Deep neural networks for genomic prediction do not estimate marker effects
Open Access
- 1 October 2021
- journal article
- research article
- Published by Wiley in The Plant Genome
- Vol. 14 (3) , e20147
Abstract
Genomic prediction is a promising technology for advancing both plant and animal breeding, with many different prediction models evaluated in the literature. It has been suggested that the ability of powerful nonlinear models, such as deep neural networks, to capture complex epistatic effects between markers offers advantages for genomic prediction. However, these methods tend not to outperform classical linear methods, leaving it an open question why this capacity to model nonlinear effects does not seem to result in better predictive capability. In this work, we propose the theory that, because of a previously described principle called shortcut learning, deep neural networks tend to base their predictions on overall genetic relatedness rather than on the effects of particular markers such as epistatic effects. Using several datasets of crop plants [lentil ( Lens culinaris Medik.), wheat ( Triticum aestivum L.), and Brassica carinata A. Braun], we demonstrate the network's indifference to the values of the markers by showing that the same network, provided with only the locations of matches between markers for two individuals, is able to perform prediction to the same level of accuracy.Keywords
All Related Versions
Funding Information
- University of Saskatchewan
This publication has 19 references indexed in Scilit:
- Genomic Selection in Plant Breeding: Methods, Models, and PerspectivesTrends in Plant Science, 2017
- Efficient Estimation of Realized Kinship from Single Nucleotide Polymorphism GenotypesGenetics, 2017
- Genomic Prediction of Gene Bank Wheat LandracesG3: Genes, Genomes, Genetics, 2016
- Kernel-based whole-genome prediction of complex traits: a reviewFrontiers in Genetics, 2014
- Genomic selection using regularized linear regression models: ridge regression, lasso, elastic net and their extensionsBMC Proceedings, 2012
- Predicting complex quantitative traits with Bayesian neural networks: a case study with Jersey cows and wheatBMC Genomic Data, 2011
- Prediction of Genetic Values of Quantitative Traits in Plant Breeding Using Pedigree and Molecular MarkersGenetics, 2010
- Estimating Effects and Making Predictions from Genome-Wide Marker DataStatistical Science, 2009
- Genomic selectionJournal of Animal Breeding and Genetics, 2007
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991