Multi-environment Genomic Prediction of Plant Traits Using Deep Learners With Dense Architecture

A review of multimodal deep learning methods for genomic-enabled prediction in plant breeding

Deep learning methods have been applied when working to enhance the prediction accuracy of traditional statistical methods in the field of plant breeding. Although deep learning seems to be a promising approach for genomic prediction, it has proven to have some limitations, since its conventional methods fail to leverage all available information. Multimodal deep learning methods aim to improve the predictive power of their unimodal counterparts by introducing several modalities (sources) of input information. In this review, we introduce some theoretical basic concepts of multimodal deep learning and provide a list of the most widely used neural network architectures in deep learning, as well as the available strategies to fuse data from different modalities. We mention some of the available computational resources for the practical implementation of multimodal deep learning problems. We finally performed a review of applications of multimodal deep learning to genomic selection in plant breeding and other related fields. We present a meta-picture of the practical performance of multimodal deep learning methods to highlight how these tools can help address complex problems in the field of plant breeding. We discussed some relevant considerations that researchers should keep in mind when applying multimodal deep learning methods. Multimodal deep learning holds significant potential for various fields, including genomic selection. While multimodal deep learning displays enhanced prediction capabilities over unimodal deep learning and other machine learning methods, it demands more computational resources. Multimodal deep learning effectively captures intermodal interactions, especially when integrating data from different sources. To apply multimodal deep learning in genomic selection, suitable architectures and fusion strategies must be chosen. It is relevant to keep in mind that multimodal deep learning, like unimodal deep learning, is a powerful tool but should be carefully applied. Given its predictive edge over traditional methods, multimodal deep learning is valuable in addressing challenges in plant breeding and food security amid a growing global population.

Big data and artificial intelligence-aided crop breeding: Progress and prospects

The past decade has witnessed rapid developments in gene discovery, biological big data (BBD), artificial intelligence (AI)-aided technologies, and molecular breeding. These advancements are expected to accelerate crop breeding under the pressure of increasing demands for food. Here, we first summarize current breeding methods and discuss the need for new ways to support breeding efforts. Then, we review how to combine BBD and AI technologies for genetic dissection, exploring functional genes, predicting regulatory elements and functional domains, and phenotypic prediction. Finally, we propose the concept of intelligent precision design breeding (IPDB) driven by AI technology and offer ideas about how to implement IPDB. We hope that IPDB will enhance the predictability, efficiency, and cost of crop breeding compared with current technologies. As an example of IPDB, we explore the possibilities offered by CropGPT, which combines biological techniques, bioinformatics, and breeding art from breeders, and presents an open, shareable, and cooperative breeding system. IPDB provides integrated services and communication platforms for biologists, bioinformatics experts, germplasm resource specialists, breeders, dealers, and farmers, and should be well suited for future breeding.

Genomic prediction of yield-related traits and genome-based establishment of heterotic pattern in maize hybrid breeding of Southwest China

When genomic prediction is implemented in breeding maize (Zea mays L.), it can accelerate the breeding process and reduce cost to a large extent. In this study, 11 yield-related traits of maize were used to evaluate four genomic prediction methods including rrBLUP, HEBLP|A, RF, and LightGBM. In all the 11 traits, rrBLUP had similar predictive accuracy to HEBLP|A, and so did RF to LightGBM, but rrBLUP and HEBLP|A outperformed RF and LightGBM in 8 traits. Furthermore, genomic prediction-based heterotic pattern of yield was established based on 64620 crosses of maize in Southwest China, and the result showed that one of the parent lines of the top 5% crosses came from temp-tropic or tropic germplasm, which is highly consistent with the actual situation in breeding, and that heterotic pattern (Reid+ × Suwan+) will be a major heterotic pattern of Southwest China in the future.

Evaluation of deep learning for predicting rice traits using structural and single-nucleotide genomic variants

BACKGROUND

Structural genomic variants (SVs) are prevalent in plant genomes and have played an important role in evolution and domestication, as they constitute a significant source of genomic and phenotypic variability. Nevertheless, most methods in quantitative genetics focusing on crop improvement, such as genomic prediction, consider only Single Nucleotide Polymorphisms (SNPs). Deep Learning (DL) is a promising strategy for genomic prediction, but its performance using SVs and SNPs as genetic markers remains unknown.

RESULTS

We used rice to investigate whether combining SVs and SNPs can result in better trait prediction over SNPs alone and examine the potential advantage of Deep Learning (DL) networks over Bayesian Linear models. Specifically, the performances of BayesC (considering additive effects) and a Bayesian Reproducible Kernel Hilbert space (RKHS) regression (considering both additive and non-additive effects) were compared to those of two different DL architectures, the Multilayer Perceptron, and the Convolution Neural Network, to explore their prediction ability by using various marker input strategies. We found that exploiting structural and nucleotide variation slightly improved prediction ability on complex traits in 87% of the cases. DL models outperformed Bayesian models in 75% of the studied cases, considering the four traits and the two validation strategies used. Finally, DL systematically improved prediction ability of binary traits against the Bayesian models.

CONCLUSIONS

Our study reveals that the use of structural genomic variants can improve trait prediction in rice, independently of the methodology used. Also, our results suggest that Deep Learning (DL) networks can perform better than Bayesian models in the prediction of binary traits, and in quantitative traits when the training and target sets are not closely related. This highlights the potential of DL to enhance crop improvement in specific scenarios and the importance to consider SVs in addition to SNPs in genomic selection.

Wheat genetic resources have avoided disease pandemics, improved food security, and reduced environmental footprints: A review of historical impacts and future opportunities

The use of plant genetic resources (PGR)-wild relatives, landraces, and isolated breeding gene pools-has had substantial impacts on wheat breeding for resistance to biotic and abiotic stresses, while increasing nutritional value, end-use quality, and grain yield. In the Global South, post-Green Revolution genetic yield gains are generally achieved with minimal additional inputs. As a result, production has increased, and millions of hectares of natural ecosystems have been spared. Without PGR-derived disease resistance, fungicide use would have easily doubled, massively increasing selection pressure for fungicide resistance. It is estimated that in wheat, a billion liters of fungicide application have been avoided just since 2000. This review presents examples of successful use of PGR including the relentless battle against wheat rust epidemics/pandemics, defending against diseases that jump species barriers like blast, biofortification giving nutrient-dense varieties and the use of novel genetic variation for improving polygenic traits like climate resilience. Crop breeding genepools urgently need to be diversified to increase yields across a range of environments (>200 Mha globally), under less predictable weather and biotic stress pressure, while increasing input use efficiency. Given that the ~0.8 m PGR in wheat collections worldwide are relatively untapped and massive impacts of the tiny fraction studied, larger scale screenings and introgression promise solutions to emerging challenges, facilitated by advanced phenomic and genomic tools. The first translocations in wheat to modify rhizosphere microbiome interaction (reducing biological nitrification, reducing greenhouse gases, and increasing nitrogen use efficiency) is a landmark proof of concept. Phenomics and next-generation sequencing have already elucidated exotic haplotypes associated with biotic and complex abiotic traits now mainstreamed in breeding. Big data from decades of global yield trials can elucidate the benefits of PGR across environments. This kind of impact cannot be achieved without widescale sharing of germplasm and other breeding technologies through networks and public-private partnerships in a pre-competitive space.

Linking genetic markers and crop model parameters using neural networks to enhance genomic prediction of integrative traits

Introduction

Predicting the performance (yield or other integrative traits) of cultivated plants is complex because it involves not only estimating the genetic value of the candidates to selection, the interactions between the genotype and the environment (GxE) but also the epistatic interactions between genomic regions for a given trait, and the interactions between the traits contributing to the integrative trait. Classical Genomic Prediction (GP) models mostly account for additive effects and are not suitable to estimate non-additive effects such as epistasis. Therefore, the use of machine learning and deep learning methods has been previously proposed to model those non-linear effects.

