Conducting Molecular Biomarker Discovery Studies in Plants
Molecular biomarkers are molecules whose concentrations in a biological system inform about the current phenotypical state and, more importantly, may also be predictive of future phenotypic trait endpoints. The identification of biomarkers has gained much attention in targeted plant breeding since technologies have become available that measure many molecules across different levels of molecular organization and at decreasing costs. In this chapter, we outline the general strategy and workflow of conducting biomarker discovery studies. Critical aspects of study design as well as the statistical data analysis and model building will be highlighted.
Key words:Biomarker OMICS technologies Machine learning Classification Feature selection Phenotype Study design Breeding Plants
Support for this work was provided by the BMELV-funded TROST and the BMBF-funded SEPSAPE projects.
- 17.Bergmann W (1992) Colour atlas nutritional disorders of plants: visual and analytical diagnosis. Gustav Fisher Verlag, Jena. GermanyGoogle Scholar
- 21.Hastie T, Tibshirani R, Friedman J (2001) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, New YorkGoogle Scholar
- 23.Bishop CM (2006) Pattern recognition and machine learning. Springer, New YorkGoogle Scholar
- 26.Mccullagh P (1980) Regression-models for ordinal data. J R Stat Soc Series B Methodol 42:109–142Google Scholar
- 27.Lal TN, Chapelle O, Weston J, Elisseeff A (2006) Embedded methods. In: Guyon G, Nikravesh, Zadeh (eds) Feature extraction: foundation and applications. Springer, New York, pp 137–162Google Scholar
- 28.Huda S, Yearwood J, Strainieri A (2010) Hybrid wrapper-filter approaches for input feature selection using maximum relevance and artificial neural network input gain measurement approximation (ANNIGMA). NSS ‘10 Proceedings of the 2010 Fourth International Conference on Network and Systems SecurityGoogle Scholar
- 30.Guyon I, Gunn S, Nikravesh M, Zadeh LA (2006) Feature extraction: foundations and applications (studies in fuzziness and soft computing). Springer, New YorkGoogle Scholar
- 31.Kantardzic M (2002) Data mining: concepts, models, methods, and algorithms. Wiley Hoboken, New Jersey, USAGoogle Scholar
- 34.Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. Proc Int Conf Artific IntelliGoogle Scholar
- 35.Tibshirani R (1996) Regression shrinkage and selection via the Lasso. J R Stat Soc Series B Methodol 58:267–288Google Scholar
- 36.Efron B, Tibshirani RJ (1994) An introduction to the bootstrap. Chapman & HallGoogle Scholar