as a method to improve feature extraction and classification in NMR spectra. Furthermore, a multiple testing procedure based on a false discovery rate (FDR) was used to identify important metabolite features in the complex wavelet domain. Experimental results with real NMR spectra showed that classification models constructed with the complex wavelet coefficients selected by the FDR-based procedure yield lower rates of misclassification than models constructed with original features and conventional wavelet coefficients.",
keywords = "Classification tree, Complex wavelet transforms, False discovery rates, Gabor coefficients, High-resolution NMR spectra, Metabolomics",
author = "Kim, {Seoung Bum} and Zhou Wang and Soontorn Oraintara and Chivalai Temiyasathit and Yodchanan Wongsawat",
year = "2008",
month = "2",
day = "15",
doi = "10.1016/j.chemolab.2007.09.005",
language = "English",
volume = "90",
pages = "161--168",
journal = "Chemometrics and Intelligent Laboratory Systems",
issn = "0169-7439",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Feature selection and classification of high-resolution NMR spectra in the complex wavelet transform domain

AU - Kim, Seoung Bum

AU - Wang, Zhou

AU - Oraintara, Soontorn

AU - Temiyasathit, Chivalai

AU - Wongsawat, Yodchanan

PY - 2008/2/15

Y1 - 2008/2/15

N2 - Successful identification of the important metabolite features in high-resolution nuclear magnetic resonance (NMR) spectra is a crucial task for the discovery of biomarkers that have the potential for early diagnosis of disease and subsequent monitoring of its progression. Although a number of traditional features extraction/selection methods are available, most of them have been conducted in the original frequency domain and disregarded the fact that an NMR spectrum comprises a number of local bumps and peaks with different scales. In the present study a complex wavelet transform that can handle multiscale information efficiently and has an energy shift-insensitive property is proposed as a method to improve feature extraction and classification in NMR spectra. Furthermore, a multiple testing procedure based on a false discovery rate (FDR) was used to identify important metabolite features in the complex wavelet domain. Experimental results with real NMR spectra showed that classification models constructed with the complex wavelet coefficients selected by the FDR-based procedure yield lower rates of misclassification than models constructed with original features and conventional wavelet coefficients.

AB - Successful identification of the important metabolite features in high-resolution nuclear magnetic resonance (NMR) spectra is a crucial task for the discovery of biomarkers that have the potential for early diagnosis of disease and subsequent monitoring of its progression. Although a number of traditional features extraction/selection methods are available, most of them have been conducted in the original frequency domain and disregarded the fact that an NMR spectrum comprises a number of local bumps and peaks with different scales. In the present study a complex wavelet transform that can handle multiscale information efficiently and has an energy shift-insensitive property is proposed as a method to improve feature extraction and classification in NMR spectra. Furthermore, a multiple testing procedure based on a false discovery rate (FDR) was used to identify important metabolite features in the complex wavelet domain. Experimental results with real NMR spectra showed that classification models constructed with the complex wavelet coefficients selected by the FDR-based procedure yield lower rates of misclassification than models constructed with original features and conventional wavelet coefficients.

KW - Classification tree

KW - Complex wavelet transforms

KW - False discovery rates

KW - Gabor coefficients

KW - High-resolution NMR spectra

KW - Metabolomics

UR - http://www.scopus.com/inward/record.url?scp=38349178369&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38349178369&partnerID=8YFLogxK

U2 - 10.1016/j.chemolab.2007.09.005

DO - 10.1016/j.chemolab.2007.09.005

M3 - Article

AN - SCOPUS:38349178369

VL - 90

SP - 161

EP - 168

JO - Chemometrics and Intelligent Laboratory Systems

JF - Chemometrics and Intelligent Laboratory Systems

SN - 0169-7439

IS - 2

ER -