Accuracy Of Genomic Prediction Research Articles

Genomic prediction of resistance to Hymenoscyphus fraxineus in common ash (Fraxinus excelsior L.) populations.

The increase in introduced insect pests and pathogens due to anthropogenic environmental changes has become a major concern for tree species worldwide. Common ash (Fraxinus excelsior L.) is one of such species facing a significant threat from the invasive fungal pathogen Hymenoscyphus fraxineus. Some studies have indicated that the susceptibility of ash to the pathogen is genetically determined, providing some hope for accelerated breeding programs that are aimed at increasing the resistance of ash populations. To address this challenge, we used a genomic selection strategy to identify potential genetic markers that are associated with resistance to the pathogen causing ash dieback. Through genome-wide association studies (GWAS) of 300 common ash individuals from 30 populations across Poland (ddRAD, dataset A), we identified six significant SNP loci with a p-value ≤1 × 10-4 associated with health status. To further evaluate the effectiveness of GWAS markers in predicting health status, we considered two genomic prediction scenarios. Firstly, we conducted cross-validation on dataset A. Secondly, we trained markers on dataset A and tested them on dataset B, which involved whole-genome sequencing of 20 individuals from two populations. Genomic prediction analysis revealed that the top SNPs identified via GWAS exhibited notably higher prediction accuracies compared to randomly selected SNPs, particularly with a larger number of SNPs. Cross-validation analyses using dataset A showcased high genomic prediction accuracy, predicting tree health status with over 90% accuracy across the top SNP sets ranging from 500 to 10,000 SNPs from the GWAS datasets. However, no significant results emerged for health status when the model trained on dataset A was tested on dataset B. Our findings illuminate potential genetic markers associated with resistance to ash dieback, offering support for future breeding programs in Poland aimed at combating ash dieback and bolstering conservation efforts for this invaluable tree species.

Genome-wide association study and genomic prediction of resistance to summer mortality in Pacific oyster (Crassostrea gigas) using whole genome resequencing

The Pacific oyster Crassostrea gigas is one of the most important farmed marine shellfish worldwide. However, massive mortality during the summer months caused significant economic losses to the C. gigas farming industry. Understanding the genetic architecture of resistance traits has been an ongoing research issue, and the incorporation of genomic information into breeding programs is expected to accelerate the process of genetic improvement. Genomic selection (GS), as a new approach of genetic improvement, has great potential for breeding new lines with adaptive advantages. In this study, we conducted a genome-wide association study (GWAS) for summer mortality resistance and estimated the accuracy of genomic predictions using different methods. The heritability of the C. gigas summer mortality resistance was low, with heritability of 0.108 ± 0.036, 0.161 ± 0.102 and 0.134 ± 0.043 for PBLUP, GBLUP and ssGBLUP, respectively. In addition, we detected 9,783,674 SNPs and used a mixed linear model to identify 18 significant SNPs associated with summer mortality resistance. The phenotypic variance explained (PVE) for these SNPs ranged from 8.25% to 10.14%. Based on these significantly related SNPs, nine significant candidate genes were identified (TLR4, HEX, SLC22A8, PDE2A, HUWE1, SLMAP, RAD52, TBK1 and RAPH1). The prediction accuracy using PBLUP, GBLUP, ssGBLUP, and weight ssGBLUP (WssGBLUP) was 0.549 ± 0.026, 0.381 ± 0.074, 0.544 ± 0.026, and 0.869 ± 0.018, respectively. Therefore, WssGBLUP models are more suitable for genomic prediction of summer mortality resistance in C. gigas. Our results suggest a polygenic genetic architecture that provide new perspectives for studying candidate genes for resistance to summer mortality, which may facilitate the genetic improvement for resistance lines in C. gigas.

