Plant microphenotype: from innovative imaging to computational analysis.

The microphenotype plays a key role in bridging the gap between the genotype and the complex macro phenotype. In this article, we review the advances in data acquisition and the intelligent analysis of plant microphenotyping and present applications of microphenotyping in plant science over the past two decades. We then point out several challenges in this field and suggest that cross-scale image acquisition strategies, powerful artificial intelligence algorithms, advanced genetic analysis, and computational phenotyping need to be established and performed to better understand interactions among genotype, environment, and management. Microphenotyping has entered the era of Microphenotyping 3.0 and will largely advance functional genomics and plant science.

Deciphering genetic basis of developmental and agronomic traits by integrating high-throughput optical phenotyping and genome-wide association studies in wheat.

Dissecting the genetic basis of complex traits such as dynamic growth and yield potential is a major challenge in crops. Monitoring the growth throughout growing season in a large wheat population to uncover the temporal genetic controls for plant growth and yield-related traits has so far not been explored. In this study, a diverse wheat panel composed of 288 lines was monitored by a non-invasive and high-throughput phenotyping platform to collect growth traits from seedling to grain filling stage and their relationship with yield-related traits was further explored. Whole genome re-sequencing of the panel provided 12.64 million markers for a high-resolution genome-wide association analysis using 190 image-based traits and 17 agronomic traits. A total of 8327 marker-trait associations were detected and clustered into 1605 quantitative trait loci (QTLs) including a number of known genes or QTLs. We identified 277 pleiotropic QTLs controlling multiple traits at different growth stages which revealed temporal dynamics of QTLs action on plant development and yield production in wheat. A candidate gene related to plant growth that was detected by image traits was further validated. Particularly, our study demonstrated that the yield-related traits are largely predictable using models developed based on i-traits and provide possibility for high-throughput early selection, thus to accelerate breeding process. Our study explored the genetic architecture of growth and yield-related traits by combining high-throughput phenotyping and genotyping, which further unravelled the complex and stage-specific contributions of genetic loci to optimize growth and yield in wheat.

High-throughput phenotyping-based quantitative trait loci mapping reveals the genetic architecture of the salt stress tolerance of Brassica napus.

Salt stress is a major limiting factor that severely affects the survival and growth of crops. It is important to understand the salt stress tolerance ability of Brassica napus and explore the underlying related genetic resources. We used a high-throughput phenotyping platform to quantify 2111 image-based traits (i-traits) of a natural population under three different salt stress conditions and an intervarietal substitution line (ISL) population under nine different stress conditions to monitor and evaluate the salt stress tolerance of B. napus over time. We finally identified 928 high-quality i-traits associated with the salt stress tolerance of B. napus. Moreover, we mapped the salt stress-related loci in the natural population via a genome-wide association study and performed a linkage analysis associated with the ISL population, respectively. These results revealed 234 candidate genes associated with salt stress response, and two novel candidate genes, BnCKX5 and BnERF3, were experimentally verified to regulate the salt stress tolerance of B. napus. This study demonstrates the feasibility of using high-throughput phenotyping-based quantitative trait loci mapping to accurately and comprehensively quantify i-traits associated with B. napus. The mapped loci could be used for genomics-assisted breeding to genetically improve the salt stress tolerance of B. napus.

A Novel Method for Filled/Unfilled Grain Classification Based on Structured Light Imaging and Improved PointNet+.

China is the largest producer and consumer of rice, and the classification of filled/unfilled rice grains is of great significance for rice breeding and genetic analysis. The traditional method for filled/unfilled rice grain identification was generally manual, which had the disadvantages of low efficiency, poor repeatability, and low precision. In this study, we have proposed a novel method for filled/unfilled grain classification based on structured light imaging and Improved PointNet++. Firstly, the 3D point cloud data of rice grains were obtained by structured light imaging. And then the specified processing algorithms were developed for the single grain segmentation, and data enhancement with normal vector. Finally, the PointNet++ network was improved by adding an additional Set Abstraction layer and combining the maximum pooling of normal vectors to realize filled/unfilled rice grain point cloud classification. To verify the model performance, the Improved PointNet++ was compared with six machine learning methods, PointNet and PointConv. The results showed that the optimal machine learning model is XGboost, with a classification accuracy of 91.99%, while the classification accuracy of Improved PointNet++ was 98.50% outperforming the PointNet 93.75% and PointConv 92.25%. In conclusion, this study has demonstrated a novel and effective method for filled/unfilled grain recognition.

