Improved classification accuracy in 1- and 2-dimensional NMR metabolomics data using the variance stabilising generalised logarithm transformation

Classifying nuclear magnetic resonance (NMR) spectra is a crucial step in many metabolomics experiments. Since several multivariate classification techniques depend upon the variance of the data, it is important to first minimise any contribution from unwanted technical variance arising from sample...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:BMC bioinformatics Jg. 8; H. 1; S. 234
Hauptverfasser: Parsons, Helen M, Ludwig, Christian, Günther, Ulrich L, Viant, Mark R
Format: Journal Article
Sprache:Englisch
Veröffentlicht: England BioMed Central Ltd 02.07.2007
BioMed Central
BMC
Schlagworte:
ISSN:1471-2105, 1471-2105
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Classifying nuclear magnetic resonance (NMR) spectra is a crucial step in many metabolomics experiments. Since several multivariate classification techniques depend upon the variance of the data, it is important to first minimise any contribution from unwanted technical variance arising from sample preparation and analytical measurements, and thereby maximise any contribution from wanted biological variance between different classes. The generalised logarithm (glog) transform was developed to stabilise the variance in DNA microarray datasets, but has rarely been applied to metabolomics data. In particular, it has not been rigorously evaluated against other scaling techniques used in metabolomics, nor tested on all forms of NMR spectra including 1-dimensional (1D) 1H, projections of 2D 1H, 1H J-resolved (pJRES), and intact 2D J-resolved (JRES). Here, the effects of the glog transform are compared against two commonly used variance stabilising techniques, autoscaling and Pareto scaling, as well as unscaled data. The four methods are evaluated in terms of the effects on the variance of NMR metabolomics data and on the classification accuracy following multivariate analysis, the latter achieved using principal component analysis followed by linear discriminant analysis. For two of three datasets analysed, classification accuracies were highest following glog transformation: 100% accuracy for discriminating 1D NMR spectra of hypoxic and normoxic invertebrate muscle, and 100% accuracy for discriminating 2D JRES spectra of fish livers sampled from two rivers. For the third dataset, pJRES spectra of urine from two breeds of dog, the glog transform and autoscaling achieved equal highest accuracies. Additionally we extended the glog algorithm to effectively suppress noise, which proved critical for the analysis of 2D JRES spectra. We have demonstrated that the glog and extended glog transforms stabilise the technical variance in NMR metabolomics datasets. This significantly improves the discrimination between sample classes and has resulted in higher classification accuracies compared to unscaled, autoscaled or Pareto scaled data. Additionally we have confirmed the broad applicability of the glog approach using three disparate datasets from different biological samples using 1D NMR spectra, 1D projections of 2D JRES spectra, and intact 2D JRES spectra.
AbstractList Classifying nuclear magnetic resonance (NMR) spectra is a crucial step in many metabolomics experiments. Since several multivariate classification techniques depend upon the variance of the data, it is important to first minimise any contribution from unwanted technical variance arising from sample preparation and analytical measurements, and thereby maximise any contribution from wanted biological variance between different classes. The generalised logarithm (glog) transform was developed to stabilise the variance in DNA microarray datasets, but has rarely been applied to metabolomics data. In particular, it has not been rigorously evaluated against other scaling techniques used in metabolomics, nor tested on all forms of NMR spectra including 1-dimensional (1D) 1H, projections of 2D 1H, 1H J-resolved (pJRES), and intact 2D J-resolved (JRES). Here, the effects of the glog transform are compared against two commonly used variance stabilising techniques, autoscaling and Pareto scaling, as well as unscaled data. The four methods are evaluated in terms of the effects on the variance of NMR metabolomics data and on the classification accuracy following multivariate analysis, the latter achieved using principal component analysis followed by linear discriminant analysis. For two of three datasets analysed, classification accuracies were highest following glog transformation: 100% accuracy for discriminating 1D NMR spectra of hypoxic and normoxic invertebrate muscle, and 100% accuracy for discriminating 2D JRES spectra of fish livers sampled from two rivers. For the third dataset, pJRES spectra of urine from two breeds of dog, the glog transform and autoscaling achieved equal highest accuracies. Additionally we extended the glog algorithm to effectively suppress noise, which proved critical for the analysis of 2D JRES spectra. We have demonstrated that the glog and extended glog transforms stabilise the technical variance in NMR metabolomics datasets. This significantly improves the discrimination between sample classes and has resulted in higher classification accuracies compared to unscaled, autoscaled or Pareto scaled data. Additionally we have confirmed the broad applicability of the glog approach using three disparate datasets from different biological samples using 1D NMR spectra, 1D projections of 2D JRES spectra, and intact 2D JRES spectra.
