Evaluation of Effective Class-Balancing Techniques for CNN-Based Assessment of Aphanomyces Root Rot Resistance in Pea (Pisum sativum L.).

Aphanomyces root rot (ARR) is a devastating disease that affects the production of pea. The plants are prone to infection at any growth stage, and there are no chemical or cultural controls. Thus, the development of resistant pea cultivars is important. Phenomics technologies to support the selection of resistant cultivars through phenotyping can be valuable. One such approach is to couple imaging technologies with deep learning algorithms that are considered efficient for the assessment of disease resistance across a large number of plant genotypes. In this study, the resistance to ARR was evaluated through a CNN-based assessment of pea root images. The proposed model, DeepARRNet, was designed to classify the pea root images into three classes based on ARR severity scores, namely, resistant, intermediate, and susceptible classes. The dataset consisted of 1581 pea root images with a skewed distribution. Hence, three effective data-balancing techniques were identified to solve the prevalent problem of unbalanced datasets. Random oversampling with image transformations, generative adversarial network (GAN)-based image synthesis, and loss function with class-weighted ratio were implemented during the training process. The result indicated that the classification F1-score was 0.92 ± 0.03 when GAN-synthesized images were added, 0.91 ± 0.04 for random resampling, and 0.88 ± 0.05 when class-weighted loss function was implemented, which was higher than when an unbalanced dataset without these techniques were used (0.83 ± 0.03). The systematic approaches evaluated in this study can be applied to other image-based phenotyping datasets, which can aid the development of deep-learning models with improved performance.

Image-Based Phenotyping of Flowering Intensity in Cool-Season Crops.

The timing and duration of flowering are key agronomic traits that are often associated with the ability of a variety to escape abiotic stress such as heat and drought. Flowering information is valuable in both plant breeding and agricultural production management. Visual assessment, the standard protocol used for phenotyping flowering, is a low-throughput and subjective method. In this study, we evaluated multiple imaging sensors (RGB and multiple multispectral cameras), image resolution (proximal/remote sensing at 1.6 to 30 m above ground level/AGL), and image processing (standard and unsupervised learning) techniques in monitoring flowering intensity of four cool-season crops (canola, camelina, chickpea, and pea) to enhance the accuracy and efficiency in quantifying flowering traits. The features (flower area, percentage of flower area with respect to canopy area) extracted from proximal (1.6-2.2 m AGL) RGB and multispectral (with near infrared, green and blue band) image data were strongly correlated (r up to 0.89) with visual rating scores, especially in pea and canola. The features extracted from unmanned aerial vehicle integrated RGB image data (15-30 m AGL) could also accurately detect and quantify large flowers of winter canola (r up to 0.84), spring canola (r up to 0.72), and pea (r up to 0.72), but not camelina or chickpea flowers. When standard image processing using thresholds and unsupervised machine learning such as k-means clustering were utilized for flower detection and feature extraction, the results were comparable. In general, for applicability of imaging for flower detection, it is recommended that the image data resolution (i.e., ground sampling distance) is at least 2-3 times smaller than that of the flower size. Overall, this study demonstrates the feasibility of utilizing imaging for monitoring flowering intensity in multiple varieties of evaluated crops.

Dissecting the Genetic Architecture of Aphanomyces Root Rot Resistance in Lentil by QTL Mapping and Genome-Wide Association Study.

Lentil (Lens culinaris Medikus) is an important source of protein for people in developing countries. Aphanomyces root rot (ARR) has emerged as one of the most devastating diseases affecting lentil production. In this study, we applied two complementary quantitative trait loci (QTL) analysis approaches to unravel the genetic architecture underlying this complex trait. A recombinant inbred line (RIL) population and an association mapping population were genotyped using genotyping by sequencing (GBS) to discover novel single nucleotide polymorphisms (SNPs). QTL mapping identified 19 QTL associated with ARR resistance, while association mapping detected 38 QTL and highlighted accumulation of favorable haplotypes in most of the resistant accessions. Seven QTL clusters were discovered on six chromosomes, and 15 putative genes were identified within the QTL clusters. To validate QTL mapping and genome-wide association study (GWAS) results, expression analysis of five selected genes was conducted on partially resistant and susceptible accessions. Three of the genes were differentially expressed at early stages of infection, two of which may be associated with ARR resistance. Our findings provide valuable insight into the genetic control of ARR, and genetic and genomic resources developed here can be used to accelerate development of lentil cultivars with high levels of partial resistance to ARR.

