Models to estimate genetic gain of soybean seed yield from annual multi-environment field trials.

KEY MESSAGE: Simulations demonstrated that estimates of realized genetic gain from linear mixed models using regional trials are biased to some degree. Thus, we recommend multiple selected models to obtain a range of reasonable estimates. Genetic improvements of discrete characteristics are obvious and easy to demonstrate, while quantitative traits require reliable and accurate methods to disentangle the confounding genetic and non-genetic components. Stochastic simulations of soybean [Glycine max (L.) Merr.] breeding programs were performed to evaluate linear mixed models to estimate the realized genetic gain (RGG) from annual multi-environment trials (MET). True breeding values were simulated under an infinitesimal model to represent the genetic contributions to soybean seed yield under various MET conditions. Estimators were evaluated using objective criteria of bias and linearity. Covariance modeling and direct versus indirect estimation-based models resulted in a substantial range of estimated values, all of which were biased to some degree. Although no models produced unbiased estimates, the three best-performing models resulted in an average bias of [Formula: see text] kg/ha[Formula: see text]/yr[Formula: see text] ([Formula: see text] bu/ac[Formula: see text]/yr[Formula: see text]). Rather than relying on a single model to estimate RGG, we recommend the application of several models with minimal and directional bias. Further, based on the parameters used in the simulations, we do not think it is appropriate to use any single model to compare breeding programs or quantify the efficiency of proposed new breeding strategies. Lastly, for public soybean programs breeding for maturity groups II and III in North America, the estimated RGG values ranged from 18.16 to 39.68 kg/ha[Formula: see text]/yr[Formula: see text] (0.27-0.59 bu/ac[Formula: see text]/yr[Formula: see text]) from 1989 to 2019. These results provide strong evidence that public breeders have significantly improved soybean germplasm for seed yield in the primary production areas of North America.

Interaction between Rag genes results in a unique synergistic transcriptional response that enhances soybean resistance to soybean aphids.

BACKGROUND: Pyramiding different resistance genes into one plant genotype confers enhanced resistance at the phenotypic level, but the molecular mechanisms underlying this effect are not well-understood. In soybean, aphid resistance is conferred by Rag genes. We compared the transcriptional response of four soybean genotypes to aphid feeding to assess how the combination of Rag genes enhanced the soybean resistance to aphid infestation. RESULTS: A strong synergistic interaction between Rag1 and Rag2, defined as genes differentially expressed only in the pyramid genotype, was identified. This synergistic effect in the Rag1/2 phenotype was very evident early (6 h after infestation) and involved unique biological processes. However, the response of susceptible and resistant genotypes had a large overlap 12 h after aphid infestation. Transcription factor (TF) analyses identified a network of interacting TF that potentially integrates signaling from Rag1 and Rag2 to produce the unique Rag1/2 response. Pyramiding resulted in rapid induction of phytochemicals production and deposition of lignin to strengthen the secondary cell wall, while repressing photosynthesis. We also identified Glyma.07G063700 as a novel, strong candidate for the Rag1 gene. CONCLUSIONS: The synergistic interaction between Rag1 and Rag2 in the Rag1/2 genotype can explain its enhanced resistance phenotype. Understanding molecular mechanisms that support enhanced resistance in pyramid genotypes could facilitate more directed approaches for crop improvement.

An explainable deep machine vision framework for plant stress phenotyping.

