Breaking the curse of dimensionality to identify causal variants in Breeding 4

Review of applications of artificial intelligence (AI) methods in crop research

Sophisticated and modern crop improvement techniques can bridge the gap for feeding the ever-increasing population. Artificial intelligence (AI) refers to the simulation of human intelligence in machines, which refers to the application of computational algorithms, machine learning (ML) and deep learning (DL) techniques. This is aimed to generalise patterns and relationships from historical data, employing various mathematical optimisation techniques thus making prediction models for facilitating selection of superior genotypes. These techniques are less resource intensive and can solve the problem based on the analysis of large-scale phenotypic datasets. ML for genomic selection (GS) uses high-throughput genotyping technologies to gather genetic information on a large number of markers across the genome. The prediction of GS models is based on the mathematical relation between genotypic and phenotypic data from the training population. ML techniques have emerged as powerful tools for genome editing through analysing large-scale genomic data and facilitating the development of accurate prediction models. Precise phenotyping is a prerequisite to advance crop breeding for solving agricultural production-related issues. ML algorithms can solve this problem through generating predictive models, based on the analysis of large-scale phenotypic datasets. DL models also have the potential reliability of precise phenotyping. This review provides a comprehensive overview on various ML and DL models, their applications, potential to enhance the efficiency, specificity and safety towards advanced crop improvement protocols such as genomic selection, genome editing, along with phenotypic prediction to promote accelerated breeding.

Reviewing the essential roles of remote phenotyping, GWAS and explainable AI in practical marker-assisted selection for drought-tolerant winter wheat breeding

Marker-assisted selection (MAS) plays a crucial role in crop breeding improving the speed and precision of conventional breeding programmes by quickly and reliably identifying and selecting plants with desired traits. However, the efficacy of MAS depends on several prerequisites, with precise phenotyping being a key aspect of any plant breeding programme. Recent advancements in high-throughput remote phenotyping, facilitated by unmanned aerial vehicles coupled to machine learning, offer a non-destructive and efficient alternative to traditional, time-consuming, and labour-intensive methods. Furthermore, MAS relies on knowledge of marker-trait associations, commonly obtained through genome-wide association studies (GWAS), to understand complex traits such as drought tolerance, including yield components and phenology. However, GWAS has limitations that artificial intelligence (AI) has been shown to partially overcome. Additionally, AI and its explainable variants, which ensure transparency and interpretability, are increasingly being used as recognised problem-solving tools throughout the breeding process. Given these rapid technological advancements, this review provides an overview of state-of-the-art methods and processes underlying each MAS, from phenotyping, genotyping and association analyses to the integration of explainable AI along the entire workflow. In this context, we specifically address the challenges and importance of breeding winter wheat for greater drought tolerance with stable yields, as regional droughts during critical developmental stages pose a threat to winter wheat production. Finally, we explore the transition from scientific progress to practical implementation and discuss ways to bridge the gap between cutting-edge developments and breeders, expediting MAS-based winter wheat breeding for drought tolerance.

A comparative study of 11 non-linear regression models highlighting autoencoder, DBN, and SVR, enhanced by SHAP importance analysis in soybean branching prediction

To explore a robust tool for advancing digital breeding practices through an artificial intelligence-driven phenotype prediction expert system, we undertook a thorough analysis of 11 non-linear regression models. Our investigation specifically emphasized the significance of Support Vector Regression (SVR) and SHapley Additive exPlanations (SHAP) in predicting soybean branching. By using branching data (phenotype) of 1918 soybean accessions and 42 k SNP (Single Nucleotide Polymorphism) polymorphic data (genotype), this study systematically compared 11 non-linear regression AI models, including four deep learning models (DBN (deep belief network) regression, ANN (artificial neural network) regression, Autoencoders regression, and MLP (multilayer perceptron) regression) and seven machine learning models (e.g., SVR (support vector regression), XGBoost (eXtreme Gradient Boosting) regression, Random Forest regression, LightGBM regression, GPs (Gaussian processes) regression, Decision Tree regression, and Polynomial regression). After being evaluated by four valuation metrics: R2 (R-squared), MAE (Mean Absolute Error), MSE (Mean Squared Error), and MAPE (Mean Absolute Percentage Error), it was found that the SVR, Polynomial Regression, DBN, and Autoencoder outperformed other models and could obtain a better prediction accuracy when they were used for phenotype prediction. In the assessment of deep learning approaches, we exemplified the SVR model, conducting analyses on feature importance and gene ontology (GO) enrichment to provide comprehensive support. After comprehensively comparing four feature importance algorithms, no notable distinction was observed in the feature importance ranking scores across the four algorithms, namely Variable Ranking, Permutation, SHAP, and Correlation Matrix, but the SHAP value could provide rich information on genes with negative contributions, and SHAP importance was chosen for feature selection. The results of this study offer valuable insights into AI-mediated plant breeding, addressing challenges faced by traditional breeding programs. The method developed has broad applicability in phenotype prediction, minor QTL (quantitative trait loci) mining, and plant smart-breeding systems, contributing significantly to the advancement of AI-based breeding practices and transitioning from experience-based to data-based breeding.