Methods

In this study, we propose a type of Artificial Neural Network (ANN) called Convolutional Neural Network (CNN) and compare it to two classical GP regression methods for their ability to predict an integrative trait of sorghum: aboveground fresh weight accumulation. We also suggest that the use of a crop growth model (CGM) can enhance predictions of integrative traits by decomposing them into more heritable intermediate traits.

Results

The results show that CNN outperformed both LASSO and Bayes C methods in accuracy, suggesting that CNN are better suited to predict integrative traits. Furthermore, the predictive ability of the combined CGM-GP approach surpassed that of GP without the CGM integration, irrespective of the regression method used.

Discussion

These results are consistent with recent works aiming to develop Genome-to-Phenotype models and advocate for the use of non-linear prediction methods, and the use of combined CGM-GP to enhance the prediction of crop performances.

Near-infrared reflectance spectroscopy phenomic prediction can perform similarly to genomic prediction of maize agronomic traits across environments

For nearly two decades, genomic prediction and selection have supported efforts to increase genetic gains in plant and animal improvement programs. However, novel phenomic strategies for predicting complex traits in maize have recently proven beneficial when integrated into across-environment sparse genomic prediction models. One phenomic data modality is whole grain near-infrared spectroscopy (NIRS), which records reflectance values of biological samples (e.g., maize kernels) based on chemical composition. Predictions of hybrid maize grain yield (GY) and 500-kernel weight (KW) across 2 years (2011-2012) and two management conditions (water-stressed and well-watered) were conducted using combinations of reflectance data obtained from high-throughput, F2 whole-kernel scans and genomic data obtained from genotyping-by-sequencing within four different cross-validation (CV) schemes (CV2, CV1, CV0, and CV00). When predicting the performance of untested genotypes in characterized (CV1) environments, genomic data were better than phenomic data for GY (0.689 ± 0.024-genomic vs. 0.612 ± 0.045-phenomic), but phenomic data were better than genomic data for KW (0.535 ± 0.034-genomic vs. 0.617 ± 0.145-phenomic). Multi-kernel models (combinations of phenomic and genomic relationship matrices) did not surpass single-kernel models for GY prediction in CV1 or CV00 (prediction of untested genotypes in uncharacterized environments); however, these models did outperform the single-kernel models for prediction of KW in these same CVs. Lasso regression applied to the NIRS data set selected a subset of 216 NIRS bands that achieved comparable prediction abilities to the full phenomic data set of 3112 bands predicting GY and KW under CV1 and CV00.

Abiotic Stress Tolerance Boosted by Genetic Diversity in Plants

Plant breeding [...].

Genomic prediction using machine learning: a comparison of the performance of regularized regression, ensemble, instance-based and deep learning methods on synthetic and empirical data

BACKGROUND

The accurate prediction of genomic breeding values is central to genomic selection in both plant and animal breeding studies. Genomic prediction involves the use of thousands of molecular markers spanning the entire genome and therefore requires methods able to efficiently handle high dimensional data. Not surprisingly, machine learning methods are becoming widely advocated for and used in genomic prediction studies. These methods encompass different groups of supervised and unsupervised learning methods. Although several studies have compared the predictive performances of individual methods, studies comparing the predictive performance of different groups of methods are rare. However, such studies are crucial for identifying (i) groups of methods with superior genomic predictive performance and assessing (ii) the merits and demerits of such groups of methods relative to each other and to the established classical methods. Here, we comparatively evaluate the genomic predictive performance and informally assess the computational cost of several groups of supervised machine learning methods, specifically, regularized regression methods, deep, ensemble and instance-based learning algorithms, using one simulated animal breeding dataset and three empirical maize breeding datasets obtained from a commercial breeding program.

RESULTS

Our results show that the relative predictive performance and computational expense of the groups of machine learning methods depend upon both the data and target traits and that for classical regularized methods, increasing model complexity can incur huge computational costs but does not necessarily always improve predictive accuracy. Thus, despite their greater complexity and computational burden, neither the adaptive nor the group regularized methods clearly improved upon the results of their simple regularized counterparts. This rules out selection of one procedure among machine learning methods for routine use in genomic prediction. The results also show that, because of their competitive predictive performance, computational efficiency, simplicity and therefore relatively few tuning parameters, the classical linear mixed model and regularized regression methods are likely to remain strong contenders for genomic prediction.

CONCLUSIONS

The dependence of predictive performance and computational burden on target datasets and traits call for increasing investments in enhancing the computational efficiency of machine learning algorithms and computing resources.

Genomic prediction with machine learning in sugarcane, a complex highly polyploid clonally propagated crop with substantial non-additive variation for key traits

Sugarcane has a complex, highly polyploid genome with multi-species ancestry. Additive models for genomic prediction of clonal performance might not capture interactions between genes and alleles from different ploidies and ancestral species. As such, genomic prediction in sugarcane presents an interesting case for machine learning (ML) methods, which are purportedly able to deal with high levels of complexity in prediction. Here, we investigated deep learning (DL) neural networks, including multilayer networks (MLP) and convolution neural networks (CNN), and an ensemble machine learning approach, random forest (RF), for genomic prediction in sugarcane. The data set used was 2912 sugarcane clones, scored for 26,086 genome wide single nucleotide polymorphism markers, with final assessment trial data for total cane harvested (TCH), commercial cane sugar (CCS), and fiber content (Fiber). The clones in the latest trial (2017) were used as a validation set. We compared prediction accuracy of these methods to genomic best linear unbiased prediction (GBLUP) extended to include dominance and epistatic effects. The prediction accuracies from GBLUP models were up to 0.37 for TCH, 0.43 for CCS, and 0.48 for Fiber, while the optimized ML models had prediction accuracies of 0.35 for TCH, 0.38 for CCS, and 0.48 for Fiber. Both RF and DL neural network models have comparable predictive ability with the additive GBLUP model but are less accurate than the extended GBLUP model.

Accurate prediction of quantitative traits with failed SNP calls in canola and maize

In modern plant breeding, genomic selection is becoming the gold standard to select superior genotypes in large breeding populations that are only partially phenotyped. Many breeding programs commonly rely on single-nucleotide polymorphism (SNP) markers to capture genome-wide data for selection candidates. For this purpose, SNP arrays with moderate to high marker density represent a robust and cost-effective tool to generate reproducible, easy-to-handle, high-throughput genotype data from large-scale breeding populations. However, SNP arrays are prone to technical errors that lead to failed allele calls. To overcome this problem, failed calls are often imputed, based on the assumption that failed SNP calls are purely technical. However, this ignores the biological causes for failed calls-for example: deletions-and there is increasing evidence that gene presence-absence and other kinds of genome structural variants can play a role in phenotypic expression. Because deletions are frequently not in linkage disequilibrium with their flanking SNPs, permutation of missing SNP calls can potentially obscure valuable marker-trait associations. In this study, we analyze published datasets for canola and maize using four parametric and two machine learning models and demonstrate that failed allele calls in genomic prediction are highly predictive for important agronomic traits. We present two statistical pipelines, based on population structure and linkage disequilibrium, that enable the filtering of failed SNP calls that are likely caused by biological reasons. For the population and trait examined, prediction accuracy based on these filtered failed allele calls was competitive to standard SNP-based prediction, underlying the potential value of missing data in genomic prediction approaches. The combination of SNPs with all failed allele calls or the filtered allele calls did not outperform predictions with only SNP-based prediction due to redundancy in genomic relationship estimates.

Improved genomic prediction using machine learning with Variational Bayesian sparsity

BACKGROUND

Genomic prediction has become a powerful modelling tool for assessing line performance in plant and livestock breeding programmes. Among the genomic prediction modelling approaches, linear based models have proven to provide accurate predictions even when the number of genetic markers exceeds the number of data samples. However, breeding programmes are now compiling data from large numbers of lines and test environments for analyses, rendering these approaches computationally prohibitive. Machine learning (ML) now offers a solution to this problem through the construction of fully connected deep learning architectures and high parallelisation of the predictive task. However, the fully connected nature of these architectures immediately generates an over-parameterisation of the network that needs addressing for efficient and accurate predictions.

