A Deep Learning Framework for Processing and Classification of Hyperspectral Rice Seed Images Grown under High Day and Night Temperatures

A framework combining two powerful tools of hyperspectral imaging and deep learning for the processing and classification of hyperspectral images (HSI) of rice seeds is presented. A seed-based approach that trains a three-dimensional convolutional neural network (3D-CNN) using the full seed spectral hypercube for classifying the seed images from high day and high night temperatures, both including a control group, is developed. A pixel-based seed classification approach is implemented using a deep neural network (DNN). The seed and pixel-based deep learning architectures are validated and tested using hyperspectral images from five different rice seed treatments with six different high temperature exposure durations during day, night, and both day and night. A stand-alone application with Graphical User Interfaces (GUI) for calibrating, preprocessing, and classification of hyperspectral rice seed images is presented. The software application can be used for training two deep learning architectures for the classification of any type of hyperspectral seed images. The average overall classification accuracy of 91.33% and 89.50% is obtained for seed-based classification using 3D-CNN for five different treatments at each exposure duration and six different high temperature exposure durations for each treatment, respectively. The DNN gives an average accuracy of 94.83% and 91% for five different treatments at each exposure duration and six different high temperature exposure durations for each treatment, respectively. The accuracies obtained are higher than those presented in the literature for hyperspectral rice seed image classification. The HSI analysis presented here is on the Kitaake cultivar, which can be extended to study the temperature tolerance of other rice cultivars.

Graph Convolutional Network Using Adaptive Neighborhood Laplacian Matrix for Hyperspectral Images with Application to Rice Seed Image Classification

Graph convolutional neural network architectures combine feature extraction and convolutional layers for hyperspectral image classification. An adaptive neighborhood aggregation method based on statistical variance integrating the spatial information along with the spectral signature of the pixels is proposed for improving graph convolutional network classification of hyperspectral images. The spatial-spectral information is integrated into the adjacency matrix and processed by a single-layer graph convolutional network. The algorithm employs an adaptive neighborhood selection criteria conditioned by the class it belongs to. Compared to fixed window-based feature extraction, this method proves effective in capturing the spectral and spatial features with variable pixel neighborhood sizes. The experimental results from the Indian Pines, Houston University, and Botswana Hyperion hyperspectral image datasets show that the proposed AN-GCN can significantly improve classification accuracy. For example, the overall accuracy for Houston University data increases from 81.71% (MiniGCN) to 97.88% (AN-GCN). Furthermore, the AN-GCN can classify hyperspectral images of rice seeds exposed to high day and night temperatures, proving its efficacy in discriminating the seeds under increased ambient temperature treatments.

Rice Chalky Grain 5 regulates natural variation for grain quality under heat stress

Heat stress occurring during rice (Oryza sativa) grain development reduces grain quality, which often manifests as increased grain chalkiness. Although the impact of heat stress on grain yield is well-studied, the genetic basis of rice grain quality under heat stress is less explored as quantifying grain quality is less tractable than grain yield. To address this, we used an image-based colorimetric assay (Red, R; and Green, G) for genome-wide association analysis to identify genetic loci underlying the phenotypic variation in rice grains exposed to heat stress. We found the R to G pixel ratio (RG) derived from mature grain images to be effective in distinguishing chalky grains from translucent grains derived from control (28/24°C) and heat stressed (36/32°C) plants. Our analysis yielded a novel gene, rice Chalky Grain 5 (OsCG5) that regulates natural variation for grain chalkiness under heat stress. OsCG5 encodes a grain-specific, expressed protein of unknown function. Accessions with lower transcript abundance of OsCG5 exhibit higher chalkiness, which correlates with higher RG values under stress. These findings are supported by increased chalkiness of OsCG5 knock-out (KO) mutants relative to wildtype (WT) under heat stress. Grains from plants overexpressing OsCG5 are less chalky than KOs but comparable to WT under heat stress. Compared to WT and OE, KO mutants exhibit greater heat sensitivity for grain size and weight relative to controls. Collectively, these results show that the natural variation at OsCG5 may contribute towards rice grain quality under heat stress.

