, Volume 10, Issue 3, pp 375–385 | Cite as

Chemometrics models for overcoming high between subject variability: applications in clinical metabolic profiling studies

  • Yun XuEmail author
  • Stephen J. Fowler
  • Ardeshir Bayat
  • Royston Goodacre
Original Article


In human metabolic profiling studies, between-subject variability is often the dominant feature and can mask the potential classifications of clinical interest. Conventional models such as principal component analysis (PCA) are usually not effective in such situations and it is therefore highly desirable to find a suitable model which is able to discover the underlying pattern hidden behind the high between-subject variability. In this study we employed two clinical metabolomics data sets as the testing grounds, in which such variability had been observed, and we demonstrate that a proper choice of chemometrics model can help to overcome this issue of high between-subject variability. Two data sets were used to represent two different types of experiment designs. The first data set was obtained from a small-scale study investigating volatile organic compounds (VOCs) collected from chronic wounds using a skin patch device and analysed by thermal desorption-gas chromatography-mass spectrometry. Five patients were recruited and for each patient three sites sampled in triplicate: healthy skin, boundary of the lesion and top of the lesion, the aim was to discriminate these three types of samples based on their VOC profile. The second data set was from a much larger study involving 35 healthy subjects, 47 patients with chronic obstructive pulmonary disease and 33 with asthma. The VOCs in the breath of each subject were collected using a mask device and analysed again by GC–MS with the aim of discriminating the three types of subjects based on breath VOC profiles. Multilevel simultaneous component analysis, multilevel partial least squares for discriminant analysis, ANOVA-PCA, and a novel simplified ANOVA-PCA model—which we have named ANOVA-Mean Centre (ANOVA-MC)—were applied on these two data sets. Significantly improved results were obtained by using these models. We also present a novel validation procedure to verify statistically the results obtained from those models.


Metabolic profiling Between-subject variability Multilevel simultaneous component analysis Multilevel partial least squares for discriminant analysis ANOVA PCA ANOVA simultaneous component analysis ANOVA mean-centre Breath analysis 



We thank Dr. Maria Basanta and Dr. Baharudin Ibrahim for providing the breath VOCs data; Dr. Alexi Thomas, Dr. Svetlana Riazanskaia and Dr. William Cheung for providing the skin VOCs data.

Supplementary material

11306_2013_616_MOESM1_ESM.docx (37 kb)
Supplementary material 1 (DOCX 36 kb)