Abstract Background Classifying nuclear magnetic resonance (NMR) spectra is a crucial step in many metabolomics experiments. Since several multivariate classification techniques depend upon the variance of the data, it is important to first minimise any contribution from unwanted technical variance arising from sample preparation and analytical measurements, and thereby maximise any contribution from wanted biological variance between different classes. The generalised logarithm (glog) transform was developed to stabilise the variance in DNA microarray datasets, but has rarely been applied to metabolomics data. In particular, it has not been rigorously evaluated against other scaling techniques used in metabolomics, nor tested on all forms of NMR spectra including 1-dimensional (1D) 1H, projections of 2D 1H, 1H J-resolved (pJRES), and intact 2D J-resolved (JRES). Results Here, the effects of the glog transform are compared against two commonly used variance stabilising techniques, autoscaling and Pareto scaling, as well as unscaled data. The four methods are evaluated in terms of the effects on the variance of NMR metabolomics data and on the classification accuracy following multivariate analysis, the latter achieved using principal component analysis followed by linear discriminant analysis. For two of three datasets analysed, classification accuracies were highest following glog transformation: 100% accuracy for discriminating 1D NMR spectra of hypoxic and normoxic invertebrate muscle, and 100% accuracy for discriminating 2D JRES spectra of fish livers sampled from two rivers. For the third dataset, pJRES spectra of urine from two breeds of dog, the glog transform and autoscaling achieved equal highest accuracies. Additionally we extended the glog algorithm to effectively suppress noise, which proved critical for the analysis of 2D JRES spectra. Conclusion We have demonstrated that the glog and extended glog transforms stabilise the technical variance in NMR metabolomics datasets. This significantly improves the discrimination between sample classes and has resulted in higher classification accuracies compared to unscaled, autoscaled or Pareto scaled data. Additionally we have confirmed the broad applicability of the glog approach using three disparate datasets from different biological samples using 1D NMR spectra, 1D projections of 2D JRES spectra, and intact 2D JRES spectra.
Background Classifying nuclear magnetic resonance (NMR) spectra is a crucial step in many metabolomics experiments. Since several multivariate classification techniques depend upon the variance of the data, it is important to first minimise any contribution from unwanted technical variance arising from sample preparation and analytical measurements, and thereby maximise any contribution from wanted biological variance between different classes. The generalised logarithm (glog) transform was developed to stabilise the variance in DNA microarray datasets, but has rarely been applied to metabolomics data. In particular, it has not been rigorously evaluated against other scaling techniques used in metabolomics, nor tested on all forms of NMR spectra including 1-dimensional (1D) super(1)H, projections of 2D super(1)H, super(1)H J-resolved (pJRES), and intact 2D J-resolved (JRES). Results Here, the effects of the glog transform are compared against two commonly used variance stabilising techniques, autoscaling and Pareto scaling, as well as unscaled data. The four methods are evaluated in terms of the effects on the variance of NMR metabolomics data and on the classification accuracy following multivariate analysis, the latter achieved using principal component analysis followed by linear discriminant analysis. For two of three datasets analysed, classification accuracies were highest following glog transformation: 100% accuracy for discriminating 1D NMR spectra of hypoxic and normoxic invertebrate muscle, and 100% accuracy for discriminating 2D JRES spectra of fish livers sampled from two rivers. For the third dataset, pJRES spectra of urine from two breeds of dog, the glog transform and autoscaling achieved equal highest accuracies. Additionally we extended the glog algorithm to effectively suppress noise, which proved critical for the analysis of 2D JRES spectra. Conclusion We have demonstrated that the glog and extended glog transforms stabilise the technical variance in NMR metabolomics datasets. This significantly improves the discrimination between sample classes and has resulted in higher classification accuracies compared to unscaled, autoscaled or Pareto scaled data. Additionally we have confirmed the broad applicability of the glog approach using three disparate datasets from different biological samples using 1D NMR spectra, 1D projections of 2D JRES spectra, and intact 2D JRES spectra.
