Plant Methods最新文献

Integrating genotype-by-Environment (GxE) interactions into genomic prediction models has been demonstrated to enhance the accuracy of predictions for crops exposed to unfavourable environmental conditions. However, despite the increasing complexity of machine learning models in genomic prediction, no model or approach has been found to be overall superior in comparison to a classical genomic best linear unbiased prediction (GBLUP) model. In this paper, we compared two GBLUP models (Linear Mixed Effects model and Bayesian GBLUP) with two machine learning models (Random Forest and Extreme Gradient Boosting) on the EUCLEG soybean genotype set phenotyped in Belgium and Serbia. We found similar performance for the Bayesian GBLUP and the two machine learning methods. However, using a workflow that decomposed the environment-specific BLUPs into a main genetic and an interaction GxE effect, we found increased predictive ability for the interaction component compared to a single-component approach. Furthermore, conducting a machine learning-genome wide association study (ML-GWAS) on both components allowed us to identify important markers for the main genetic effect, as well as environment-specific markers. These could then be associated with correlated markers in other environments. By constructing a small random forest model using only 50 uncorrelated, important markers we constructed a genomic prediction model with similar predictive ability over all scenarios when compared to the large models including all markers. The results demonstrate a new, integrated genomic prediction and machine learning-genome-wide association study (ML-GWAS) approach, aimed at high predictive ability and coupled marker detection in the soybean genome for traits phenotyped in different environments.

BACKGROUND ACACIA MELANOXYLON: is an important species for establishing pulpwood plantations due to its high application value in engineered wood products. However, the lack of a well-established in vitro regeneration system has severely constrained its industrial-scale propagation and the induction of tetraploids. RESULTS: In this study, using the superior A. melanoxylon clone SR3, an in vitro regeneration system using a bud-bearing stem segment was established. A DKW medium supplemented with 0.5 mg/L 6-BA, 0.1 mg/L IAA, and 0.2 mg/L NAA was determined as the optimal differentiation medium. Adding 0.5 mg/L IBA and 0.25 mg/L NAA to the 1/2 MS medium produced a higher rooting percentage and root number. To determine the optimal timing for tetraploid induction in A. melanoxylon, morphological, cytological, and flow cytometric analyses were conducted on the swollen tissue at the base of the bud-bearing stem segment. On the 5th day of preculture, white callus tissue was observed, characterized by vigorous cell division and the highest G₂/M-phase cell content in the adventitious bud primordia. After colchicine treatment, the tetraploid induction efficiency on the 5th day of preculture was significantly higher compared to the 4th or 6th day. The highest induction rate of 12.26 ± 0.80% was achieved with 100 mg/L colchicine for 72 h on the 5th day of preculture. Furthermore, tetraploid A. melanoxylon exhibited morphological traits such as reduced plant height, leaf number, and stomatal density. CONCLUSIONS: This study establishes a stable and effective method for in vitro tetraploid induction in A. melanoxylon, providing theoretical and technical support for polyploid breeding and laying the groundwork for subsequent triploid development.

Wheat is significantly impacted by fungal diseases, which result in severe economic losses. These diseases result from pathogenic spores invading wheat. Rapid and accurate detection of these spores is essential for post-harvest contamination risk assessment and early warning. Traditional detection methods are time-consuming and labor-intensive, and difficult to detect small target spores in complex environments. Therefore, a YOLO-ASF-MobileViT detection algorithm is proposed to detect pathogenic wheat spores with varying sizes, shapes, and textures. Four types of common pathogenic wheat spores are used as the study object, including Fusarium graminearum, Aspergillus flavus, Tilletia foetida (sporidium maturum), and Tilletia foetida (sporidium immaturum). The Attentional Scale Sequence Fusion (ASF) is integrated into the original YOLOv5s to enhance the capture of small details in spore images and fuse multi-scale feature information of spores. Additionally, the Mobile Vision Transformer (MobileViT) attention mechanism is incorporated to enhance both local and global feature extraction for small spores. Experimental results show that the proposed YOLO-ASF-MobileViT model achieves an overall mAP@0.5 of 97.0%, outperforming advanced detectors such as TPH-YOLO (95.6%) and MG-YOLO (95.5%). Compared to the baseline YOLOv5s model, it improves the average detection accuracy by 1.6%, with a notable 4.3% increase in detecting small Aspergillus flavus spores (reaching 90.8%). The model maintains high robustness in challenging scenarios such as spore adhesion, occlusion, blur, and noise. This approach enables efficient and accurate detection of wheat fungal spores, supporting early contamination warning in post-harvest management.

Background: Spikelet number, a core phenotypic parameter for wheat yield composition, requires precise estimation through accurate spike contour extraction and differentiation between grain surfaces and spikelet surfaces. However, technical challenges persist in precise spike segmentation under complex field backgrounds and morphological differentiation between grain/spikelet surfaces.

