, 1:227 | Cite as

Novel biomarkers for pre-eclampsia detected using metabolomics and machine learning

  • Louise C. KennyEmail author
  • Warwick B. Dunn
  • David I. Ellis
  • Jenny Myers
  • Philip N. Baker
  • GOPEC Consortium
  • Douglas B. KellEmail author


Pre-eclampsia is a multi-system disorder of pregnancy with major maternal and perinatal implications. Emerging therapeutic strategies are most likely to be maximally effective if commenced weeks or even months prior to the clinical presentation of the disease. Although widespread plasma alterations precede the clinical onset of pre-eclampsia, no single plasma constituent has emerged as a sensitive or specific predictor of risk. Consequently, currently available methods of identifying the condition prior to clinical presentation are of limited clinical use. We have exploited genetic programming, a powerful data mining method, to identify patterns of metabolites that distinguish plasma from patients with pre-eclampsia from that taken from healthy, matched controls. High-resolution gas chromatography time-of-flight mass spectrometry (GC-tof-MS) was performed on 87 plasma samples from women with pre-eclampsia and 87 matched controls. Normalised peak intensity data were fed into the Genetic Programming (GP) system which was set up to produce a model that gave an output of 1 for patients and 0 for controls. The model was trained on 50% of the data generated and tested on a separate hold-out set of 50%. The model generated by GP from the GC-tof-MS data identified a metabolomic pattern that could be used to produce two simple rules that together discriminate pre-eclampsia from normal pregnant controls using just 3 of the metabolite peak variables, with a sensitivity of 100% and a specificity of 98%. Thus, pre-eclampsia can be diagnosed at the level of small-molecule metabolism in blood plasma. These findings justify a prospective assessment of metabolomic technology as a screening tool for pre-eclampsia, while identification of the metabolites involved may lead to an improved understanding of the aetiological basis of pre-eclampsia and thus the development of targeted therapies.


pre-eclampsia mass spectrometry GC-MS metabolomics machine learning genetic programming prognosis diagnosis classification 



LK, JM, & PB thank Tommy’s, the Baby Charity, for financial support. DBK thanks the BBSRC, EPSRC and the Royal Society of Chemistry for financial support.

The authors wish to thank Jenny Robinson and Dympna Tansinda for their assistance with the collection of control plasma samples. We thank an anonymous referee for a useful comment.


