Abstract
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/.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 5
Claim · model-written summary
Deep learning showed no advantage over linear model methods for genomic prediction, except when epistasis was important.
Verbatim
e0“two important small fruits or berries: strawberry and blueberry”
e1“In terms of genomic prediction, we did not find an advantage of DL over linear model methods, except when the epistasis component was important”
Claim · model-written summary
For the full additive architecture, linear Bayesian models were better than convolutional neural networks in predictive accuracy.
Verbatim
e0“two important small fruits or berries: strawberry and blueberry”
e2“Linear Bayesian models were better than convolutional neural networks for the full additive architecture, whereas the opposite was observed under strong epistasis”
e3“Bayesian linear models can match or exceed the predictive accuracy of DL”
Claim · model-written summary
Under strong epistasis, convolutional neural networks outperformed linear Bayesian models in predictive accuracy.
Verbatim
e0“two important small fruits or berries: strawberry and blueberry”
e2“Linear Bayesian models were better than convolutional neural networks for the full additive architecture, whereas the opposite was observed under strong epistasis”
e3“Bayesian linear models can match or exceed the predictive accuracy of DL”
Claim · model-written summary
The number of convolutional filters and regularization in the first layers can have an important effect on deep learning model performance.
Verbatim
e0“two important small fruits or berries: strawberry and blueberry”
e4“the number of convolutional filters and regularization in the first layers can have an important effect on model performance”
Claim · model-written summary
With a parameterization for non-linear effects, Bayesian linear models can match or exceed the predictive accuracy of deep learning.
Verbatim
e0“two important small fruits or berries: strawberry and blueberry”
e3“Bayesian linear models can match or exceed the predictive accuracy of DL”