Current approaches for accurate identification, classification, and quantification of biotic and abiotic stresses in crop research and production are predominantly visual and require specialized training. However, such techniques are hindered by subjectivity resulting from inter- and intrarater cognitive variability. This translates to erroneous decisions and a significant waste of resources. Here, we demonstrate a machine learning framework's ability to identify and classify a diverse set of foliar stresses in soybean [Glycine max (L.) Merr.] with remarkable accuracy. We also present an explanation mechanism, using the top-K high-resolution feature maps that isolate the visual symptoms used to make predictions. This unsupervised identification of visual symptoms provides a quantitative measure of stress severity, allowing for identification (type of foliar stress), classification (low, medium, or high stress), and quantification (stress severity) in a single framework without detailed symptom annotation by experts. We reliably identified and classified several biotic (bacterial and fungal diseases) and abiotic (chemical injury and nutrient deficiency) stresses by learning from over 25,000 images. The learned model is robust to input image perturbations, demonstrating viability for high-throughput deployment. We also noticed that the learned model appears to be agnostic to species, seemingly demonstrating an ability of transfer learning. The availability of an explainable model that can consistently, rapidly, and accurately identify and quantify foliar stresses would have significant implications in scientific research, plant breeding, and crop production. The trained model could be deployed in mobile platforms (e.g., unmanned air vehicles and automated ground scouts) for rapid, large-scale scouting or as a mobile application for real-time detection of stress by farmers and researchers.

Comparing Early Transcriptomic Responses of 18 Soybean (Glycine max) Genotypes to Iron Stress.

Iron deficiency chlorosis (IDC) is an abiotic stress that negatively affects soybean (Glycine max [L.] Merr.) production. Much of our knowledge of IDC stress responses is derived from model plant species. Gene expression, quantitative trait loci (QTL) mapping, and genome-wide association studies (GWAS) performed in soybean suggest that stress response differences exist between model and crop species. Our current understanding of the molecular response to IDC in soybeans is largely derived from gene expression studies using near-isogenic lines differing in iron efficiency. To improve iron efficiency in soybeans and other crops, we need to expand gene expression studies to include the diversity present in germplasm collections. Therefore, we collected 216 purified RNA samples (18 genotypes, two tissue types [leaves and roots], two iron treatments [sufficient and deficient], three replicates) and used RNA sequencing to examine the expression differences of 18 diverse soybean genotypes in response to iron deficiency. We found a rapid response to iron deficiency across genotypes, most responding within 60 min of stress. There was little evidence of an overlap of specific differentially expressed genes, and comparisons of gene ontology terms and transcription factor families suggest the utilization of different pathways in the stress response. These initial findings suggest an untapped genetic potential within the soybean germplasm collection that could be used for the continued improvement of iron efficiency in soybean.

Deconstructing the genetic architecture of iron deficiency chlorosis in soybean using genome-wide approaches.

BACKGROUND: Iron (Fe) is an essential micronutrient for plant growth and development. Iron deficiency chlorosis (IDC), caused by calcareous soils or high soil pH, can limit iron availability, negatively affecting soybean (Glycine max) yield. This study leverages genome-wide association study (GWAS) and a genome-wide epistatic study (GWES) with previous gene expression studies to identify regions of the soybean genome important in iron deficiency tolerance. RESULTS: A GWAS and a GWES were performed using 460 diverse soybean PI lines from 27 countries, in field and hydroponic iron stress conditions, using more than 36,000 single nucleotide polymorphism (SNP) markers. Combining this approach with available RNA-sequencing data identified significant markers, genomic regions, and novel genes associated with or responding to iron deficiency. Sixty-nine genomic regions associated with IDC tolerance were identified across 19 chromosomes via the GWAS, including the major-effect quantitative trait locus (QTL) on chromosome Gm03. Cluster analysis of significant SNPs in this region deconstructed this historically prominent QTL into four distinct linkage blocks, enabling the identification of multiple candidate genes for iron chlorosis tolerance. The complementary GWES identified SNPs in this region interacting with nine other genomic regions, providing the first evidence of epistatic interactions impacting iron deficiency tolerance. CONCLUSIONS: This study demonstrates that integrating cutting edge genome wide association (GWA), genome wide epistasis (GWE), and gene expression studies is a powerful strategy to identify novel iron tolerance QTL and candidate loci from diverse germplasm. Crops, unlike model species, have undergone selection for thousands of years, constraining and/or enhancing stress responses. Leveraging genomics-enabled approaches to study these adaptations is essential for future crop improvement.

Multi-objective optimized genomic breeding strategies for sustainable food improvement.