Multi-Trait Bayesian Models Enhance the Accuracy of Genomic Prediction in Multi-Breed Reference Populations

Multi-Trait Bayesian Models Enhance the Accuracy of Genomic Prediction in Multi-Breed Reference Populations

Accuracy of Genomic prediction for fleece traits in Inner Mongolia Cashmere goats

The fleece traits are important economic traits of goats. With the reduction of sequencing and genotyping cost and the improvement of related technologies, genomic selection for goats has become possible. The research collect pedigree, phenotype and genotype information of 2299 Inner Mongolia Cashmere goats (IMCGs) individuals. We estimate fixed effects, and compare the estimates of variance components, heritability and genomic predictive ability of fleece traits in IMCGs when using the pedigree based Best Linear Unbiased Prediction (ABLUP), Genomic BLUP (GBLUP) or single-step GBLUP (ssGBLUP). The fleece traits considered are cashmere production (CP), cashmere diameter (CD), cashmere length (CL) and fiber length (FL). It was found that year of production, sex, herd and individual ages had highly significant effects on the four fleece traits (P < 0.01). All of these factors should be considered when the genetic parameters of fleece traits in IMCGs are evaluated. The heritabilities of FL, CL, CP and CD with ABLUP, GBLUP and ssGBLUP methods were 0.26 ~ 0.31, 0.05 ~ 0.08, 0.15 ~ 0.20 and 0.22 ~ 0.28, respectively. Therefore, it can be inferred that the genetic progress of CL is relatively slow. The predictive ability of fleece traits in IMCGs with GBLUP (56.18% to 69.06%) and ssGBLUP methods (66.82% to 73.70%) was significantly higher than that of ABLUP (36.73% to 41.25%). For the ssGBLUP method is significantly (29% ~ 33%) higher than that with ABLUP, and which is slightly (4% ~ 14%) higher than that of GBLUP. The ssGBLUP will be as an superiors method for using genomic selection of fleece traits in Inner Mongolia Cashmere goats.

Pooled DNA sequencing in hairy vetch (Vicia villosa Roth) reveals QTL for seed dormancy but not pod dehiscence.

Hairy vetch (Vicia villosa Roth) is a promising legume cover crop, but its use is limited by high rates of pod dehiscence and seed dormancy. We used phenotypically contrasting pooled DNA samples (n=24 with 29-74 individuals per sample) from an ongoing cover crop breeding program across four environments (site-year combinations: Maryland 2020, Maryland 2022, Wisconsin 2021, Wisconsin 2022) to find genetic associations and genomic prediction accuracies for pod dehiscence and seed dormancy. We also combined pooled DNA sample genetic association results with the results of a prior genome-wide association study. Genomic prediction resulted in positive predictive abilities for both traits between environments and with an independent dataset (0.34-0.50), but reduced predictive ability for DNA pools with divergent seed dormancy in the Maryland environments (0.07-0.15). The pooled DNA samples found six significant (false discovery rate q-value<0.01) quantitative trait loci (QTL) for seed dormancy and four significant QTL for pod dehiscence. Unfortunately, the minor alleles of the pod dehiscence QTL increased the rate of pod dehiscence and are not useful for marker-assisted selection. When combined with a prior association study, sixteen seed dormancy QTL and zero pod dehiscence QTL were significant. Combining the association studies did not increase the detection of useful QTL.

Marker Density and Models to Improve the Accuracy of Genomic Selection for Growth and Slaughter Traits in Meat Rabbits.

The selection and breeding of good meat rabbit breeds are fundamental to their industrial development, and genomic selection (GS) can employ genomic information to make up for the shortcomings of traditional phenotype-based breeding methods. For the practical implementation of GS in meat rabbit breeding, it is necessary to assess different marker densities and GS models. Here, we obtained low-coverage whole-genome sequencing (lcWGS) data from 1515 meat rabbits (including parent herd and half-sibling offspring). The specific objectives were (1) to derive a baseline for heritability estimates and genomic predictions based on randomly selected marker densities and (2) to assess the accuracy of genomic predictions for single- and multiple-trait linear mixed models. We found that a marker density of 50 K can be used as a baseline for heritability estimation and genomic prediction. For GS, the multi-trait genomic best linear unbiased prediction (GBLUP) model results in more accurate predictions for virtually all traits compared to the single-trait model, with improvements greater than 15% for all of them, which may be attributed to the use of information on genetically related traits. In addition, we discovered a positive correlation between the performance of the multi-trait GBLUP and the genetic correlation between the traits. We anticipate that this approach will provide solutions for GS, as well as optimize breeding programs, in meat rabbits.

Enhancing Genomic Prediction Accuracy for Body Conformation Traits in Korean Holstein Cattle.