StomataScorer: a portable and high-throughput leaf stomata trait scorer combined with deep learning and an improved CV model.

To measure stomatal traits automatically and nondestructively, a new method for detecting stomata and extracting stomatal traits was proposed. Two portable microscopes with different resolutions (TipScope with a 40× lens attached to a smartphone and ProScope HR2 with a 400× lens) are used to acquire images of living stomata in maize leaves. FPN model was used to detect stomata in the TipScope images and measure the stomata number and stomatal density. Faster RCNN model was used to detect opening and closing stomata in the ProScope HR2 images, and the number of opening and closing stomata was measured. An improved CV model was used to segment pores of opening stomata, and a total of 6 pore traits were measured. Compared to manual measurements, the square of the correlation coefficient (R2 ) of the 6 pore traits was higher than 0.85, and the mean absolute percentage error (MAPE) of these traits was 0.02%-6.34%. The dynamic stomata changes between wild-type B73 and mutant Zmfab1a were explored under drought and re-watering condition. The results showed that Zmfab1a had a higher resilience than B73 on leaf stomata. In addition, the proposed method was tested to measure the leaf stomatal traits of other nine species. In conclusion, a portable and low-cost stomata phenotyping method that could accurately and dynamically measure the characteristic parameters of living stomata was developed. An open-access and user-friendly web portal was also developed which has the potential to be used in the stomata phenotyping of large populations in the future.

A MITE variation-associated heat-inducible isoform of a heat-shock factor confers heat tolerance through regulation of JASMONATE ZIM-DOMAIN genes in rice.

High temperatures cause huge yield losses in rice. Heat-shock factors (Hsfs) are key transcription factors which regulate the expression of heat stress-responsive genes, but natural variation in and functional characterization of Hsfs have seldom been reported. A significant heat response locus was detected via a genome-wide association study (GWAS) using green leaf area as an indicative trait. A miniature inverted-repeat transposable element (MITE) in the promoter of a candidate gene, HTG3 (heat-tolerance gene on chromosome 3), was found to be significantly associated with heat-induced expression of HTG3 and heat tolerance (HT). The MITE-absent variant has been selected in heat-prone rice-growing regions. HTG3a is an alternatively spliced isoform encoding a functional Hsf, and experiments using overexpression and knockout rice lines showed that HTG3a positively regulates HT at both vegetative and reproductive stages. The HTG3-regulated genes were enriched for heat shock proteins and jasmonic acid signaling. Two heat-responsive JASMONATE ZIM-DOMAIN (JAZ) genes were confirmed to be directly upregulated by HTG3a, and one of them, OsJAZ9, positively regulates HT. We conclude that HTG3 plays an important role in HT through the regulation of JAZs and other heat-responsive genes. The MITE-absent allele may be valuable for HT breeding in rice.

High-throughput unmanned aerial vehicle-based phenotyping provides insights into the dynamic process and genetic basis of rapeseed waterlogging response in the field.

Waterlogging severely affects the growth, development, and yield of crops. Accurate high-throughput phenotyping is important for exploring the dynamic crop waterlogging response in the field, and the genetic basis of waterlogging tolerance. In this study, a multi-model remote sensing phenotyping platform based on an unmanned aerial vehicle (UAV) was used to assess the genetic response of rapeseed (Brassica napus) to waterlogging, by measuring morphological traits and spectral indices over 2 years. The dynamic responses of the morphological and spectral traits indicated that the rapeseed waterlogging response was severe before the middle stage within 18 d after recovery, but it subsequently decreased partly. Genome-wide association studies identified 289 and 333 loci associated with waterlogging tolerance in 2 years. Next, 25 loci with at least nine associations with waterlogging-related traits were defined as highly reliable loci, and 13 loci were simultaneously identified by waterlogging tolerance coefficients of morphological traits, spectral indices, and common factors. Forty candidate genes were predicted in the regions of 13 overlapping loci. Our study provides insights into the understanding of the dynamic process and genetic basis of rapeseed waterlogging response in the field by a high-throughput UAV phenotyping platform. The highly reliable loci identified in this study are valuable for breeding waterlogging-tolerant rapeseed cultivars.