  1. Allen J., Davey H.M., Broadhurst D., Rowland J.J., Oliver S.G. and Kell D.B. (2004) Discrimination of the modes of action of antifungal substances by use of metabolic footprinting. Appl. Env. Micr. 70, 6157–6165CrossRefGoogle Scholar
  2. Bino R.J., Hall R.D., Fiehn O., Kopka J., Saito K., Draper J., Nikolau B.J., Mendes P., Roessner-Tunali U., Beale M.H., Trethewey R.N., Lange B.M., Wurtele E.S. and Sumner L.W. (2004) Potential of metabolomics as a functional genomics tool. Trends Plant Sci 9, 418–425CrossRefPubMedGoogle Scholar
  3. Breiman L. (2001) Statistical modeling: The two cultures. Stat. Sci. 16, 199–215CrossRefGoogle Scholar
  4. Brindle J.T., Antti H., Holmes E., Tranter G., Nicholson J.K., Bethell H.W., Clarke S., Schofield P.M., McKilligin E., Mosedale D.E. and Grainger D.J. (2002) Rapid and noninvasive diagnosis of the presence and severity of coronary heart disease using 1H-NMR-based metabonomics. Nat Med 8, 1439–1444CrossRefPubMedGoogle Scholar
  5. Brown M., Dunn W.B., Ellis D.I., Goodacre R., Handl J., Knowles J.D., O’Hagan S., Spasic I. and Kell D.B. (2005) A metabolome pipeline: from concept to data to knowledge. Metabolomics 1, 35–46CrossRefGoogle Scholar
  6. CESDI (1998) Confidential Enquiry into stillbirths and deaths in infancy. 5th Annual Report. Maternal and Child Health Research ConsortiumGoogle Scholar
  7. Dunn W.B. and Ellis D.I. (2005) Metabolomics: current analytical platforms and methodologies. Trends Anal Chem 24, 285–294CrossRefGoogle Scholar
  8. Dunn W.B., Bailey N.J.C. and Johnson H.E. (2005) Measuring the metabolome: current analytical technologies. Analyst 130, 606–625CrossRefPubMedGoogle Scholar
  9. Ellis D.I., Broadhurst D., Kell D.B., Rowland J.J. and Goodacre R. (2002) Rapid and quantitative detection of the microbial spoilage of meat by Fourier transform infrared spectroscopy and machine learning. Appl Environ Microbiol 68, 2822–2828CrossRefPubMedGoogle Scholar
  10. Ellis D.I., Harrigan G.G. and Goodacre R. (2003) Metabolic Fingerprinting with Fourier Transform Infrared Spectroscopy. In: Harrigan G.G. and Goodacre R. (eds), Metabolic Profiling: Its role in Biomarker Discovery and Gene Function Analysis. Kluwer Academic, BostonGoogle Scholar
  11. Fiehn O., Kopka J., Dormann P., Altmann T., Trethewey R.N. and Willmitzer L. (2000) Metabolite profiling for plant functional genomics. Nat Biotechnol 18, 1157–1161CrossRefPubMedGoogle Scholar
  12. Frank R. and Hargreaves R. (2003) Clinical biomarkers in drug discovery and development. Nat Rev Drug Discov 2, 566–580CrossRefPubMedGoogle Scholar
  13. Gardosi J. (1998) The application of individualised fetal growth curves. J Perinat Med 26, 137–142PubMedGoogle Scholar
  14. Golub T.R., Slonim D.K., Tamayo P., Huard C., Gaasenbeek M., Mesirov J.P., Coller H., Loh M.L., Downing J.R., Caligiuri M.A., Bloomfield C.D. and Lander E.S. (1999) Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring. Science 286, 531–537CrossRefPubMedGoogle Scholar
  15. Goodacre R., Vaidyanathan S., Dunn W.B., Harrigan G.G. and Kell D.B. (2004) Metabolomics by numbers: acquiring and understanding global metabolite data. Trends Biotechnol 22, 245–252CrossRefPubMedGoogle Scholar
  16. van der Greef J., Stroobant P. and van der Heijden R. (2004) The role of analytical sciences in medical systems biology. Curr Opin Chem Biol 8, 559–565CrossRefPubMedGoogle Scholar
  17. Harrigan G.G. and Goodacre R. (eds), (2003) Metabolic profiling: its role in biomarker discovery and gene function analysis. Kluwer Academic Publishers, BostonGoogle Scholar
  18. Hayman R., Brockelsby J., Kenny L. and Baker P. (1999) Preeclampsia: the endothelium, circulating factor(s) and vascular endothelial growth factor. J Soc Gynecol Investig 6, 3–10CrossRefPubMedGoogle Scholar
  19. Hibbard B. and Milner D. (1994) Reports on confidential enquiries into maternal deaths: an audit of previous recommendations. Health Trends 26, 26–28PubMedGoogle Scholar
  20. Jellum E., Bjornson I., Nesbakken R., Johansson E. and Wold S. (1981) Classification of human cancer cells by means of capillary gas chromatography and pattern recognition analysis. J Chromatogr 217, 231–237CrossRefPubMedGoogle Scholar
  21. Kell D.B. (2002) Genotype:phenotype mapping: genes as computer programs. Trends Genet 18, 555–559CrossRefPubMedGoogle Scholar
  22. Kell D.B. (2004) Metabolomics and systems biology: making sense of the soup. Curr Opin Microbiol 7, 296–307CrossRefPubMedGoogle Scholar
  23. Kell, D.B. (2005) Metabolomics, machine learning and modelling: towards an understanding of the language of cells. Biochem Soc Trans 33, in pressGoogle Scholar
