000			03248nab|a22004097a|4500
001			65752
003			MX-TxCIM
005			20240919021233.0
008			20228s2022||||mx |||p|op||||00||0|eng|d
022			_a2073-4425 (Online)
024	8		_ahttps://doi.org/10.3390/genes13081494
040			_aMX-TxCIM
041			_aeng
100	1		_aMontesinos-Lopez, O.A. _8I1706800 _92700 _gGenetic Resources Program
245	1	2	_aA comparison of three machine learning methods for multivariate genomic prediction using the sparse kernels method (SKM) library
260			_bMDPI, _c2022. _aBasel (Switzerland) :
500			_aPeer review
500			_aOpen Access
520			_aGenomic selection (GS) changed the way plant breeders select genotypes. GS takes advantage of phenotypic and genotypic information to training a statistical machine learning model, which is used to predict phenotypic (or breeding) values of new lines for which only genotypic information is available. Therefore, many statistical machine learning methods have been proposed for this task. Multi-trait (MT) genomic prediction models take advantage of correlated traits to improve prediction accuracy. Therefore, some multivariate statistical machine learning methods are popular for GS. In this paper, we compare the prediction performance of three MT methods: the MT genomic best linear unbiased predictor (GBLUP), the MT partial least squares (PLS) and the multi-trait random forest (RF) methods. Benchmarking was performed with six real datasets. We found that the three investigated methods produce similar results, but under predictors with genotype (G) and environment (E), that is, E + G, the MT GBLUP achieved superior performance, whereas under predictors E + G + genotype (Formula presented.) environment (GE) and G + GE, random forest achieved the best results. We also found that the best predictions were achieved under the predictors E + G and E + G + GE. Here, we also provide the R code for the implementation of these three statistical machine learning methods in the sparse kernel method (SKM) library, which offers not only options for single-trait prediction with various statistical machine learning methods but also some options for MT predictions that can help to capture improved complex patterns in datasets that are common in genomic selection.
546			_aText in English
591			_aMontesinos-Lopez, O.A. : No CIMMYT Affiliation
591			_aHernández-Suárez, C.M. : Not in IRS staff list but CIMMYT Affiliation
650		7	_aGenotypes _2AGROVOC _91134
650		7	_aKernels _2AGROVOC _91168
650		7	_aMachine learning _2AGROVOC _911127
650		7	_aPlant breeding _gAGROVOC _2 _91203
650		7	_aForecasting _2AGROVOC _92701
650		7	_aMarker-assisted selection _2AGROVOC _910737
700	1		_aMontesinos-Lopez, A. _92702
700	1		_aCano-Paez, B. _929337
700	1		_aHernández Suárez, C.M. _9521
700	1		_aSantana-Mancilla, P.C. _917803
700	1		_aCrossa, J. _gGenetic Resources Program _8CCJL01 _959
773	0		_tGenes _gv. 13, no. 8, art. 1494 _dBasel (Switzerland) : MDPI, 2022. _x2073-4425
856			_yOpen Access through DSpace _uhttps://hdl.handle.net/10883/22288
942			_cJA _n0 _2ddc
999			_c65752 _d65744