Accelerating genetic gains for quantitative resistance to verticillium wilt through predictive breeding in strawberry

Verticillium wilt (VW), a devastating vascular wilt disease of strawberry (Fragaria × $\times$ ananassa), has caused economic losses for nearly a century. This disease is caused by the soil-borne pathogen Verticillium dahliae, which occurs nearly worldwide and causes disease in numerous agriculturally important plants. The development of VW-resistant cultivars is critically important for the sustainability of strawberry production. We previously showed that a preponderance of the genetic resources (asexually propagated hybrid individuals) preserved in public germplasm collections were moderately to highly susceptible and that genetic gains for increased resistance to VW have been negligible over the last 60 years. To more fully understand the challenges associated with breeding for increased quantitative resistance to this pathogen, we developed and phenotyped a training population of hybrids (n = 564 $n = 564$ ) among elite parents with a wide range of resistance phenotypes. When these data were combined with training data from a population of elite and exotic hybrids (n = 386 $n = 386$ ), genomic prediction accuracies of 0.47-0.48 were achieved and were predicted to explain 70%-75% of the additive genetic variance for resistance. We concluded that breeding values for resistance to VW can be predicted with sufficient accuracy for effective genomic selection with routine updating of training populations.

Charting plant gene functions in the multi-omics and single-cell era

Despite the increased access to high-quality plant genome sequences, the set of genes with a known function remains far from complete. With the advent of novel bulk and single-cell omics profiling methods, we are entering a new era where advanced and highly integrative functional annotation strategies are being developed to elucidate the functions of all plant genes. Here, we review different multi-omics approaches to improve functional and regulatory gene characterization and highlight the power of machine learning and network biology to fully exploit the complementary information embedded in different omics layers. Finally, we discuss the potential of emerging single-cell methods and algorithms to further increase the resolution, allowing generation of functional insights about plant biology.

Breeding crops for drought-affected environments and improved climate resilience

Breeding climate-resilient crops with improved levels of abiotic and biotic stress resistance as a response to climate change presents both opportunities and challenges. Applying the framework of the "breeder's equation," which is used to predict the response to selection for a breeding program cycle, we review methodologies and strategies that have been used to successfully breed crops with improved levels of drought resistance, where the target population of environments (TPEs) is a spatially and temporally heterogeneous mixture of drought-affected and favorable (water-sufficient) environments. Long-term improvement of temperate maize for the US corn belt is used as a case study and compared with progress for other crops and geographies. Integration of trait information across scales, from genomes to ecosystems, is needed to accurately predict yield outcomes for genotypes within the current and future TPEs. This will require transdisciplinary teams to explore, identify, and exploit novel opportunities to accelerate breeding program outcomes; both improved germplasm resources and improved products (cultivars, hybrids, clones, and populations) that outperform and replace the products in use by farmers, in combination with modified agronomic management strategies suited to their local environments.

Connecting the dots between cell surface- and intracellular-triggered immune pathways in plants

Plants can detect microbial molecules via surface-localized pattern-recognition receptors (PRRs) and intracellular immune receptors from the nucleotide-binding, leucine-rich repeat receptor (NLR) family. The corresponding pattern-triggered (PTI) and effector-triggered (ETI) immunity were long considered separate pathways, although they converge on largely similar cellular responses, such as calcium influx and overlapping gene reprogramming. A number of studies recently uncovered genetic and molecular interconnections between PTI and ETI, highlighting the complexity of the plant immune network. Notably, PRR- and NLR-mediated immune responses require and potentiate each other to reach an optimal immune output. How PTI and ETI connect to confer robust immunity in different plant species, including crops will be an exciting future research area.