The Holstein breed is the mainstay of dairy production in Korea. In this study, we evaluated the genomic prediction accuracy for body conformation traits in Korean Holstein cattle, using a range of π levels (0.75, 0.90, 0.99, and 0.995) in Bayesian methods (BayesB and BayesC). Focusing on 24 traits, we analyzed the impact of different π levels on prediction accuracy. We observed a general increase in accuracy at higher levels for specific traits, with variations depending on the Bayesian method applied. Notably, the highest accuracy was achieved for rear teat angle when using deregressed estimated breeding values including parent average as a response variable. We further demonstrated that incorporating parent average into deregressed estimated breeding values enhances genomic prediction accuracy, showcasing the effectiveness of the model in integrating both offspring and parental genetic information. Additionally, we identified 18 significant window regions through genome-wide association studies, which are crucial for future fine mapping and discovery of causal mutations. These findings provide valuable insights into the efficiency of genomic selection for body conformation traits in Korean Holstein cattle and highlight the potential for advancements in the prediction accuracy using larger datasets and more sophisticated genomic models.

Selective Genotyping and Phenotyping for Optimization of Genomic Prediction Models for Populations with Different Diversity.

To overcome the different challenges to food security caused by a growing population and climate change, soybean (Glycine max (L.) Merr.) breeders are creating novel cultivars that have the potential to improve productivity while maintaining environmental sustainability. Genomic selection (GS) is an advanced approach that may accelerate the rate of genetic gain in breeding using genome-wide molecular markers. The accuracy of genomic selection can be affected by trait architecture and heritability, marker density, linkage disequilibrium, statistical models, and training set. The selection of a minimal and optimal marker set with high prediction accuracy can lower genotyping costs, computational time, and multicollinearity. Selective phenotyping could reduce the number of genotypes tested in the field while preserving the genetic diversity of the initial population. This study aimed to evaluate different methods of selective genotyping and phenotyping on the accuracy of genomic prediction for soybean yield. The evaluation was performed on three populations: recombinant inbred lines, multifamily diverse lines, and germplasm collection. Strategies adopted for marker selection were as follows: SNP (single nucleotide polymorphism) pruning, estimation of marker effects, randomly selected markers, and genome-wide association study. Reduction of the number of genotypes was performed by selecting a core set from the initial population based on marker data, yet maintaining the original population's genetic diversity. Prediction ability using all markers and genotypes was different among examined populations. The subsets obtained by the model-based strategy can be considered the most suitable for marker selection for all populations. The selective phenotyping based on makers in all cases had higher values of prediction ability compared to minimal values of prediction ability of multiple cycles of random selection, with the highest values of prediction obtained using AN approach and 75% population size. The obtained results indicate that selective genotyping and phenotyping hold great potential and can be integrated as tools for improving or retaining selection accuracy by reducing genotyping or phenotyping costs for genomic selection.

Evaluating and Predicting the Performance of Sorghum Lines in an Elite by Exotic Backcross-Nested Association Mapping Population.

Maintaining or introducing genetic diversity into plant breeding programs is necessary for continual genetic gain; however, diversity at the cost of reduced performance is not something sought by breeders. To this end, backcross-nested association mapping (BC-NAM) populations, in which the recurrent parent is an elite line, can be employed as a strategy to introgress diversity from unadapted accessions while maintaining agronomic performance. This study evaluates (i) the hybrid performance of sorghum lines from 18 BC1-NAM families and (ii) the potential of genomic prediction to screen lines from BC1-NAM families for hybrid performance prior to phenotypic evaluation. Despite the diverse geographical origins and agronomic performance of the unadapted parents for BC1-NAM families, many BC1-derived lines performed significantly better in the hybrid trials than the elite recurrent parent, R.Tx436. The genomic prediction accuracies for grain yield, plant height, and days to mid-anthesis were acceptable, but the prediction accuracies for plant height were lower than expected. While the prediction accuracies increased when including more individuals in the training set, improvements tended to plateau between two and five lines per family, with larger training sets being required for more complex traits such as grain yield. Therefore, genomic prediction models can be optimized in a large BC1-NAM population with a relatively low fraction of individuals needing to be evaluated. These results suggest that genomic prediction is an effective method of pre-screening lines within BC1-NAM families prior to evaluation in extensive hybrid field trials.

