Progress in the rate of improvement in autopolyploid species has been limited compared with diploids, mainly because software and methods to apply advanced prediction and selection methodologies in autopolyploids are lacking. The objectives of this research were to (i) develop an R package for autopolyploids to construct the relationship matrix derived from pedigree information that accounts for autopolyploidy and double reduction and (ii) use the package to estimate the level and effect of double reduction in an autotetraploid blueberry breeding population with extensive pedigree information. The package is unique, as it can create A‐matrices for different levels of ploidy and double reduction, which can then be used by breeders to fit mixed models in the context of predicting breeding values (BVs). Using the data from this blueberry population, we found for all the traits that tetrasomic inheritance creates a better fit than disomic inheritance. In one of the five traits studied, the level of double reduction was different from zero, decreasing the estimated heritability, but it did not affect the prediction of BVs. We also discovered that different depths of pedigree would have significant implications on the estimation of double reduction using this approach. This freely available R package is available for autopolyploid breeders to estimate the level of double reduction present in their populations and the impact in the estimation of genetic parameters as well as to use advanced methods of prediction and selection.

The application of quantitative genetics in plant and animal breeding has largely focused on additive models, which may also capture dominance and epistatic effects. Partitioning genetic variance into its additive and nonadditive components using pedigree-based models (P-genomic best linear unbiased predictor) (P-BLUP) is difficult with most commonly available family structures. However, the availability of dense panels of molecular markers makes possible the use of additive- and dominance-realized genomic relationships for the estimation of variance components and the prediction of genetic values (G-BLUP). We evaluated height data from a multifamily population of the tree species Pinus taeda with a systematic series of models accounting for additive, dominance, and first-order epistatic interactions (additive by additive, dominance by dominance, and additive by dominance), using either pedigree- or marker-based information. We show that, compared with the pedigree, use of realized genomic relationships in marker-based models yields a substantially more precise separation of additive and nonadditive components of genetic variance. We conclude that the marker-based relationship matrices in a model including additive and nonadditive effects performed better, improving breeding value prediction. Moreover, our results suggest that, for tree height in this population, the additive and nonadditive components of genetic variance are similar in magnitude. This novel result improves our current understanding of the genetic control and architecture of a quantitative trait and should be considered when developing breeding strategies.

Significance: Consumers often regard heirloom fruit varieties grown in the garden as more flavorful than commercial varieties purchased at the grocery store. While plant breeders have historically focused on improving producer-orientated traits such as yield, consumer-oriented traits such as flavor have regularly been neglected. This is, in part, due to the difficulty associated with measuring the sensory perceptions of flavor. Here, we combine fruit chemical and consumer sensory panel information to train machine learning models that can predict how flavorful a fruit will be from its chemistry. By increasing the throughput of flavor evaluations, these models will help plant breeders to integrate flavor earlier in the breeding pipeline and aid in the design of varieties with exceptional flavor profiles.

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/.

The resemble between relatives computed from pedigree and genomic data is an important resource for geneticists and ecologists, who are interested in understanding how genes influence phenotypic variation, fitness adaptation, and population dynamics. The AGHmatrix software is an R package focused on the construction of pedigree (A matrix) and/or molecular markers (G matrix), with the possibility of building a combined matrix of pedigree corrected by molecular markers (H matrix). Designed to estimate the relationships for any ploidy level, the software also includes auxiliary functions related to filtering molecular markers, and checks pedigree errors in large data sets. After computing the relationship matrices, results from the AGHmatrix can be used in different contexts, including on prediction of (genomic) estimated breeding values and genome-wide association studies. AGHmatrix v2.1.0 is available under GPL-3 license in CRAN at https://cran.r-project.org/web/packages/AGHmatrix/index.html and also in GitHub at https://github.com/rramadeu/AGHmatrix. It has a comprehensive tutorial, and it follows with real data examples.