  24. Kell D.B. and Mendes P. (2000) Snapshots of systems:metabolic control analysis and biotechnology in the post-genomic era. In: Cornish-Brown A. and Cárdenas M.L. (eds), Technological and Medical Implications of Metabolic Control Analysis. Kluwer Academic, Boston, pp. 3–25Google Scholar
  25. Kell D.B. and Oliver S.G. (2004) Here is the evidence, now what is the hypothesis? The complementary roles of inductive and hypothesis-driven science in the post-genomic era. Bioessays 26, 99–105CrossRefPubMedGoogle Scholar
  26. Kell D.B., Darby R.M. and Draper J. (2001) Genomic computing: explanatory analysis of plant expression profiling data using machine learning. Plant Physiol 126, 943–951CrossRefPubMedGoogle Scholar
  27. Kell D.B., Brown M., Davey H.M., Dunn W.B., Spasic I. and Oliver S.G. (2005) Metabolic footprinting and Systems Biology: the medium is the message. Nat Rev Microbiol, July issue, in pressGoogle Scholar
  28. Kenny L.C., Baker P.N., Kendall D.A., Randall M.D. and Dunn W.R. (2002) Differential mechanisms of endothelium-dependent vasodilator responses in human myometrial small arteries in normal pregnancy and pre-eclampsia. Clin Sci (Lond) 103, 67–73CrossRefGoogle Scholar
  29. Koza J.R. (1992) Genetic programming: on the programming of computers by means of natural selection. MIT Press, Cambridge, MAGoogle Scholar
  30. Lesko L.J. and Atkinson A.J., Jr. (2001) Use of biomarkers and surrogate endpoints in drug development and regulatory decision making: criteria, validation, strategies. Annu Rev Pharmacol Toxicol 41, 347–366CrossRefPubMedGoogle Scholar
  31. Lewis G. (2001) Why women die. Report on Confidential Enquiries into Maternal Deaths in the United Kingdom 1997–1999. Department of Health, Welsh Office, Scottish Office Department of Health, Department of Health and Social Services, Northern Ireland, LondonGoogle Scholar
  32. O’Hagan S., Dunn W.B., Brown M., Knowles J.D. and Kell D.B. (2005) Closed-loop, multiobjective optimisation of analytical instrumentation: gas-chromatography-time-of-flight mass spectrometry of the metabolomes of human serum and of yeast fermentations. Anal Chem 77, 290–303CrossRefPubMedGoogle Scholar
  33. Oliver S.G., Winson M.K., Kell D.B. and Baganz F. (1998) Systematic functional analysis of the yeast genome. Trends Biotechnol 16, 373–378CrossRefPubMedGoogle Scholar
  34. Petricoin E.F., Ardekani A.M., Hitt B.A., Levine P.J., Fusaro V.A., Steinberg S.M., Mills G.B., Simone C., Fishman D.A., Kohn E.C. and Liotta L.A. (2002) Use of proteomic patterns in serum to identify ovarian cancer. Lancet 359, 572–577CrossRefPubMedGoogle Scholar
  35. Pijnenborg R., Anthony J., Davey D.A., Rees A., Tiltman A., Vercruysse L. and van Assche A. (1991) Placental bed spiral arteries in the hypertensive disorders of pregnancy. Br J Obstet Gynaecol 98, 648–655PubMedGoogle Scholar
  36. Raamsdonk L.M., Teusink B., Broadhurst D., Zhang N., Hayes A., Walsh M.C., Berden J.A., Brindle K.M., Kell D.B., Rowland J.J., Westerhoff H.V., van Dam K. and Oliver S.G. (2001) A functional genomics strategy that uses metabolome data to reveal the phenotype of silent mutations. Nat Biotechnol 19, 45–50CrossRefPubMedGoogle Scholar
  37. Rashed M.S. (2001) Clinical applications of tandem mass spectrometry: ten years of diagnosis and screening for inherited metabolic diseases. J Chromatogr B Biomed Sci Appl 758, 27–48CrossRefPubMedGoogle Scholar
  38. Roberts J.M., Taylor R.N., Musci T.J., Rodgers G.M., Hubel C.A. and McLaughlin M.K. (1989) Preeclampsia: an endothelial cell disorder. Am J Obstet Gynecol 161, 1200–1204PubMedGoogle Scholar
  39. Rodgers G.M., Taylor R.N. and Roberts J.M. (1988) Preeclampsia is associated with a serum factor cytotoxic to human endothelial cells. Am J Obstet Gynecol 159, 908–914PubMedGoogle Scholar
  40. Shi Y., Evans J.E. and Rock K.L. (2003) Molecular identification of a danger signal that alerts the immune system to dying cells. Nature 425, 516–521CrossRefPubMedGoogle Scholar
  41. Urbanczyk-Wochniak E., Luedemann A., Kopka J., Selbig J., Roessner-Tunali U., Willmitzer L. and Fernie A.R. (2003) Parallel analysis of transcript and metabolic profiles: a new approach in systems biology. EMBO Rep 4, 989–993CrossRefPubMedGoogle Scholar
  42. Whitfield P.D., German A.J. and Noble P.J. (2004) Metabolomics: an emerging post-genomic tool for nutrition. Br J Nutr 92, 549–555CrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media, Inc. 2005

Authors and Affiliations

  • Louise C. Kenny
    • 1
    Email author
  • Warwick B. Dunn
    • 2
  • David I. Ellis
    • 2
  • Jenny Myers
    • 1
  • Philip N. Baker
    • 1
  • GOPEC Consortium
  • Douglas B. Kell
    • 2
    Email author
  1. 1.The Maternal and Fetal Health Research CentreUniversity of ManchesterManchesterUK
  2. 2.School of ChemistryUniversity of ManchesterManchesterUK

Personalised recommendations