Search Results (119)

Rice (Oryza sativa L.) is a major global staple crop, yet its productivity is severely constrained by rice blast disease caused by Magnaporthe oryzae. FK506-binding proteins (FKBPs) are peptidyl-prolyl cis-trans isomerases involved in protein folding, stress response, and signaling regulation, but their roles in rice blast resistance remain unclear. In this study, we performed a comprehensive identification and characterization of FKBP gene family members in two rice cultivars, Nipponbare (NIP) and Zhonghua 11 (ZH11), based on the latest T2T (telomere-to-telomere) genome assembly of ZH11 and the reference genome of NIP. A total of 24 and 29 FKBP genes were detected in NIP and ZH11, respectively, indicating a slight expansion in ZH11. Phylogenetic and collinearity analyses revealed strong conservation of FKBP family members between the two cultivars, while several ZH11-specific genes likely resulted from recent duplication events. Promoter analysis showed that FKBP genes are enriched in stress and hormone responsive cis-elements, particularly those related to ABA, MeJA, and SA signaling. Transcriptomic and RT-qPCR analyses demonstrated that multiple FKBP genes were significantly regulated during M. oryzae infection, suggesting their potential involvement in defense signaling pathways. This study provides a comprehensive overview of FKBP gene family evolution and expression in rice, identifies candidate genes potentially associated with blast resistance, and offers valuable insights for molecular breeding aimed at improving disease resistance in rice. Full article

Rice diseases pose a critical threat to global food security. While deep learning offers a promising path toward automated diagnosis, clear guidelines for model selection in resource-constrained agricultural environments are still lacking. This study presents a systematic benchmark of five deep convolutional neural networks (CNNs)—Visual Geometry Group (VGG)16, VGG19, Residual Network (ResNet)101V2, Xception, and Densely Connected Convolutional Network (DenseNet)121—for rice disease identification using a public leaf image dataset. The models, initialized with ImageNet pre-trained weights, were rigorously evaluated under a unified framework, including 5-fold cross-validation and a challenging out-of-distribution (OOD) generalization test. Our results demonstrate a clear performance hierarchy, with DenseNet121 emerging as the superior model. It achieved the highest OOD accuracy and F1-score (both 85.08%) while exhibiting the greatest parameter efficiency (8.1 million parameters), making it ideally suited for edge deployment. In contrast, architectures with large fully connected layers (VGG) or less efficient feature learning mechanisms (Xception, ResNet101V2) showed lower performance in this specific task. This study confirms the critical impact of architectural design choices, provides a reproducible performance baseline, and identifies DenseNet121 as a robust, efficient, and highly recommendable CNN for practical rice disease diagnosis in precision agriculture. Full article

Biological control is an effective and environmentally friendly strategy for managing plant diseases. In this study, a broad-spectrum antagonistic bacterium, designated strain AN6, was isolated from rice plants and exhibited potent inhibitory activity against a variety of phytopathogens. In Oxford cup assays, AN6 suppressed the growth of Xanthomonas oryzae pv. oryzae (Xoo) by 73.60%, and its cell-free culture filtrate caused pronounced morphological deformation in the bacterial cells. Further in vitro assays, including dual-culture assays, volatile organic compound (VOC) assays, and cell-free supernatant (CFS) assays, demonstrated that AN6 also exerted strong antifungal effects against several pathogenic fungi. In addition, the strain was found to produce proteases and siderophores, which may contribute to its antagonistic capabilities. Taxonomic identification based on morphological traits, 16S rRNA and gyrA gene sequencing, average nucleotide identity (ANI), in silico DNA–DNA hybridization (isDDH), and phylogenetic analysis classified strain AN6 as Bacillus velezensis. Whole-genome sequencing revealed that AN6 harbors a 3,929,788 bp genome comprising 4025 protein-coding genes with a GC content of 46.50%. Thirteen biosynthetic gene clusters (BGCs) associated with the production of secondary metabolites—such as nonribosomal peptides, polyketides, and dipeptide antibiotics—were identified. The pot experiment further validated the biocontrol potential of AN6, achieving an 80.49% reduction in rice bacterial blight caused by Xanthomonas oryzae pv. oryzae. Collectively, these results indicate that B. velezensis AN6 is a promising candidate for development as a highly effective biocontrol agent for the integrated management of diverse plant diseases. Full article