RESULTS

In this research we explore the use of an ML architecture governed by variational Bayesian sparsity in its initial layers that we have called VBS-ML. The use of VBS-ML provides a mechanism for feature selection of important markers linked to the trait, immediately reducing the network over-parameterisation. Selected markers then propagate to the remaining fully connected feed-forward components of the ML network to form the final genomic prediction. We illustrated the approach with four large Australian wheat breeding data sets that range from 2665 lines to 10375 lines genotyped across a large set of markers. For all data sets, the use of the VBS-ML architecture improved genomic prediction accuracy over legacy linear based modelling approaches.

CONCLUSIONS

An ML architecture governed under a variational Bayesian paradigm was shown to improve genomic prediction accuracy over legacy modelling approaches. This VBS-ML approach can be used to dramatically decrease the parameter burden on the network and provide a computationally feasible approach for improving genomic prediction conducted with large breeding population numbers and genetic markers.

The Progression in Developing Genomic Resources for Crop Improvement

Sequencing technologies have rapidly evolved over the past two decades, and new technologies are being continually developed and commercialized. The emerging sequencing technologies target generating more data with fewer inputs and at lower costs. This has also translated to an increase in the number and type of corresponding applications in genomics besides enhanced computational capacities (both hardware and software). Alongside the evolving DNA sequencing landscape, bioinformatics research teams have also evolved to accommodate the increasingly demanding techniques used to combine and interpret data, leading to many researchers moving from the lab to the computer. The rich history of DNA sequencing has paved the way for new insights and the development of new analysis methods. Understanding and learning from past technologies can help with the progress of future applications. This review focuses on the evolution of sequencing technologies, their significant enabling role in generating plant genome assemblies and downstream applications, and the parallel development of bioinformatics tools and skills, filling the gap in data analysis techniques.

deepGBLUP: joint deep learning networks and GBLUP framework for accurate genomic prediction of complex traits in Korean native cattle

BACKGROUND

Genomic prediction has become widespread as a valuable tool to estimate genetic merit in animal and plant breeding. Here we develop a novel genomic prediction algorithm, called deepGBLUP, which integrates deep learning networks and a genomic best linear unbiased prediction (GBLUP) framework. The deep learning networks assign marker effects using locally-connected layers and subsequently use them to estimate an initial genomic value through fully-connected layers. The GBLUP framework estimates three genomic values (additive, dominance, and epistasis) by leveraging respective genetic relationship matrices. Finally, deepGBLUP predicts a final genomic value by summing all the estimated genomic values.

RESULTS

We compared the proposed deepGBLUP with the conventional GBLUP and Bayesian methods. Extensive experiments demonstrate that the proposed deepGBLUP yields state-of-the-art performance on Korean native cattle data across diverse traits, marker densities, and training sizes. In addition, they show that the proposed deepGBLUP can outperform the previous methods on simulated data across various heritabilities and quantitative trait loci (QTL) effects.

CONCLUSIONS

We introduced a novel genomic prediction algorithm, deepGBLUP, which successfully integrates deep learning networks and GBLUP framework. Through comprehensive evaluations on the Korean native cattle data and simulated data, deepGBLUP consistently achieved superior performance across various traits, marker densities, training sizes, heritabilities, and QTL effects. Therefore, deepGBLUP is an efficient method to estimate an accurate genomic value. The source code and manual for deepGBLUP are available at https://github.com/gywns6287/deepGBLUP .

Forecasting trait responses in novel environments to aid seed provenancing under climate change

Revegetation projects face the major challenge of sourcing optimal plant material. This is often done with limited information about plant performance and increasingly requires factoring resilience to climate change. Functional traits can be used as quantitative indices of plant performance and guide seed provenancing, but trait values expected under novel conditions are often unknown. To support climate-resilient provenancing efforts, we develop a trait prediction model that integrates the effect of genetic variation with fine-scale temperature variation. We train our model on multiple field plantings of Arabidopsis thaliana and predict two relevant fitness traits-days-to-bolting and fecundity-across the species' European range. Prediction accuracy was high for days-to-bolting and moderate for fecundity, with the majority of trait variation explained by temperature differences between plantings. Projection under future climate predicted a decline in fecundity, although this response was heterogeneous across the range. In response, we identified novel genotypes that could be introduced to genetically offset the fitness decay. Our study highlights the value of predictive models to aid seed provenancing and improve the success of revegetation projects.

Comparing artificial-intelligence techniques with state-of-the-art parametric prediction models for predicting soybean traits

Soybean [Glycine max (L.) Merr.] is a significant source of protein and oil and is also widely used as animal feed. Thus, developing lines that are superior in terms of yield, protein, and oil content is important to feed the ever-growing population. As opposed to high-cost phenotyping, genotyping is both cost and time efficient for breeders because evaluating new lines in different environments (location-year combinations) can be costly. Several genomic prediction (GP) methods have been developed to use the marker and environment data effectively to predict the yield or other relevant phenotypic traits of crops. Our study compares a conventional GP method (genomic best linear unbiased predictor [GBLUP]), a kernel method (Gaussian kernel [GK]), an artificial-intelligence (AI) method (deep learning [DL]), and a hybrid method that corresponds to the emulation of a DL model using a kernel method (an arc-cosine kernel [AK]) in terms of their prediction accuracies for predicting grain yield, oil, and protein using data from the soybean nested association mapping experiment (1,379 genotypes tested in six environments, all genotypes in all environments). The relative performance of the four methods varied with the response variable and whether the model includes the genotype × environmental interaction (G×E) effects or not. The GBLUP consistently showed better performances, whereas GK and AK followed a similar pattern to GBLUP and DL performed slightly worse than the other three methods in most of the cases; however, this may also be attributed to suboptimal hyperparameters. The DL method performed particularly worse than the other three methods in presence of the G×E effects.

Multi-environment Genomic Selection in Rice Elite Breeding Lines

BACKGROUND

Assessing the performance of elite lines in target environments is essential for breeding programs to select the most relevant genotypes. One of the main complexities in this task resides in accounting for the genotype by environment interactions. Genomic prediction models that integrate information from multi-environment trials and environmental covariates can be efficient tools in this context. The objective of this study was to assess the predictive ability of different genomic prediction models to optimize the use of multi-environment information. We used 111 elite breeding lines representing the diversity of the international rice research institute breeding program for irrigated ecosystems. The lines were evaluated for three traits (days to flowering, plant height, and grain yield) in 15 environments in Asia and Africa and genotyped with 882 SNP markers. We evaluated the efficiency of genomic prediction to predict untested environments using seven multi-environment models and three cross-validation scenarios.

RESULTS

The elite lines were found to belong to the indica group and more specifically the indica-1B subgroup which gathered improved material originating from the Green Revolution. Phenotypic correlations between environments were high for days to flowering and plant height (33% and 54% of pairwise correlation greater than 0.5) but low for grain yield (lower than 0.2 in most cases). Clustering analyses based on environmental covariates separated Asia's and Africa's environments into different clusters or subclusters. The predictive abilities ranged from 0.06 to 0.79 for days to flowering, 0.25-0.88 for plant height, and - 0.29-0.62 for grain yield. We found that models integrating genotype-by-environment interaction effects did not perform significantly better than models integrating only main effects (genotypes and environment or environmental covariates). The different cross-validation scenarios showed that, in most cases, the use of all available environments gave better results than a subset.

CONCLUSION

Multi-environment genomic prediction models with main effects were sufficient for accurate phenotypic prediction of elite lines in targeted environments. These results will help refine the testing strategy to update the genomic prediction models to improve predictive ability.