The purpose of breeding programs is to obtain sustainable gains in multiple traits while controlling the loss of genetic variation. The decisions at each breeding cycle involve multiple, usually competing, objectives; these complex decisions can be supported by the insights that are gained by applying multi-objective optimization principles to breeding. The discussion in this manuscript includes the definition of several multi-objective optimized breeding approaches within the phenotypic or genomic breeding frameworks and the comparison of these approaches with the standard multi-trait breeding schemes such as tandem selection, independent culling and index selection. Proposed methods are demonstrated with two empirical data sets and simulations. In addition, we have described several graphical tools that can aid breeders in arriving at a compromise decision. The results show that the proposed methodology is a viable approach to answer several real breeding problems. In simulations, the newly proposed methods resulted in gains larger than the methods previously proposed including index selection: Compared to the best alternative breeding strategy, the gains from multi-objective optimized parental proportions approaches were about 20-30% higher at the end of long-term simulations of breeding cycles. In addition, the flexibility of the multi-objective optimized breeding strategies were displayed with methods and examples covering non-dominated selection, assignment of optimal parental proportions, using genomewide marker effects in producing optimal mating designs, and finally in selection of training populations for genomic prediction.

Abundance of the arbuscular mycorrhizal fungal taxa associated with the roots and rhizosphere soil of different durum wheat cultivars in the Canadian prairies.

Understanding the variation in how wheat genotypes shape their arbuscular mycorrhizal (AM) fungal communities in a prairie environment is foundational to breeding for enhanced AM fungi-wheat interactions. The AM fungal communities associated with 32 durum wheat genotypes were described by pyrosequencing of amplicons. The experiment was set up at two locations in the Canadian prairies. The intensively managed site was highly dominated by Funneliformis. Genotype influenced the AM fungal community in the rhizosphere soil, but there was no evidence of a differential genotype effect on the AM fungal community of durum wheat roots. The influence of durum wheat genotype on the AM fungal community of the soil was less important at the intensively managed site. Certain durum wheat genotypes, such as Strongfield, Plenty, and CDC Verona, were associated with high abundance of Paraglomus, and Dominikia was undetected in the rhizosphere of the recent cultivars Enterprise, Eurostar, Commander, and Brigade. Genetic variation in the association of durum wheat with AM fungi suggests the possibility of increasing the sustainability of cropping systems through the use of durum wheat genotypes that select highly effective AM fungal taxa residing in the agricultural soils of the Canadian prairies.

Quantitative trait loci for resistance to stripe rust of wheat revealed using global field nurseries and opportunities for stacking resistance genes.

KEY MESSAGE: Quantitative trait loci controlling stripe rust resistance were identified in adapted Canadian spring wheat cultivars providing opportunity for breeders to stack loci using marker-assisted breeding. Stripe rust or yellow rust, caused by Puccinia striiformis Westend. f. sp. tritici Erikss., is a devastating disease of common wheat (Triticum aestivum L.) in many regions of the world. The objectives of this research were to identify and map quantitative trait loci (QTL) associated with stripe rust resistance in adapted Canadian spring wheat cultivars that are effective globally, and investigate opportunities for stacking resistance. Doubled haploid (DH) populations from the crosses Vesper/Lillian, Vesper/Stettler, Carberry/Vesper, Stettler/Red Fife and Carberry/AC Cadillac were phenotyped for stripe rust severity and infection response in field nurseries in Canada (Lethbridge and Swift Current), New Zealand (Lincoln), Mexico (Toluca) and Kenya (Njoro), and genotyped with SNP markers. Six QTL for stripe rust resistance in the population of Vesper/Lillian, five in Vesper/Stettler, seven in Stettler/Red Fife, four in Carberry/Vesper and nine in Carberry/AC Cadillac were identified. Lillian contributed stripe rust resistance QTL on chromosomes 4B, 5A, 6B and 7D, AC Cadillac on 2A, 2B, 3B and 5B, Carberry on 1A, 1B, 4A, 4B, 7A and 7D, Stettler on 1A, 2A, 3D, 4A, 5B and 6A, Red Fife on 2D, 3B and 4B, and Vesper on 1B, 2B and 7A. QTL on 1A, 1B, 2A, 2B, 3B, 4A, 4B, 5B, 7A and 7D were observed in multiple parents. The populations are compelling sources of recombination of many stripe rust resistance QTL for stacking disease resistance. Gene pyramiding should be possible with little chance of linkage drag of detrimental genes as the source parents were mostly adapted cultivars widely grown in Canada.