Rice sheath rot has progressively developed into a growing threat to global rice production, particularly in intensively managed systems conducive to disease development. Therefore, accurate identification of the causal pathogen and the development of sustainable management strategies represent urgent scientific requirements. In this study, we isolated the causal organism of rice sheath rot from infected rice tissues and identified it as Fusarium verticillioides based on multi-locus sequence analysis. Eight endophytic bacterial strains were recovered from healthy rice root systems. Among the isolates, Bacillus velezensis isolate 7-A exhibited the strongest antifungal activity against F. verticillioides. This isolate demonstrated broad-spectrum antifungal activity, with inhibition rates ranging from 54.8% to 71.8%. Phylogenetic analysis based on 16S rRNA and gyrB gene sequences identified it as B. velezensis. Further characterization revealed that B. velezensis 7-A is capable of secreting proteases and synthesizing siderophores. The filtered liquid from sterile fermentation markedly inhibited the growth of mycelium in F. verticillioides and induced marked morphological abnormalities. Liquid LC-MS analysis identified multiple antifungal active substances, including camphor, ginkgolides B, salicin, cinnamic acid, hydroxygenkwanin, stearamide, β-carotene, and others. A pot experiment demonstrated that the fermentation broth of B. velezensis 7-A effectively suppressed the occurrence of rice sheath rot, achieving a relative control efficacy of 61.3%, which is comparable to that of a 10% carbendazim water-dispersible granule (WDG). Additionally, isolate 7-A enhances plant disease resistance by activating the activities of key defense enzymes. These findings provide preliminary insights into its potential application in integrated and sustainable disease management programs. Full article

Protein–protein interactions (PPIs) are significant in understanding the complex molecular processes of plant growth, disease resistance, and stress responses. Machine learning (ML) has recently emerged as a powerful tool that can predict and analyze PPIs, offering complementary insights into traditional experimental approaches. It also accounts for proteoforms, distinct molecular variants of proteins arising from alternative splicing, or genetic variations and modifications, which can significantly influence PPI dynamics and specificity in rice. This review presents a comprehensive summary of ML-based methods for PPI predictions in rice (Oryza sativa) based on recent developments in algorithmic innovation, feature extraction processes, and computational resources. We present applications of these models in the discovery of candidate genes, unknown protein annotations, identification of plant–pathogen interactions, and precision breeding. Case studies demonstrate the utility of ML-based methods in improving rice resistance to abiotic and biotic stresses. Additionally, this review highlights key challenges like data limits, model generalizability, and future directions like multi-omics, deep learning and artificial intelligence (AI). This review provides a roadmap for researchers aiming to use ML to generate predictive and mechanistic insights on rice PPI networks, hence helping to achieve enhanced crop improvement programs. Full article