Method: Building on two-year multi-angle wheat spike imagery, we propose an enhanced YOLOv9-LDS multi-scale object detection framework. The algorithm innovatively constructs a lightweight depthwise separable network (LDSNet) as backbone, balancing computational efficiency and accuracy through channel re-parameterization strategy; incorporates an Efficient Local Attention (ELA) module to build feature enhancement networks, and employs dual-path feature fusion mechanisms to strengthen edge texture responses, significantly improving discrimination of overlapping spikes and complex backgrounds. Further optimizes the loss function system by replacing traditional IoU with Scylla Intersection over Union (SIoU) metric, enhancing bounding box regression through dynamic focus factors, and adding high-resolution small-object detection layers to mitigate dense spikelet feature loss.

Results: Independent test set validation shows the improved model achieves 83.9% contour integrity recognition rate and 92.4% mAP@0.5, exceeding baseline by 3.2 and 5.3% points respectively. Ablation studies confirm LDSNet-ELA integration reduces false positives by 27.6%, while the enhanced loss function system improves small-object recall by 19.4%.

Conclusions: The proposed framework demonstrates superior performance in complex field scenarios with dense targets and dynamic illumination. The multi-scale feature synergy enhancement mechanism overcomes traditional models' limitations in detecting overlapping spikes. This method not only enables precise spike phenotyping but also provides robust algorithmic support for intelligent field spikelet counting systems, advancing translational applications in crop phenomics.

Background: Fusarium Head Blight (FHB) is a destructive fungal disease affecting wheat and barley, leading to significant yield losses and reduced grain quality. Susceptibility to FHB is influenced by genetic factors, environmental conditions, and genotype-by-environment interactions (GxE), making it challenging to predict disease resistance across diverse environments. This study investigates GxE in a long-term spring wheat multi-environment uniform nursery trial focusing on the evaluation of resistant lines in northern US breeding programs.

Results: Traditionally, GxE has been analyzed as a reaction norm over an environment index. Here, we computed the environment index as a linear combination of environmental covariables specific to each environment, and we derived an environment relationship matrix. Three methods were compared, all aimed at predicting untested genotypes in untested environments: the widely used Finlay-Wilkinson regression (FW), the joint-genomic regression analysis (JGRA) method, and mixed models incorporating an environmental covariates matrix. These were benchmarked against a baseline genomic selection model (GS) without environmental covariates. Predictive abilities were assessed within and across environments. The results revealed that the JGRA marker effect method was more accurate than GS in within- and across-environment predictions, although the differences were small. The predictive ability slightly decreased when the target environment was less related to the training environments. Mixed models performed similarly to JGRA within-environment, but JGRA outperformed the other methods for across-environment predictions. Additionally, JGRA identified significant genetic markers associated with baseline FHB resistance and environmental sensitivity. Furthermore, location-specific genomic estimated breeding values were predicted, providing insights into genotype stability across varying locations.

Conclusion: These findings highlight the value of incorporating environmental covariates to increase predictive ability and improve the selection of resistant genotypes for diverse, untested environments. By leveraging this approach, breeders can effectively exploit GxE interactions to improve disease management at no additional cost.

Background: In major soybean-growing regions worldwide, vertical (three-dimensional) planting systems are widely adopted. Achieving precise phenotyping of individual soybean plants is crucial for breeding shade-tolerant cultivars and optimizing high yields. However, canopy shading from taller crops severely restricts the acquisition of phenotypic information from the lower-growing soybeans, and conventional phenotyping platforms struggle to meet the demands of such complex planting structures. To address this challenge, this study developed a field-based high-throughput phenotyping platform specifically designed to accommodate the structural characteristics of vertical planting systems.

Results: The platform integrates the characteristics of vertical planting systems and consists of an imaging system and a rail-based transportation system.The imaging system balances the growth requirements of soybeans under natural conditions with the stability of indoor imaging, and is equipped with adjustable sensors, an automated rotating stage for image capture, and modules for image classification and storage. The transportation system includes X and Y dual-directional tracks and programmable rail carts, enabling automated movement of potted soybean plants in the field. Platform performance was validated through correlation analysis and predictive modeling. The extracted plant height and width showed high agreement with manual measurements, with coefficients of determination (R²) of 0.99 and 0.95, respectively. During the vegetative stage, the predictive accuracy (R²) for canopy fresh weight and leaf area reached 0.965 and 0.972, demonstrating strong predictive performance and robustness. In addition, the platform supports modular sensor integration and features an open-source control architecture, allowing seamless incorporation of additional sensors such as infrared cameras, LiDAR, and fluorescence imaging. This expands trait detection capacity while reducing costs for reuse and secondary development.