Classifying nuclear magnetic resonance (NMR) spectra is a crucial step in many metabolomics experiments. Since several multivariate classification techniques depend upon the variance of the data, it is important to first minimise any contribution from unwanted technical variance arising from sample preparation and analytical measurements, and thereby maximise any contribution from wanted biological variance between different classes. The generalised logarithm (glog) transform was developed to stabilise the variance in DNA microarray datasets, but has rarely been applied to metabolomics data. In particular, it has not been rigorously evaluated against other scaling techniques used in metabolomics, nor tested on all forms of NMR spectra including 1-dimensional (1D) 1H, projections of 2D 1H, 1H J-resolved (pJRES), and intact 2D J-resolved (JRES).BACKGROUNDClassifying nuclear magnetic resonance (NMR) spectra is a crucial step in many metabolomics experiments. Since several multivariate classification techniques depend upon the variance of the data, it is important to first minimise any contribution from unwanted technical variance arising from sample preparation and analytical measurements, and thereby maximise any contribution from wanted biological variance between different classes. The generalised logarithm (glog) transform was developed to stabilise the variance in DNA microarray datasets, but has rarely been applied to metabolomics data. In particular, it has not been rigorously evaluated against other scaling techniques used in metabolomics, nor tested on all forms of NMR spectra including 1-dimensional (1D) 1H, projections of 2D 1H, 1H J-resolved (pJRES), and intact 2D J-resolved (JRES).Here, the effects of the glog transform are compared against two commonly used variance stabilising techniques, autoscaling and Pareto scaling, as well as unscaled data. The four methods are evaluated in terms of the effects on the variance of NMR metabolomics data and on the classification accuracy following multivariate analysis, the latter achieved using principal component analysis followed by linear discriminant analysis. For two of three datasets analysed, classification accuracies were highest following glog transformation: 100% accuracy for discriminating 1D NMR spectra of hypoxic and normoxic invertebrate muscle, and 100% accuracy for discriminating 2D JRES spectra of fish livers sampled from two rivers. For the third dataset, pJRES spectra of urine from two breeds of dog, the glog transform and autoscaling achieved equal highest accuracies. Additionally we extended the glog algorithm to effectively suppress noise, which proved critical for the analysis of 2D JRES spectra.RESULTSHere, the effects of the glog transform are compared against two commonly used variance stabilising techniques, autoscaling and Pareto scaling, as well as unscaled data. The four methods are evaluated in terms of the effects on the variance of NMR metabolomics data and on the classification accuracy following multivariate analysis, the latter achieved using principal component analysis followed by linear discriminant analysis. For two of three datasets analysed, classification accuracies were highest following glog transformation: 100% accuracy for discriminating 1D NMR spectra of hypoxic and normoxic invertebrate muscle, and 100% accuracy for discriminating 2D JRES spectra of fish livers sampled from two rivers. For the third dataset, pJRES spectra of urine from two breeds of dog, the glog transform and autoscaling achieved equal highest accuracies. Additionally we extended the glog algorithm to effectively suppress noise, which proved critical for the analysis of 2D JRES spectra.We have demonstrated that the glog and extended glog transforms stabilise the technical variance in NMR metabolomics datasets. This significantly improves the discrimination between sample classes and has resulted in higher classification accuracies compared to unscaled, autoscaled or Pareto scaled data. Additionally we have confirmed the broad applicability of the glog approach using three disparate datasets from different biological samples using 1D NMR spectra, 1D projections of 2D JRES spectra, and intact 2D JRES spectra.CONCLUSIONWe have demonstrated that the glog and extended glog transforms stabilise the technical variance in NMR metabolomics datasets. This significantly improves the discrimination between sample classes and has resulted in higher classification accuracies compared to unscaled, autoscaled or Pareto scaled data. Additionally we have confirmed the broad applicability of the glog approach using three disparate datasets from different biological samples using 1D NMR spectra, 1D projections of 2D JRES spectra, and intact 2D JRES spectra.