Functional Allele Validation by Gene Editing to Leverage the Wealth of Genetic Resources for Crop Improvement

Advances in molecular technologies over the past few decades, such as high-throughput DNA marker genotyping, have provided more powerful plant breeding approaches, including marker-assisted selection and genomic selection. At the same time, massive investments in plant genetics and genomics, led by whole genome sequencing, have led to greater knowledge of genes and genetic pathways across plant genomes. However, there remains a gap between approaches focused on forward genetics, which start with a phenotype to map a mutant locus or QTL with the goal of cloning the causal gene, and approaches using reverse genetics, which start with large-scale sequence data and work back to the gene function. The recent establishment of efficient CRISPR-Cas-based gene editing promises to bridge this gap and provide a rapid method to functionally validate genes and alleles identified through studies of natural variation. CRISPR-Cas techniques can be used to knock out single or multiple genes, precisely modify genes through base and prime editing, and replace alleles. Moreover, technologies such as protoplast isolation, in planta transformation, and the use of developmental regulatory genes promise to enable high-throughput gene editing to accelerate crop improvement.

Utilizing CRISPR-Cas in Tropical Crop Improvement: A Decision Process for Fitting Genome Engineering to Your Species

Adopting modern gene-editing technologies for trait improvement in agriculture requires important workflow developments, yet these developments are not often discussed. Using tropical crop systems as a case study, we describe a workflow broken down into discrete processes with specific steps and decision points that allow for the practical application of the CRISPR-Cas gene editing platform in a crop of interest. While we present the steps of developing genome-edited plants as sequential, in practice parts can be done in parallel, which are discussed in this perspective. The main processes include 1) understanding the genetic basis of the trait along with having the crop’s genome sequence, 2) testing and optimization of the editing reagents, development of efficient 3) tissue culture and 4) transformation methods, and 5) screening methods to identify edited events with commercial potential. Our goal in this perspective is to help any lab that wishes to implement this powerful, easy-to-use tool in their pipeline, thus aiming to democratize the technology.

Deep neural networks for genomic prediction do not estimate marker effects

Genomic prediction is a promising technology for advancing both plant and animal breeding, with many different prediction models evaluated in the literature. It has been suggested that the ability of powerful nonlinear models, such as deep neural networks, to capture complex epistatic effects between markers offers advantages for genomic prediction. However, these methods tend not to outperform classical linear methods, leaving it an open question why this capacity to model nonlinear effects does not seem to result in better predictive capability. In this work, we propose the theory that, because of a previously described principle called shortcut learning, deep neural networks tend to base their predictions on overall genetic relatedness rather than on the effects of particular markers such as epistatic effects. Using several datasets of crop plants [lentil (Lens culinaris Medik.), wheat (Triticum aestivum L.), and Brassica carinata A. Braun], we demonstrate the network's indifference to the values of the markers by showing that the same network, provided with only the locations of matches between markers for two individuals, is able to perform prediction to the same level of accuracy.

Genome optimization via virtual simulation to accelerate maize hybrid breeding

The employment of doubled-haploid (DH) technology in maize has vastly accelerated the efficiency of developing inbred lines. The selection of superior lines has to rely on genotypes with genomic selection (GS) model, rather than phenotypes due to the high expense of field phenotyping. In this work, we implemented 'genome optimization via virtual simulation (GOVS)' using the genotype and phenotype data of 1404 maize lines and their F1 progeny. GOVS simulates a virtual genome encompassing the most abundant 'optimal genotypes' or 'advantageous alleles' in a genetic pool. Such a virtually optimized genome, although can never be developed in reality, may help plot the optimal route to direct breeding decisions. GOVS assists in the selection of superior lines based on the genomic fragments that a line contributes to the simulated genome. The assumption is that the more fragments of optimal genotypes a line contributes to the assembly, the higher the likelihood of the line favored in the F1 phenotype, e.g. grain yield. Compared to traditional GS method, GOVS-assisted selection may avoid using an arbitrary threshold for the predicted F1 yield to assist selection. Additionally, the selected lines contributed complementary sets of advantageous alleles to the virtual genome. This feature facilitates plotting the optimal route for DH production, whereby the fewest lines and F1 combinations are needed to pyramid a maximum number of advantageous alleles in the new DH lines. In summary, incorporation of DH production, GS and genome optimization will ultimately improve genomically designed breeding in maize. Short abstract: Doubled-haploid (DH) technology has been widely applied in maize breeding industry, as it greatly shortens the period of developing homozygous inbred lines via bypassing several rounds of self-crossing. The current challenge is how to efficiently screen the large volume of inbred lines based on genotypes. We present the toolbox of genome optimization via virtual simulation (GOVS), which complements the traditional genomic selection model. GOVS simulates a virtual genome encompassing the most abundant 'optimal genotypes' in a breeding population, and then assists in selection of superior lines based on the genomic fragments that a line contributes to the simulated genome. Availability of GOVS (https://govs-pack.github.io/) to the public may ultimately facilitate genomically designed breeding in maize.

