Hostname: page-component-cd9895bd7-dk4vv Total loading time: 0 Render date: 2024-12-21T16:34:16.483Z Has data issue: false hasContentIssue false
  • English
  • Français

Machine learning links seed composition, glucosinolates and viability of oilseed rape after 31 years of long-term storage

Published online by Cambridge University Press:  12 July 2018

Manuela Nagel ,
Katharina Holstein ,
Evelin Willner  and
Andreas Börner
Manuela Nagel*
Affiliation:
Genebank Department, Leibniz-Institute of Plant Genetics and Crop Plant Research (IPK Gatersleben), Seeland, Germany
Katharina Holstein
Affiliation:
Fraunhofer Institute for Factory Operation and Automation (IFF), Magdeburg, Germany
Evelin Willner
Affiliation:
Genebank Department, Leibniz-Institute of Plant Genetics and Crop Plant Research (IPK Gatersleben), Seeland, Germany
Andreas Börner
Affiliation:
Genebank Department, Leibniz-Institute of Plant Genetics and Crop Plant Research (IPK Gatersleben), Seeland, Germany
*
Author for correspondence: Manuela Nagel, Email: Nagel@ipk-gatersleben.de
Get access Rights & Permissions [Opens in a new window]

Abstract

Seed longevity is influenced by many factors, a widely discussed one of which is the seed lipid content and fatty acid composition. Here, linear and non-linear regressions based on machine learning were applied to analyse germinability and seed composition of a set of 42 oilseed rape (Brassica napus L.) accessions grown under the same single environment and at the same time following a period of up to 31 years storage at 7°C. Mean viability was halved after 27.0 years of storage, but this figure concealed a major influence of genotype. There was also wide variation with respect to fatty acid composition, particularly with respect to oleic, α-linolenic, eicosenoic and erucic acid. Linear regression (rL) revealed significant correlation coefficients between normal seedling appearance and the content of α-linolenic acid (+0.52) and total oil (+0.59). Multivariate regression using artificial neural networks including a radial basis function (RBF), a multilayer perceptron (MLP) and a partial least square (PLS) recognized underlying structures and revealed high significant correlation coefficients (rM) for oil content (+0.87), eicosenoic acid (+0.75), stearic acid (+0.73) and lignoceric acid (+0.97). Oil content or a combination of oleic, α-linolenic, arachidic, eicosenoic and eicosadienoic acids and glucosinolates resulted in highest model fitting parameters R2 of 0.90 and 0.88, respectively. In addition, the glucosinolate content, predominantly in the Brassicaceae family and ranging from 4.6 to 79.5 µM, was negatively correlated with viability (rL = ‒0.43). Summarizing, oil content, some fatty acids and glucosinolates contribute to variations in average half-life (15.2 to 50.7 years) of oilseed rape seeds. In contrast to linear regression, multivariate regression using artificial neural networks revealed high associations for combinations of parameters including underestimated minor fatty acids such as arachidic, stearic and eicosadienoic acids. This indicates that genetic and seed composition factors contribute to seed longevity. In addition, multivariate regressions might be a successful approach to predict seed viability based on fatty acids and seed oil content.