PollenDetect: An Open-Source Pollen Viability Status Recognition System Based on Deep Learning Neural Networks.

Pollen grains, the male gametophytes for reproduction in higher plants, are vulnerable to various stresses that lead to loss of viability and eventually crop yield. A conventional method for assessing pollen viability is manual counting after staining, which is laborious and hinders high-throughput screening. We developed an automatic detection tool (PollenDetect) to distinguish viable and nonviable pollen based on the YOLOv5 neural network, which is adjusted to adapt to the small target detection task. Compared with manual work, PollenDetect significantly reduced detection time (from approximately 3 min to 1 s for each image). Meanwhile, PollenDetect can maintain high detection accuracy. When PollenDetect was tested on cotton pollen viability, 99% accuracy was achieved. Furthermore, the results obtained using PollenDetect show that high temperature weakened cotton pollen viability, which is highly similar to the pollen viability results obtained using 2,3,5-triphenyltetrazolium formazan quantification. PollenDetect is an open-source software that can be further trained to count different types of pollen for research purposes. Thus, PollenDetect is a rapid and accurate system for recognizing pollen viability status, and is important for screening stress-resistant crop varieties for the identification of pollen viability and stress resistance genes during genetic breeding research.

Combining UAV-RGB high-throughput field phenotyping and genome-wide association study to reveal genetic variation of rice germplasms in dynamic response to drought stress.

Accurate and high-throughput phenotyping of the dynamic response of a large rice population to drought stress in the field is a bottleneck for genetic dissection and breeding of drought resistance. Here, high-efficiency and high-frequent image acquisition by an unmanned aerial vehicle (UAV) was utilized to quantify the dynamic drought response of a rice population under field conditions. Deep convolutional neural networks (DCNNs) and canopy height models were applied to extract highly correlated phenotypic traits including UAV-based leaf-rolling score (LRS_uav), plant water content (PWC_uav) and a new composite trait, drought resistance index by UAV (DRI_uav). The DCNNs achieved high accuracy (correlation coefficient R = 0.84 for modeling set and R = 0.86 for test set) to replace manual leaf-rolling rating. PWC_uav values were precisely estimated (correlation coefficient R = 0.88) and DRI_uav was modeled to monitor the drought resistance of rice accessions dynamically and comprehensively. A total of 111 significantly associated loci were detected by genome-wide association study for the three dynamic traits, and 30.6% of them were not detected in previous mapping studies using nondynamic drought response traits. Unmanned aerial vehicle and deep learning are confirmed effective phenotyping techniques for more complete genetic dissection of rice dynamic responses to drought and exploration of valuable alleles for drought resistance improvement.

A high-throughput and low-cost maize ear traits scorer.

In this study, based on automatic control and image processing, a high-throughput and low-cost maize ear traits scorer (METS) was developed for the automatic measurement of 34 maize ear traits. In total, 813 maize ears were measured using METS, and the results showed that the square of the correlation coefficient (R2) of the manual measurements versus the automatic measurements for ear length, ear diameter, and kernel thickness were 0.96, 0.79, and 0.85, respectively. These maize ear traits could be used to classify the type, and the results showed that the classification accuracy of the support vector machine (SVM) model for the test set was better than that of the random forest (RF) model. In addition, the general applicability of the image analysis pipeline was also demonstrated on other independent maize ear phenotyping platforms. In conclusion, equipped with image processing and automatic control technologies, we have developed a high-throughput method for maize ear scoring, which could be popularized in maize functional genetics, genomics, and breeding applications. Supplementary Information: The online version contains supplementary material available at 10.1007/s11032-021-01205-4.

High-throughput phenotyping accelerates the dissection of the dynamic genetic architecture of plant growth and yield improvement in rapeseed.