Haplotype associated RNA expression (HARE) improves prediction of complex traits in maize

Genomic prediction typically relies on associations between single-site polymorphisms and traits of interest. This representation of genomic variability has been successful for predicting many complex traits. However, it usually cannot capture the combination of alleles in haplotypes and it has generated little insight about the biological function of polymorphisms. Here we present a novel and cost-effective method for imputing cis haplotype associated RNA expression (HARE), studied their transferability across tissues, and evaluated genomic prediction models within and across populations. HARE focuses on tightly linked cis acting causal variants in the immediate vicinity of the gene, while excluding trans effects from diffusion and metabolism. Therefore, HARE estimates were more transferrable across different tissues and populations compared to measured transcript expression. We also showed that HARE estimates captured one-third of the variation in gene expression. HARE estimates were used in genomic prediction models evaluated within and across two diverse maize panels–a diverse association panel (Goodman Association panel) and a large half-sib panel (Nested Association Mapping panel)–for predicting 26 complex traits. HARE resulted in up to 15% higher prediction accuracy than control approaches that preserved haplotype structure, suggesting that HARE carried functional information in addition to information about haplotype structure. The largest increase was observed when the model was trained in the Nested Association Mapping panel and tested in the Goodman Association panel. Additionally, HARE yielded higher within-population prediction accuracy as compared to measured expression values. The accuracy achieved by measured expression was variable across tissues, whereas accuracy by HARE was more stable across tissues. Therefore, imputing RNA expression of genes by haplotype is stable, cost-effective, and transferable across populations.

Genomic marker data is widely used in the prediction of many traits. However, prediction has been primarily carried out within populations and without explicit modeling of RNA or protein expression. In this study, we explored the prediction of field traits within and across populations using estimated RNA expression attributable to only the DNA sequence around a gene. We showed that the estimated RNA expression was more transferable across populations and tissues than measured RNA expression. We improved prediction of field traits up to 15% using estimated gene expression as compared to observed expression or gene sequence alone. Overall, these findings indicate that structural and functional information in the gene sequence is highly transferable.

Identification and utilization of genetic determinants of trait measurement errors in image-based, high-throughput phenotyping

The accuracy of trait measurements greatly affects the quality of genetic analyses. During automated phenotyping, trait measurement errors, i.e. differences between automatically extracted trait values and ground truth, are often treated as random effects that can be controlled by increasing population sizes and/or replication number. In contrast, there is some evidence that trait measurement errors may be partially under genetic control. Consistent with this hypothesis, we observed substantial nonrandom, genetic contributions to trait measurement errors for five maize (Zea mays) tassel traits collected using an image-based phenotyping platform. The phenotyping accuracy varied according to whether a tassel exhibited "open" versus. "closed" branching architecture, which is itself under genetic control. Trait-associated SNPs (TASs) identified via genome-wide association studies (GWASs) conducted on five tassel traits that had been phenotyped both manually (i.e. ground truth) and via feature extraction from images exhibit little overlap. Furthermore, identification of TASs from GWASs conducted on the differences between the two values indicated that a fraction of measurement error is under genetic control. Similar results were obtained in a sorghum (Sorghum bicolor) plant height dataset, demonstrating that trait measurement error is genetically determined in multiple species and traits. Trait measurement bias cannot be controlled by increasing population size and/or replication number.

