Exploring deep learning for complex trait genomic prediction in polyploid outcrossing species
Zingaretti, Laura M.
Gezan, Salvador Alejandro
Ferrão, Luis Felipe V.
Osorio, Luis F.
Muñoz, Patricio R.
Whitaker, Vance M.
Genomic prediction (GP) is the procedure whereby the genetic merits of untested candidates are predicted using genome wide marker information. Although numerous examples of GP exist in plants and animals, applications to polyploid organisms are still scarce, partly due to limited genome resources and the complexity of this system. Deep learning (DL) techniques comprise a heterogeneous collection of machine learning algorithms that have excelled at many prediction tasks. A potential advantage of DL for GP over standard linear model methods is that DL can potentially take into account all genetic interactions, including dominance and epistasis, which are expected to be of special relevance in most polyploids. In this study, we evaluated the predictive accuracy of linear and DL techniques in two important small fruits or berries: strawberry and blueberry. The two datasets contained a total of 1,358 allopolyploid strawberry (2n=8x=112) and 1,802 autopolyploid blueberry (2n=4x=48) individuals, genotyped for 9,908 and 73,045 single nucleotide polymorphism (SNP) markers, respectively, and phenotyped for five agronomic traits each. DL depends on numerous parameters that influence performance and optimizing hyperparameter values can be a critical step. Here we show that interactions between hyperparameter combinations should be expected and that the number of convolutional filters and regularization in the first layers can have an important effect on model performance. In terms of genomic prediction, we did not find an advantage of DL over linear model methods, except when the epistasis component was important. Linear Bayesian models were better than convolutional neural networks for the full additive architecture, whereas the opposite was observed under strong epistasis. However, by using a parameterization capable of taking into account these non-linear effects, Bayesian linear models can match or exceed the predictive accuracy of DL. A semiautomatic implementation of the DL pipeline is available at https://github.com/lauzingaretti/deepGP/.
633 - Cultius i produccions
Is part of
Frontiers in Plant Science
Zingaretti, Laura M., Salvador Alejandro Gezan, Luis Felipe V. Ferrão, Luis F. Osorio, Amparo Monfort, Patricio R. Muñoz, Vance M. Whitaker, and Miguel Pérez-Enciso. 2020. "Exploring Deep Learning For Complex Trait Genomic Prediction In Polyploid Outcrossing Species". Frontiers In Plant Science 11. Frontiers Media SA. doi:10.3389/fpls.2020.00025.
Grant agreement number
MINECO/Programa Estatal de I+D+I orientada a los retos de la sociedad/AGL2016-78709-R/ES/UTILIZACION DE SECUENCIAS COMPLETAS PARA LA MEJORA DE ESPECIES DOMESTICAS/
MINECO/ /SEV-2015-0533/ES/ /
MINECO-FEDER/Programa Estatal de fomento de la investigación científica y técnica de excelencia/BFU2016-77236-P/ES/FUNCION DEL RELOJ CIRCADIANO EN EL CONTROL DE LAS RESPUESTAS DE LA PLANTA A CAMBIOS MEDIOAMBIENTALES/
This item appears in the following Collection(s)
The following license files are associated with this item:
Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by/4.0/