Genome-wide association and epistasis studies unravel the genetic architecture of sudden death syndrome resistance in soybean.

Soybean [Glycine max (L.) Merr.] is an economically important crop that is grown worldwide. Sudden death syndrome (SDS), caused by Fusarium virguliforme, is one of the top yield-limiting diseases in soybean. However, the genetic basis of SDS resistance, especially with respect to epistatic interactions, is still unclear. To better understand the genetic architecture of soybean SDS resistance, genome-wide association and epistasis studies were performed using a population of 214 germplasm accessions and 31,914 SNPs from the SoySNP50K Illumina Infinium BeadChip. Twelve loci and 12 SNP-SNP interactions associated with SDS resistance were identified at various time points after inoculation. These additive and epistatic loci together explained 24-52% of the phenotypic variance. Disease-resistant, pathogenesis-related and chitin- and wound-responsive genes were identified in the proximity of peak SNPs, including stress-induced receptor-like kinase gene 1 (SIK1), which is pinpointed by a trait-associated SNP and encodes a leucine-rich repeat-containing protein. We report that the proportion of phenotypic variance explained by identified loci may be considerably improved by taking epistatic effects into account. This study shows the necessity of considering epistatic effects in soybean SDS resistance breeding using marker-assisted and genomic selection approaches. Based on our findings, we propose a model for soybean root defense against the SDS pathogen. Our results facilitate identification of the molecular mechanism underlying SDS resistance in soybean, and provide a genetic basis for improvement of soybean SDS resistance through breeding strategies based on additive and epistatic effects.

Potential to breed for mycorrhizal association in durum wheat.

The selection of genotypes under high soil fertility may alter the effectiveness of mycorrhizal symbioses naturally forming between crop plants and the mycorrhizal fungi residing in cultivated fields. We tested the hypothesis that the mycorrhizal symbiosis of 5 landraces functions better than the mycorrhizal symbiosis of 27 cultivars of durum wheat that were bred after the development of the fertilizer industry. We examined the development of mycorrhiza and the response of these genotypes to mycorrhiza formation after 4 weeks of growth under high and low soil fertility levels in the greenhouse. The durum wheat genotypes were seeded in an established extraradical hyphal network of Rhizophagus irregularis and in a control soil free of mycorrhizal fungi. The percentage of root length colonized by mycorrhizal fungi was lower in landraces (21%) than in cultivars (27%; P = 0.04) and in the most recent releases (29%; P = 0.02), which were selected under high soil fertility levels. Plant growth response to mycorrhiza varied from -36% to +19%. Overall, durum wheat plant breeding in Canada has increased the mycorrhizal development in wheat grown at a low soil fertility level. However, breeding had inconsistent effects on mycorrhizal development and has led to the production of cultivars with patterns of regulation ranging from unimproved to inefficient.

Out-of-Distribution Detection Algorithms for Robust Insect Classification.