Integration of genome-wide association and genomic prediction for dissecting seed protein and amino acid in foxtail millet

ContextThe exploitation and utilization of genetic variation in crop germplasm benefit genomics-informed breeding programs. The integration of genome-wide association study (GWAS) and genomic prediction (GP) holds promise for illustrating genetic basis of phenotypic variation. Currently, the use of this integrative approach for dissecting grain protein and amino acid traits remains limited in crop species. ObjectiveThe research objectives were to identify significant single nucleotide polymorphisms (SNPs) associated with seed protein and amino acids and to assess the genomic predictive ability for nutritional traits in natural population of foxtail millet. MethodsIn this study, the concentrations of seed protein and 17 amino acids were assessed in a training population consisting of 238 diverse accessions of foxtail millet. The significant SNPs associated with these phenotypes were identified by GWAS with a mix-linear model. Extensive cross-validation was performed to evaluate the accuracy of genomic prediction of seed nutritional traits. Furthermore, the genomic prediction model was optimized and externally validated in 211 untested materials with the most significant SNPs obtained from GWAS. ResultsA significant genotype variance was detected for seed protein and amino acids and broad-sense heritability (h2) ranged from 0.45 to 0.87 (P < 0.05). The GWAS identified 39 significant SNPs associated with 15 amino acids (p < 1e-06), explaining an average of 12.2% phenotypic variation per locus. The number of significant SNPs ranged from 1 (Asp, Ile, Glu) to 23 for Phe amino acid, including six SNPs associated with one or multiple amino acids. In the training population, the prediction accuracies of protein and amino acids, tested using the 10-fold cross-validation model with whole genome-wide SNPs, ranged from 0.23 (Glu) to 0.60 (Lys) with an average value of 0.44%. Population structure had little effect on the prediction accuracy. In an empirical validation experiment involving 211 untested accessions, the averaged prediction accuracy increased by 12.3% across all traits when using the 1000 top SNPs obtained from GWAS, compared with the same number of randomly selected SNPs from the entire genome. ConclusionsLarge variations of seed protein and amino acids were found in a natural population of foxtail millet. GWAS identified 39 significant SNPs associated with 15 amino acids, and six SNPs were linked to more than one trait. The 10-fold cross-validation model produced the relatively higher prediction accuracies in seed quality traits of diverse accessions. By applying the significant SNPs from GWAS to the untested accessions, the use of 1000 GWAS-top SNPs resulted in more powerful predictions for complex nutritional traits than those using the same number of randomly selected SNPs across the genome. SignificanceThe research highlights the importance and effectiveness of integrative GWAS and genomic prediction in revealing the genetic architecture of seed protein and amino acid variation in foxtail millet. The results provide valuable insights into assessment and improvement of germplasm resources for advancing precision crop phenotyping and enhancing breeding programs for crop nutritional traits.

Genetic factors underlying host resistance to Rhipicephalus microplus tick infestation in Braford cattle: a systems biology perspective.

Approximately 80% of the world's cattle are raised in regions with a high risk of tick-borne diseases, resulting in significant economic losses due to parasitism by Rhipicephalus (Boophilus) microplus. However, the lack of a systemic biology approach hampers a comprehensive understanding of tick-host interactions that mediate tick resistance phenotypes. Here, we conducted a genome-wide association study (GWAS) of 2933 Braford cattle and found 340 single-nucleotide polymorphisms (SNPs) associated with tick counts. Gene expression analyses were performed on skin samples obtained from previously tick-exposed heifers with extremely high or low estimated breeding values for R. microplus counts. Evaluations were performed both before and after artificial infestation with ticks. Differentially expressed genes were found within 1-Mb windows centered at significant SNPs from GWAS. A total of 330 genes were related to the breakdown of homeostasis that was induced by larval attachment to bovine skin. Enrichment analysis pointed to a key role of proteolysis and signal transduction via JAK/STAT, NFKB and WNT/beta catenin signaling pathways. Integrative analysis on matrixEQTL revealed two cis-eQTLs and four significant SNPs in the genes peptidyl arginine deiminase type IV (PADI4) and LOC11449251. The integration of genomic data from QTL maps and transcriptome analyses has identified a set of twelve key genes that show significant associations with tick loads. These genes could be key candidates to improve the accuracy of genomic predictions for tick resistance in Braford cattle.