Rapeseed is the second most important oil crop species and is widely cultivated worldwide. However, overcoming the 'phenotyping bottleneck' has remained a significant challenge. A clear goal of high-throughput phenotyping is to bridge the gap between genomics and phenomics. In addition, it is important to explore the dynamic genetic architecture underlying rapeseed plant growth and its contribution to final yield. In this work, a high-throughput phenotyping facility was used to dynamically screen a rapeseed intervarietal substitution line population during two growing seasons. We developed an automatic image analysis pipeline to quantify 43 dynamic traits across multiple developmental stages, with 12 time points. The time-resolved i-traits could be extracted to reflect shoot growth and predict the final yield of rapeseed. Broad phenotypic variation and high heritability were observed for these i-traits across all developmental stages. A total of 337 and 599 QTLs were identified, with 33.5% and 36.1% consistent QTLs for each trait across all 12 time points in the two growing seasons, respectively. Moreover, the QTLs responsible for yield indicators colocalized with those of final yield, potentially providing a new mechanism of yield regulation. Our results indicate that high-throughput phenotyping can provide novel insights into the dynamic genetic architecture of rapeseed growth and final yield, which would be useful for future genetic improvements in rapeseed.

Phenomics-based GWAS analysis reveals the genetic architecture for drought resistance in cotton.

Drought resistance (DR) is a complex trait that is regulated by a variety of genes. Without comprehensive profiling of DR-related traits, the knowledge of the genetic architecture for DR in cotton remains limited. Thus, there is a need to bridge the gap between genomics and phenomics. In this study, an automatic phenotyping platform (APP) was systematically applied to examine 119 image-based digital traits (i-traits) during drought stress at the seedling stage, across a natural population of 200 representative upland cotton accessions. Some novel i-traits, as well as some traditional i-traits, were used to evaluate the DR in cotton. The phenomics data allowed us to identify 390 genetic loci by genome-wide association study (GWAS) using 56 morphological and 63 texture i-traits. DR-related genes, including GhRD2, GhNAC4, GhHAT22 and GhDREB2, were identified as candidate genes by some digital traits. Further analysis of candidate genes showed that Gh_A04G0377 and Gh_A04G0378 functioned as negative regulators for cotton drought response. Based on the combined digital phenotyping, GWAS analysis and transcriptome data, we conclude that the phenomics dataset provides an excellent resource to characterize key genetic loci with an unprecedented resolution which can inform future genome-based breeding for improved DR in cotton.

Combining high-throughput micro-CT-RGB phenotyping and genome-wide association study to dissect the genetic architecture of tiller growth in rice.

Manual phenotyping of rice tillers is time consuming and labor intensive, and lags behind the rapid development of rice functional genomics. Thus, automated, non-destructive methods of phenotyping rice tiller traits at a high spatial resolution and high throughput for large-scale assessment of rice accessions are urgently needed. In this study, we developed a high-throughput micro-CT-RGB imaging system to non-destructively extract 739 traits from 234 rice accessions at nine time points. We could explain 30% of the grain yield variance from two tiller traits assessed in the early growth stages. A total of 402 significantly associated loci were identified by genome-wide association study, and dynamic and static genetic components were found across the nine time points. A major locus associated with tiller angle was detected at time point 9, which contained a major gene, TAC1. Significant variants associated with tiller angle were enriched in the 3'-untranslated region of TAC1. Three haplotypes for the gene were found, and rice accessions containing haplotype H3 displayed much smaller tiller angles. Further, we found two loci containing associations with both vigor-related traits identified by high-throughput micro-CT-RGB imaging and yield. The superior alleles would be beneficial for breeding for high yield and dense planting.

High-Throughput Phenotyping and QTL Mapping Reveals the Genetic Architecture of Maize Plant Growth.

With increasing demand for novel traits in crop breeding, the plant research community faces the challenge of quantitatively analyzing the structure and function of large numbers of plants. A clear goal of high-throughput phenotyping is to bridge the gap between genomics and phenomics. In this study, we quantified 106 traits from a maize (Zea mays) recombinant inbred line population (n = 167) across 16 developmental stages using the automatic phenotyping platform. Quantitative trait locus (QTL) mapping with a high-density genetic linkage map, including 2,496 recombinant bins, was used to uncover the genetic basis of these complex agronomic traits, and 988 QTLs have been identified for all investigated traits, including three QTL hotspots. Biomass accumulation and final yield were predicted using a combination of dissected traits in the early growth stage. These results reveal the dynamic genetic architecture of maize plant growth and enhance ideotype-based maize breeding and prediction.

RiceVarMap: a comprehensive database of rice genomic variations.