Plants encounter a variety of beneficial and harmful insects during their growth cycle. Accurate identification (i.e., detecting insects' presence) and classification (i.e., determining the type or class) of these insect species is critical for implementing prompt and suitable mitigation strategies. Such timely actions carry substantial economic and environmental implications. Deep learning-based approaches have produced models with good insect classification accuracy. Researchers aim to implement identification and classification models in agriculture, facing challenges when input images markedly deviate from the training distribution (e.g., images like vehicles, humans, or a blurred image or insect class that is not yet trained on). Out-of-distribution (OOD) detection algorithms provide an exciting avenue to overcome these challenges as they ensure that a model abstains from making incorrect classification predictions on images that belong to non-insect and/or untrained insect classes. As far as we know, no prior in-depth exploration has been conducted on the role of the OOD detection algorithms in addressing agricultural issues. Here, we generate and evaluate the performance of state-of-the-art OOD algorithms on insect detection classifiers. These algorithms represent a diversity of methods for addressing an OOD problem. Specifically, we focus on extrusive algorithms, i.e., algorithms that wrap around a well-trained classifier without the need for additional co-training. We compared three OOD detection algorithms: (a) maximum softmax probability, which uses the softmax value as a confidence score; (b) Mahalanobis distance (MAH)-based algorithm, which uses a generative classification approach; and (c) energy-based algorithm, which maps the input data to a scalar value, called energy. We performed an extensive series of evaluations of these OOD algorithms across three performance axes: (a) Base model accuracy: How does the accuracy of the classifier impact OOD performance? (b) How does the level of dissimilarity to the domain impact OOD performance? (c) Data imbalance: How sensitive is OOD performance to the imbalance in per-class sample size? Evaluating OOD algorithms across these performance axes provides practical guidelines to ensure the robust performance of well-trained models in the wild, which is a key consideration for agricultural applications. Based on this analysis, we proposed the most effective OOD algorithm as wrapper for the insect classifier with highest accuracy. We presented the results of its OOD detection performance in the paper. Our results indicate that OOD detection algorithms can significantly enhance user trust in insect pest classification by abstaining classification under uncertain conditions.

Cyber-agricultural systems for crop breeding and sustainable production.

The cyber-agricultural system (CAS) represents an overarching framework of agriculture that leverages recent advances in ubiquitous sensing, artificial intelligence, smart actuators, and scalable cyberinfrastructure (CI) in both breeding and production agriculture. We discuss the recent progress and perspective of the three fundamental components of CAS - sensing, modeling, and actuation - and the emerging concept of agricultural digital twins (DTs). We also discuss how scalable CI is becoming a key enabler of smart agriculture. In this review we shed light on the significance of CAS in revolutionizing crop breeding and production by enhancing efficiency, productivity, sustainability, and resilience to changing climate. Finally, we identify underexplored and promising future directions for CAS research and development.

Using machine learning enabled phenotyping to characterize nodulation in three early vegetative stages in soybean.

The symbiotic relationship between soybean [Glycine max L. (Merr.)] roots and bacteria (Bradyrhizobium japonicum) lead to the development of nodules, important legume root structures where atmospheric nitrogen (N2) is fixed into bio-available ammonia (NH3) for plant growth and development. With the recent development of the Soybean Nodule Acquisition Pipeline (SNAP), nodules can more easily be quantified and evaluated for genetic diversity and growth patterns across unique soybean root system architectures. We explored six diverse soybean genotypes across three field year combinations in three early vegetative stages of development and report the unique relationships between soybean nodules in the taproot and non-taproot growth zones of diverse root system architectures of these genotypes. We found unique growth patterns in the nodules of taproots showing genotypic differences in how nodules grew in count, size, and total nodule area per genotype compared to non-taproot nodules. We propose that nodulation should be defined as a function of both nodule count and individual nodule area resulting in a total nodule area per root or growth regions of the root. We also report on the relationships between the nodules and total nitrogen in the seed at maturity, finding a strong correlation between the taproot nodules and final seed nitrogen at maturity. The applications of these findings could lead to an enhanced understanding of the plant-Bradyrhizobium relationship and exploring these relationships could lead to leveraging greater nitrogen use efficiency and nodulation carbon to nitrogen production efficiency across the soybean germplasm.

"Canopy fingerprints" for characterizing three-dimensional point cloud data of soybean canopies.