Genome-wide association mapping and genomic prediction of stalk rot in two mid-altitude tropical maize populations

Maize stalk rot reduces grain yield and quality. Information about the genetics of resistance to maize stalk rot could help breeders design effective breeding strategies for the trait. Genomic prediction may be a more effective breeding strategy for stalk-rot resistance than marker-assisted selection. We performed a genome-wide association study (GWAS) and genomic prediction of resistance in testcross hybrids of 677 inbred lines from the Tuxpeño and non-Tuxpeño heterotic pools grown in three environments and genotyped with 200,681 single-nucleotide polymorphisms (SNPs). Eighteen SNPs associated with stalk rot shared genomic regions with gene families previously associated with plant biotic and abiotic responses. More favorable SNP haplotypes traced to tropical than to temperate progenitors of the inbred lines. Incorporating genotype-by-environment (G × E) interaction increased genomic prediction accuracy.

Genomic dissection of the correlation between milk yield and various health traits using functional and evolutionary information about imputed sequence variants of 34,497 German Holstein cows

BackgroundOver the last decades, it was subject of many studies to investigate the genomic connection of milk production and health traits in dairy cattle. Thereby, incorporating functional information in genomic analyses has been shown to improve the understanding of biological and molecular mechanisms shaping complex traits and the accuracies of genomic prediction, especially in small populations and across-breed settings. Still, little is known about the contribution of different functional and evolutionary genome partitioning subsets to milk production and dairy health. Thus, we performed a uni- and a bivariate analysis of milk yield (MY) and eight health traits using a set of ~34,497 German Holstein cows with 50K chip genotypes and ~17 million imputed sequence variants divided into 27 subsets depending on their functional and evolutionary annotation. In the bivariate analysis, eight trait-combinations were observed that contrasted MY with each health trait. Two genomic relationship matrices (GRM) were included, one consisting of the 50K chip variants and one consisting of each set of subset variants, to obtain subset heritabilities and genetic correlations. In addition, 50K chip heritabilities and genetic correlations were estimated applying merely the 50K GRM.ResultsIn general, 50K chip heritabilities were larger than the subset heritabilities. The largest heritabilities were found for MY, which was 0.4358 for the 50K and 0.2757 for the subset heritabilities. Whereas all 50K genetic correlations were negative, subset genetic correlations were both, positive and negative (ranging from -0.9324 between MY and mastitis to 0.6662 between MY and digital dermatitis). The subsets containing variants which were annotated as noncoding related, splice sites, untranslated regions, metabolic quantitative trait loci, and young variants ranked highest in terms of their contribution to the traits’ genetic variance. We were able to show that linkage disequilibrium between subset variants and adjacent variants did not cause these subsets’ high effect.ConclusionOur results confirm the connection of milk production and health traits in dairy cattle via the animals’ metabolic state. In addition, they highlight the potential of including functional information in genomic analyses, which helps to dissect the extent and direction of the observed traits’ connection in more detail.

Deep learning methods improve genomic prediction of wheat breeding.

In the field of plant breeding, various machine learning models have been developed and studied to evaluate the genomic prediction (GP) accuracy of unseen phenotypes. Deep learning has shown promise. However, most studies on deep learning in plant breeding have been limited to small datasets, and only a few have explored its application in moderate-sized datasets. In this study, we aimed to address this limitation by utilizing a moderately large dataset. We examined the performance of a deep learning (DL) model and compared it with the widely used and powerful best linear unbiased prediction (GBLUP) model. The goal was to assess the GP accuracy in the context of a five-fold cross-validation strategy and when predicting complete environments using the DL model. The results revealed the DL model outperformed the GBLUP model in terms of GP accuracy for two out of the five included traits in the five-fold cross-validation strategy, with similar results in the other traits. This indicates the superiority of the DL model in predicting these specific traits. Furthermore, when predicting complete environments using the leave-one-environment-out (LOEO) approach, the DL model demonstrated competitive performance. It is worth noting that the DL model employed in this study extends a previously proposed multi-modal DL model, which had been primarily applied to image data but with small datasets. By utilizing a moderately large dataset, we were able to evaluate the performance and potential of the DL model in a context with more information and challenging scenario in plant breeding.