Confirmation of Fusarium root rot resistance QTL Fsp-Ps 2.1 of pea under controlled conditions.

BACKGROUND: Dry pea production has increased substantially in North America over the last few decades. With this expansion, significant yield losses have been attributed to an escalation in Fusarium root rots in pea fields. Among the most significant rot rotting pathogenic fungal species, Fusarium solani fsp. pisi (Fsp) is one of the main causal agents of root rot of pea. High levels of partial resistance to Fsp has been identified in plant genetic resources. Genetic resistance offers one of the best solutions to control this root rotting fungus. A recombinant inbred population segregating for high levels of partial resistance, previously single nucleotide polymorphism (SNP) genotyped using genotyping-by-sequencing, was phenotyped for disease reaction in replicated and repeated greenhouse trials. Composite interval mapping was deployed to identify resistance-associated quantitative trait loci (QTL). RESULTS: Three QTL were identified using three disease reaction criteria: root disease severity, ratios of diseased vs. healthy shoot heights and dry plant weights under controlled conditions using pure cultures of Fusarium solani fsp. pisi. One QTL Fsp-Ps 2.1 explains 44.4-53.4% of the variance with a narrow confidence interval of 1.2 cM. The second and third QTL Fsp-Ps3.2 and Fsp-Ps3.3 are closely linked and explain only 3.6-4.6% of the variance. All of the alleles are contributed by the resistant parent PI 180693. CONCLUSION: With the confirmation of Fsp-Ps 2.1 now in two RIL populations, SNPs associated with this region make a good target for marker-assisted selection in pea breeding programs to obtain high levels of partial resistance to Fusarium root rot caused by Fusarium solani fsp. pisi.

Phenotyping of Plant Biomass and Performance Traits Using Remote Sensing Techniques in Pea (Pisum sativum, L.).

Field pea cultivars are constantly improved through breeding programs to enhance biotic and abiotic stress tolerance and increase seed yield potential. In pea breeding, the Above Ground Biomass (AGBM) is assessed due to its influence on seed yield, canopy closure, and weed suppression. It is also the primary yield component for peas used as a cover crop and/or grazing. Measuring AGBM is destructive and labor-intensive process. Sensor-based phenotyping of such traits can greatly enhance crop breeding efficiency. In this research, high resolution RGB and multispectral images acquired with unmanned aerial systems were used to assess phenotypes in spring and winter pea breeding plots. The Green Red Vegetation Index (GRVI), Normalized Difference Vegetation Index (NDVI), Normalized Difference Red Edge Index (NDRE), plot volume, canopy height, and canopy coverage were extracted from RGB and multispectral information at five imaging times (between 365 to 1948 accumulated degree days/ADD after 1 May) in four winter field pea experiments and at three imaging times (between 1231 to 1648 ADD) in one spring field pea experiment. The image features were compared to ground-truth data including AGBM, lodging, leaf type, days to 50% flowering, days to physiological maturity, number of the first reproductive node, and seed yield. In two of the winter pea experiments, a strong correlation between image features and seed yield was observed at 1268 ADD (flowering). An increase in correlation between image features with the phenological traits such as days to 50% flowering and days to physiological maturity was observed at about 1725 ADD in these winter pea experiments. In the spring pea experiment, the plot volume estimated from images was highly correlated with ground truth canopy height (r = 0.83) at 1231 ADD. In two other winter pea experiments and the spring pea experiment, the GRVI and NDVI features were significantly correlated with AGBM at flowering. When selected image features were used to develop a least absolute shrinkage and selection operator model for AGBM estimation, the correlation coefficient between the actual and predicted AGBM was 0.60 and 0.84 in the winter and spring pea experiments, respectively. A SPOT-6 satellite image (1.5 m resolution) was also evaluated for its applicability to assess biomass and seed yield. The image features extracted from satellite imagery showed significant correlation with seed yield in two winter field pea experiments, however, the trend was not consistent. In summary, the study supports the potential of using unmanned aerial system-based imaging techniques to estimate biomass and crop performance in pea breeding programs.

Near-infrared spectroscopic models for analysis of winter pea (Pisum sativum L.) quality constituents.

