DOI: 10.5507/vup.21.24459677.27

Feature selection for genomic prediction of perennial ryegrass forage quality

Agnieszka Konkolewska, Patrick Conaghan, Dan Milbourne, Michael Dineen, Susanne Barth, Rachel Keirse, Stephen Byrne

Feature selection enables the identification of important SNPs for development of low-density genotyping assays for use in genomic selection. The objective of this study was to evaluate genetic algorithms for feature selection prior to genomic prediction of forage digestibility in Lolium perenne. The reference population consisted of 1800 genotypes from 30 diploid populations consisting of 10 cultivars, 8 full-sib families, 8 half-sib families and 4 ecotypes. Plants were established in a spaced plant field trial and forage dry matter digestibility (DMD) was determined with near-infrared spectroscopy (NIRS). Genomic predictions based on genotyping-by-sequencing (GBS) data were performed on a full marker dataset and reduced marker subsets. Genetic algorithms enabled us to select subsets of features with predictive ability comparable to the entire SNPs set. While further optimization is required, identifying key predictor variables may enable selection for forage quality using inexpensive marker systems.

stránky: 113-116



Reference

  1. Arojju S.K., Conaghan P., Barth S., Milbourne D., Casler M.D., Hodkinson T.R.... Byrne S.L. (2018): Genomic prediction of crown rust resistance in Lolium perenne. BMC Genetics 19(1), 35. Přejít k původnímu zdroji...
  2. Burns G.A., Gilliland T.J., McGilloway D.A., O'Donovan M., Lewis E., Blount N., O'Kiely P. (2010): Using NIRS to predict composition characteristics of Lolium perenne L. cultivars. Advances in Animal Biosciences 1(1), 321-321. Přejít k původnímu zdroji...
  3. Elshire R.J., Glaubitz J.C., Sun Q., Poland J.A., Kawamoto K., Buckler E.S., Mitchell S.E. (2011): A robust, simple genotyping-by-sequencing (GBS) approach for high diversity species. PLoS ONE 6(5), e19379. Přejít k původnímu zdroji...
  4. Endelman J.B. (2011): Ridge regression and other kernels for genomic selection with R package rrBLUP. The Plant Genome 4(3), 250-5. Přejít k původnímu zdroji...
  5. Hickey J.M., Chiurugwi T., Mackay I., Powell W., Eggen A., Kilian A.... Beyene Y. (2017): Genomic prediction unifies animal and plant breeding programs to form platforms for biological discovery. Nature Genetics 49(9), 1297-1303. Přejít k původnímu zdroji...
  6. Whitley D. (1994): A genetic algorithm tutorial. Statistics and computing 4, 65-85. Přejít k původnímu zdroji...