Wild emmer introgression alters root-to-shoot growth dynamics in durum wheat in response to water stress

Water deficit during the early vegetative growth stages of wheat (Triticum) can limit shoot growth and ultimately impact grain productivity. Introducing diversity in wheat cultivars to enhance the range of phenotypic responses to water limitations during vegetative growth can provide potential avenues for mitigating subsequent yield losses. We tested this hypothesis in an elite durum wheat background by introducing a series of introgressions from a wild emmer (Triticum turgidum ssp. dicoccoides) wheat. Wild emmer populations harbor rich phenotypic diversity for drought-adaptive traits. To determine the effect of these introgressions on vegetative growth under water-limited conditions, we used image-based phenotyping to catalog divergent growth responses to water stress ranging from high plasticity to high stability. One of the introgression lines exhibited a significant shift in root-to-shoot ratio in response to water stress. We characterized this shift by combining genetic analysis and root transcriptome profiling to identify candidate genes (including a root-specific kinase) that may be linked to the root-to-shoot carbon reallocation under water stress. Our results highlight the potential of introducing functional diversity into elite durum wheat for enhancing the range of water stress adaptation.

SeedExtractor: An Open-Source GUI for Seed Image Analysis

Accurate measurement of seed size parameters is essential for both breeding efforts aimed at enhancing yields and basic research focused on discovering genetic components that regulate seed size. To address this need, we have developed an open-source graphical user interface (GUI) software, SeedExtractor that determines seed size and shape (including area, perimeter, length, width, circularity, and centroid), and seed color with capability to process a large number of images in a time-efficient manner. In this context, our application takes ∼2 s for analyzing an image, i.e., significantly less compared to the other tools. As this software is open-source, it can be modified by users to serve more specific needs. The adaptability of SeedExtractor was demonstrated by analyzing scanned seeds from multiple crops. We further validated the utility of this application by analyzing mature-rice seeds from 231 accessions in Rice Diversity Panel 1. The derived seed-size traits, such as seed length, width, were used for genome-wide association analysis. We identified known loci for regulating seed length (GS3) and width (qSW5/GW5) in rice, which demonstrates the accuracy of this application to extract seed phenotypes and accelerate trait discovery. In summary, we present a publicly available application that can be used to determine key yield-related traits in crops.

Allelic variation in rice Fertilization Independent Endosperm 1 contributes to grain width under high night temperature stress

A higher minimum (night-time) temperature is considered a greater limiting factor for reduced rice yield than a similar increase in maximum (daytime) temperature. While the physiological impact of high night temperature (HNT) has been studied, the genetic and molecular basis of HNT stress response remains unexplored. We examined the phenotypic variation for mature grain size (length and width) in a diverse set of rice accessions under HNT stress. Genome-wide association analysis identified several HNT-specific loci regulating grain size as well as loci that are common for optimal and HNT stress conditions. A novel locus contributing to grain width under HNT conditions colocalized with Fie1, a component of the FIS-PRC2 complex. Our results suggest that the allelic difference controlling grain width under HNT is a result of differential transcript-level response of Fie1 in grains developing under HNT stress. We present evidence to support the role of Fie1 in grain size regulation by testing overexpression (OE) and knockout mutants under heat stress. The OE mutants were either unaltered or had a positive impact on mature grain size under HNT, while the knockouts exhibited significant grain size reduction under these conditions.

MADS78 and MADS79 Are Essential Regulators of Early Seed Development in Rice

MADS box transcription factors (TFs) are subdivided into type I and II based on phylogenetic analysis. The type II TFs regulate floral organ identity and flowering time, but type I TFs are relatively less characterized. Here, we report the functional characterization of two type I MADS box TFs in rice (Oryza sativa), MADS78 and MADS79 Transcript abundance of both these genes in developing seed peaked at 48 h after fertilization and was suppressed by 96 h after fertilization, corresponding to syncytial and cellularized stages of endosperm development, respectively. Seeds overexpressing MADS78 and MADS 79 exhibited delayed endosperm cellularization, while CRISPR-Cas9-mediated single knockout mutants showed precocious endosperm cellularization. MADS78 and MADS 79 were indispensable for seed development, as a double knockout mutant failed to make viable seeds. Both MADS78 and 79 interacted with MADS89, another type I MADS box, which enhances nuclear localization. The expression analysis of Fie1, a rice FERTILIZATION-INDEPENDENT SEED-POLYCOMB REPRESSOR COMPLEX2 component, in MADS78 and 79 mutants and vice versa established an antithetical relation, suggesting that Fie1 could be involved in negative regulation of MADS78 and MADS 79 Misregulation of MADS78 and MADS 79 perturbed auxin homeostasis and carbon metabolism, as evident by misregulation of genes involved in auxin transport and signaling as well as starch biosynthesis genes causing structural abnormalities in starch granules at maturity. Collectively, we show that MADS78 and MADS 79 are essential regulators of early seed developmental transition and impact both seed size and quality in rice.