Long non-coding RNAs (lncRNAs) have emerged as pivotal regulators in plant immune responses, yet their roles in rice resistance against Magnaporthe oryzae (M. oryzae) remain inadequately explored. In this study, we integrated translatome data with conventional genome annotations to construct an optimized protein-coding dataset. Subsequently, we developed a robust pipeline (“RiceLncRNA”) for the accurate identification of rice lncRNAs. Using strand-specific RNA-sequencing (ssRNA-seq) data from the resistant (IR25), susceptible (LTH), and Nipponbare (NPB) varieties under M. oryzae infection, we identified 9003 high-confidence lncRNAs, significantly improving identification accuracy over traditional methods. Among the differentially expressed lncRNAs (DELs), those unique to IR25 were enriched in the biosynthetic pathways of phenylalanine, tyrosine, and tryptophan, which suggests that they are associated with the production of salicylic acid (SA) and auxin (IAA) precursors, which may be involved in defense responses. Conversely, DELs specific to LTH primarily clustered within carbon metabolism pathways, indicating a metabolic reprogramming mechanism. Notably, 21 DELs responded concurrently in both IR25 and LTH at 12 h and 24 h post-inoculation, indicating a synergistic regulation of jasmonic acid (JA) and ethylene (ET) signaling while partially suppressing IAA pathways. Weighted gene co-expression network analysis (WGCNA) and competing endogenous RNA (ceRNA) network analysis revealed that key lncRNAs (e.g., LncRNA.9497.1) may function as miRNA “sponges”, potentially influencing the expression of receptor-like kinases (RLKs), resistance (R) proteins, and hormone signaling pathways. The reliability of these findings was confirmed through qRT-PCR and cloning experiments. In summary, our study provides an optimized rice lncRNA annotation framework and reveals the mechanism by which lncRNAs enhance rice blast resistance through the regulation of hormone signaling pathways. These findings offer an important molecular basis for rice disease-resistant breeding. Full article

The timely and correct identification of rice diseases is essential to ensuring rice productivity. However, many methods have drawbacks such as slow recognition speed, low recognition accuracy and overly complex models that are unfavorable for portability. Therefore, this study proposes an improved model for accurately classifying rice diseases based on a two-level routing attention mechanism and dynamic convolution based on the above difficulties. The model employs Alterable Kernel Convolution with dynamic, irregularly shaped convolutional kernels and Bi-level Routing Attention that utilizes sparsity to reduce parameters and involves a GPU-friendly dense matrix multiplication, which can achieve high-precision rice disease recognition while ensuring lightweight and recognition speed. The model successfully classified 10 species, including nine diseased and healthy rice, with 97.31% accuracy and a 97.18% F1-score. Our proposed method outperforms MobileNetV3-large, EfficientNet-b0, Swin Transformer-tiny and ResNet-50 by 1.73%, 1.82%, 1.25% and 0.67%, respectively. Meanwhile, the model contains only $4.453\times {10}^6$ parameters and achieves an inference time of 6.13 s, which facilitates deployment on mobile devices.The proposed MobileViT_BiAK method effectively identifies rice diseases while providing a lightweight and high-performance classification solution. Full article

The yield and quality of rice are severely affected by rice disease, which can result in crop failure. Early and precise identification of rice plant diseases enables timely action, minimizing potential economic losses. Deep convolutional neural networks (CNNs) have significantly advanced image classification accuracy by leveraging powerful feature extraction capabilities, outperforming traditional machine learning methods. In this work, we propose a dual attention-guided lightweight network for fast and precise recognition of rice diseases with small lesions and high similarity. First, to efficiently extract features while reducing computational redundancy, we incorporate FasterNet using partial convolution (PC-Conv). Furthermore, to enhance the network’s ability to capture fine-grained lesion details, we introduce a dual-attention mechanism that aggregates long-range contextual information in both spatial and channel dimensions. Additionally, we construct a large-scale rice disease dataset, named RD-6, which contains 2196 images across six categories, to support model training and evaluation. Finally, the proposed rice disease detection method is evaluated on the RD-6 dataset, demonstrating its superior performance over other state-of-the-art methods, especially in terms of recognition efficiency. For instance, the method achieves an average accuracy of 99.9%, recall of 99.8%, precision of 100%, specificity of 100%, and F1-score of 99.9%. Additionally, the proposed method has only 3.6 M parameters, demonstrating higher efficiency without sacrificing accuracy. Full article