Rice Variation Map (RiceVarMap, http:/ricevarmap.ncpgr.cn) is a database of rice genomic variations. The database provides comprehensive information of 6,551,358 single nucleotide polymorphisms (SNPs) and 1,214,627 insertions/deletions (INDELs) identified from sequencing data of 1479 rice accessions. The SNP genotypes of all accessions were imputed and evaluated, resulting in an overall missing data rate of 0.42% and an estimated accuracy greater than 99%. The SNP/INDEL genotypes of all accessions are available for online query and download. Users can search SNPs/INDELs by identifiers of the SNPs/INDELs, genomic regions, gene identifiers and keywords of gene annotation. Allele frequencies within various subpopulations and the effects of the variation that may alter the protein sequence of a gene are also listed for each SNP/INDEL. The database also provides geographical details and phenotype images for various rice accessions. In particular, the database provides tools to construct haplotype networks and design PCR-primers by taking into account surrounding known genomic variations. These data and tools are highly useful for exploring genetic variations and evolution studies of rice and other species.

Genome-wide association study of rice (Oryza sativa L.) leaf traits with a high-throughput leaf scorer.

Leaves are the plant's solar panel and food factory, and leaf traits are always key issues to investigate in plant research. Traditional methods for leaf trait measurement are time-consuming. In this work, an engineering prototype has been established for high-throughput leaf scoring (HLS) of a large number of Oryza sativa accessions. The mean absolute per cent of errors in traditional measurements versus HLS were below 5% for leaf number, area, shape, and colour. Moreover, HLS can measure up to 30 leaves per minute. To demonstrate the usefulness of HLS in dissecting the genetic bases of leaf traits, a genome-wide association study (GWAS) was performed for 29 leaf traits related to leaf size, shape, and colour at three growth stages using HLS on a panel of 533 rice accessions. Nine associated loci contained known leaf-related genes, such as Nal1 for controlling the leaf width. In addition, a total of 73, 123, and 177 new loci were detected for traits associated with leaf size, colour, and shape, respectively. In summary, after evaluating the performance with a large number of rice accessions, the combination of GWAS and high-throughput leaf phenotyping (HLS) has proven a valuable strategy to identify the genetic loci controlling rice leaf traits.

An Overview of High-Throughput Crop Phenotyping: Platform, Image Analysis, Data Mining, and Data Management.

In this chapter, we explore the application of high-throughput crop phenotyping facilities for phenotype data acquisition and the extraction of significant information from the collected data through image processing and data mining methods. Additionally, the construction and outlook of crop phenotype databases are introduced and the need for global cooperation and data sharing is emphasized. High-throughput crop phenotyping significantly improves accuracy and efficiency compared to traditional measurements, making significant contributions to overcoming bottlenecks in the phenotyping field and advancing crop genetics.

Maturity Classification of Rapeseed Using Hyperspectral Image Combined with Machine Learning.

Oilseed rape is an important oilseed crop planted worldwide. Maturity classification plays a crucial role in enhancing yield and expediting breeding research. Conventional methods of maturity classification are laborious and destructive in nature. In this study, a nondestructive classification model was established on the basis of hyperspectral imaging combined with machine learning algorithms. Initially, hyperspectral images were captured for 3 distinct ripeness stages of rapeseed, and raw spectral data were extracted from the hyperspectral images. The raw spectral data underwent preprocessing using 5 pretreatment methods, namely, Savitzky-Golay, first derivative, second derivative (D2nd), standard normal variate, and detrend, as well as various combinations of these methods. Subsequently, the feature wavelengths were extracted from the processed spectra using competitive adaptive reweighted sampling, successive projection algorithm (SPA), iterative spatial shrinkage of interval variables (IVISSA), and their combination algorithms, respectively. The classification models were constructed using the following algorithms: extreme learning machine, k-nearest neighbor, random forest, partial least-squares discriminant analysis, and support vector machine (SVM) algorithms, applied separately to the full wavelength and the feature wavelengths. A comparative analysis was conducted to evaluate the performance of diverse preprocessing methods, feature wavelength selection algorithms, and classification models, and the results showed that the model based on preprocessing-feature wavelength selection-machine learning could effectively predict the maturity of rapeseed. The D2nd-IVISSA-SPA-SVM model exhibited the highest modeling performance, attaining an accuracy rate of 97.86%. The findings suggest that rapeseed maturity can be rapidly and nondestructively ascertained through hyperspectral imaging.