BACKGROUND: Winter pea (Pisum sativum L.) grows well in a wide geographic region, both as a forage and cover crop. Understanding the quality constituents of this crop is important for both end uses; however, analysis of quality constituents by conventional wet chemistry methods is laborious, slow and costly. Near infrared reflectance spectroscopy (NIRS) is a precise, accurate, rapid and cheap alternative to using wet chemistry for estimating quality constituents. We developed and validated NIRS calibration models for constituent analysis of this crop. RESULTS: Of the 11 constituent models developed, nine constituents including moisture, dry-matter, total-nitrogen, crude protein, acid detergent fiber, neutral detergent fiber, AD-lignin, cellulose and non-fibrous carbohydrate had low standard errors and a high coefficient of determination (R2 = 0.88-0.98; 1 - VR, which is the coefficient of determination during cross-validation = 0.77-0.92) for both calibration and cross-validation, indicating their potential for quantitative predictability. The calibration models for ash (R2 = 0.65; 1 - VR = 0.46) and hemicellulose (R2 = 0.75; 1 - VR = 0.50) also appeared to be adequate for qualitative screening. Predictions of an independent validation set yielded reliable agreement between the NIRS predicted values and the reference values with low standard error of prediction (SEP), low bias, high coefficient of determination (r2 = 0.82-0.95), high ratios of performance to deviation (RPD = SD/SEP; 2.30-3.85) and high ratios of performance to interquartile distance (RPIQ = IQ/SEP; 2.57-7.59) for all 11 constituents. CONCLUSION: Precise, accurate and rapid analysis of winter pea for major forage and cover crop quality constituents can be performed at a low cost using the NIRS calibration models developed. © 2018 Society of Chemical Industry.

Genome-wide SNP identification, linkage map construction and QTL mapping for seed mineral concentrations and contents in pea (Pisum sativum L.).

BACKGROUND: Marker-assisted breeding is now routinely used in major crops to facilitate more efficient cultivar improvement. This has been significantly enabled by the use of next-generation sequencing technology to identify loci and markers associated with traits of interest. While rich in a range of nutritional components, such as protein, mineral nutrients, carbohydrates and several vitamins, pea (Pisum sativum L.), one of the oldest domesticated crops in the world, remains behind many other crops in the availability of genomic and genetic resources. To further improve mineral nutrient levels in pea seeds requires the development of genome-wide tools. The objectives of this research were to develop these tools by: identifying genome-wide single nucleotide polymorphisms (SNPs) using genotyping by sequencing (GBS); constructing a high-density linkage map and comparative maps with other legumes, and identifying quantitative trait loci (QTL) for levels of boron, calcium, iron, potassium, magnesium, manganese, molybdenum, phosphorous, sulfur, and zinc in the seed, as well as for seed weight. RESULTS: In this study, 1609 high quality SNPs were found to be polymorphic between 'Kiflica' and 'Aragorn', two parents of an F6-derived recombinant inbred line (RIL) population. Mapping 1683 markers including 75 previously published markers and 1608 SNPs developed from the present study generated a linkage map of size 1310.1 cM. Comparative mapping with other legumes demonstrated that the highest level of synteny was observed between pea and the genome of Medicago truncatula. QTL analysis of the RIL population across two locations revealed at least one QTL for each of the mineral nutrient traits. In total, 46 seed mineral concentration QTLs, 37 seed mineral content QTLs, and 6 seed weight QTLs were discovered. The QTLs explained from 2.4% to 43.3% of the phenotypic variance. CONCLUSION: The genome-wide SNPs and the genetic linkage map developed in this study permitted QTL identification for pea seed mineral nutrients that will serve as important resources to enable marker-assisted selection (MAS) for nutritional quality traits in pea breeding programs.

Genome-wide association mapping of partial resistance to Aphanomyces euteiches in pea.