Digitalizing breeding in plants: A new trend of next-generation breeding based on genomic prediction

As the world's population grows and food needs diversification, the demand for cereals and horticultural crops with beneficial traits increases. In order to meet a variety of demands, suitable cultivars and innovative breeding methods need to be developed. Breeding methods have changed over time following the advance of genetics. With the advent of new sequencing technology in the early 21st century, predictive breeding, such as genomic selection (GS), emerged when large-scale genomic information became available. GS shows good predictive ability for the selection of individuals with traits of interest even for quantitative traits by using various types of the whole genome-scanning markers, breaking away from the limitations of marker-assisted selection (MAS). In the current review, we briefly describe the history of breeding techniques, each breeding method, various statistical models applied to GS and methods to increase the GS efficiency. Consequently, we intend to propose and define the term digital breeding through this review article. Digital breeding is to develop a predictive breeding methods such as GS at a higher level, aiming to minimize human intervention by automatically proceeding breeding design, propagating breeding populations, and to make selections in consideration of various environments, climates, and topography during the breeding process. We also classified the phases of digital breeding based on the technologies and methods applied to each phase. This review paper will provide an understanding and a direction for the final evolution of plant breeding in the future.

Crop genomic selection with deep learning and environmental data: A survey

Machine learning techniques for crop genomic selections, especially for single-environment plants, are well-developed. These machine learning models, which use dense genome-wide markers to predict phenotype, routinely perform well on single-environment datasets, especially for complex traits affected by multiple markers. On the other hand, machine learning models for predicting crop phenotype, especially deep learning models, using datasets that span different environmental conditions, have only recently emerged. Models that can accept heterogeneous data sources, such as temperature, soil conditions and precipitation, are natural choices for modeling GxE in multi-environment prediction. Here, we review emerging deep learning techniques that incorporate environmental data directly into genomic selection models.

Modeling genotype × environment interaction for single and multitrait genomic prediction in potato (Solanum tuberosum L.)

In this study, we extend research on genomic prediction (GP) to polysomic polyploid plant species with the main objective to investigate single-trait (ST) and multitrait (MT) multienvironment (ME) models using field trial data from 3 locations in Sweden [Helgegården (HEL), Mosslunda (MOS), Umeå (UM)] over 2 years (2020, 2021) of 253 potato cultivars and breeding clones for 5 tuber weight traits and 2 tuber flesh quality characteristics. This research investigated the GP of 4 genome-based prediction models with genotype × environment interactions (GEs): (1) ST reaction norm model (M1), (2) ST model considering covariances between environments (M2), (3) ST M2 extended to include a random vector that utilizes the environmental covariances (M3), and (4) MT model with GE (M4). Several prediction problems were analyzed for each of the GP accuracy of the 4 models. Results of the prediction of traits in HEL, the high yield potential testing site in 2021, show that the best-predicted traits were tuber flesh starch (%), weight of tuber above 60 or below 40 mm in size, and the total tuber weight. In terms of GP, accuracy model M4 gave the best prediction accuracy in 3 traits, namely tuber weight of 40-50 or above 60 mm in size, and total tuber weight, and very similar in the starch trait. For MOS in 2021, the best predictive traits were starch, weight of tubers above 60, 50-60, or below 40 mm in size, and the total tuber weight. MT model M4 was the best GP model based on its accuracy when some cultivars are observed in some traits. For the GP accuracy of traits in UM in 2021, the best predictive traits were the weight of tubers above 60, 50-60, or below 40 mm in size, and the best model was MT M4, followed by models ST M3 and M2.

AM, Lukács BA, Barta Z, Maćków W, Wolski GJ. Comparison of discriminant methods and deep learning analysis in plant taxonomy: a case study of Elatine

Elatine is a genus in which, flower and seed characteristics are the most important diagnostic features; i.e. seed shape and the structure of its cover found to be the most reliable identification character. We used a combination of classic discriminant methods by combining with deep learning techniques to analyze seed morphometric data within 28 populations of six Elatine species from 11 countries throughout the Northern Hemisphere to compare the obtained results and then check their taxonomic classification. Our findings indicate that among the discriminant methods, Quadratic Discriminant Analysis (QDA) had the highest percentage of correct matching (mean fit-91.23%); only the deep machine learning method based on Convolutional Neural Network (CNN) was characterized by a higher match (mean fit-93.40%). The QDA method recognized the seeds of E. brochonii and E. orthosperma with 99% accuracy, and the CNN method with 100%. Other taxa, such as E. alsinastrum, E. trianda, E. californica and E. hungarica were matched with an accuracy of at least 95% (CNN). Our results indicate that the CNN obtains remarkably more accurate classifications than classic discriminant methods, and better recognizes the entire taxa pool analyzed. The least recognized species are E. macropoda and E. hexandra (88% and 78% match).

A comparison of classical and machine learning-based phenotype prediction methods on simulated data and three plant species

Genomic selection is an integral tool for breeders to accurately select plants directly from genotype data leading to faster and more resource-efficient breeding programs. Several prediction methods have been established in the last few years. These range from classical linear mixed models to complex non-linear machine learning approaches, such as Support Vector Regression, and modern deep learning-based architectures. Many of these methods have been extensively evaluated on different crop species with varying outcomes. In this work, our aim is to systematically compare 12 different phenotype prediction models, including basic genomic selection methods to more advanced deep learning-based techniques. More importantly, we assess the performance of these models on simulated phenotype data as well as on real-world data from Arabidopsis thaliana and two breeding datasets from soy and corn. The synthetic phenotypic data allow us to analyze all prediction models and especially the selected markers under controlled and predefined settings. We show that Bayes B and linear regression models with sparsity constraints perform best under different simulation settings with respect to explained variance. Further, we can confirm results from other studies that there is no superiority of more complex neural network-based architectures for phenotype prediction compared to well-established methods. However, on real-world data, for which several prediction models yield comparable results with slight advantages for Elastic Net, this picture is less clear, suggesting that there is a lot of room for future research.

Utilizing genomics and historical data to optimize gene pools for new breeding programs: A case study in winter wheat

With the rapid generation and preservation of both genomic and phenotypic information for many genotypes within crops and across locations, emerging breeding programs have a valuable opportunity to leverage these resources to 1) establish the most appropriate genetic foundation at program inception and 2) implement robust genomic prediction platforms that can effectively select future breeding lines. Integrating genomics-enabled¹ breeding into cultivar development can save costs and allow resources to be reallocated towards advanced (i.e., later) stages of field evaluation, which can facilitate an increased number of testing locations and replicates within locations. In this context, a reestablished winter wheat breeding program was used as a case study to understand best practices to leverage and tailor existing genomic and phenotypic resources to determine optimal genetics for a specific target population of environments. First, historical multi-environment phenotype data, representing 1,285 advanced breeding lines, were compiled from multi-institutional testing as part of the SunGrains cooperative and used to produce GGE biplots and PCA for yield. Locations were clustered based on highly correlated line performance among the target population of environments into 22 subsets. For each of the subsets generated, EMMs and BLUPs were calculated using linear models with the ‘lme4’ R package. Second, for each subset, TPs representative of the new SC breeding lines were determined based on genetic relatedness using the ‘STPGA’ R package. Third, for each TP, phenotypic values and SNP data were incorporated into the ‘rrBLUP’ mixed models for generation of GEBVs of YLD, TW, HD and PH. Using a five-fold cross-validation strategy, an average accuracy of r = 0.42 was obtained for yield between all TPs. The validation performed with 58 SC elite breeding lines resulted in an accuracy of r = 0.62 when the TP included complete historical data. Lastly, QTL-by-environment interaction for 18 major effect genes across three geographic regions was examined. Lines harboring major QTL in the absence of disease could potentially underperform (e.g., Fhb1 R-gene), whereas it is advantageous to express a major QTL under biotic pressure (e.g., stripe rust R-gene). This study highlights the importance of genomics-enabled breeding and multi-institutional partnerships to accelerate cultivar development.