  1. Assfalg, Michael, Bertini, I., Colangiuli, D., Luchinat, C., Schäfer, H., Schütz, B., et al. (2008). Evidence of different metabolic phenotypes in humans. Proceedings of the National Academy of Sciences of the United States of America, 105, 1420–1424.CrossRefPubMedPubMedCentralGoogle Scholar
  2. Basanta, M., Ibrahim, B., Dockry, R., Tal-Singer, R., Douce, D., Woodcock, A., et al. (2012). Exhaled volatile organic compounds as potential biomarkers in chronic obstructive pulmonary disease. Respiration Research, 13, 72.CrossRefGoogle Scholar
  3. Biais, B., Allwood, J. W., Deborde, C., Xu, Y., Maucourt, M., Beauvoit, B., et al. (2009). 1H NMR, GC–EI-TOFMS, and data set correlation for fruit metabolomics: application to spatial metabolite analysis in melon. Analytical Chemistry, 81, 2884–2894.CrossRefPubMedGoogle Scholar
  4. Blatt, M., Wiseman, S., & Domany, E. (1996). Superparamagnetic clustering of data. Physical Review Letters, 76, 3251–3254.CrossRefPubMedGoogle Scholar
  5. Brereton, R. G. (2003). Chemometrics: Data analysis for the laboratory and chemical plant. Chichester: Wiley.CrossRefGoogle Scholar
  6. Cheung, W., Xu, Y., Thomas, C. L. P., & Goodacre, R. (2008). Discrimination of bacteria using pyrolysis-gas chromatography-differential mobility spectrometry (Py-GC-DMS) and chemometrics. Analyst, 134, 557–563.CrossRefPubMedGoogle Scholar
  7. de Noord, O. E., & Theobald, E. H. (2005). Multilevel component analysis and multilevel PLS of chemical process data. Journal of Chemometrics, 19, 301–307.CrossRefGoogle Scholar
  8. Efron, B., & Tibshirani, R. (1993). An introduction to the bootstrap. New York: Chapman & Hall.CrossRefGoogle Scholar
  9. Fens, N., Zwinderman, A. H., van der Schee, M. P. C., de Nijs, S. B., Dijkers, E., Roldaan, A. C., et al. (2009). Exhaled breath profiling enables discrimination of chronic obstructive pulmonary disease and asthma. American Journal of Respiratory and Critical Care Medicine, 180, 1076–1082.CrossRefPubMedGoogle Scholar
  10. Ferreira, D. L. S., Kittiwachana, S., Fido, L. A., Thompson, D. R., Escott, R. E. A., & Brereton, R. G. (2009). Multilevel simultaneous component analysis for fault detection in multicampaign process monitoring: Application to on-line high performance liquid chromatography of a continuous process. Analyst, 137, 1571–1585.CrossRefGoogle Scholar
  11. Harrington, P. B., Vieira, N. E., Espinoza, J., Nien, J. K., Romero, R., & Yergey, A. L. (2005). Analysis of variance-principal component analysis: A soft tool for proteomic discovery. Analytica Chimica Acta, 544, 118–127.CrossRefGoogle Scholar
  12. Hartigan, J. A., & Wong, M. A. (1979). A K-means Clustering Algorithm. Journal of the Royal Statistical Society Series C (Applied Statistics), 28, 100–108.Google Scholar
  13. Ibrahim, B., Basanta, M., Cadden, P., Singh, D., Douce, D., Woodcock, A., et al. (2011). Non-invasive phenotyping using exhaled volatile organic compounds in asthma. Thorax, 66, 804–809.CrossRefPubMedGoogle Scholar
  14. Jansen, J. J., Hoefsloot, H. C. J., Greef, J., Timmerman, M. E., & Smilde, A. K. (2005a). Multilevel component analysis of time-resolved metabolomics data. Analytica Chimica Acta, 530, 173–183.CrossRefGoogle Scholar
  15. Jansen, J. J., Hoefsloot, H. C. J., Greef, J., Timmerman, M. E., Westerhuis, J. A., & Smilde, A. K. (2005b). ASCA: Analysis of multivariate data obtained from an experimental design. Journal of Chemometrics, 19, 469–481.CrossRefGoogle Scholar
  16. Kohonen, Teuvo. (1982). Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43, 59–69.CrossRefGoogle Scholar
  17. MacNee, W. (2009). Accelerated lung aging: a novel pathogenic mechanism of chronic obstructive pulmonary disease (COPD). Biochemical Society Transactions, 37, 819–823.CrossRefPubMedGoogle Scholar
  18. Penn, D. J., Oberzaucher, E., Grammer, K., Fischer, G., Soini, H. A., Wiesler, D., et al. (2007). Individual and gender fingerprints in human body odour. Journal of the Royal Society, Interface, 4, 331–340.CrossRefPubMedGoogle Scholar
  19. Smilde, A. K., Jansen, J. J., Hoefsloot, H. C. J., Lamers, R-Jan, van der Greef, J., & Timmerman, M. E. (2005). ANOVA-simultaneous component analysis (ASCA): A new tool for analyzing designed metabolomics data. Bioinformatics, 21, 3043–3048.CrossRefPubMedGoogle Scholar
  20. Smilde, A. K., Timmerman, M. E., Hendriks, M. M. W. B., Jansen, J. J., & Hoefsloot, H. C. J. (2012). Generic framework for high-dimensional fixed-effects ANOVA. Briefings in Bioinformatics, 13, 524–535.CrossRefPubMedGoogle Scholar
  21. Thomas, A. N., Riazanskaia, S., Cheung, W., Xu, Y., Goodacre, R., Thomas, C. L. P., et al. (2010). Novel noninvasive identification of biomarkers by analytical profiling of chronic wounds using volatile organic compounds. Wound Repair and Regeneration, 18, 391–400.CrossRefPubMedGoogle Scholar
  22. Timmerman, M. E. (2006). Multilevel component analysis. British Journal of Mathematical and Statistical Psychology, 59, 301–320.CrossRefPubMedGoogle Scholar
  23. van Velzen, E. J. J., Westerhuis, J. A., van Duynhoven, J. P. M., et al. (2008). Multilevel data analysis of a crossover designed human nutritional intervention study. Journal of Proteome Research, 7, 4483–4491.CrossRefPubMedGoogle Scholar
  24. Vis, D. J., Westerhuis, J. A., Smilde, A. K., & van der Greef, J. (2007). Statistical validation of megavariate effects in ASCA. BMC Bioinformatics, 8, 322–330.CrossRefPubMedPubMedCentralGoogle Scholar
  25. Westerhuis, J. A., van Velzen, E. J. J., Hoefsloot, C. J., & Smilde, A. K. (2010). Multivariate paired data analysis: Multilevel PLSDA versus OPLSDA. Metabolomics, 6, 119–128.CrossRefPubMedGoogle Scholar
  26. Wold, S., Sjöström, M., & Eriksson, L. (2001). PLS-regression: A basic tool of chemometrics. Chemometrics and Intelligent Laboratory Systems, 58, 109–130.CrossRefGoogle Scholar
  27. Xu, Y., Cheung, W., Winder, C. L., & Goodacre, R. (2010). VOC-based metabolic profiling for food spoilage detection with the application to detecting Salmonella typhimurium-contaminated pork. Analytical and Bioanalytical Chemistry, 397, 2439–2449.CrossRefPubMedGoogle Scholar
  28. Zwanenburg, G., Hoefsloot, H. C. J., Westerhuis, J. A., Jansen, J. J., & Smilde, A. K. (2011). ANOVA-principal component analysis and ANOVA-simultaneous component analysis: A comparison. Journal of Chemometrics, 25, 561–567.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Yun Xu
    • 1
    Email author
  • Stephen J. Fowler
    • 2
    • 3
    • 4
  • Ardeshir Bayat
    • 5
  • Royston Goodacre
    • 1
  1. 1.Manchester Institute of Biotechnology & School of ChemistryUniversity of ManchesterManchesterUK
  2. 2.Manchester Academic Health Science CentreUniversity of ManchesterManchesterUK
  3. 3.NIHR Respiratory and Allergy Clinical Research FacilityUniversity Hospital of South ManchesterManchesterUK
  4. 4.Lancashire Teaching Hospitals NHS Foundation TrustPrestonUK
  5. 5.Plastic & Reconstructive Surgery Research, Manchester Institute of BiotechnologyUniversity of ManchesterManchesterUK

Personalised recommendations