ArticleNumber 234
Audience Academic
Author Ludwig, Christian
Viant, Mark R
Parsons, Helen M
Günther, Ulrich L
AuthorAffiliation 3 School of Biosciences, The University of Birmingham, Edgbaston, Birmingham, B15 2TT, UK
1 Centre for Systems Biology, The University of Birmingham, Edgbaston, Birmingham, B15 2TT, UK
2 The Henry Wellcome Building for Biomolecular NMR Spectroscopy, The University of Birmingham, Edgbaston, Birmingham, B15 2TT, UK
AuthorAffiliation_xml – name: 2 The Henry Wellcome Building for Biomolecular NMR Spectroscopy, The University of Birmingham, Edgbaston, Birmingham, B15 2TT, UK
– name: 3 School of Biosciences, The University of Birmingham, Edgbaston, Birmingham, B15 2TT, UK
– name: 1 Centre for Systems Biology, The University of Birmingham, Edgbaston, Birmingham, B15 2TT, UK
Author_xml – sequence: 1
  givenname: Helen M
  surname: Parsons
  fullname: Parsons, Helen M
– sequence: 2
  givenname: Christian
  surname: Ludwig
  fullname: Ludwig, Christian
– sequence: 3
  givenname: Ulrich L
  surname: Günther
  fullname: Günther, Ulrich L
– sequence: 4
  givenname: Mark R
  surname: Viant
  fullname: Viant, Mark R
BackLink https://www.ncbi.nlm.nih.gov/pubmed/17605789$$D View this record in MEDLINE/PubMed
BookMark eNqFkktv1DAUhSNURB-wZocsISGxSBvHceJskKqKx0gFpAJr69q-zrhK7MHOVPRv8IvxzJSqg0AoCyf3fufc2D7HxYEPHoviOa1OKRXtGW06Wta04qUoa9Y8Ko7uKwcP3g-L45Suq4p2ouJPikPatRXvRH9U_FxMqxhu0BA9QkrOOg2zC56A1usI-pY4T2hJwBtSl8ZN6FNuw0g-fbwiE86gwhgmpxMxMANZJ-cHMi-R3EB04DWSlBk3um1jQI8R8kceOIYhI_NyInMEn2yI03b00-KxhTHhs7v1pPj27u3Xiw_l5ef3i4vzy1Jz0c9loxRnjFvWNo2ymqG1VlNuOgXaKuzqHrDnVtvO1Ng2Bpq6VqJra1txYymyk2Kx8zUBruUqugnirQzg5LYQ4iAhzk6PKFnftdBYhkyoRvUtKNUjhVaZjlmjdPZ6s_NardWERqPPexr3TPc73i3lEG4k7VveCJENXt0ZxPB9jWmWk0saxxE8hnWSrahZX1X8v2BdsaZpaZ_BlztwgLwD523Ig_UGlue0FYwLtp17-hcqPwbzpeawWZfre4LXe4LMzPhjHmCdklx8udpnXzw8lfvj-B2_DPAdoGNIKaKV2s3bEOS_cKOkldzEXG6CLDdBlkLmmGfd2R-6e-t_KH4B5FUBRg
CitedBy_id crossref_primary_10_1016_j_fsi_2013_09_037
crossref_primary_10_1002_clen_201000515
crossref_primary_10_1007_s11306_011_0350_z
crossref_primary_10_3389_fmolb_2021_669082
crossref_primary_10_1007_s11105_011_0368_4
crossref_primary_10_1016_j_clnu_2020_10_051
crossref_primary_10_1371_journal_pone_0004251
crossref_primary_10_1086_689590
crossref_primary_10_1214_20_BA1208
crossref_primary_10_1016_j_ecoenv_2018_03_040
crossref_primary_10_1039_C6AY03102A
crossref_primary_10_1002_etc_446
crossref_primary_10_1155_2016_9162074
crossref_primary_10_1016_j_jprot_2013_09_001
crossref_primary_10_1111_raq_12146
crossref_primary_10_1002_nbm_1345
crossref_primary_10_1007_s10646_010_0569_x
crossref_primary_10_1016_j_chemolab_2020_104169
crossref_primary_10_1289_ehp_0900985
crossref_primary_10_1002_mrc_2501
crossref_primary_10_1007_s00344_011_9244_6
crossref_primary_10_1038_srep40275
crossref_primary_10_1093_icb_ict015
crossref_primary_10_1371_journal_pone_0056422
crossref_primary_10_1016_j_etap_2011_05_006
crossref_primary_10_1371_journal_pone_0026155
crossref_primary_10_1016_j_chemolab_2011_05_006
crossref_primary_10_1088_1755_1315_252_3_032166
crossref_primary_10_3390_md9091566
crossref_primary_10_1021_es9008689
crossref_primary_10_1016_j_fsi_2017_02_042
crossref_primary_10_3390_md11114158
crossref_primary_10_1016_j_jfoodeng_2019_109684
crossref_primary_10_1016_j_foodres_2025_116327
crossref_primary_10_1016_j_physa_2013_12_054
crossref_primary_10_1016_j_chemosphere_2015_08_029
crossref_primary_10_1515_biol_2022_0556
crossref_primary_10_1016_j_aquatox_2010_08_005
crossref_primary_10_3390_ijms24021591
crossref_primary_10_1111_are_13178
crossref_primary_10_1016_j_chroma_2011_01_024
crossref_primary_10_3390_metabo10110470
crossref_primary_10_1007_s11306_018_1321_4
crossref_primary_10_1016_j_etap_2013_11_016
crossref_primary_10_3390_molecules25173972
crossref_primary_10_3390_metabo15010048
crossref_primary_10_1016_j_etap_2014_02_015
crossref_primary_10_1016_j_ab_2017_02_006
crossref_primary_10_1038_s41598_017_03108_x
crossref_primary_10_1002_tox_22057
crossref_primary_10_1007_s00343_013_2124_0
crossref_primary_10_1016_j_aca_2017_09_019
crossref_primary_10_1111_anu_12420
crossref_primary_10_1016_j_aquatox_2009_07_005
crossref_primary_10_1002_cem_2880