Conclusion: This study demonstrated the feasibility of combining natural field conditions with standardized indoor imaging for phenotypic research on soybeans under vertical planting systems. The platform provides a flexible and scalable technical solution for analyzing plant architecture and screening germplasm in complex planting environments, opening up new technological pathways for precision agriculture and crop breeding research.

Disease incidence is a key factor contributing to reduced crop yield. Thus, early identification of crop diseases is crucial for minimizing the effects of disease incidence and maximizing crop yield. Therefore, this study aims to identify soybean yellow mottle mosaic virus (SYMMV) using the hyperspectral imaging (HSI) method combined with the machine learning (ML) technique. The soybeans were cultivated under two different environmental conditions, namely, EN I and EN II. In EN I, soybean plants were infected with SYMMV at the third vegetative growth stage, whereas in EN II, infected seeds were used. A reverse transcription polymerase chain reaction was conducted to distinguish the infected from noninfected plants. Mean spectrum values obtained from regions of interest in the Environmental Visualizing Images software served as data, while their respective wavelengths were used as features for ML models. The information gain method was used for the selection of characteristic wavelengths associated with disease identification. Continuous wavelengths ranging from 653 nm to 682 nm showed more information gain in both environments, indicating their significant role in SYMMV classification. Two classification models, random forest and k-nearest neighbor, classified the infected and noninfected plants at an early stage with over 90% accuracy. The support vector machine classified the disease with an average accuracy of > 95% across both environments, showing the best performance among the selected models. The logistic regression model showed lower accuracy, exceeding 82% in EN I, but improved to > 90% in EN II. These findings suggest that HSI combined with ML is the best alternative to the traditional method of disease identification in plants.

Background: Plant growth prediction assists physiologists and botanists in analyzing future development trends, thereby shortening experimental cycles and reducing costs. Traditional growth prediction methods mainly focused on phenotypic traits instead of images, which leads to limited visual interpretability.

Results: This article proposed a visualized growth prediction method based on an improved Pix2PixHD network, incorporating spatial attention mechanisms, an improved loss function, and a modified dropout strategy to enhance prediction accuracy and visual fidelity. The proposed method can employ maize images from early time points to predict the images of later stages. The prediction results are presented in the form of side-view growth images with a resolution of 1024 × 1024 pixels, enabling the capture of detailed, organ-level growth information. This study conducted experiments on 696 varieties, a highly genetically diverse maize population derived from the crossbreeding of 24 foundational Chinese inbred lines. The results showed that Fréchet Inception Distance, Peak Signal-to-Noise Ratio and structural similarity between the predicted images and the actual images reached 20.27, 23.23 and 0.899, respectively. The model achieved a mean Pearson correlation coefficient of 0.939 between predicted and actual phenotypic traits, while maintaining robust performance across different time intervals. It was also demonstrated that the model outperformed the existing related studies. The code is available online.

Conclusion: The results showed that the method can make realistic predictions of multi-variety maize growth based on high-resolution generation. Furthermore, it can achieve prediction of maize growth throughout the entire growth cycle with high accuracy. In conclusion, this article provided a novel solution for visualized growth prediction of large plants with complex physiological structures throughout the entire growth cycle. A primary limitation of this study is its focus on modeling and predicting crop growth under uniform environmental conditions, without considering environmental variability. Future work will aim to incorporate diverse environmental factors into the model to enhance its robustness and predictive accuracy.

Purpose: To overcome the risk of cellular damage and RNA degradation caused by high temperatures and cellular damage induced by laser capture microdissection (LCM) during plant single cell or small cell cluster isolation, we developed a rapid and simple method for single-cell separation and trace RNA extraction. The extracted RNA can be used for Smart-seq analysis, enabling comprehensive studies of various cell types.

Method: We used the secretory cells of Ligusticum chuanxiong Hort. fibrous root. First, we performed paraffin embedding to maintain RNA stability, and then examined the optimal slice thickness to obtain intact secretory cells. We compared the RNA quality of secretory cells isolated by LCM versus manual dissection under a microscope with a scalpel. Finally, xylene was introduced into the lysis buffer, followed by rapid shaking to achieve simultaneous dewaxing and cell lysis, and the xylene layer was then removed by centrifugation.

Result: A slice thickness of $20\mu \text{m}$ best preserved the integrity of secretory cells. Compared with LCM, this method yielded higher quality RNA. The obtained transcriptomic data showed an average Q30 score exceeding 91% and a genome mapping rate surpassing 86%.

Conclusion: This method can yield high-quality trace RNA suitable for Smart-seq analysis. Moreover, the significant differences in the transcriptomes of various small cell clusters types demonstrate the effectiveness and specificity of our manual dissection method.