Genetic diversity and evolutionary patterns of Taraxacum kok-saghyz Rodin

Taraxacum kok-saghyz Rodin (TKS) is an important potential alternative source of natural inulin and rubber production, which has great significance for the production of industrial products. In this study, we sequenced 58 wild TKS individuals collected from four different geography regions worldwide to elucidate the population structure, genetic diversity, and the patterns of evolution. Also, the first flowering time, crown diameter, morphological characteristics of leaf, and scape of all TKS individuals were measured and evaluated statistically. Phylogenetic analysis based on SNPs and cluster analysis based on agronomic traits showed that all 58 TKS individuals could be roughly divided into three distinct groups: (a) Zhaosu County in Xinjiang (population AB, including a few individuals from population C and D); (b) Tekes County in Xinjiang (population C); and (c) Tuzkol lake in Kazakhstan (population D). Population D exhibited a closer genetic relationship with population C compared with population AB. Genetic diversity analysis further revealed that population expansion from C and D to AB occurred, as well as gene flow between them. Additionally, some natural selection regions were identified in AB population. Function annotation of candidate genes identified in these regions revealed that they mainly participated in biological regulation processes, such as transporter activity, structural molecule activity, and molecular function regulator. We speculated that the genes identified in selective sweep regions may contribute to TKS adaptation to the Yili River Valley of Xinjiang. In general, this study provides new insights in clarifying population structure and genetic diversity analysis of TKS using SNP molecular markers and agronomic traits.

Designing Future Crops: Genomics-Assisted Breeding Comes of Age

Over the past decade, genomics-assisted breeding (GAB) has been instrumental in harnessing the potential of modern genome resources and characterizing and exploiting allelic variation for germplasm enhancement and cultivar development. Sustaining GAB in the future (GAB 2.0) will rely upon a suite of new approaches that fast-track targeted manipulation of allelic variation for creating novel diversity and facilitate their rapid and efficient incorporation in crop improvement programs. Genomic breeding strategies that optimize crop genomes with accumulation of beneficial alleles and purging of deleterious alleles will be indispensable for designing future crops. In coming decades, GAB 2.0 is expected to play a crucial role in breeding more climate-smart crop cultivars with higher nutritional value in a cost-effective and timely manner.

Tackling G × E × M interactions to close on-farm yield-gaps: creating novel pathways for crop improvement by predicting contributions of genetics and management to crop productivity

KEY MESSAGE

Climate change and Genotype-by-Environment-by-Management interactions together challenge our strategies for crop improvement. Research to advance prediction methods for breeding and agronomy is opening new opportunities to tackle these challenges and overcome on-farm crop productivity yield-gaps through design of responsive crop improvement strategies. Genotype-by-Environment-by-Management (G × E × M) interactions underpin many aspects of crop productivity. An important question for crop improvement is "How can breeders and agronomists effectively explore the diverse opportunities within the high dimensionality of the complex G × E × M factorial to achieve sustainable improvements in crop productivity?" Whenever G × E × M interactions make important contributions to attainment of crop productivity, we should consider how to design crop improvement strategies that can explore the potential space of G × E × M possibilities, reveal the interesting Genotype-Management (G-M) technology opportunities for the Target Population of Environments (TPE), and enable the practical exploitation of the associated improved levels of crop productivity under on-farm conditions. Climate change adds additional layers of complexity and uncertainty to this challenge, by introducing directional changes in the environmental dimension of the G × E × M factorial. These directional changes have the potential to create further conditional changes in the contributions of the genetic and management dimensions to future crop productivity. Therefore, in the presence of G × E × M interactions and climate change, the challenge for both breeders and agronomists is to co-design new G-M technologies for a non-stationary TPE. Understanding these conditional changes in crop productivity through the relevant sciences for each dimension, Genotype, Environment, and Management, creates opportunities to predict novel G-M technology combinations suitable to achieve sustainable crop productivity and global food security targets for the likely climate change scenarios. Here we consider critical foundations required for any prediction framework that aims to move us from the current unprepared state of describing G × E × M outcomes to a future responsive state equipped to predict the crop productivity consequences of G-M technology combinations for the range of environmental conditions expected for a complex, non-stationary TPE under the influences of climate change.