Advances in imaging hardware allow high throughput capture of the detailed three-dimensional (3D) structure of plant canopies. The point cloud data is typically post-processed to extract coarse-scale geometric features (like volume, surface area, height, etc.) for downstream analysis. We extend feature extraction from 3D point cloud data to various additional features, which we denote as 'canopy fingerprints'. This is motivated by the successful application of the fingerprint concept for molecular fingerprints in chemistry applications and acoustic fingerprints in sound engineering applications. We developed an end-to-end pipeline to generate canopy fingerprints of a three-dimensional point cloud of soybean [Glycine max (L.) Merr.] canopies grown in hill plots captured by a terrestrial laser scanner (TLS). The pipeline includes noise removal, registration, and plot extraction, followed by the canopy fingerprint generation. The canopy fingerprints are generated by splitting the data into multiple sub-canopy scale components and extracting sub-canopy scale geometric features. The generated canopy fingerprints are interpretable and can assist in identifying patterns in a database of canopies, querying similar canopies, or identifying canopies with a certain shape. The framework can be extended to other modalities (for instance, hyperspectral point clouds) and tuned to find the most informative fingerprint representation for downstream tasks. These canopy fingerprints can aid in the utilization of canopy traits at previously unutilized scales, and therefore have applications in plant breeding and resilient crop production.

Deep learning-based phenotyping for genome wide association studies of sudden death syndrome in soybean.

Using a reliable and accurate method to phenotype disease incidence and severity is essential to unravel the complex genetic architecture of disease resistance in plants, and to develop disease resistant cultivars. Genome-wide association studies (GWAS) involve phenotyping large numbers of accessions, and have been used for a myriad of traits. In field studies, genetic accessions are phenotyped across multiple environments and replications, which takes a significant amount of labor and resources. Deep Learning (DL) techniques can be effective for analyzing image-based tasks; thus DL methods are becoming more routine for phenotyping traits to save time and effort. This research aims to conduct GWAS on sudden death syndrome (SDS) of soybean [Glycine max L. (Merr.)] using disease severity from both visual field ratings and DL-based (using images) severity ratings collected from 473 accessions. Images were processed through a DL framework that identified soybean leaflets with SDS symptoms, and then quantified the disease severity on those leaflets into a few classes with mean Average Precision of 0.34 on unseen test data. Both visual field ratings and image-based ratings identified significant single nucleotide polymorphism (SNP) markers associated with disease resistance. These significant SNP markers are either in the proximity of previously reported candidate genes for SDS or near potentially novel candidate genes. Four previously reported SDS QTL were identified that contained a significant SNPs, from this study, from both a visual field rating and an image-based rating. The results of this study provide an exciting avenue of using DL to capture complex phenotypic traits from images to get comparable or more insightful results compared to subjective visual field phenotyping of traits for disease symptoms.

Raffinose Family Oligosaccharides: Friend or Foe for Human and Plant Health?

Raffinose family oligosaccharides (RFOs) are widespread across the plant kingdom, and their concentrations are related to the environment, genotype, and harvest time. RFOs are known to carry out many functions in plants and humans. In this paper, we provide a comprehensive review of RFOs, including their beneficial and anti-nutritional properties. RFOs are considered anti-nutritional factors since they cause flatulence in humans and animals. Flatulence is the single most important factor that deters consumption and utilization of legumes in human and animal diets. In plants, RFOs have been reported to impart tolerance to heat, drought, cold, salinity, and disease resistance besides regulating seed germination, vigor, and longevity. In humans, RFOs have beneficial effects in the large intestine and have shown prebiotic potential by promoting the growth of beneficial bacteria reducing pathogens and putrefactive bacteria present in the colon. In addition to their prebiotic potential, RFOs have many other biological functions in humans and animals, such as anti-allergic, anti-obesity, anti-diabetic, prevention of non-alcoholic fatty liver disease, and cryoprotection. The wide-ranging applications of RFOs make them useful in food, feed, cosmetics, health, pharmaceuticals, and plant stress tolerance; therefore, we review the composition and diversity of RFOs, describe the metabolism and genetics of RFOs, evaluate their role in plant and human health, with a primary focus in grain legumes.

PATRIOT: A Pipeline for Tracing Identity-by-Descent for Chromosome Segments to Improve Genomic Prediction in Self-Pollinating Crop Species.