Integrating a growth degree-days based reaction norm methodology and multi-trait modeling for genomic prediction in wheat

Multi-trait and multi-environment analyses can improve genomic prediction by exploiting between-trait correlations and genotype-by-environment interactions. In the context of reaction norm models, genotype-by-environment interactions can be described as functions of high-dimensional sets of markers and environmental covariates. However, comprehensive multi-trait reaction norm models accounting for marker × environmental covariates interactions are lacking. In this article, we propose to extend a reaction norm model incorporating genotype-by-environment interactions through (co)variance structures of markers and environmental covariates to a multi-trait reaction norm case. To do that, we propose a novel methodology for characterizing the environment at different growth stages based on growth degree-days (GDD). The proposed models were evaluated by variance components estimation and predictive performance for winter wheat grain yield and protein content in a set of 2,015 F6-lines. Cross-validation analyses were performed using leave-one-year-location-out (CV1) and leave-one-breeding-cycle-out (CV2) strategies. The modeling of genomic [SNPs] × environmental covariates interactions significantly improved predictive ability and reduced the variance inflation of predicted genetic values for grain yield and protein content in both cross-validation schemes. Trait-assisted genomic prediction was carried out for multi-trait models, and it significantly enhanced predictive ability and reduced variance inflation in all scenarios. The genotype by environment interaction modeling via genomic [SNPs] × environmental covariates interactions, combined with trait-assisted genomic prediction, boosted the benefits in predictive performance. The proposed multi-trait reaction norm methodology is a comprehensive approach that allows capitalizing on the benefits of multi-trait models accounting for between-trait correlations and reaction norm models exploiting high-dimensional genomic and environmental information.

A Review of Deep Learning Applications for the Next Generation of Cognitive Networks

Intelligence capabilities will be the cornerstone in the development of next-generation cognitive networks. These capabilities allow them to observe network conditions, learn from them, and then, using prior knowledge gained, respond to its operating environment to optimize network performance. This study aims to offer an overview of the current state of the art related to the use of deep learning in applications for intelligent cognitive networks that can serve as a reference for future initiatives in this field. For this, a systematic literature review was carried out in three databases, and eligible articles were selected that focused on using deep learning to solve challenges presented by current cognitive networks. As a result, 14 articles were analyzed. The results showed that applying algorithms based on deep learning to optimize cognitive data networks has been approached from different perspectives in recent years and in an experimental way to test its technological feasibility. In addition, its implications for solving fundamental challenges in current wireless networks are discussed.

Association Studies and Genomic Prediction for Genetic Improvements in Agriculture

To feed the fast growing global population with sufficient food using limited global resources, it is urgent to develop and utilize cutting-edge technologies and improve efficiency of agricultural production. In this review, we specifically introduce the concepts, theories, methods, applications and future implications of association studies and predicting unknown genetic value or future phenotypic events using genomics in the area of breeding in agriculture. Genome wide association studies can identify the quantitative genetic loci associated with phenotypes of importance in agriculture, while genomic prediction utilizes individual genetic value to rank selection candidates to improve the next generation of plants or animals. These technologies and methods have improved the efficiency of genetic improvement programs for agricultural production via elite animal breeds and plant varieties. With the development of new data acquisition technologies, there will be more and more data collected from high-through-put technologies to assist agricultural breeding. It will be crucial to extract useful information among these large amounts of data and to face this challenge, more efficient algorithms need to be developed and utilized for analyzing these data. Such development will require knowledge from multiple disciplines of research.

Plant Genotype to Phenotype Prediction Using Machine Learning

Genomic prediction tools support crop breeding based on statistical methods, such as the genomic best linear unbiased prediction (GBLUP). However, these tools are not designed to capture non-linear relationships within multi-dimensional datasets, or deal with high dimension datasets such as imagery collected by unmanned aerial vehicles. Machine learning (ML) algorithms have the potential to surpass the prediction accuracy of current tools used for genotype to phenotype prediction, due to their capacity to autonomously extract data features and represent their relationships at multiple levels of abstraction. This review addresses the challenges of applying statistical and machine learning methods for predicting phenotypic traits based on genetic markers, environment data, and imagery for crop breeding. We present the advantages and disadvantages of explainable model structures, discuss the potential of machine learning models for genotype to phenotype prediction in crop breeding, and the challenges, including the scarcity of high-quality datasets, inconsistent metadata annotation and the requirements of ML models.

Genome-Enabled Prediction Methods Based on Machine Learning

Growth of artificial intelligence and machine learning (ML) methodology has been explosive in recent years. In this class of procedures, computers get knowledge from sets of experiences and provide forecasts or classification. In genome-wide based prediction (GWP), many ML studies have been carried out. This chapter provides a description of main semiparametric and nonparametric algorithms used in GWP in animals and plants. Thirty-four ML comparative studies conducted in the last decade were used to develop a meta-analysis through a Thurstonian model, to evaluate algorithms with the best predictive qualities. It was found that some kernel, Bayesian, and ensemble methods displayed greater robustness and predictive ability. However, the type of study and data distribution must be considered in order to choose the most appropriate model for a given problem.

Machine Learning for Plant Stress Modeling: A Perspective towards Hormesis Management

Plant stress is one of the most significant factors affecting plant fitness and, consequently, food production. However, plant stress may also be profitable since it behaves hormetically; at low doses, it stimulates positive traits in crops, such as the synthesis of specialized metabolites and additional stress tolerance. The controlled exposure of crops to low doses of stressors is therefore called hormesis management, and it is a promising method to increase crop productivity and quality. Nevertheless, hormesis management has severe limitations derived from the complexity of plant physiological responses to stress. Many technological advances assist plant stress science in overcoming such limitations, which results in extensive datasets originating from the multiple layers of the plant defensive response. For that reason, artificial intelligence tools, particularly Machine Learning (ML) and Deep Learning (DL), have become crucial for processing and interpreting data to accurately model plant stress responses such as genomic variation, gene and protein expression, and metabolite biosynthesis. In this review, we discuss the most recent ML and DL applications in plant stress science, focusing on their potential for improving the development of hormesis management protocols.

Automated Machine Learning: A Case Study of Genomic "Image-Based" Prediction in Maize Hybrids

Machine learning methods such as multilayer perceptrons (MLP) and Convolutional Neural Networks (CNN) have emerged as promising methods for genomic prediction (GP). In this context, we assess the performance of MLP and CNN on regression and classification tasks in a case study with maize hybrids. The genomic information was provided to the MLP as a relationship matrix and to the CNN as "genomic images." In the regression task, the machine learning models were compared along with GBLUP. Under the classification task, MLP and CNN were compared. In this case, the traits (plant height and grain yield) were discretized in such a way to create balanced (moderate selection intensity) and unbalanced (extreme selection intensity) datasets for further evaluations. An automatic hyperparameter search for MLP and CNN was performed, and the best models were reported. For both task types, several metrics were calculated under a validation scheme to assess the effect of the prediction method and other variables. Overall, MLP and CNN presented competitive results to GBLUP. Also, we bring new insights on automated machine learning for genomic prediction and its implications to plant breeding.