Heterosis and Hybrid Crop Breeding: A Multidisciplinary Review

Although hybrid crop varieties are among the most popular agricultural innovations, the rationale for hybrid crop breeding is sometimes misunderstood. Hybrid breeding is slower and more resource-intensive than inbred breeding, but it allows systematic improvement of a population by recurrent selection and exploitation of heterosis simultaneously. Inbred parental lines can identically reproduce both themselves and their F1 progeny indefinitely, whereas outbred lines cannot, so uniform outbred lines must be bred indirectly through their inbred parents to harness heterosis. Heterosis is an expected consequence of whole-genome non-additive effects at the population level over evolutionary time. Understanding heterosis from the perspective of molecular genetic mechanisms alone may be elusive, because heterosis is likely an emergent property of populations. Hybrid breeding is a process of recurrent population improvement to maximize hybrid performance. Hybrid breeding is not maximization of heterosis per se, nor testing random combinations of individuals to find an exceptional hybrid, nor using heterosis in place of population improvement. Though there are methods to harness heterosis other than hybrid breeding, such as use of open-pollinated varieties or clonal propagation, they are not currently suitable for all crops or production environments. The use of genomic selection can decrease cycle time and costs in hybrid breeding, particularly by rapidly establishing heterotic pools, reducing testcrossing, and limiting the loss of genetic variance. Open questions in optimal use of genomic selection in hybrid crop breeding programs remain, such as how to choose founders of heterotic pools, the importance of dominance effects in genomic prediction, the necessary frequency of updating the training set with phenotypic information, and how to maintain genetic variance and prevent fixation of deleterious alleles.

Western Corn Rootworm, Plant and Microbe Interactions: A Review and Prospects for New Management Tools

The western corn rootworm, Diabrotica virgifera virgifera LeConte, is resistant to four separate classes of traditional insecticides, all Bacillius thuringiensis (Bt) toxins currently registered for commercial use, crop rotation, innate plant resistance factors, and even double-stranded RNA (dsRNA) targeting essential genes via environmental RNA interference (RNAi), which has not been sold commercially to date. Clearly, additional tools are needed as management options. In this review, we discuss the state-of-the-art knowledge about biotic factors influencing herbivore success, including host location and recognition, plant defensive traits, plant-microbe interactions, and herbivore-pathogens/predator interactions. We then translate this knowledge into potential new management tools and improved biological control.

A quantitative genomics map of rice provides genetic insights and guides breeding

Extensive allelic variation in agronomically important genes serves as the basis of rice breeding. Here, we present a comprehensive map of rice quantitative trait nucleotides (QTNs) and inferred QTN effects based on eight genome-wide association study cohorts. Population genetic analyses revealed that domestication, local adaptation and heterosis are all associated with QTN allele frequency changes. A genome navigation system, RiceNavi, was developed for QTN pyramiding and breeding route optimization, and implemented in the improvement of a widely cultivated indica variety. This work presents an efficient platform that bridges ever-increasing genomic knowledge and diverse improvement needs in rice.

Tapping Diversity From the Wild: From Sampling to Implementation

The diversity observed among crop wild relatives (CWRs) and their ability to flourish in unfavorable and harsh environments have drawn the attention of plant scientists and breeders for many decades. However, it is also recognized that the benefit gained from using CWRs in breeding is a potential rose between thorns of detrimental genetic variation that is linked to the trait of interest. Despite the increased interest in CWRs, little attention was given so far to the statistical, analytical, and technical considerations that should guide the sampling design, the germplasm characterization, and later its implementation in breeding. Here, we review the entire process of sampling and identifying beneficial genetic variation in CWRs and the challenge of using it in breeding. The ability to detect beneficial genetic variation in CWRs is strongly affected by the sampling design which should be adjusted to the spatial and temporal variation of the target species, the trait of interest, and the analytical approach used. Moreover, linkage disequilibrium is a key factor that constrains the resolution of searching for beneficial alleles along the genome, and later, the ability to deplete linked deleterious genetic variation as a consequence of genetic drag. We also discuss how technological advances in genomics, phenomics, biotechnology, and data science can improve the ability to identify beneficial genetic variation in CWRs and to exploit it in strive for higher-yielding and sustainable crops.

Adoption and Optimization of Genomic Selection To Sustain Breeding for Apricot Fruit Quality

Genomic selection (GS) is a breeding approach which exploits genome-wide information and whose unprecedented success has shaped several animal and plant breeding schemes through delivering their genetic progress. This is the first study assessing the potential of GS in apricot (Prunus armeniaca) to enhance postharvest fruit quality attributes. Genomic predictions were based on a F1 pseudo-testcross population, comprising 153 individuals with contrasting fruit quality traits. They were phenotyped for physical and biochemical fruit metrics in contrasting climatic conditions over two years. Prediction accuracy (PA) varied from 0.31 for glucose content with the Bayesian LASSO (BL) to 0.78 for ethylene production with RR-BLUP, which yielded the most accurate predictions in comparison to Bayesian models and only 10% out of 61,030 SNPs were sufficient to reach accurate predictions. Useful insights were provided on the genetic architecture of apricot fruit quality whose integration in prediction models improved their performance, notably for traits governed by major QTL. Furthermore, multivariate modeling yielded promising outcomes in terms of PA within training partitions partially phenotyped for target traits. This provides a useful framework for the implementation of indirect selection based on easy-to-measure traits. Thus, we highlighted the main levers to take into account for the implementation of GS for fruit quality in apricot, but also to improve the genetic gain in perennial species.