BACKGROUND: Genome-wide association (GWA) mapping has recently emerged as a valuable approach for refining the genetic basis of polygenic resistance to plant diseases, which are increasingly used in integrated strategies for durable crop protection. Aphanomyces euteiches is a soil-borne pathogen of pea and other legumes worldwide, which causes yield-damaging root rot. Linkage mapping studies reported quantitative trait loci (QTL) controlling resistance to A. euteiches in pea. However the confidence intervals (CIs) of these QTL remained large and were often linked to undesirable alleles, which limited their application in breeding. The aim of this study was to use a GWA approach to validate and refine CIs of the previously reported Aphanomyces resistance QTL, as well as identify new resistance loci. METHODS: A pea-Aphanomyces collection of 175 pea lines, enriched in germplasm derived from previously studied resistant sources, was evaluated for resistance to A. euteiches in field infested nurseries in nine environments and with two strains in climatic chambers. The collection was genotyped using 13,204 SNPs from the recently developed GenoPea Infinium® BeadChip. RESULTS: GWA analysis detected a total of 52 QTL of small size-intervals associated with resistance to A. euteiches, using the recently developed Multi-Locus Mixed Model. The analysis validated six of the seven previously reported main Aphanomyces resistance QTL and detected novel resistance loci. It also provided marker haplotypes at 14 consistent QTL regions associated with increased resistance and highlighted accumulation of favourable haplotypes in the most resistant lines. Previous linkages between resistance alleles and undesired late-flowering alleles for dry pea breeding were mostly confirmed, but the linkage between loci controlling resistance and coloured flowers was broken due to the high resolution of the analysis. A high proportion of the putative candidate genes underlying resistance loci encoded stress-related proteins and others suggested that the QTL are involved in diverse functions. CONCLUSION: This study provides valuable markers, marker haplotypes and germplasm lines to increase levels of partial resistance to A. euteiches in pea breeding.

A pulse crop dataset of agronomic traits and multispectral images from multiple environments.

Crop yield potential in breeding trials can be captured using unmanned aerial vehicle (UAV) based multispectral imagery. Several digital traits or phenotypes such as vegetation indices can represent canopy crop vigor and overall plant health, which can be used to evaluate differences in performance across varieties in crop breeding programs. This dataset contains agronomic data for named cultivars and breeding lines of spring-sown dry pea and chickpea, and over 275 multispectral images from advanced and preliminary breeding trials. The breeding trials were located at three locations in the "Palouse" region of Eastern Washington and Northern Idaho of the United States across 2017, 2018 and 2019 cropping seasons. The multispectral images were captured using a UAV integrated with a 5-band multispectral camera at multiple time points from early vegetative growth through pod development stages during each cropping season. This dataset details seed yield information from trials of dry peas and chickpea that were obtained from each location, as well as additional agronomic and phenological data recorded at one location (mostly Pullman, WA) for each cropping season. The dataset also includes 20-78 megabytes (MB) Tagged Image Format (TIF) uncalibrated stitched orthomosaic images generated from the photogrammetric software. The images can be processed using any convenient image processing algorithm to obtain vegetation indices and other useful information.

QTL meta-analysis provides a comprehensive view of loci controlling partial resistance to Aphanomyces euteiches in four sources of resistance in pea.

BACKGROUND: Development of durable plant genetic resistance to pathogens through strategies of QTL pyramiding and diversification requires in depth knowledge of polygenic resistance within the available germplasm. Polygenic partial resistance to Aphanomyces root rot, caused by Aphanomyces euteiches, one of the most damaging pathogens of pea worldwide, was previously dissected in individual mapping populations. However, there are no data available regarding the diversity of the resistance QTL across a broader collection of pea germplasm. In this study, we performed a meta-analysis of Aphanomyces root rot resistance QTL in the four main sources of resistance in pea and compared their genomic localization with genes/QTL controlling morphological or phenological traits and with putative candidate genes. RESULTS: Meta-analysis, conducted using 244 individual QTL reported previously in three mapping populations (Puget x 90-2079, Baccara x PI180693 and Baccara x 552) and in a fourth mapping population in this study (DSP x 90-2131), resulted in the identification of 27 meta-QTL for resistance to A. euteiches. Confidence intervals of meta-QTL were, on average, reduced four-fold compared to mean confidence intervals of individual QTL. Eleven consistent meta-QTL, which highlight seven highly consistent genomic regions, were identified. Few meta-QTL specificities were observed among mapping populations, suggesting that sources of resistance are not independent. Seven resistance meta-QTL, including six of the highly consistent genomic regions, co-localized with six of the meta-QTL identified in this study for earliness and plant height and with three morphological genes (Af, A, R). Alleles contributing to the resistance were often associated with undesirable alleles for dry pea breeding. Candidate genes underlying six main meta-QTL regions were identified using colinearity between the pea and Medicago truncatula genomes. CONCLUSIONS: QTL meta-analysis provided an overview of the moderately low diversity of loci controlling partial resistance to A. euteiches in four main sources of resistance in pea. Seven highly consistent genomic regions with potential use in marker-assisted-selection were identified. Confidence intervals at several main QTL regions were reduced and co-segregation among resistance and morphological/phenological alleles was identified. Further work will be required to identify the best combinations of QTL for durably increasing partial resistance to A. euteiches.