Assessment of genomic prediction reliability and optimization of experimental designs in multi-environment trials

New forms of the coefficient of determination can help to forecast the accuracy of genomic prediction and optimize experimental designs in multi-environment trials with genotype-by-environment interactions. In multi-environment trials, the relative performance of genotypes may vary depending on the environmental conditions, and this phenomenon is commonly referred to as genotype-by-environment interaction (G[Formula: see text]E). With genomic prediction, G[Formula: see text]E can be accounted for by modeling the genetic covariance between trials, even when the overall experimental design is highly unbalanced between trials, thanks to the genomic relationship between genotypes. In this study, we propose new forms of the coefficient of determination (CD, i.e., the expected model-based square correlation between a genetic value and its corresponding prediction) that can be used to forecast the genomic prediction reliability of genotypes, both for their trial-specific performance and their mean performance. As the expected prediction reliability based on these new CD criteria is generally a good approximation of the observed reliability, we demonstrate that they can be used to optimize multi-environment trials in the presence of G[Formula: see text]E. In addition, this reliability may be highly variable between genotypes, especially in unbalanced designs with complex pedigree relationships between genotypes. Therefore, it can be useful for breeders to assess it before selecting genotypes based on their predicted genetic values. Using a wheat population evaluated both for simulated and phenology traits, and two maize populations evaluated for grain yield, we illustrate this approach and confirm the value of our new CD criteria.

Incorporating Omics Data in Genomic Prediction

In this chapter, we discuss the motivation for integrating other types of omics data into genomic prediction methods. We give an overview of literature investigating the performance of omics-enhanced predictions, and highlight potential pitfalls when applying these methods in breeding. We emphasize that the statistical methods available for genomic data can be transferred to the general omics case. However, when using a framework of omic relationship matrices, the standardization of the variables may be more relevant than it is for a genomic relationship matrix based on single-nucleotide polymorphisms.

Accounting for Correlation Between Traits in Genomic Prediction

Genomic enabled prediction is playing a key role for the success of genomic selection (GS). However, according to the No Free Lunch Theorem, there is not a universal model that performs well for all data sets. Due to this, many statistical and machine learning models are available for genomic prediction. When multitrait data is available, models that are able to account for correlations between phenotypic traits are preferred, since these models help increase the prediction accuracy when the degree of correlation is moderate to large. For this reason, in this chapter we review multitrait models for genome-enabled prediction and we illustrate the power of this model with real examples. In addition, we provide details of the software (R code) available for its application to help users implement these models with its own data. The multitrait models were implemented under conventional Bayesian Ridge regression and best linear unbiased predictor, but also under a deep learning framework. The multitrait deep learning framework helps implement prediction models with mixed outcomes (continuous, binary, ordinal, and count, measured on different scales), which is not easy in conventional statistical models. The illustrative examples are very detailed in order to make the implementation of multitrait models in plant and animal breeding friendlier for breeders and scientists.

Overview of Genomic Prediction Methods and the Associated Assumptions on the Variance of Marker Effect, and on the Architecture of the Target Trait

Genomic selection (GS) is a methodology that revolutionized the process of breeding improved genetic materials in plant and animal breeding programs. It uses predicted genomic values of the potential of untested/unobserved genotypes as surrogates of phenotypes during the selection process. Such that the predicted genomic values are obtained using exclusively the marker profiles of the untested genotypes, and these potentially can be used by breeders for screening the genotypes to be advanced in the breeding pipeline, to identify potential parents for next improvement cycles, or to find optimal crosses for targeting genotypes among others. Conceptually, GS initially requires a set of genotypes with both molecular marker information and phenotypic data for model calibration and then the performance of untested genotypes is predicted using their marker profiles only. Hence, it is expected that breeders would look at these values in order to conduct selections. Even though the concept of GS seems trivial, due to the high dimensional nature of the data delivered from modern sequencing technologies where the number of molecular markers (p) excess by far the number of data points available for model fitting (n; p ≫ n) a complete renovated set of prediction models was needed to cope with this challenge. In this chapter, we provide a conceptual framework for comparing statistical models to overcome the "large p, small n problem." Given the very large diversity of GS models only the most popular are presented here; mainly we focused on linear regression-based models and nonparametric models that predict the genetic estimated breeding values (GEBV) in a single environment considering a single trait only, mainly in the context of plant breeding.

Genome and Environment Based Prediction Models and Methods of Complex Traits Incorporating Genotype × Environment Interaction

Genomic-enabled prediction models are of paramount importance for the successful implementation of genomic selection (GS) based on breeding values. As opposed to animal breeding, plant breeding includes extensive multienvironment and multiyear field trial data. Hence, genomic-enabled prediction models should include genotype × environment (G × E) interaction, which most of the time increases the prediction performance when the response of lines are different from environment to environment. In this chapter, we describe a historical timeline since 2012 related to advances of the GS models that take into account G × E interaction. We describe theoretical and practical aspects of those GS models, including the gains in prediction performance when including G × E structures for both complex continuous and categorical scale traits. Then, we detailed and explained the main G × E genomic prediction models for complex traits measured in continuous and noncontinuous (categorical) scale. Related to G × E interaction models this review also examine the analyses of the information generated with high-throughput phenotype data (phenomic) and the joint analyses of multitrait and multienvironment field trial data that is also employed in the general assessment of multitrait G × E interaction. The inclusion of nongenomic data in increasing the accuracy and biological reliability of the G × E approach is also outlined. We show the recent advances in large-scale envirotyping (enviromics), and how the use of mechanistic computational modeling can derive the crop growth and development aspects useful for predicting phenotypes and explaining G × E.

Environment-specific genomic prediction ability in maize using environmental covariates depends on environmental similarity to training data

Technology advances have made possible the collection of a wealth of genomic, environmental, and phenotypic data for use in plant breeding. Incorporation of environmental data into environment-specific genomic prediction is hindered in part because of inherently high data dimensionality. Computationally efficient approaches to combining genomic and environmental information may facilitate extension of genomic prediction models to new environments and germplasm, and better understanding of genotype-by-environment (G × E) interactions. Using genomic, yield trial, and environmental data on 1,918 unique hybrids evaluated in 59 environments from the maize Genomes to Fields project, we determined that a set of 10,153 SNP dominance coefficients and a 5-day temporal window size for summarizing environmental variables were optimal for genomic prediction using only genetic and environmental main effects. Adding marker-by-environment variable interactions required dimension reduction, and we found that reducing dimensionality of the genetic data while keeping the full set of environmental covariates was best for environment-specific genomic prediction of grain yield, leading to an increase in prediction ability of 2.7% to achieve a prediction ability of 80% across environments when data were masked at random. We then measured how prediction ability within environments was affected under stratified training-testing sets to approximate scenarios commonly encountered by plant breeders, finding that incorporation of marker-by-environment effects improved prediction ability in cases where training and test sets shared environments, but did not improve prediction in new untested environments. The environmental similarity between training and testing sets had a greater impact on the efficacy of prediction than genetic similarity between training and test sets.

A New Deep Learning Calibration Method Enhances Genome-Based Prediction of Continuous Crop Traits

Genomic selection (GS) has the potential to revolutionize predictive plant breeding. A reference population is phenotyped and genotyped to train a statistical model that is used to perform genome-enabled predictions of new individuals that were only genotyped. In this vein, deep neural networks, are a type of machine learning model and have been widely adopted for use in GS studies, as they are not parametric methods, making them more adept at capturing nonlinear patterns. However, the training process for deep neural networks is very challenging due to the numerous hyper-parameters that need to be tuned, especially when imperfect tuning can result in biased predictions. In this paper we propose a simple method for calibrating (adjusting) the prediction of continuous response variables resulting from deep learning applications. We evaluated the proposed deep learning calibration method (DL_M2) using four crop breeding data sets and its performance was compared with the standard deep learning method (DL_M1), as well as the standard genomic Best Linear Unbiased Predictor (GBLUP). While the GBLUP was the most accurate model overall, the proposed deep learning calibration method (DL_M2) helped increase the genome-enabled prediction performance in all data sets when compared with the traditional DL method (DL_M1). Taken together, we provide evidence for extending the use of the proposed calibration method to evaluate its potential and consistency for predicting performance in the context of GS applied to plant breeding.