High-quality disease segmentation plays a crucial role in the precise identification of rice diseases. Although the existing deep learning methods can identify the disease on rice leaves to a certain extent, these methods often face challenges in dealing with multi-scale disease spots and irregularly growing disease spots. In order to solve the challenges of rice leaf disease segmentation, we propose KBNet, a novel multi-modal framework integrating language and visual features for rice disease segmentation, leveraging the complementary strengths of CNN and Transformer architectures. Firstly, we propose the Kalman Filter Enhanced Kolmogorov–Arnold Networks (KF-KAN) module, which combines the modeling ability of KANs for nonlinear features and the dynamic update mechanism of the Kalman filter to achieve accurate extraction and fusion of multi-scale lesion information. Secondly, we introduce the Boundary-Constrained Physical-Information Neural Network (BC-PINN) module, which embeds the physical priors, such as the growth law of the lesion, into the loss function to strengthen the modeling of irregular lesions. At the same time, through the boundary punishment mechanism, the accuracy of edge segmentation is further improved and the overall segmentation effect is optimized. The experimental results show that the KBNet framework demonstrates solid performance in handling complex and diverse rice disease segmentation tasks and provides key technical support for disease identification, prevention, and control in intelligent agriculture. This method has good popularization value and broad application potential in agricultural intelligent monitoring and management. Full article

This study proposes CEL-DL-Bagging (Cross-Entropy Loss-optimized Deep Learning Bagging), a multi-model fusion framework that integrates cross-entropy loss-weighted voting with Bootstrap Aggregating (Bagging). First, we develop a lightweight recognition architecture by embedding a salient position attention (SPA) mechanism into four base networks (YOLOv5s-cls, EfficientNet-B0, MobileNetV3, and ShuffleNetV2), significantly enhancing discriminative feature extraction for disease patterns. Our experiments show that these SPA-enhanced models achieve consistent accuracy gains of 0.8–1.7 percentage points, peaking at 97.86%. Building on this, we introduce DB-CEWSV—an ensemble framework combining Deep Bootstrap Aggregating (DB) with adaptive Cross-Entropy Weighted Soft Voting (CEWSV). The system dynamically optimizes model weights based on their cross-entropy performance, using SPA-augmented networks as base learners. The final integrated model attains 98.33% accuracy, outperforming the strongest individual base learner by 0.48 percentage points. Compared with single models, the ensemble learning algorithm proposed in this study led to better generalization and robustness of the ensemble learning model and better identification of rice diseases in the natural background. It provides a technical reference for applying rice disease identification in practical engineering. Full article

Rice blast caused by Magnaporthe oryzae is a major cause of yield reductions and quality deterioration in rice. Therefore, early detection of the disease is necessary for controlling the spread of rice blast. This study proposed a dual-channel feature fusion model (DCFM) to achieve effective identification of rice blast. The DCFM model extracted spectral features using successive projection algorithm (SPA), random frog (RFrog), and competitive adaptive reweighted sampling (CARS), and extracted spatial features from spectral images using MobileNetV2 combined with the convolutional block attention module (CBAM). Then, these features were fused using the feature fusion adaptive conditioning module in DCFM and input into the fully connected layer for disease identification. The results show that the model combining spectral and spatial features was superior to the classification models based on single features for rice blast detection, with OA and Kappa higher than 90% and 88%, respectively. The DCFM model based on SPA screening obtained the best results, with an OA of 96.72% and a Kappa of 95.97%. Overall, this study enables the early and accurate identification of rice blast, providing a rapid and reliable method for rice disease monitoring and management. It also offers a valuable reference for the detection of other crop diseases. Full article

Villosiclava virens (anamorph: Ustilaginoidea virens), the causal fungal pathogen of rice false smut, has been found to produce various secondary metabolites. The albino strain LN02 is a natural albino phenotype mutant of V. virens due to its inability to produce ustilaginoidins. The fermentation of V. virens LN02 was performed in solid rice medium to obtain fungal cultures, which were chemically investigated. After removing the known metabolites, two new dimeric sorbicillinoids, namely ustisorbicillinols G (1) and H (2), were isolated from the ethyl acetate extract. Their structures were elucidated using spectroscopic data analyses and quantum chemical calculations. Compounds 1 and 2 displayed antibacterial activity towards Ralstonia solanacearum, Agrobacterium tumefaciens and Bacillus subtilis, with median inhibitory concentration (IC₅₀) values of 19.76–25.43 μg/mL for 1 and 25.35–45.48 μg/mL for 2. The discovery of new sorbicillinoids will increase the diversity of the secondary metabolites of V. virens and provide candidates for the creation of new antimicrobials as well. Full article