Genomic signatures and candidate genes of lint yield and fibre quality improvement in Upland cotton in Xinjiang

Xinjiang has been the largest and highest yield cotton production region not only in China, but also in the world. Improvements in Upland cotton cultivars in Xinjiang have occurred via pedigree selection and/or crossing of elite alleles from the former Soviet Union and other cotton producing regions of China. But it is unclear how genomic constitutions from foundation parents have been selected and inherited. Here, we deep-sequenced seven historic foundation parents, comprising four cultivars introduced from the former Soviet Union (108Ф, C1470, 611Б and KK1543) and three from United States and Africa (DPL15, STV2B and UGDM), and re-sequenced sixty-nine Xinjiang modern cultivars. Phylogenetic analysis of more than 2 million high-quality single nucleotide polymorphisms allowed their classification two groups, suggesting that Xinjiang Upland cotton cultivars were not only spawned from 108Ф, C1470, 611Б and KK1543, but also had a close kinship with DPL15, STV2B and UGDM. Notably, identity-by-descent (IBD) tracking demonstrated that the former Soviet Union cultivars have made a huge contribution to modern cultivar improvement in Xinjiang. A total of 156 selective sweeps were identified. Among them, apoptosis-antagonizing transcription factor gene (GhAATF1) and mitochondrial transcription termination factor family protein gene (GhmTERF1) were highly involved in the determination of lint percentage. Additionally, the auxin response factor gene (GhARF3) located in inherited IBD segments from 108Ф and 611Б was highly correlated with fibre quality. These results provide an insight into the genomics of artificial selection for improving cotton production and facilitate next-generation precision breeding of cotton and other crops.

QTG-Finder2: A Generalized Machine-Learning Algorithm for Prioritizing QTL Causal Genes in Plants

Linkage mapping has been widely used to identify quantitative trait loci (QTL) in many plants and usually requires a time-consuming and labor-intensive fine mapping process to find the causal gene underlying the QTL. Previously, we described QTG-Finder, a machine-learning algorithm to rationally prioritize candidate causal genes in QTLs. While it showed good performance, QTG-Finder could only be used in Arabidopsis and rice because of the limited number of known causal genes in other species. Here we tested the feasibility of enabling QTG-Finder to work on species that have few or no known causal genes by using orthologs of known causal genes as the training set. The model trained with orthologs could recall about 64% of Arabidopsis and 83% of rice causal genes when the top 20% ranked genes were considered, which is similar to the performance of models trained with known causal genes. The average precision was 0.027 for Arabidopsis and 0.029 for rice. We further extended the algorithm to include polymorphisms in conserved non-coding sequences and gene presence/absence variation as additional features. Using this algorithm, QTG-Finder2, we trained and cross-validated Sorghum bicolor and Setaria viridis models. The S. bicolor model was validated by causal genes curated from the literature and could recall 70% of causal genes when the top 20% ranked genes were considered. In addition, we applied the S. viridis model and public transcriptome data to prioritize a plant height QTL and identified 13 candidate genes. QTL-Finder2 can accelerate the discovery of causal genes in any plant species and facilitate agricultural trait improvement.

Counting on Crossovers: Controlled Recombination for Plant Breeding

Crossovers (COs), that drive genetic exchange between homologous chromosomes, are strongly biased toward subtelomeric regions in plant species. Manipulating the rate and positions of COs to increase the genetic variation accessible to breeders is a longstanding goal. Use of genome editing reagents that induce double-stranded breaks (DSBs) or modify the epigenome at desired sites of recombination, and manipulation of CO factors, are increasingly applicable approaches for achieving this goal. These strategies for 'controlled recombination' have potential to reduce the time and expense associated with traditional breeding, reveal currently inaccessible genetic diversity, and increase control over the inheritance of preferred haplotypes. Considerable challenges to address include translating knowledge from models to crop species and determining the best stages of the breeding cycle at which to control recombination.