Predicting phenotypes from genetic, environment, management, and historical data using CNNs

Convolutional Neural Networks (CNNs) can perform similarly or better than standard genomic prediction methods when sufficient genetic, environmental, and management data are provided. Predicting phenotypes from genetic (G), environmental (E), and management (M) conditions is a long-standing challenge with implications to agriculture, medicine, and conservation. Most methods reduce the factors in a dataset (feature engineering) in a subjective and potentially oversimplified manner. Deep neural networks such as Multilayer Perceptrons (MPL) and Convolutional Neural Networks (CNN) can overcome this by allowing the data itself to determine which factors are most important. CNN models were developed for predicting agronomic yield from a combination of replicated trials and historical yield survey data. The results were more accurate than standard methods when tested on held-out G, E, and M data (r = 0.50 vs. r = 0.43), and performed slightly worse than standard methods when only G was held out (r = 0.74 vs. r = 0.80). Pre-training on historical data increased accuracy compared to trial data alone. Saliency map analysis indicated the CNN has "learned" to prioritize many factors of known agricultural importance.

Multitrait machine- and deep-learning models for genomic selection using spectral information in a wheat breeding program

Prediction of breeding values is central to plant breeding and has been revolutionized by the adoption of genomic selection (GS). Use of machine- and deep-learning algorithms applied to complex traits in plants can improve prediction accuracies. Because of the tremendous increase in collected data in breeding programs and the slow rate of genetic gain increase, it is required to explore the potential of artificial intelligence in analyzing the data. The main objectives of this study include optimization of multitrait (MT) machine- and deep-learning models for predicting grain yield and grain protein content in wheat (Triticum aestivum L.) using spectral information. This study compares the performance of four machine- and deep-learning-based unitrait (UT) and MT models with traditional genomic best linear unbiased predictor (GBLUP) and Bayesian models. The dataset consisted of 650 recombinant inbred lines (RILs) from a spring wheat breeding program grown for three years (2014-2016), and spectral data were collected at heading and grain filling stages. The MT-GS models performed 0-28.5 and -0.04 to 15% superior to the UT-GS models. Random forest and multilayer perceptron were the best performing machine- and deep-learning models to predict both traits. Four explored Bayesian models gave similar accuracies, which were less than machine- and deep-learning-based models and required increased computational time. Green normalized difference vegetation index (GNDVI) best predicted grain protein content in seven out of the nine MT-GS models. Overall, this study concluded that machine- and deep-learning-based MT-GS models increased prediction accuracy and should be employed in large-scale breeding programs.

Application of a Poisson deep neural network model for the prediction of count data in genome-based prediction

Genomic selection (GS) is revolutionizing conventional ways of developing new plants and animals. However, because it is a predictive methodology, GS strongly depends on statistical and machine learning to perform these predictions. For continuous outcomes, more models are available for GS. Unfortunately, for count data outcomes, there are few efficient statistical machine learning models for large datasets or for datasets with fewer observations than independent variables. For this reason, in this paper, we applied the univariate version of the Poisson deep neural network (PDNN) proposed earlier for genomic predictions of count data. The model was implemented with (a) the negative log-likelihood of Poisson distribution as the loss function, (b) the rectified linear activation unit as the activation function in hidden layers, and (c) the exponential activation function in the output layer. The advantage of the PDNN model is that it captures complex patterns in the data by implementing many nonlinear transformations in the hidden layers. Moreover, since it was implemented in Tensorflow as the back-end, and in Keras as the front-end, the model can be applied to moderate and large datasets, which is a significant advantage over previous GS models for count data. The PDNN model was compared with deep learning models with continuous outcomes, conventional generalized Poisson regression models, and conventional Bayesian regression methods. We found that the PDNN model outperformed the Bayesian regression and generalized Poisson regression methods in terms of prediction accuracy, although it was not better than the conventional deep neural network with continuous outcomes.

Increased Predictive Accuracy of Multi-Environment Genomic Prediction Model for Yield and Related Traits in Spring Wheat (Triticum aestivum L.)

Genomic selection (GS) has the potential to improve the selection gain for complex traits in crop breeding programs from resource-poor countries. The GS model performance in multi-environment (ME) trials was assessed for 141 advanced breeding lines under four field environments via cross-predictions. We compared prediction accuracy (PA) of two GS models with or without accounting for the environmental variation on four quantitative traits of significant importance, i.e., grain yield (GRYLD), thousand-grain weight, days to heading, and days to maturity, under North and Central Indian conditions. For each trait, we generated PA using the following two different ME cross-validation (CV) schemes representing actual breeding scenarios: (1) predicting untested lines in tested environments through the ME model (ME_CV1) and (2) predicting tested lines in untested environments through the ME model (ME_CV2). The ME predictions were compared with the baseline single-environment (SE) GS model (SE_CV1) representing a breeding scenario, where relationships and interactions are not leveraged across environments. Our results suggested that the ME models provide a clear advantage over SE models in terms of robust trait predictions. Both ME models provided 2-3 times higher prediction accuracies for all four traits across the four tested environments, highlighting the importance of accounting environmental variance in GS models. While the improvement in PA from SE to ME models was significant, the CV1 and CV2 schemes did not show any clear differences within ME, indicating the ME model was able to predict the untested environments and lines equally well. Overall, our results provide an important insight into the impact of environmental variation on GS in smaller breeding programs where these programs can potentially increase the rate of genetic gain by leveraging the ME wheat breeding trials.

Status and advances in mining for blackleg (Leptosphaeria maculans) quantitative resistance (QR) in oilseed rape (Brassica napus)

KEY MESSAGE

Quantitative resistance (QR) loci discovered through genetic and genomic analyses are abundant in the Brassica napus genome, providing an opportunity for their utilization in enhancing blackleg resistance. Quantitative resistance (QR) has long been utilized to manage blackleg in Brassica napus (canola, oilseed rape), even before major resistance genes (R-genes) were extensively explored in breeding programmes. In contrast to R-gene-mediated qualitative resistance, QR reduces blackleg symptoms rather than completely eliminating the disease. As a polygenic trait, QR is controlled by numerous genes with modest effects, which exerts less pressure on the pathogen to evolve; hence, its effectiveness is more durable compared to R-gene-mediated resistance. Furthermore, combining QR with major R-genes has been shown to enhance resistance against diseases in important crops, including oilseed rape. For these reasons, there has been a renewed interest among breeders in utilizing QR in crop improvement. However, the mechanisms governing QR are largely unknown, limiting its deployment. Advances in genomics are facilitating the dissection of the genetic and molecular underpinnings of QR, resulting in the discovery of several loci and genes that can be potentially deployed to enhance blackleg resistance. Here, we summarize the efforts undertaken to identify blackleg QR loci in oilseed rape using linkage and association analysis. We update the knowledge on the possible mechanisms governing QR and the advances in searching for the underlying genes. Lastly, we lay out strategies to accelerate the genetic improvement of blackleg QR in oilseed rape using improved phenotyping approaches and genomic prediction tools.

Multi-trait genomic-enabled prediction enhances accuracy in multi-year wheat breeding trials

Implementing genomic-based prediction models in genomic selection requires an understanding of the measures for evaluating prediction accuracy from different models and methods using multi-trait data. In this study, we compared prediction accuracy using six large multi-trait wheat data sets (quality and grain yield). The data were used to predict 1 year (testing) from the previous year (training) to assess prediction accuracy using four different prediction models. The results indicated that the conventional Pearson’s correlation between observed and predicted values underestimated the true correlation value, whereas the corrected Pearson’s correlation calculated by fitting a bivariate model was higher than the division of the Pearson’s correlation by the squared root of the heritability across traits, by 2.53–11.46%. Across the datasets, the corrected Pearson’s correlation was higher than the uncorrected by 5.80–14.01%. Overall, we found that for grain yield the prediction performance was highest using a multi-trait compared to a single-trait model. The higher the absolute genetic correlation between traits the greater the benefits of multi-trait models for increasing the genomic-enabled prediction accuracy of traits.