Selecting High-Performing and Stable Pea Genotypes in Multi-Environmental Trial (MET): Applying AMMI, GGE-Biplot, and BLUP Procedures.

A large amount of data on various traits is accumulated over the course of a breeding program and can be used to optimize various aspects of the crop improvement pipeline. We leveraged data from advanced yield trials (AYT) of three classes of peas (green, yellow, and winter peas) collected over ten years (2012-2021) to analyze and test key aspects fundamental to pea breeding. Six balanced datasets were used to test the predictive success of the BLUP and AMMI family models. Predictive assessment using cross-validation indicated that BLUP offered better predictive accuracy as compared to any AMMI family model. However, BLUP may not always identify the best genotype that performs well across environments. AMMI and GGE, two statistical tools used to exploit GE, could fill this gap and aid in understanding how genotypes perform across environments. AMMI's yield by environmental IPCA1, WAASB by yield plot, and GGE biplot were shown to be useful in identifying genotypes for specific or broad adaptability. When compared to the most favorable environment, we observed a yield reduction of 80-87% in the most unfavorable environment. The seed yield variability across environments was caused in part by weather variability. Hotter conditions in June and July as well as low precipitation in May and June affected seed yield negatively. In conclusion, the findings of this study are useful to breeders in the variety selection process and growers in pea production.

Remote sensing for field pea yield estimation: A study of multi-scale data fusion approaches in phenomics.

Introduction: Remote sensing using unmanned aerial systems (UAS) are prevalent for phenomics and precision agricultural applications. The high-resolution data for these applications can provide useful spectral characteristics of crops associated with performance traits such as seed yield. With the recent availability of high-resolution satellite imagery, there has been growing interest in using this technology for plot-scale remote sensing applications, particularly those related to breeding programs. This study compared the features extracted from high-resolution satellite and UAS multispectral imagery (visible and near-infrared) to predict the seed yield from two diverse plot-scale field pea yield trials (advanced breeding and variety testing) using the random forest model. Methods: The multi-modal (spectral and textural features) and multi-scale (satellite and UAS) data fusion approaches were evaluated to improve seed yield prediction accuracy across trials and time points. These approaches included both image fusion, such as pan-sharpening of satellite imagery with UAS imagery using intensity-hue-saturation transformation and additive wavelet luminance proportional approaches, and feature fusion, which involved integrating extracted spectral features. In addition, we also compared the image fusion approach to high-definition satellite data with a resolution of 0.15 m/pixel. The effectiveness of each approach was evaluated with data at both individual and combined time points. Results and discussion: The major findings can be summarized as follows: (1) the inclusion of the texture features did not improve the model performance, (2) the performance of the model using spectral features from satellite imagery at its original resolution can provide similar results as UAS imagery, with variation depending on the field pea yield trial under study and the growth stage, (3) the model performance improved after applying multi-scale, multiple time point feature fusion, (4) the features extracted from the pan-sharpened satellite imagery using intensity-hue-saturation transformation (image fusion) showed better model performance than those with original satellite imagery or high definition imagery, and (5) the green normalized difference vegetation index and transformed triangular vegetation index were identified as key features contributing to high model performance across trials and time points. These findings demonstrate the potential of high-resolution satellite imagery and data fusion approaches for plot-scale phenomics applications.

Prediction of Protein Concentration in Pea (Pisum sativum L.) Using Near-Infrared Spectroscopy (NIRS) Systems.