crossref_primary_10_1007_s11306_011_0347_7
crossref_primary_10_1038_ncomms1562
crossref_primary_10_1371_journal_pone_0165884
crossref_primary_10_1186_1741_7007_6_25
crossref_primary_10_1007_s10886_016_0771_2
crossref_primary_10_1371_journal_pone_0164394
crossref_primary_10_1016_j_aquatox_2016_03_012
crossref_primary_10_1002_pca_1186
crossref_primary_10_1038_s41597_020_0545_0
crossref_primary_10_3390_app12062824
crossref_primary_10_1016_j_fsi_2013_05_009
crossref_primary_10_4155_fmc_09_54
crossref_primary_10_1007_s00344_012_9305_5
crossref_primary_10_1039_B808986H
crossref_primary_10_1016_j_fsi_2014_05_033
crossref_primary_10_1093_gigascience_giae005
crossref_primary_10_1007_s11306_020_01686_y
crossref_primary_10_1016_j_etap_2010_12_003
crossref_primary_10_1016_j_pocean_2015_04_022
crossref_primary_10_1038_s41597_022_01264_y
crossref_primary_10_1111_acel_13149
crossref_primary_10_1007_s11306_012_0415_7
crossref_primary_10_1038_srep25125
crossref_primary_10_1038_nprot_2016_156
crossref_primary_10_1016_j_neo_2016_11_003
crossref_primary_10_1016_j_toxlet_2015_10_031
crossref_primary_10_1016_j_fsi_2016_11_051
crossref_primary_10_1016_j_hal_2017_12_002
crossref_primary_10_1016_j_aquaculture_2014_10_023
crossref_primary_10_1371_journal_pone_0235415
crossref_primary_10_1002_clen_201100208
crossref_primary_10_1007_s11306_016_1030_9
crossref_primary_10_1016_j_etap_2014_04_007
crossref_primary_10_1002_nbm_1428
crossref_primary_10_1016_j_aquatox_2017_09_010
crossref_primary_10_3390_metabo7010008
crossref_primary_10_1093_toxsci_kfq247
crossref_primary_10_1007_s11356_014_3859_7
crossref_primary_10_1007_s00300_013_1375_8
crossref_primary_10_1002_mrc_5373
crossref_primary_10_3390_metabo12010029
crossref_primary_10_1016_j_jprot_2013_08_004
crossref_primary_10_1016_j_trac_2007_12_001
crossref_primary_10_1007_s11306_011_0366_4
crossref_primary_10_1016_j_ecoenv_2012_03_016
crossref_primary_10_1016_j_lwt_2025_118507
crossref_primary_10_1007_s11306_008_0133_3
crossref_primary_10_1002_art_38021
crossref_primary_10_1016_j_chemosphere_2015_01_055
crossref_primary_10_1016_j_ecoenv_2012_02_022
crossref_primary_10_1007_s11306_008_0152_0
crossref_primary_10_3390_cancers13133140
crossref_primary_10_1007_s00216_013_6856_7
crossref_primary_10_1016_j_cbpc_2021_109022
crossref_primary_10_1007_s11306_011_0355_7
crossref_primary_10_1016_j_ab_2007_10_002
crossref_primary_10_3390_metabo12080679
crossref_primary_10_1002_clen_201000410
crossref_primary_10_1186_1471_2105_12_413
crossref_primary_10_1016_j_fsi_2013_09_014
crossref_primary_10_1158_0008_5472_CAN_15_0202
crossref_primary_10_1371_journal_pone_0187545
crossref_primary_10_1007_s10646_012_0992_2
crossref_primary_10_1007_s00343_013_2037_y
crossref_primary_10_1007_s11306_010_0221_z
crossref_primary_10_3389_fimmu_2021_725641
crossref_primary_10_1007_s10646_011_0699_9
crossref_primary_10_1007_s10646_017_1777_4
crossref_primary_10_1186_1471_2105_9_280
crossref_primary_10_1593_neo_81396
crossref_primary_10_1007_s11306_014_0693_3
crossref_primary_10_1007_s11306_009_0194_y
crossref_primary_10_1093_treephys_tpz049
crossref_primary_10_3389_fpubh_2020_00176
crossref_primary_10_1016_j_csda_2017_06_001
crossref_primary_10_1089_omi_2009_0139
crossref_primary_10_1016_j_jprot_2014_08_010
crossref_primary_10_1016_j_marenvres_2011_04_002
crossref_primary_10_1186_1471_2105_12_366
crossref_primary_10_1016_j_ecoenv_2015_05_005
crossref_primary_10_1128_JVI_00187_16
crossref_primary_10_1021_es1037222
crossref_primary_10_1016_j_chemosphere_2017_08_083
crossref_primary_10_1093_bib_bbv077
crossref_primary_10_1038_sdata_2014_12
crossref_primary_10_1002_mrc_2535
crossref_primary_10_3390_metabo13070879
crossref_primary_10_1007_s11306_007_0092_0
Cites_doi 10.1021/es062745w
10.1093/bioinformatics/btg178
10.1016/j.bbrc.2003.09.092
10.1038/ng1031
10.1016/j.tibtech.2004.03.007
10.1016/S0003-2670(03)00094-1
10.1093/bioinformatics/btg245
10.1093/bioinformatics/18.suppl_1.S105
10.1186/1471-2164-7-142
10.1007/s10886-006-9152-6
10.1007/s11306-005-4429-2
10.1006/jmre.2000.2121
10.1089/1536231041388348
10.1017/CBO9780511812651
10.1016/j.phytochem.2006.08.018
10.1021/ac0156870
10.1016/j.ab.2003.07.026
10.1016/S0003-2670(03)00060-6
10.1016/S0079-6565(00)00036-4
10.1093/bioinformatics/btg107
10.1074/jbc.M410200200
10.1016/0308-8146(95)00220-0
10.1007/s11306-006-0043-1
ContentType Journal Article
Copyright COPYRIGHT 2007 BioMed Central Ltd.
Copyright © 2007 Parsons et al; licensee BioMed Central Ltd. 2007 Parsons et al; licensee BioMed Central Ltd.