The lowering genotyping cost is ushering in a wider interest and adoption of genomic prediction and selection in plant breeding programs worldwide. However, improper conflation of historical and recent linkage disequilibrium between markers and genes restricts high accuracy of genomic prediction (GP). Multiple ancestors may share a common haplotype surrounding a gene, without sharing the same allele of that gene. This prevents parsing out genetic effects associated with the underlying allele of that gene among the set of ancestral haplotypes. We present "Parental Allele Tracing, Recombination Identification, and Optimal predicTion" (i.e., PATRIOT) approach that utilizes marker data to allow for a rapid identification of lines carrying specific alleles, increases the accuracy of genomic relatedness and diversity estimates, and improves genomic prediction. Leveraging identity-by-descent relationships, PATRIOT showed an improvement in GP accuracy by 16.6% relative to the traditional rrBLUP method. This approach will help to increase the rate of genetic gain and allow available information to be more effectively utilized within breeding programs.

Crop yield prediction integrating genotype and weather variables using deep learning.

Accurate prediction of crop yield supported by scientific and domain-relevant insights, is useful to improve agricultural breeding, provide monitoring across diverse climatic conditions and thereby protect against climatic challenges to crop production. We used performance records from Uniform Soybean Tests (UST) in North America to build a Long Short Term Memory (LSTM)-Recurrent Neural Network based model that leveraged pedigree relatedness measures along with weekly weather parameters to dissect and predict genotype response in multiple-environments. Our proposed models outperformed other competing machine learning models such as Support Vector Regression with Radial Basis Function kernel (SVR-RBF), least absolute shrinkage and selection operator (LASSO) regression and the data-driven USDA model for yield prediction. Additionally, for providing interpretability of the important time-windows in the growing season, we developed a temporal attention mechanism for LSTM models. The outputs of such interpretable models could provide valuable insights to plant breeders.

Using Machine Learning to Develop a Fully Automated Soybean Nodule Acquisition Pipeline (SNAP).

Nodules form on plant roots through the symbiotic relationship between soybean (Glycine max L. Merr.) roots and bacteria (Bradyrhizobium japonicum) and are an important structure where atmospheric nitrogen (N2) is fixed into bioavailable ammonia (NH3) for plant growth and development. Nodule quantification on soybean roots is a laborious and tedious task; therefore, assessment is frequently done on a numerical scale that allows for rapid phenotyping, but is less informative and suffers from subjectivity. We report the Soybean Nodule Acquisition Pipeline (SNAP) for nodule quantification that combines RetinaNet and UNet deep learning architectures for object (i.e., nodule) detection and segmentation. SNAP was built using data from 691 unique roots from diverse soybean genotypes, vegetative growth stages, and field locations and has a good model fit (R 2 = 0.99). SNAP reduces the human labor and inconsistencies of counting nodules, while acquiring quantifiable traits related to nodule growth, location, and distribution on roots. The ability of SNAP to phenotype nodules on soybean roots at a higher throughput enables researchers to assess the genetic and environmental factors, and their interactions on nodulation from an early development stage. The application of SNAP in research and breeding pipelines may lead to more nitrogen use efficiency for soybean and other legume species cultivars, as well as enhanced insight into the plant-Bradyrhizobium relationship.

Meta-GWAS for quantitative trait loci identification in soybean.

We report a meta-Genome Wide Association Study involving 73 published studies in soybean [Glycine max L. (Merr.)] covering 17,556 unique accessions, with improved statistical power for robust detection of loci associated with a broad range of traits. De novo GWAS and meta-analysis were conducted for composition traits including fatty acid and amino acid composition traits, disease resistance traits, and agronomic traits including seed yield, plant height, stem lodging, seed weight, seed mottling, seed quality, flowering timing, and pod shattering. To examine differences in detectability and test statistical power between single- and multi-environment GWAS, comparison of meta-GWAS results to those from the constituent experiments were performed. Using meta-GWAS analysis and the analysis of individual studies, we report 483 peaks at 393 unique loci. Using stringent criteria to detect significant marker-trait associations, 59 candidate genes were identified, including 17 agronomic traits loci, 19 for seed-related traits, and 33 for disease reaction traits. This study identified potentially valuable candidate genes that affect multiple traits. The success in narrowing down the genomic region for some loci through overlapping mapping results of multiple studies is a promising avenue for community-based studies and plant breeding applications.