Genomic Selection for End-Use Quality and Processing Traits in Soft White Winter Wheat Breeding Program with Machine and Deep Learning Models

Breeding for grain yield, biotic and abiotic stress resistance, and end-use quality are important goals of wheat breeding programs. Screening for end-use quality traits is usually secondary to grain yield due to high labor needs, cost of testing, and large seed requirements for phenotyping. Genomic selection provides an alternative to predict performance using genome-wide markers under forward and across location predictions, where a previous year's dataset can be used to build the models. Due to large datasets in breeding programs, we explored the potential of the machine and deep learning models to predict fourteen end-use quality traits in a winter wheat breeding program. The population used consisted of 666 wheat genotypes screened for five years (2015-19) at two locations (Pullman and Lind, WA, USA). Nine different models, including two machine learning (random forest and support vector machine) and two deep learning models (convolutional neural network and multilayer perceptron) were explored for cross-validation, forward, and across locations predictions. The prediction accuracies for different traits varied from 0.45-0.81, 0.29-0.55, and 0.27-0.50 under cross-validation, forward, and across location predictions. In general, forward prediction accuracies kept increasing over time due to increments in training data size and was more evident for machine and deep learning models. Deep learning models were superior over the traditional ridge regression best linear unbiased prediction (RRBLUP) and Bayesian models under all prediction scenarios. The high accuracy observed for end-use quality traits in this study support predicting them in early generations, leading to the advancement of superior genotypes to more extensive grain yield trails. Furthermore, the superior performance of machine and deep learning models strengthens the idea to include them in large scale breeding programs for predicting complex traits.

Harnessing translational research in wheat for climate resilience

Despite being the world's most widely grown crop, research investments in wheat (Triticum aestivum and Triticum durum) fall behind those in other staple crops. Current yield gains will not meet 2050 needs, and climate stresses compound this challenge. However, there is good evidence that heat and drought resilience can be boosted through translating promising ideas into novel breeding technologies using powerful new tools in genetics and remote sensing, for example. Such technologies can also be applied to identify climate resilience traits from among the vast and largely untapped reserve of wheat genetic resources in collections worldwide. This review describes multi-pronged research opportunities at the focus of the Heat and Drought Wheat Improvement Consortium (coordinated by CIMMYT), which together create a pipeline to boost heat and drought resilience, specifically: improving crop design targets using big data approaches; developing phenomic tools for field-based screening and research; applying genomic technologies to elucidate the bases of climate resilience traits; and applying these outputs in developing next-generation breeding methods. The global impact of these outputs will be validated through the International Wheat Improvement Network, a global germplasm development and testing system that contributes key productivity traits to approximately half of the global wheat-growing area.

Harnessing Crop Wild Diversity for Climate Change Adaptation

Warming and drought are reducing global crop production with a potential to substantially worsen global malnutrition. As with the green revolution in the last century, plant genetics may offer concrete opportunities to increase yield and crop adaptability. However, the rate at which the threat is happening requires powering new strategies in order to meet the global food demand. In this review, we highlight major recent 'big data' developments from both empirical and theoretical genomics that may speed up the identification, conservation, and breeding of exotic and elite crop varieties with the potential to feed humans. We first emphasize the major bottlenecks to capture and utilize novel sources of variation in abiotic stress (i.e., heat and drought) tolerance. We argue that adaptation of crop wild relatives to dry environments could be informative on how plant phenotypes may react to a drier climate because natural selection has already tested more options than humans ever will. Because isolated pockets of cryptic diversity may still persist in remote semi-arid regions, we encourage new habitat-based population-guided collections for genebanks. We continue discussing how to systematically study abiotic stress tolerance in these crop collections of wild and landraces using geo-referencing and extensive environmental data. By uncovering the genes that underlie the tolerance adaptive trait, natural variation has the potential to be introgressed into elite cultivars. However, unlocking adaptive genetic variation hidden in related wild species and early landraces remains a major challenge for complex traits that, as abiotic stress tolerance, are polygenic (i.e., regulated by many low-effect genes). Therefore, we finish prospecting modern analytical approaches that will serve to overcome this issue. Concretely, genomic prediction, machine learning, and multi-trait gene editing, all offer innovative alternatives to speed up more accurate pre- and breeding efforts toward the increase in crop adaptability and yield, while matching future global food demands in the face of increased heat and drought. In order for these 'big data' approaches to succeed, we advocate for a trans-disciplinary approach with open-source data and long-term funding. The recent developments and perspectives discussed throughout this review ultimately aim to contribute to increased crop adaptability and yield in the face of heat waves and drought events.

Machine learning in plant science and plant breeding

Technological developments have revolutionized measurements on plant genotypes and phenotypes, leading to routine production of large, complex data sets. This has led to increased efforts to extract meaning from these measurements and to integrate various data sets. Concurrently, machine learning has rapidly evolved and is now widely applied in science in general and in plant genotyping and phenotyping in particular. Here, we review the application of machine learning in the context of plant science and plant breeding. We focus on analyses at different phenotype levels, from biochemical to yield, and in connecting genotypes to these. In this way, we illustrate how machine learning offers a suite of methods that enable researchers to find meaningful patterns in relevant plant data.

A review of deep learning applications for genomic selection

BACKGROUND

Several conventional genomic Bayesian (or no Bayesian) prediction methods have been proposed including the standard additive genetic effect model for which the variance components are estimated with mixed model equations. In recent years, deep learning (DL) methods have been considered in the context of genomic prediction. The DL methods are nonparametric models providing flexibility to adapt to complicated associations between data and output with the ability to adapt to very complex patterns.

MAIN BODY

We review the applications of deep learning (DL) methods in genomic selection (GS) to obtain a meta-picture of GS performance and highlight how these tools can help solve challenging plant breeding problems. We also provide general guidance for the effective use of DL methods including the fundamentals of DL and the requirements for its appropriate use. We discuss the pros and cons of this technique compared to traditional genomic prediction approaches as well as the current trends in DL applications.

CONCLUSIONS

The main requirement for using DL is the quality and sufficiently large training data. Although, based on current literature GS in plant and animal breeding we did not find clear superiority of DL in terms of prediction power compared to conventional genome based prediction models. Nevertheless, there are clear evidences that DL algorithms capture nonlinear patterns more efficiently than conventional genome based. Deep learning algorithms are able to integrate data from different sources as is usually needed in GS assisted breeding and it shows the ability for improving prediction accuracy for large plant breeding data. It is important to apply DL to large training-testing data sets.

Deep Learning for Predicting Complex Traits in Spring Wheat Breeding Program

Genomic selection (GS) is transforming the field of plant breeding and implementing models that improve prediction accuracy for complex traits is needed. Analytical methods for complex datasets traditionally used in other disciplines represent an opportunity for improving prediction accuracy in GS. Deep learning (DL) is a branch of machine learning (ML) which focuses on densely connected networks using artificial neural networks for training the models. The objective of this research was to evaluate the potential of DL models in the Washington State University spring wheat breeding program. We compared the performance of two DL algorithms, namely multilayer perceptron (MLP) and convolutional neural network (CNN), with ridge regression best linear unbiased predictor (rrBLUP), a commonly used GS model. The dataset consisted of 650 recombinant inbred lines (RILs) from a spring wheat nested association mapping (NAM) population planted from 2014-2016 growing seasons. We predicted five different quantitative traits with varying genetic architecture using cross-validations (CVs), independent validations, and different sets of SNP markers. Hyperparameters were optimized for DL models by lowering the root mean square in the training set, avoiding model overfitting using dropout and regularization. DL models gave 0 to 5% higher prediction accuracy than rrBLUP model under both cross and independent validations for all five traits used in this study. Furthermore, MLP produces 5% higher prediction accuracy than CNN for grain yield and grain protein content. Altogether, DL approaches obtained better prediction accuracy for each trait, and should be incorporated into a plant breeder's toolkit for use in large scale breeding programs.