Copyright_xml – notice: COPYRIGHT 2007 BioMed Central Ltd.
– notice: Copyright © 2007 Parsons et al; licensee BioMed Central Ltd. 2007 Parsons et al; licensee BioMed Central Ltd.
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
ISR
7QO
8FD
FR3
P64
7X8
5PM
DOA
DOI 10.1186/1471-2105-8-234
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Science (Gale In Context)
Biotechnology Research Abstracts
Technology Research Database
Engineering Research Database
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ: Directory of Open Access Journal (DOAJ)
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Engineering Research Database
Biotechnology Research Abstracts
Technology Research Database
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitleList MEDLINE

Engineering Research Database
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ: Directory of Open Access Journal (DOAJ)
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 1471-2105
EndPage 234
ExternalDocumentID oai_doaj_org_article_3976a4f3e38b4b96abb9e1a6bd73fdbc
PMC1965488
A168358388
17605789
10_1186_1471_2105_8_234
Genre Comparative Study
Research Support, Non-U.S. Gov't
Evaluation Study
Journal Article
GeographicLocations United Kingdom
GeographicLocations_xml – name: United Kingdom
GroupedDBID ---
0R~
123
23N
2VQ
2WC
4.4
53G
5VS
6J9
AAFWJ
AAJSJ
AAKPC
AASML
AAYXX
ABDBF
ACGFO
ACGFS
ACIHN
ACIWK
ACPRK
ACUHS
ADBBV
ADMLS
ADRAZ
ADUKV
AEAQA
AENEX
AFPKN
AFRAH
AHBYD
AHMBA
AHSBF
AHYZX
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMTXH
AOIJS
BAPOH
BAWUL
BCNDV
BENPR
BFQNJ
BMC
C1A
C6C
CITATION
CS3
DIK
DU5
E3Z
EAD
EAP
EAS
EBD
EBLON
EBS
EJD
EMB
EMK
EMOBN
ESX
F5P
GROUPED_DOAJ
GX1
H13
HYE
IAO
ICD
IHR
INH
INR
IPNFZ
ISR
ITC
KQ8
M48
MK~
ML0
M~E
O5R
O5S
OK1
OVT
P2P
PGMZT
PIMPY
PQQKQ
RBZ
RIG
RNS
ROL
RPM
RSV
SBL
SOJ
SV3
TR2
TUS
W2D
WOQ
WOW
XH6
XSB
ALIPV
CGR
CUY
CVF
ECM
EIF
NPM
7QO
8FD
FR3
P64
7X8
5PM
ID FETCH-LOGICAL-c589t-4bb5335f3644bfc3efffc15d7bacfbe729ae95fcf7d2e64da422b8762f05df1e3
IEDL.DBID DOA
ISICitedReferencesCount 184
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000249273600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1471-2105
IngestDate Fri Oct 03 12:53:15 EDT 2025
Thu Aug 21 18:43:01 EDT 2025
Thu Sep 04 16:24:54 EDT 2025
Tue Oct 07 09:25:49 EDT 2025
Mon Oct 20 23:18:27 EDT 2025
Mon Oct 20 17:17:52 EDT 2025
Thu Oct 16 16:11:53 EDT 2025
Thu Apr 03 06:56:55 EDT 2025
Sat Nov 29 02:18:00 EST 2025
Tue Nov 18 21:54:40 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License This is an Open Access article distributed under the terms of the Creative Commons Attribution License (), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c589t-4bb5335f3644bfc3efffc15d7bacfbe729ae95fcf7d2e64da422b8762f05df1e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ObjectType-Article-2
ObjectType-Feature-1
ObjectType-Undefined-3
OpenAccessLink https://doaj.org/article/3976a4f3e38b4b96abb9e1a6bd73fdbc
PMID 17605789
PQID 20344619
PQPubID 23462
ParticipantIDs doaj_primary_oai_doaj_org_article_3976a4f3e38b4b96abb9e1a6bd73fdbc
pubmedcentral_primary_oai_pubmedcentral_nih_gov_1965488
proquest_miscellaneous_68239005
proquest_miscellaneous_20344619
gale_infotracmisc_A168358388
gale_infotracacademiconefile_A168358388
gale_incontextgauss_ISR_A168358388
pubmed_primary_17605789
crossref_citationtrail_10_1186_1471_2105_8_234
crossref_primary_10_1186_1471_2105_8_234
PublicationCentury 2000
PublicationDate 2007-07-02
PublicationDateYYYYMMDD 2007-07-02
PublicationDate_xml – month: 07
  year: 2007
  text: 2007-07-02
  day: 02
PublicationDecade 2000
PublicationPlace England
PublicationPlace_xml – name: England
– name: London
PublicationTitle BMC bioinformatics
PublicationTitleAlternate BMC Bioinformatics
PublicationYear 2007
Publisher BioMed Central Ltd
BioMed Central
BMC
Publisher_xml – name: BioMed Central Ltd
– name: BioMed Central
– name: BMC
References 1606_CR22
HT Widarto (1606_CR18) 2006; 32
L Eriksson (1606_CR3) 2001
MR Viant (1606_CR15) 2003; 310
GA Churchill (1606_CR8) 2002; 32
1606_CR27
CY Lin (1606_CR23) 2007; 3
JC Lindon (1606_CR5) 2001; 39
ME Dumas (1606_CR17) 2002; 74
Y Wang (1606_CR20) 2003; 323