Breeding for increased protein concentration is a priority in field peas. Having a quick, accurate, and non-destructive protein quantification method is critical for screening breeding materials, which the near-infrared spectroscopy (NIRS) system can provide. Partial least square regression (PLSR) models to predict protein concentration were developed and compared for DA7250 and FT9700 NIRS systems. The reference protein data were accurate and exhibited a wider range of variation (15.3−29.8%). Spectral pre-treatments had no clear advantage over analyses based on raw spectral data. Due to the large number of samples used in this study, prediction accuracies remained similar across calibration sizes. The final PLSR models for the DA7250 and FT9700 systems required 10 and 13 latent variables, respectively, and performed well and were comparable (R2 = 0.72, RMSE = 1.22, and bias = 0.003 for DA7250; R2 = 0.79, RMSE = 1.23, and bias = 0.055 for FT9700). Considering three groupings for protein concentration (Low: <20%, Medium: ≥20%, but ≤25%, and High: >25%), none of the entries changed from low to high or vice versa between the observed and predicted values for the DA7250 system. Only a single entry moved from a low category in the observed data to a high category in the predicted data for the FT9700 system in the calibration set. Although the FT9700 system outperformed the DA7250 system by a small margin, both systems had the potential to predict protein concentration in pea seeds for breeding purposes. Wavelengths between 950 nm and 1650 nm accounted for most of the variation in pea protein concentration.

New consistent QTL in pea associated with partial resistance to Aphanomyces euteiches in multiple French and American environments.

Partial resistances, often controlled by quantitative trait loci (QTL), are considered to be more durable than monogenic resistances. Therefore, a precursor to developing efficient breeding programs for polygenic resistance to pathogens should be a greater understanding of genetic diversity and stability of resistance QTL in plants. In this study, we deciphered the diversity and stability of resistance QTL to Aphanomyces euteiches in pea towards pathogen variability, environments and scoring criteria, from two new sources of partial resistance (PI 180693 and 552), effective in French and USA infested fields. Two mapping populations of 178 recombinant inbred lines each, derived from crosses between 552 or PI 180693 (partially resistant) and Baccara (susceptible), were used to identify QTL for Aphanomyces root rot resistance in controlled and in multiple French and USA field conditions using several resistance criteria. We identified a total of 135 additive-effect QTL corresponding to 23 genomic regions and 13 significant epistatic interactions associated with partial resistance to A. euteiches in pea. Among the 23 additive-effect genomic regions identified, five were consistently detected, and showed highly stable effects towards A. euteiches strains, environments, resistance criteria, condition tests and RIL populations studied. These results confirm the complexity of inheritance of partial resistance to A. euteiches in pea and provide good bases for the choice of consistent QTL to use in marker-assisted selection schemes to increase current levels of resistance to A. euteiches in pea breeding programs.

Crop Performance Evaluation of Chickpea and Dry Pea Breeding Lines Across Seasons and Locations Using Phenomics Data.

The Pacific Northwest is an important pulse production region in the United States. Currently, pulse crop (chickpea, lentil, and dry pea) breeders rely on traditional phenotyping approaches to collect performance and agronomic data to support decision making. Traditional phenotyping poses constraints on data availability (e.g., number of locations and frequency of data acquisition) and throughput. In this study, phenomics technologies were applied to evaluate the performance and agronomic traits in two pulse (chickpea and dry pea) breeding programs using data acquired over multiple seasons and locations. An unmanned aerial vehicle-based multispectral imaging system was employed to acquire image data of chickpea and dry pea advanced yield trials from three locations during 2017-2019. The images were analyzed semi-automatically with custom image processing algorithm and features were extracted, such as canopy area and summary statistics associated with vegetation indices. The study demonstrated significant correlations (P < 0.05) between image-based features (e.g., canopy area and sum normalized difference vegetation index) with yield (r up to 0.93 and 0.85 for chickpea and dry pea, respectively), days to 50% flowering (r up to 0.76 and 0.85, respectively), and days to physiological maturity (r up to 0.58 and 0.84, respectively). Using image-based features as predictors, seed yield was estimated using least absolute shrinkage and selection operator regression models, during which, coefficients of determination as high as 0.91 and 0.80 during model testing for chickpea and dry pea, respectively, were achieved. The study demonstrated the feasibility to monitor agronomic traits and predict seed yield in chickpea and dry pea breeding trials across multiple locations and seasons using phenomics tools. Phenomics technologies can assist plant breeders to evaluate the performance of breeding materials more efficiently and accelerate breeding programs.

Harnessing Genetic Diversity in the USDA Pea Germplasm Collection Through Genomic Prediction.