Keywords

artificial neural networksBrassica napusfatty acidsgene bankgerminationmultivariate regressionseed conservationseed longevityseed viability
Type
Research Paper
Information
Seed Science Research , Volume 28 , Issue 4 , December 2018 , pp. 340 - 348
Copyright
Copyright © Cambridge University Press 2018 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Andre, M (2003) Multivariate analysis and classification of the chemical quality of 7-aminocephalosporanic acid using near-infrared reflectance spectroscopy. Analytical Chemistry 75, 3460–3467.Google Scholar
Bailly, C (2004) Active oxygen species and antioxidants in seed biology. Seed Science Research 14, 93–107.Google Scholar
Bettey, M, Finch-Savage, WE, King, GJ and Lynn, JR (2000) Quantitative genetic analysis of seed vigour and pre-emergence seedling growth traits in Brassica oleracea. New Phytologist 148, 277–286.Google Scholar
Bewley, JD, Bradford, KJ, Hilhorst, HWM and Nonogaki, H (2013) Seeds: Physiology of Development, Germination and Dormancy, 3rd edition. New York: Springer.Google Scholar
Borges, A, Abreu, AC, Ferreira, C, Saavedra, MJ, Simoes, LC and Simoes, M (2015) Antibacterial activity and mode of action of selected glucosinolate hydrolysis products against bacterial pathogens. Journal of Food Science and Technology-Mysore 52, 4737–4748.Google Scholar
Clark, SR, Baune, BT, Schubert, KO, Lavoie, S, Smesny, S, Rice, SM, Schäfer, MR, Benninger, F, Feucht, M, Klier, CM, McGorry, PD and Amminger, GP (2016) Prediction of transition from ultra-high risk to first-episode psychosis using a probabilistic model combining history, clinical assessment and fatty-acid biomarkers. Translational Psychiatry 6, e897.Google Scholar
Crapiste, GH, Brevedan, MIV and Carelli, AA (1999) Oxidation of sunflower oil during storage. Journal of the American Oil Chemists Society 76, 1437–1443.Google Scholar
Cybenko, G (1989) Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems (MCSS) 2, 303–314.Google Scholar
de Jong, TJ, Isanta, MT and Hesse, E (2013) Comparison of the crop species Brassica napus and wild B. rapa: characteristics relevant for building up a persistent seed bank in the soil. Seed Science Research 23, 169–179.Google Scholar
Elliott, RH, Franke, C and Rakow, GFW (2008) Effects of seed size and seed weight on seedling establishment, vigour and tolerance of Argentine canola (Brassica napus) to flea beetles, Phyllotreta spp. Canadian Journal of Plant Science 88, 207–217.Google Scholar
Ellis, RH and Roberts, EH (1980) Improved equations for the prediction of seed longevity. Annals of Botany 45, 13–30.Google Scholar
Falk, J and Munné-Bosch, S (2010) Tocochromanol functions in plants: antioxidation and beyond. Journal of Experimental Botany 61, 1549–1566.Google Scholar
Hall, RD (2011) Biology of plant metabolomics. Annual Plant Reviews 43, 407–420.Google Scholar
Harwood, JL (1997) Plant lipid metabolism, in Dey, PM and Harborne, JB (eds), Plant Biochemistry. San Diego, CA: Academic Press.Google Scholar
Hoekstra, FA (2005) Differential longevities in desiccated anhydrobiotic plant systems. Integrative and Comparative Biology 45, 725–733.Google Scholar
Hwang, JE, Ahn, JW, Kwon, SJ, Kim, JB, Kim, SH, Kang, SY and Kim, DS (2014) Selection and molecular characterization of a high tocopherol accumulation rice mutant line induced by gamma irradiation. Molecular Biology Reports 41, 7671–7681.Google Scholar
ISTA (2014) International Rules for Seed Testing. Bassersdorf, Switzerland: International Seed Testing Association.Google Scholar
Johnson, RA and Wichern, DW (2007) Applied Multivariate Statistical Analysis (6th edition). New York, Pearson Book.Google Scholar
Komba, CG, Brunton, BJ and Hampton, JG (2007) Effect of seed size within seed lots on seed quality in kale. Seed Science and Technology 35, 244–248.Google Scholar
Kranner, I, Minibayeva, FV, Beckett, RP and Seal, CE (2010) What is stress? Concepts, definitions and applications in seed science. New Phytologist 188, 655–673.Google Scholar
Krzanowski, WJ (2000) Principles of Multivariate Analysis: A User's Perspective. New York, Oxford University Press.Google Scholar