SC Geller (1606_CR13) 2003; 19
BP Durbin (1606_CR14) 2002; 18
HC Keun (1606_CR10) 2003; 490
GLAH Jones (1606_CR6) 2004; 280
A Hines (1606_CR24) 2007; 41
S Golotvin (1606_CR26) 2000; 146
PV Purohit (1606_CR11) 2004; 8
MR Viant (1606_CR21) 2005; 1
A Craig (1606_CR9) 2006; 78
O Beckonert (1606_CR4) 2003; 490
B Durbin (1606_CR25) 2003; 19
DM Rocke (1606_CR12) 2003; 19
BD Ripley (1606_CR7) 1996
R Goodacre (1606_CR1) 2004; 22
YS Liang (1606_CR19) 2006; 67
HH van den Berg Robert (1606_CR2) 2006; 7
L Forveille (1606_CR16) 1996; 57
References_xml – volume: 78
  start-page: 2262
  issue: 7
  year: 2006
  ident: 1606_CR9
  publication-title: Analytical chemistry(Washington, DC)
– volume: 41
  start-page: 3375
  year: 2007
  ident: 1606_CR24
  publication-title: Environmental Science & Technology
  doi: 10.1021/es062745w
– volume: 19
  start-page: 1360
  year: 2003
  ident: 1606_CR25
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btg178
– volume: 310
  start-page: 943
  year: 2003
  ident: 1606_CR15
  publication-title: Biochemical and Biophysical Research Communications
  doi: 10.1016/j.bbrc.2003.09.092
– volume-title: Multi-and megavariate data analysis: principles and applications
  year: 2001
  ident: 1606_CR3
– volume: 32
  start-page: 490
  year: 2002
  ident: 1606_CR8
  publication-title: Nature Genetics
  doi: 10.1038/ng1031
– volume: 22
  start-page: 245
  year: 2004
  ident: 1606_CR1
  publication-title: Trends Biotechnol
  doi: 10.1016/j.tibtech.2004.03.007
– volume: 490
  start-page: 265
  year: 2003
  ident: 1606_CR10
  publication-title: Analytica Chimica Acta
  doi: 10.1016/S0003-2670(03)00094-1
– volume: 19
  start-page: 1817
  year: 2003
  ident: 1606_CR13
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btg245
– volume: 18
  start-page: S105
  year: 2002
  ident: 1606_CR14
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/18.suppl_1.S105
– volume: 7
  start-page: 142
  year: 2006
  ident: 1606_CR2
  publication-title: BMC Genomics
  doi: 10.1186/1471-2164-7-142
– ident: 1606_CR22
– volume: 32
  start-page: 2417
  year: 2006
  ident: 1606_CR18
  publication-title: Journal of Chemical Ecology
  doi: 10.1007/s10886-006-9152-6
– volume: 1
  start-page: 149
  year: 2005
  ident: 1606_CR21
  publication-title: Metabolomics
  doi: 10.1007/s11306-005-4429-2
– volume: 146
  start-page: 122
  year: 2000
  ident: 1606_CR26
  publication-title: J Magn Reson
  doi: 10.1006/jmre.2000.2121
– volume: 8
  start-page: 118
  year: 2004
  ident: 1606_CR11
  publication-title: OMICS
  doi: 10.1089/1536231041388348
– volume-title: Pattern Recognition and Neural Networks
  year: 1996
  ident: 1606_CR7
  doi: 10.1017/CBO9780511812651
– volume: 67
  start-page: 2503
  year: 2006
  ident: 1606_CR19
  publication-title: Phytochemistry
  doi: 10.1016/j.phytochem.2006.08.018
– volume: 74
  start-page: 2261
  year: 2002
  ident: 1606_CR17
  publication-title: Anal Chem
  doi: 10.1021/ac0156870
– volume: 323
  start-page: 26
  year: 2003
  ident: 1606_CR20
  publication-title: Anal Biochem
  doi: 10.1016/j.ab.2003.07.026
– volume: 490
  start-page: 3
  year: 2003
  ident: 1606_CR4
  publication-title: Anal Chim Acta
  doi: 10.1016/S0003-2670(03)00060-6
– volume: 39
  start-page: 1
  year: 2001
  ident: 1606_CR5
  publication-title: Progress in Nuclear Magnetic Resonance Spectroscopy
  doi: 10.1016/S0079-6565(00)00036-4
– volume: 19
  start-page: 966
  year: 2003
  ident: 1606_CR12
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btg107
– volume: 280
  start-page: 7530
  year: 2004
  ident: 1606_CR6
  publication-title: Journal of Biological Chemistry
  doi: 10.1074/jbc.M410200200
– volume: 57
  start-page: 441
  year: 1996
  ident: 1606_CR16
  publication-title: Food Chemistry
  doi: 10.1016/0308-8146(95)00220-0
– ident: 1606_CR27
– volume: 3
  start-page: 55
  year: 2007
  ident: 1606_CR23
  publication-title: Metabolomics
  doi: 10.1007/s11306-006-0043-1
SSID ssj0017805
Score 2.3378637
Snippet Classifying nuclear magnetic resonance (NMR) spectra is a crucial step in many metabolomics experiments. Since several multivariate classification techniques...