Divergent phenotypic response of rice accessions to transient heat stress during early seed development

Increasing global surface temperatures is posing a major food security challenge. Part of the solution to address this problem is to improve crop heat resilience, especially during grain development, along with agronomic decisions such as shift in planting time and increasing crop diversification. Rice is a major food crop consumed by more than 3 billion people. For rice, thermal sensitivity of reproductive development and grain filling is well-documented, while knowledge concerning the impact of heat stress (HS) on early seed development is limited. Here, we aim to study the phenotypic variation in a set of diverse rice accessions for elucidating the HS response during early seed development. To explore the variation in HS sensitivity, we investigated aus (1), indica (2), temperate japonica (2), and tropical japonica (4) accessions for their HS (39/35°C) response during early seed development that accounts for transition of endosperm from syncytial to cellularization, which broadly corresponds to 24 and 96 hr after fertilization (HAF), respectively, in rice. The two indica and one of the tropical japonica accessions exhibited severe heat sensitivity with increased seed abortion; three tropical japonicas and an aus accession showed moderate heat tolerance, while temperate japonicas exhibited strong heat tolerance. The accessions exhibiting extreme heat sensitivity maintain seed size at the expense of number of fully developed mature seeds, while the accessions showing relative resilience to the transient HS maintained number of fully developed seeds but compromised on seed size, especially seed length. Further, histochemical analysis revealed that all the tested accessions have delayed endosperm cellularization upon exposure to the transient HS by 96 HAF; however, the rate of cellularization was different among the accessions. These findings were further corroborated by upregulation of cellularization-associated marker genes in the developing seeds from the heat-stressed samples.

PI-Plat: a high-resolution image-based 3D reconstruction method to estimate growth dynamics of rice inflorescence traits

BACKGROUND

Recent advances in image-based plant phenotyping have improved our capability to study vegetative stage growth dynamics. However, more complex agronomic traits such as inflorescence architecture (IA), which predominantly contributes to grain crop yield are more challenging to quantify and hence are relatively less explored. Previous efforts to estimate inflorescence-related traits using image-based phenotyping have been limited to destructive end-point measurements. Development of non-destructive inflorescence phenotyping platforms could accelerate the discovery of the phenotypic variation with respect to inflorescence dynamics and mapping of the underlying genes regulating critical yield components.

RESULTS

The major objective of this study is to evaluate post-fertilization development and growth dynamics of inflorescence at high spatial and temporal resolution in rice. For this, we developed the Panicle Imaging Platform (PI-Plat) to comprehend multi-dimensional features of IA in a non-destructive manner. We used 11 rice genotypes to capture multi-view images of primary panicle on weekly basis after the fertilization. These images were used to reconstruct a 3D point cloud of the panicle, which enabled us to extract digital traits such as voxel count and color intensity. We found that the voxel count of developing panicles is positively correlated with seed number and weight at maturity. The voxel count from developing panicles projected overall volumes that increased during the grain filling phase, wherein quantification of color intensity estimated the rate of panicle maturation. Our 3D based phenotyping solution showed superior performance compared to conventional 2D based approaches.

CONCLUSIONS

For harnessing the potential of the existing genetic resources, we need a comprehensive understanding of the genotype-to-phenotype relationship. Relatively low-cost sequencing platforms have facilitated high-throughput genotyping, while phenotyping, especially for complex traits, has posed major challenges for crop improvement. PI-Plat offers a low cost and high-resolution platform to phenotype inflorescence-related traits using 3D reconstruction-based approach. Further, the non-destructive nature of the platform facilitates analyses of the same panicle at multiple developmental time points, which can be utilized to explore the genetic variation for dynamic inflorescence traits in cereals.

Metabolic Dynamics of Developing Rice Seeds Under High Night-Time Temperature Stress

High temperature stress during rice reproductive development results in yield losses. Reduced grain yield and grain quality has been associated with high temperature stress, and specifically with high night-time temperatures (HNT). Characterizing the impact of HNT on the phenotypic and metabolic status of developing rice seeds can provide insights into the mechanisms involved in yield and quality decline. Here, we examined the impact of warmer nights on the morphology and metabolome during early seed development in six diverse rice accessions. Seed size was sensitive to HNT in four of the six genotypes, while seed fertility and seed weight were unaffected. We observed genotypic differences for negative impact of HNT on grain quality. This was evident from the chalky grain appearance due to impaired packaging of starch granules. Metabolite profiles during early seed development (3 and 4 days after fertilization; DAF) were distinct from the early grain filling stages (7 and 10 DAF) under optimal conditions. We observed that accumulation of sugars (sucrose, fructose, and glucose) peaked at 7 DAF suggesting a major flux of carbon into glycolysis, tricarboxylic acid cycle, and starch biosynthesis during grain filling. Next, we determined hyper (HNT > control) and hypo (HNT < control) abundant metabolites and found 19 of the 57 metabolites to differ significantly between HNT and control treatments. The most prominent changes were exhibited by differential abundance of sugar and sugar alcohols under HNT, which could be linked to a protective mechanism against the HNT damage. Overall, our results indicate that combining metabolic profiles of developing grains with yield and quality parameters under high night temperature stress could provide insight for exploration of natural variation for HNT tolerance in the rice germplasm.