Lemaitre, RN, Fretts, AM, Sitlani, CM, Biggs, ML, Mukamal, K, King, IB, Song, X, Djoussé, L, Siscovick, DS, McKnight, B, Sotoodehnia, N, Kizer, JR and Mozaffarian, D (2015) Plasma phospholipid very-long-chain saturated fatty acids and incident diabetes in older adults: the Cardiovascular Health Study. The American Journal of Clinical Nutrition 101, 1047–1054.Google Scholar
Ma, L, Zhu, FG, Li, ZW, Zhang, JF, Li, X, Dong, JL and Wang, T (2015) TALEN-based mutagenesis of lipoxygenase LOX3 enhances the storage tolerance of rice (Oryza sativa) seeds. PLoS One 10), e0143877. https://doi.org/10.1371/journal.pone.0143877Google Scholar
Moody, J and Darken, CJ (1989) Fast learning in networks of locally-tuned processing units. Neural Computation 1, 281–294.Google Scholar
Nagel, M, Behrens, A-K and Börner, A (2013) Effects of Rht dwarfing alleles on wheat seed vigour after controlled deterioration. Crop and Pasture Science 64, 857–864.Google Scholar
Nagel, M and Börner, A (2010) The longevity of crop seeds stored under ambient conditions. Seed Science Research 20, 1–12.Google Scholar
Oenel, A, Fekete, A, Krischke, M, Faul, SC, Gresser, G, Havaux, M, Mueller, MJ and Berger, S (2017) Enzymatic and non-enzymatic mehanisms contribute to lipid oxidation during seed aging. Plant and Cell Physiology 58, 925–933.Google Scholar
Ponquett, RT, Smith, MT and Ross, G (1992) Lipid autoxidation and seed ageing: putative relationships between seed longevity and lipid stability. Seed Science Research 2, 51–54.Google Scholar
Priestley, DA, Cullinan, VI and Wolfe, J (1985) Differences in seed longevity at the species level. Plant Cell and Environment 8, 557–562.Google Scholar
Priestley, DA and Leopold, AC (1979) Absence of lipid oxidation during accelerated aging of soybean seeds. Plant Physiology 63, 726–729.Google Scholar
Riewe, D, Wiebach, J and Altmann, T (2017) Structure annotation and quantification of wheat seed oxidized lipids by high resolution LC-MS/MS. Plant Physiology 175, 600–618.Google Scholar
Rivas-Ubach, A, Sardans, J, Pérez-Trujillo, M, Estiarte, M and Peñuelas, J (2012) Strong relationship between elemental stoichiometry and metabolome in plants. Proceedings of the National Academy of Sciences of the USA 109, 4181–4186.Google Scholar
Rojas, R (1996) Neural Networks: A Systematic Introduction. Berlin: Springer-Verlag.Google Scholar
Rücker, B and Röbbelen, G (1996) Impact of low linolenic acid content on seed yield of winter oilseed rape (Brassica napus L.). Plant Breeding 115, 226–230.Google Scholar
Sattler, SE, Gilliland, LU, Magallanes-Lundback, M, Pollard, M and DellaPenna, D (2004) Vitamin E is essential for seed longevity, and for preventing lipid peroxidation during germination. Plant Cell 16, 1419–1432.Google Scholar
Shalev-Shwartz, S and Ben-David, S (2014) Understanding Machine Learning: From Theory to Algorithms. New York: Cambridge University Press.Google Scholar
VSN International (2013) GenStat for Windows (17th edition). Hemel Hempstead, UK.Google Scholar
Walters, C, Wheeler, LM and Grotenhuis, JM (2005) Longevity of seeds stored in a genebank: species characteristics. Seed Science Research 15, 1–20.Google Scholar
Waterworth, WM, Bray, CM and West, CE (2015) The importance of safeguarding genome integrity in germination and seed longevity. Journal of Experimental Botany 66, 3549–3558.Google Scholar
Wittkop, B, Snowdon, RJ and Friedt, W (2009) Status and perspectives of breeding for enhanced yield and quality of oilseed crops for Europe. Euphytica 170, 131–140.Google Scholar
Wold, S, Sjöström, M and Eriksson, L (2001) PLS-regression: a basic tool of chemometrics. Chemometrics and Intelligent Laboratory Systems 58, 109–130.Google Scholar
Woodfield, HK, Sturtevant, D, Borisjuk, L, Munz, E, Guschina, IA, Chapman, K and Harwood, JL (2017) Spatial and temporal mapping of key lipid species in Brassica napus seeds. Plant Physiology 173, 1998–2009.Google Scholar
Worley, B and Powers, R (2013) Multivariate analysis in metabolomics. Current Metabolomics 1, 92–107.Google Scholar
Supplementary material: File

Nagel et al. supplementary material

Nagel et al. supplementary material 1

Download Nagel et al. supplementary material(File)
File 1.4 MB