Deep learning for plant genomics and crop improvement

Our era has witnessed tremendous advances in plant genomics, characterized by an explosion of high-throughput techniques to identify multi-dimensional genome-wide molecular phenotypes at low costs. More importantly, genomics is not merely acquiring molecular phenotypes, but also leveraging powerful data mining tools to predict and explain them. In recent years, deep learning has been found extremely effective in these tasks. This review highlights two prominent questions at the intersection of genomics and deep learning: 1) how can the flow of information from genomic DNA sequences to molecular phenotypes be modeled; 2) how can we identify functional variants in natural populations using deep learning models? Additionally, we discuss the possibility of unleashing the power of deep learning in synthetic biology to create novel genomic elements with desirable functions. Taken together, we propose a central role of deep learning in future plant genomics research and crop genetic improvement.

A sorghum practical haplotype graph facilitates genome-wide imputation and cost-effective genomic prediction

Successful management and utilization of increasingly large genomic datasets is essential for breeding programs to accelerate cultivar development. To help with this, we developed a Sorghum bicolor Practical Haplotype Graph (PHG) pangenome database that stores haplotypes and variant information. We developed two PHGs in sorghum that were used to identify genome-wide variants for 24 founders of the Chibas sorghum breeding program from 0.01x sequence coverage. The PHG called single nucleotide polymorphisms (SNPs) with 5.9% error at 0.01x coverage-only 3% higher than PHG error when calling SNPs from 8x coverage sequence. Additionally, 207 progenies from the Chibas genomic selection (GS) training population were sequenced and processed through the PHG. Missing genotypes were imputed from PHG parental haplotypes and used for genomic prediction. Mean prediction accuracies with PHG SNP calls range from .57-.73 and are similar to prediction accuracies obtained with genotyping-by-sequencing or targeted amplicon sequencing (rhAmpSeq) markers. This study demonstrates the use of a sorghum PHG to impute SNPs from low-coverage sequence data and shows that the PHG can unify genotype calls across multiple sequencing platforms. By reducing input sequence requirements, the PHG can decrease the cost of genotyping, make GS more feasible, and facilitate larger breeding populations. Our results demonstrate that the PHG is a useful research and breeding tool that maintains variant information from a diverse group of taxa, stores sequence data in a condensed but readily accessible format, unifies genotypes across genotyping platforms, and provides a cost-effective option for genomic selection.

From QTLs to Adaptation Landscapes: Using Genotype-To-Phenotype Models to Characterize G×E Over Time

Genotype by environment interaction (G×E) for the target trait, e.g. yield, is an emerging property of agricultural systems and results from the interplay between a hierarchy of secondary traits involving the capture and allocation of environmental resources during the growing season. This hierarchy of secondary traits ranges from basic traits that correspond to response mechanisms/sensitivities, to intermediate traits that integrate a larger number of processes over time and therefore show a larger amount of G×E. Traits underlying yield differ in their contribution to adaptation across environmental conditions and have different levels of G×E. Here, we provide a framework to study the performance of genotype to phenotype (G2P) modeling approaches. We generate and analyze response surfaces, or adaptation landscapes, for yield and yield related traits, emphasizing the organization of the traits in a hierarchy and their development and interactions over time. We use the crop growth model APSIM-wheat with genotype-dependent parameters as a tool to simulate non-linear trait responses over time with complex trait dependencies and apply it to wheat crops in Australia. For biological realism, APSIM parameters were given a genetic basis of 300 QTLs sampled from a gamma distribution whose shape and rate parameters were estimated from real wheat data. In the simulations, the hierarchical organization of the traits and their interactions over time cause G×E for yield even when underlying traits do not show G×E. Insight into how G×E arises during growth and development helps to improve the accuracy of phenotype predictions within and across environments and to optimize trial networks. We produced a tangible simulated adaptation landscape for yield that we first investigated for its biological credibility by statistical models for G×E that incorporate genotypic and environmental covariables. Subsequently, the simulated trait data were used to evaluate statistical genotype-to-phenotype models for multiple traits and environments and to characterize relationships between traits over time and across environments, as a way to identify traits that could be useful to select for specific adaptation. Designed appropriately, these types of simulated landscapes might also serve as a basis to train other, more deep learning methodologies in order to transfer such network models to real-world situations.