Feed efficiency of dairy cattle as genetic trait

This review article is devoted to the use of feed efficiency traits in dairy cattle breeding. An efficient cow is defined as the one that produces the same amount of milk and milk solids while consuming less feed and remaining healthy and fertile; thus, allowing to reduce costs without decrease in production. Improving feed efficiency is economically important due to the increasing price of fodder. Feed efficiency is a genetically complex trait that can be described as units of product output (e.g., milk yield) per unit of feed input. Nowadays genetic evaluation of dairy cattle for feed efficiency is routinely conducted in several countries, including Australia, USA, Canada, Netherlands, Denmark, Sweden, Finland, Norway and United Kingdom. Different countries use different measures of feed efficiency of dairy cows. The main feed efficiency traits are dry matter intake, gross feed efficiency, residual feed intake, energy balance and feed saved. Genome-wide association studies demonstrated that feed efficiency in polygenic trait. Nevertheless, several genes with large effects on feed efficiency were identified. Estimates of heritability of these traits vary from 0.07 to 0.49 and show the presence of considerable genetic variation of these traits and therefore, the possibility of their genetic improvement under the conditions of inclusion in breeding programs. Changes in diet and rumen microbiome substantially impact feed efficiency of dairy cows. Feed efficiency is related to methane emissions and excess nitrogen excretion. Genetic improvement of feed efficiency requires recording of individual data on feed intake in cows. Such data are limited. Two options exist to solve this problem: use of indirect predictors and genomic prediction. Accuracy of genomic prediction varies from 0.21 to 0.61 across countries. International cooperative pro­jects such as Efficient Dairy Genome Project in Canada were launched to establish large databases and to increase accuracy of feed efficiency traits genomic prediction. Future directions of research are the use of novel technologies: mid-infrared spectroscopy, artificial intelligence, holo-omics.

Enhancing the genomic prediction accuracy of swine agricultural economic traits using an expanded one-hot encoding in CNN models1

Deep learning (DL) methods like Multilayer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs) have been applied to predict the complex traits in animal and plant breeding. However, improving the genomic prediction accuracy still presents significant challenges. In this study, we applied CNNs to predict swine traits using previously published data. Specifically, we extensively evaluated the CNN model’s performance by employing various sets of Single Nucleotide Polymorphisms (SNPs) and concluded that the CNN model achieved optimal performance when utilizing SNP sets comprising 1,000 SNPs. Furthermore, we adopted a novel approach using the one-hot encoding method that transforms the 16 different genotypes into sets of eight binary variables. This innovative encoding method significantly enhanced the CNN’s prediction accuracy for swine traits, outperforming the traditional one-hot encoding techniques. Our findings suggest that the expanded one-hot encode method can improve the accuracy of DL methods in the genomic prediction of swine agricultural economic traits. This discovery has significant implications for swine breeding programs, where genomic prediction is pivotal in improving breeding strategies. Furthermore, future research endeavors can explore additional enhancements to DL methods by incorporating advanced data pre-processing techniques.

Insight into a two‐part plant breeding scheme through Bayesian optimization of budget allocations

AbstractThe total budget of a breeding program must be divided across its different parts to maximize gain. How to optimize budget allocations for a two‐part strategy breeding scheme is an unsolved problem. We used Bayesian optimization coupled with stochastic simulations of breeding schemes to determine budget allocations that maximized gain. The breeding schemes focused on a clonal crop and included a population improvement cycle (PIC) allowing one or two breeding cycles per year leading to phenotypic evaluations in a variety development pipeline (VDP) with three stages. The gain was maximized at target years 6 or 12 after initiation of genomic selection. The breeding scheme was simulated using the AlphaSimR package. Bayesian optimization was implemented using the BoTorch module of Python to optimize budget allocations to the PIC and each stage of the VDP. Allocations to the last stage of the VDP were small because information from that stage was relatively ineffective at improving genomic prediction accuracy. An unexpected interaction between the number of PIC cycles and the target year for gain affected the budget of the PIC and could be explained by conflicting needs to increase gain in the VDP or increase genomic prediction accuracy. Divergent budget allocations could generate selection gains close to the maximum, indicating some leeway in the design of breeding schemes. Simple rules of thumb for heuristic optimization did not emerge, suggesting that breeders will need to rely on simulation coupled to optimization.