Phenotypic evaluation and efficient utilization of germplasm collections can be time-intensive, laborious, and expensive. However, with the plummeting costs of next-generation sequencing and the addition of genomic selection to the plant breeder's toolbox, we now can more efficiently tap the genetic diversity within large germplasm collections. In this study, we applied and evaluated genomic prediction's potential to a set of 482 pea (Pisum sativum L.) accessions-genotyped with 30,600 single nucleotide polymorphic (SNP) markers and phenotyped for seed yield and yield-related components-for enhancing selection of accessions from the USDA Pea Germplasm Collection. Genomic prediction models and several factors affecting predictive ability were evaluated in a series of cross-validation schemes across complex traits. Different genomic prediction models gave similar results, with predictive ability across traits ranging from 0.23 to 0.60, with no model working best across all traits. Increasing the training population size improved the predictive ability of most traits, including seed yield. Predictive abilities increased and reached a plateau with increasing number of markers presumably due to extensive linkage disequilibrium in the pea genome. Accounting for population structure effects did not significantly boost predictive ability, but we observed a slight improvement in seed yield. By applying the best genomic prediction model (e.g., RR-BLUP), we then examined the distribution of genotyped but nonphenotyped accessions and the reliability of genomic estimated breeding values (GEBV). The distribution of GEBV suggested that none of the nonphenotyped accessions were expected to perform outside the range of the phenotyped accessions. Desirable breeding values with higher reliability can be used to identify and screen favorable germplasm accessions. Expanding the training set and incorporating additional orthogonal information (e.g., transcriptomics, metabolomics, physiological traits, etc.) into the genomic prediction framework can enhance prediction accuracy.

Generalized Linear Model with Elastic Net Regularization and Convolutional Neural Network for Evaluating Aphanomyces Root Rot Severity in Lentil.

Phenomics technologies allow quantitative assessment of phenotypes across a larger number of plant genotypes compared to traditional phenotyping approaches. The utilization of such technologies has enabled the generation of multidimensional plant traits creating big datasets. However, to harness the power of phenomics technologies, more sophisticated data analysis methods are required. In this study, Aphanomyces root rot (ARR) resistance in 547 lentil accessions and lines was evaluated using Red-Green-Blue (RGB) images of roots. We created a dataset of 6,460 root images that were annotated by a plant breeder based on the disease severity. Two approaches, generalized linear model with elastic net regularization (EN) and convolutional neural network (CNN), were developed to classify disease resistance categories into three classes: resistant, partially resistant, and susceptible. The results indicated that the selected image features using EN models were able to classify three disease categories with an accuracy of up to 0.91 ± 0.004 (0.96 ± 0.005 resistant, 0.82 ± 0.009 partially resistant, and 0.92 ± 0.007 susceptible) compared to CNN with an accuracy of about 0.84 ± 0.009 (0.96 ± 0.008 resistant, 0.68 ± 0.026 partially resistant, and 0.83 ± 0.015 susceptible). The resistant class was accurately detected using both classification methods. However, partially resistant class was challenging to detect as the features (data) of the partially resistant class often overlapped with those of resistant and susceptible classes. Collectively, the findings provided insights on the use of phenomics techniques and machine learning approaches to provide quantitative measures of ARR resistance in lentil.

Advanced Imaging for Quantitative Evaluation of Aphanomyces Root Rot Resistance in Lentil.