PI-Plat: a high-resolution image-based 3D reconstruction method to estimate growth dynamics of rice inflorescence traits

BACKGROUND

Recent advances in image-based plant phenotyping have improved our capability to study vegetative stage growth dynamics. However, more complex agronomic traits such as inflorescence architecture (IA), which predominantly contributes to grain crop yield are more challenging to quantify and hence are relatively less explored. Previous efforts to estimate inflorescence-related traits using image-based phenotyping have been limited to destructive end-point measurements. Development of non-destructive inflorescence phenotyping platforms could accelerate the discovery of the phenotypic variation with respect to inflorescence dynamics and mapping of the underlying genes regulating critical yield components.

RESULTS

The major objective of this study is to evaluate post-fertilization development and growth dynamics of inflorescence at high spatial and temporal resolution in rice. For this, we developed the Panicle Imaging Platform (PI-Plat) to comprehend multi-dimensional features of IA in a non-destructive manner. We used 11 rice genotypes to capture multi-view images of primary panicle on weekly basis after the fertilization. These images were used to reconstruct a 3D point cloud of the panicle, which enabled us to extract digital traits such as voxel count and color intensity. We found that the voxel count of developing panicles is positively correlated with seed number and weight at maturity. The voxel count from developing panicles projected overall volumes that increased during the grain filling phase, wherein quantification of color intensity estimated the rate of panicle maturation. Our 3D based phenotyping solution showed superior performance compared to conventional 2D based approaches.

CONCLUSIONS

For harnessing the potential of the existing genetic resources, we need a comprehensive understanding of the genotype-to-phenotype relationship. Relatively low-cost sequencing platforms have facilitated high-throughput genotyping, while phenotyping, especially for complex traits, has posed major challenges for crop improvement. PI-Plat offers a low cost and high-resolution platform to phenotype inflorescence-related traits using 3D reconstruction-based approach. Further, the non-destructive nature of the platform facilitates analyses of the same panicle at multiple developmental time points, which can be utilized to explore the genetic variation for dynamic inflorescence traits in cereals.

Soybean proteins GmTic110 and GmPsbP are crucial for chloroplast development and function

We have identified a viable-yellow and a lethal-yellow chlorophyll-deficient mutant in soybean. Segregation patterns suggested single-gene recessive inheritance for each mutant. The viable- and lethal-yellow plants showed significant reduction of chlorophyll a and b. Photochemical energy conversion efficiency and photochemical reflectance index were reduced in the viable-yellow plants relative to the wildtype, whereas the lethal-yellow plants showed no electron transport activity. The viable-yellow plants displayed reduced thylakoid stacking, while the lethal-yellow plants exhibited failure of proplastid differentiation into normal chloroplasts with grana. Genetic analysis revealed recessive epistatic interaction between the viable- and the lethal-yellow genes. The viable-yellow gene was mapped to a 58kb region on chromosome 2 that contained seven predicted genes. A frame shift mutation, due to a single base deletion in Glyma.02g233700, resulted in an early stop codon. Glyma.02g233700 encodes a translocon in the inner membrane of chloroplast (GmTic110) that plays a critical role in plastid biogenesis. The lethal-yellow gene was mapped to an 83kb region on chromosome 3 that contained 13 predicted genes. Based on the annotated functions, we sequenced three potential candidate genes. A single base insertion in the second exon of Glyma.03G230300 resulted in a truncated protein. Glyma.03G230300 encodes for GmPsbP, an extrinsic protein of Photosystem II that is critical for oxygen evolution during photosynthesis. GmTic110 and GmPsbP displayed highly reduced expression in the viable- and lethal-yellow mutants, respectively. The yellow phenotypes in the viable- and lethal-yellow mutants were due to the loss of function of GmTic110 or GmPsbP resulting in photooxidative stress.