Envirotyping can increase genomic prediction accuracy of new environments in grain sorghum trials depending on mega‐environment

AbstractGrain sorghum [Sorghum bicolor (L.) Moench] is an important crop native to Africa and grown in many subtropical and temperate regions worldwide. The variability in production environments underscores the plasticity of sorghum genotypes and provides an opportunity to predict sorghum hybrid performance in novel environments. Reaction norms informed by envirotype data can aid in modeling the differential responses of genotypes across multi‐environment trials and ultimately increase the prediction accuracies of hybrid performance. In this study, a combination of genomic and enviromic information was applied to predict grain sorghum hybrid performance across United States sorghum production environments. Seven models based on additive, dominance, environment, and envirotype effects in two forms, and their interactions were tested under three cross‐validation schemes that simulate genomic prediction scenarios encountered by breeding programs. Relationship matrices for hybrids and environments were created from molecular and envirotypic data, respectively, to predict hybrid performance under a hierarchal Bayesian framework. When predicting unobserved environments, the envirotypic reaction norm model based on typologies produced the highest prediction accuracies for every temperate environment, but results vary in the subtropical environments, which has not been demonstrated in prior enviromic research. This study also demonstrated for the first time that envirotype data can effectively define established United States sorghum production regions and may assist breeders in resource allocation. Results support using sparse hybrid trials when breeding programs apply genomic predictions. Therefore, envirotype‐assisted genomic prediction models can expand the information available to a sorghum breeding program and aid breeders in efficiently designing hybrid trials.

Quantitative trait loci and genomic prediction for grain sugar and mineral concentrations of cowpea [Vigna unguiculata (L.) Walp.

Development of high yielding cowpea varieties coupled with good taste and rich in essential minerals can promote consumption and thus nutrition and profitability. The sweet taste of cowpea grain is determined by its sugar content, which comprises mainly sucrose and galacto-oligosaccharides (GOS) including raffinose and stachyose. However, GOS are indigestible and their fermentation in the colon can produce excess intestinal gas, causing undesirable bloating and flatulence. In this study, we aimed to examine variation in grain sugar and mineral concentrations, then map quantitative trait loci (QTLs) and estimate genomic-prediction (GP) accuracies for possible application in breeding. Grain samples were collected from a multi-parent advanced generation intercross (MAGIC) population grown in California during 2016-2017. Grain sugars were assayed using high-performance liquid chromatography. Grain minerals were determined by inductively coupled plasma-optical emission spectrometry and combustion. Considerable variation was observed for sucrose (0.6-6.9%) and stachyose (2.3-8.4%). Major QTLs for sucrose (QSuc.vu-1.1), stachyose (QSta.vu-7.1), copper (QCu.vu-1.1) and manganese (QMn.vu-5.1) were identified. Allelic effects of major sugar QTLs were validated using the MAGIC grain samples grown in West Africa in 2017. GP accuracies for minerals were moderate (0.4-0.58). These findings help guide future breeding efforts to develop mineral-rich cowpea varieties with desirable sugar content.

Machine learning methods for genomic prediction of cow behavioral traits measured by automatic milking systems in North American Holstein cattle

Identifying genome-enabled methods that provide more accurate genomic prediction is crucial when evaluating complex traits such as dairy cow behavior. In this study, we aimed to compare the predictive performance of traditional genomic prediction methods and deep learning algorithms for genomic prediction of milking refusals (MREF) and milking failures (MFAIL) in North American Holstein cows measured by automatic milking systems (milking robots). A total of 1,993,509 daily records from 4,511 genotyped Holstein cows were collected by 36 milking robot stations. After quality control, 57,600 single nucleotide polymorphisms (SNP) were available for the analyses. Four genomic prediction methods were considered: Bayesian Lasso (LASSO), Multiple Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Genomic Best Linear Unbiased Prediction (GBLUP). We implemented the first 3 methods using the Keras and TensorFlow libraries in Python (v.3.9) while the GBLUP method was implemented using the BLUPF90+ family programs. The accuracy of genomic prediction (Mean Square Error) for MREF and MFAIL was 0.34 (0.08) and 0.27 (0.08) based on LASSO, 0.36 (0.09) and 0.32 (0.09) for MLP, 0.37 (0.08) and 0.30 (0.09) for CNN, and 0.35 (0.09) and 0.31(0.09) based on GBLUP, respectively. Additionally, we observed a lower re-ranking of top selected individuals based on the MLP versus CNN methods compared with the other approaches for both MREF and MFAIL. Although the deep learning methods showed slightly higher accuracies than GBLUP, the results may not be sufficient to justify their use over traditional methods due to their higher computational demand and the difficulty of performing genomic prediction for non-genotyped individuals using deep learning procedures. Overall, this study provides insights into the potential feasibility of using deep learning methods to enhance genomic prediction accuracy for behavioral traits in livestock. Further research is needed to determine their practical applicability to large dairy cattle breeding programs.