Sample classification based on Bayesian spectral decomposition of metabonomic NMR data sets

Radka Stoyanova, Jeremy K. Nicholson, John C. Lindon, Truman R. Brown

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

1H NMR spectra of biofluids provides a wealth of biochemical information on the metabolic status of an organism. Through the application of pattern recognition and classification algorithms, the data have been shown to provide information on disease diagnosis and the beneficial and adverse effects of potential therapeutics. Here, a novel approach is described for identifying subsets of spectral patterns in databases of NMR spectra, and it is shown that the intensities of these spectral patterns can be related to the onset and recovery from a toxic lesion in both a time-related and dose-related fashion. These patterns form a new type of combination biomarker for the biological effect under study. The approach is illustrated with a study of liver toxicity in rats using NMR spectra of urine following administration of a model hepatotoxin hydrazine.

Original languageEnglish
Pages (from-to)3666-3674
Number of pages9
JournalAnalytical Chemistry
Volume76
Issue number13
DOIs
StatePublished - Jul 1 2004
Externally publishedYes

Fingerprint

hydrazine
Nuclear magnetic resonance
Decomposition
Pattern recognition
Poisons
Biomarkers
Liver
Toxicity
Rats
Recovery
Metabolomics

ASJC Scopus subject areas

  • Analytical Chemistry

Cite this

Sample classification based on Bayesian spectral decomposition of metabonomic NMR data sets. / Stoyanova, Radka; Nicholson, Jeremy K.; Lindon, John C.; Brown, Truman R.

In: Analytical Chemistry, Vol. 76, No. 13, 01.07.2004, p. 3666-3674.

Research output: Contribution to journalArticle

Stoyanova, Radka ; Nicholson, Jeremy K. ; Lindon, John C. ; Brown, Truman R. / Sample classification based on Bayesian spectral decomposition of metabonomic NMR data sets. In: Analytical Chemistry. 2004 ; Vol. 76, No. 13. pp. 3666-3674.
@article{c60cc156015f41bd92ad30ae3b1a360a,
title = "Sample classification based on Bayesian spectral decomposition of metabonomic NMR data sets",
abstract = "1H NMR spectra of biofluids provides a wealth of biochemical information on the metabolic status of an organism. Through the application of pattern recognition and classification algorithms, the data have been shown to provide information on disease diagnosis and the beneficial and adverse effects of potential therapeutics. Here, a novel approach is described for identifying subsets of spectral patterns in databases of NMR spectra, and it is shown that the intensities of these spectral patterns can be related to the onset and recovery from a toxic lesion in both a time-related and dose-related fashion. These patterns form a new type of combination biomarker for the biological effect under study. The approach is illustrated with a study of liver toxicity in rats using NMR spectra of urine following administration of a model hepatotoxin hydrazine.",
author = "Radka Stoyanova and Nicholson, {Jeremy K.} and Lindon, {John C.} and Brown, {Truman R.}",
year = "2004",
month = "7",
day = "1",
doi = "10.1021/ac049849e",
language = "English",
volume = "76",
pages = "3666--3674",
journal = "Analytical Chemistry",
issn = "0003-2700",
publisher = "American Chemical Society",
number = "13",

}

TY - JOUR

T1 - Sample classification based on Bayesian spectral decomposition of metabonomic NMR data sets

AU - Stoyanova, Radka

AU - Nicholson, Jeremy K.

AU - Lindon, John C.

AU - Brown, Truman R.

PY - 2004/7/1

Y1 - 2004/7/1

N2 - 1H NMR spectra of biofluids provides a wealth of biochemical information on the metabolic status of an organism. Through the application of pattern recognition and classification algorithms, the data have been shown to provide information on disease diagnosis and the beneficial and adverse effects of potential therapeutics. Here, a novel approach is described for identifying subsets of spectral patterns in databases of NMR spectra, and it is shown that the intensities of these spectral patterns can be related to the onset and recovery from a toxic lesion in both a time-related and dose-related fashion. These patterns form a new type of combination biomarker for the biological effect under study. The approach is illustrated with a study of liver toxicity in rats using NMR spectra of urine following administration of a model hepatotoxin hydrazine.

AB - 1H NMR spectra of biofluids provides a wealth of biochemical information on the metabolic status of an organism. Through the application of pattern recognition and classification algorithms, the data have been shown to provide information on disease diagnosis and the beneficial and adverse effects of potential therapeutics. Here, a novel approach is described for identifying subsets of spectral patterns in databases of NMR spectra, and it is shown that the intensities of these spectral patterns can be related to the onset and recovery from a toxic lesion in both a time-related and dose-related fashion. These patterns form a new type of combination biomarker for the biological effect under study. The approach is illustrated with a study of liver toxicity in rats using NMR spectra of urine following administration of a model hepatotoxin hydrazine.

UR - http://www.scopus.com/inward/record.url?scp=3042785758&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3042785758&partnerID=8YFLogxK

U2 - 10.1021/ac049849e

DO - 10.1021/ac049849e

M3 - Article

C2 - 15228339

AN - SCOPUS:3042785758

VL - 76

SP - 3666

EP - 3674

JO - Analytical Chemistry

JF - Analytical Chemistry

SN - 0003-2700

IS - 13

ER -