Aphanomyces root rot (ARR) is a soil-borne disease that results in severe yield losses in lentil. The development of resistant cultivars is one of the key strategies to control this pathogen. However, the evaluation of disease severity is limited to visual scores that can be subjective. This study utilized image-based phenotyping approaches to evaluate Aphanomyces euteiches resistance in lentil genotypes in greenhouse (351 genotypes from lentil single plant/LSP derived collection and 191 genotypes from recombinant inbred lines/RIL using digital Red-Green-Blue/RGB and hyperspectral imaging) and field (173 RIL genotypes using unmanned aerial system-based multispectral imaging) conditions. Moderate to strong correlations were observed between RGB, multispectral, and hyperspectral derived features extracted from lentil shoots/roots and visual scores. In general, root features extracted from RGB imaging were found to be strongly associated with disease severity. With only three root traits, elastic net regression model was able to predict disease severity across and within multiple datasets (R 2 = 0.45-0.73 and RMSE = 0.66-1.00). The selected features could represent visual disease scores. Moreover, we developed twelve normalized difference spectral indices (NDSIs) that were significantly correlated with disease scores: two NDSIs for lentil shoot section - computed from wavelengths of 1170, 1160, 1270, and 1280 nm (0.12 ≤ |r| ≤ 0.24, P < 0.05) and ten NDSIs for lentil root sections - computed from wavelengths in the range of 630-670, 700-840, and 1320-1530 nm (0.10 ≤ |r| ≤ 0.50, P < 0.05). Root-derived NDSIs were more accurate in predicting disease scores with an R 2 of 0.54 (RMSE = 0.86), especially when the model was trained and tested on LSP accessions, compared to R 2 of 0.25 (RMSE = 1.64) when LSP and RIL genotypes were used as train and test datasets, respectively. Importantly, NDSIs - computed from wavelengths of 700, 710, 730, and 790 nm - had strong positive correlations with disease scores (0.35 ≤r ≤ 0.50, P < 0.0001), which was confirmed in field phenotyping with similar correlations using vegetation index with red edge wavelength (normalized difference red edge, 0.36 ≤ |r| ≤ 0.57, P < 0.0001). The adopted image-based phenotyping approaches can help plant breeders to objectively quantify ARR resistance and reduce the subjectivity in selecting potential genotypes.

A community resource for exploring and utilizing genetic diversity in the USDA pea single plant plus collection.

Globally, pea (Pisum sativum L.) is an important temperate legume crop for food, feed and fodder, and many breeding programs develop cultivars adapted to these end-uses. In order to assist pea development efforts, we assembled the USDA Pea Single Plant Plus Collection (PSPPC), which contains 431 P. sativum accessions with morphological, geographic and taxonomic diversity. The collection was characterized genetically in order to maximize its value for trait mapping and genomics-assisted breeding. To that end, we used genotyping-by-sequencing-a cost-effective method for de novo single-nucleotide polymorphism (SNP) marker discovery-to generate 66 591 high-quality SNPs. These data facilitated the identification of accessions divergent from mainstream breeding germplasm that could serve as sources of novel, favorable alleles. In particular, a group of accessions from Central Asia appear nearly as diverse as a sister species, P. fulvum, and subspecies, P. sativum subsp. elatius. PSPPC genotypes can be paired with new and existing phenotype data for trait mapping; as proof-of-concept, we localized Mendel's A gene controlling flower color to its known position. We also used SNP data to define a smaller core collection of 108 accessions with similar levels of genetic diversity as the entire PSPPC, resulting in a smaller germplasm set for research screening and evaluation under limited resources. Taken together, the results presented in this study along with the release of a publicly available SNP data set comprise a valuable resource for supporting worldwide pea genetic improvement efforts.

Identification of Quantitative Trait Loci Controlling Root and Shoot Traits Associated with Drought Tolerance in a Lentil (Lens culinaris Medik.) Recombinant Inbred Line Population.

Drought is one of the major abiotic stresses limiting lentil productivity in rainfed production systems. Specific rooting patterns can be associated with drought avoidance mechanisms that can be used in lentil breeding programs. In all, 252 co-dominant and dominant markers were used for Quantitative Trait Loci (QTL) analysis on 132 lentil recombinant inbred lines based on greenhouse experiments for root and shoot traits during two seasons under progressive drought-stressed conditions. Eighteen QTLs controlling a total of 14 root and shoot traits were identified. A QTL-hotspot genomic region related to a number of root and shoot characteristics associated with drought tolerance such as dry root biomass, root surface area, lateral root number, dry shoot biomass and shoot length was identified. Interestingly, a QTL (QRSratioIX-2.30) related to root-shoot ratio, an important trait for drought avoidance, explaining the highest phenotypic variance of 27.6 and 28.9% for the two consecutive seasons, respectively, was detected. This QTL was closed to the co-dominant SNP marker TP6337 and also flanked by the two SNP TP518 and TP1280. An important QTL (QLRNIII-98.64) related to lateral root number was found close to TP3371 and flanked by TP5093 and TP6072 SNP markers. Also, a QTL (QSRLIV-61.63) associated with specific root length was identified close to TP1873 and flanked by F7XEM6b SRAP marker and TP1035 SNP marker. These two QTLs were detected in both seasons. Our results could be used for marker-assisted selection in lentil breeding programs targeting root and shoot characteristics conferring drought avoidance as an efficient alternative to slow and labor-intensive conventional breeding methods.