Novel biomarkers for pre-eclampsia detected using metabolomics and machine learning
- 1k Downloads
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.
Keywordspre-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.
- 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
- CESDI (1998) Confidential Enquiry into stillbirths and deaths in infancy. 5th Annual Report. Maternal and Child Health Research ConsortiumGoogle Scholar
- 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
- 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
- Harrigan G.G. and Goodacre R. (eds), (2003) Metabolic profiling: its role in biomarker discovery and gene function analysis. Kluwer Academic Publishers, BostonGoogle Scholar
- Kell, D.B. (2005) Metabolomics, machine learning and modelling: towards an understanding of the language of cells. Biochem Soc Trans 33, in pressGoogle Scholar
- 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
- 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
- Koza J.R. (1992) Genetic programming: on the programming of computers by means of natural selection. MIT Press, Cambridge, MAGoogle Scholar
- 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
- 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
- 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