In rice detection tasks, accurate identification of leaf streaks, pest and disease distribution, and spikelet hierarchies relies on high-quality images to distinguish between texture and hierarchy. However, existing images often suffer from texture blurring and contour shifting due to equipment and environment limitations, which affects the detection performance. In view of the fact that pests and diseases affect the whole situation and tiny details are mostly localized, we propose a rice image reconstruction method based on an adaptive two-branch heterogeneous structure. The method consists of a low-frequency branch (LFB) that recovers global features using orientation-aware extended receptive fields to capture streaky global features, such as pests and diseases, and a high-frequency branch (HFB) that enhances detail edges through an adaptive enhancement mechanism to boost the clarity of local detail regions. By introducing the dynamic weight fusion mechanism (CSDW) and lightweight gating network (LFFN), the problem of the unbalanced fusion of frequency information for rice images in traditional methods is solved. Experiments on the 4× downsampled rice test set demonstrate that the proposed method achieves a 62% reduction in parameters compared to EDSR, 41% lower computational cost (30 G) than MambaIR-light, and an average PSNR improvement of 0.68% over other methods in the study while balancing memory usage (227 M) and inference speed. In downstream task validation, rice panicle maturity detection achieves a 61.5% increase in mAP50 (0.480 → 0.775) compared to interpolation methods, and leaf pest detection shows a 2.7% improvement in average mAP50 (0.949 → 0.975). This research provides an effective solution for lightweight rice image enhancement, with its dual-branch collaborative mechanism and dynamic fusion strategy establishing a new paradigm in agricultural rice image processing. Full article

Traditional monitoring methods rely on manual field surveys, which are subjective, inefficient, and unable to meet the demand for large-scale, rapid monitoring. By using unmanned aerial vehicles (UAVs) to capture high-resolution images of rice canopy diseases and pests, combined with deep learning (DL) techniques, accurate and timely identification of diseases and pests can be achieved. We propose a method for identifying rice canopy diseases and pests using an improved YOLOv5 model (YOLOv5_DWMix). By incorporating deep separable convolutions, the MixConv module, attention mechanisms, and optimized loss functions into the YOLOv5 backbone, the model’s speed, feature extraction capability, and robustness are significantly enhanced. Additionally, to tackle the challenges posed by complex field environments and small datasets, image augmentation is employed to train the YOLOv5_DWMix model for the recognition of four common rice canopy diseases and pests. Results show that the improved YOLOv5 model achieves 95.6% average precision in detecting these diseases and pests, a 4.8% improvement over the original YOLOv5 model. The YOLOv5_DWMix model is effective and advanced in identifying rice diseases and pests, offering a solid foundation for large-scale, regional monitoring. Full article

Background/Objectives: To overcome the limitations imposed by bacterial blight on widely adopted indica–japonica hybrid rice, this study employed molecular design breeding strategies to develop a resistant germplasm. Methods: Through conventional backcross breeding combined with molecular-marker-assisted selection, the Xa23-carrying material XR39 was hybridized with the wide-compatibility restorer line R5315 harboring the S5n gene. Progeny selection integrated evaluations of agronomic traits, disease resistance identification, and test-crossing with sterile lines. Results: Five wide-compatibility restorer lines simultaneously incorporating the Xa23 and S5n genes were successfully developed, demonstrating outstanding bacterial blight resistance and restoration ability. The selected hybrid combinations, A3/RP1, A1/RP4, and A4/RP4, exhibited yield increases of 2.6–8.6% compared to the control. Conclusions: This study not only established a novel germplasm for developing bacterial blight-resistant indica–japonica hybrid rice varieties, but also established a model for gene design breeding for rice improvement. Full article