Background Classifying nuclear magnetic resonance (NMR) spectra is a crucial step in many metabolomics experiments. Since several multivariate classification...
Abstract Background Classifying nuclear magnetic resonance (NMR) spectra is a crucial step in many metabolomics experiments. Since several multivariate...
SourceID doaj
pubmedcentral
proquest
gale
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 234
SubjectTerms Algorithms
Analysis of Variance
Data Interpretation, Statistical
Gene Expression Profiling - methods
Health aspects
Magnetic Resonance Spectroscopy - methods
Metabolomics
Multivariate analysis
Nuclear magnetic resonance
Proteome - metabolism
Sensitivity and Specificity
Title Improved classification accuracy in 1- and 2-dimensional NMR metabolomics data using the variance stabilising generalised logarithm transformation
URI https://www.ncbi.nlm.nih.gov/pubmed/17605789
https://www.proquest.com/docview/20344619
https://www.proquest.com/docview/68239005
https://pubmed.ncbi.nlm.nih.gov/PMC1965488
https://doaj.org/article/3976a4f3e38b4b96abb9e1a6bd73fdbc
Volume 8
WOSCitedRecordID wos000249273600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVADU
  databaseName: BioMed Central Open Access Free
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: RBZ
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://www.biomedcentral.com/search/
  providerName: BioMedCentral
– providerCode: PRVAON
  databaseName: DOAJ: Directory of Open Access Journal (DOAJ)
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: DOA
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center)
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: M~E
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 1471-2105
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017805
  issn: 1471-2105
  databaseCode: RSV
  dateStart: 20001201
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagAokL4t3QUiyEBBfTPBzbORbUCg5doQLS3iw_tyu1WbTJVuqFH9FfzEySXTZCFRcue4gnu9bMF_ub7PgbQt4Kl_vKRce8sCnjsvTMchFY4KaSPhcuWts1m5CTiZpOq69brb6wJqyXB-4dd4j7peGxCIWy3FbCWFuFzAjrZRG9dbj6AutZJ1PD_weo1N-dK5IZg6SmHER9MiUON9cYQKTgo_2ok-3_e3He2p3GlZNbW9HJI_Jw4JD0qJ_7Y3In1E_I_b6r5PVTctO_KAieOqTGWAvUuZ8a51ZL467pvKYZo6b2NGce5f17aQ46OT2jl6EFXFzgYeWGYv0oxdL4GQWiSK8gsUaUUKCUWFTbDcx64ep5Az8IEwCT9vyStluEeFE_Iz9Ojr9_-syG1gvMlapqGbcWeGAZC6BLNroixBhdVnppDUQvACM3oSqjixDPILg3PM8tLqwxLX3MQvGc7NSLOuwSWphgjVdZFCl8VypNpXgojeSpy21V2oR8WAdAu0GXHNtjXOguP1FCY8Q0RkwrDRFLyPvNDT97SY7bTT9iRDdmqKXdXQCE6QFh-l8IS8gbxINGtYway3FmZtU0-su3M32UCWCwqlAqIe8Go7iA2TsznG4AH6DA1shyf2QJj7MbDb9ew07jENbA1WGxanSO6oyQ795uIVReVLCsJuRFD9M__pGQtkoF98oRgEeeGY_U8_NObRwlJ2GVf_k_XLlHHqzfjaf5Ptlpl6vwitxzV-28WR6Qu3KqDroHGT5Pfx3_BjlmUbs
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Improved+classification+accuracy+in+1-+and+2-dimensional+NMR+metabolomics+data+using+the+variance+stabilising+generalised+logarithm+transformation&rft.jtitle=BMC+bioinformatics&rft.au=Parsons%2C+Helen+M&rft.au=Ludwig%2C+Christian&rft.au=Gunther%2C+Ulrich+L&rft.au=Viant%2C+Mark+R&rft.date=2007-07-02&rft.pub=BioMed+Central+Ltd&rft.issn=1471-2105&rft.eissn=1471-2105&rft.volume=8&rft.spage=234&rft_id=info:doi/10.1186%2F1471-2105-8-234&rft.externalDBID=ISR&rft.externalDocID=A168358388
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1471-2105&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1471-2105&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1471-2105&client=summon