Search Results (949)

Background/Objectives: The bird cherry-oat aphid, Rhopalosiphum padi, is a major global pest of cereal crops and exhibits wing polyphenism, producing both winged (dispersive) and wingless (reproductive) morphs. Methods: To identify potential RNAi targets that could specifically disrupt the migratory winged morph, we conducted a comparative transcriptomic analysis of adult aphids. Differentially expressed genes (DEGs) were identified, annotated for their functions, and analyzed for their involvement in metabolic pathways. Results: Significant differences were observed in 121 genes between morphs: 13 were upregulated in the winged morph, while 108 were downregulated. Most DEGs were enriched in lipid metabolism and circadian rhythm pathways, suggesting that wing polymorphism may be adaptively linked to energy resource allocation strategies. Conclusions: This study firstly reveals the adult-stage-specific regulatory roles of lipid metabolism and circadian rhythm pathways in wing polyphenism, identifying six candidate genes (BCORL1, AMP-L, Pfl, Lip3L, HLFL(X7), and HLFL(X4)) for RNAi-based biocontrol strategies targeting migratory morphs. Full article

The stable marine environment is conducive to the development of the aquaculture industry. However, with the change of seawater salinity in recent years, it has had a great impact on the survival and breeding of cephalopods such as Sepia esculenta. In this study, biochemical measurement and transcriptome sequencing were performed on the larvae of S. esculenta after different salinity stresses (salinity of 20 ppt and 40 ppt), and the reliability of transcriptome results was proved by physiological indexes. We performed Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis, and gene set enrichment analysis (GSEA) on all annotated genes, and gene sets were identified, including chemokine signaling pathways, MAPK signaling pathways, and cell cycle pathways. Finally, we constructed the protein-protein interaction networks (PPI) between the core genes in these gene sets and differentially expressed genes (DEGs) to identify key genes, including NFKBIA. Among them, the NFKBIA is not only a core gene in the chemokine signaling pathway gene set under four stresses but also has a high number of protein interactions. We speculate that this gene may have important immunomodulatory functions in the face of different time and salinity stresses. The results of our study explored the molecular mechanism of S. esculenta in the face of environmental stress, revealed the key molecular regulatory pathways for its survival and adaptation under complex environmental pressures, and may provide insights relevant to the development of S. esculenta pond culture. Full article

This paper proposes a transfer learning-based approach to enhance video-driven safety risk detection in industrial environments, addressing the critical challenge of limited generalization across diverse operational scenarios. Conventional deep learning models trained on specific operational contexts often fail when applied to new environments with different lighting, camera angles, or machinery configurations, exhibiting a significant drop in performance (e.g., F1-score declining below 0.85). To overcome this issue, an incremental feature transfer learning strategy is introduced, enabling efficient adaptation of risk detection models using only small amounts of data from new scenarios. This approach leverages prior knowledge from pre-trained models to reduce the reliance on large-labeled datasets, particularly valuable in industrial settings where rare but critical safety risk events are difficult to capture. Additionally, training efficiency is improved compared with a classic approach, supporting deployment on resource-constrained edge devices. The strategy involves incremental retraining using video segments with average durations ranging from 2.5 to 25 min (corresponding to 5–50% of new scenario data), approximately, enabling scalable generalization across multiple forklift-related risk activities. Interpretability is enhanced through SHAP-based analysis, which reveals a redistribution of feature relevance toward critical components, thereby improving model transparency and reducing annotation demands. Experimental results confirm that the transfer learning strategy significantly improves detection accuracy, robustness, and adaptability, making it a practical and scalable solution for safety monitoring in dynamic industrial environments. Full article

Background: The accurate classification of brain tumor subtypes from MRI scans is critical for timely diagnosis, yet the manual annotation of large datasets remains prohibitively labor-intensive. Method: We present SSPLNet (Semi-Supervised Pseudo-Labeling Network), a dual-branch deep learning framework that synergizes confidence-guided iterative pseudo-labelling with deep feature fusion to enable robust MRI-based tumor classification in data-constrained clinical environments. SSPLNet integrates a custom convolutional neural network (CNN) and a pretrained ResNet50 model, trained semi-supervised using adaptive confidence thresholds ($\tau = 0.98 \to 0.95 \to 0.90$) to iteratively refine pseudo-labels for unlabelled MRI scans. Feature representations from both branches are fused via a dense network, combining localized texture patterns with hierarchical deep features. Results: SSPLNet achieves state-of-the-art accuracy across labelled–unlabelled data splits ($90:10$ to $10:90$), outperforming supervised baselines in extreme low-label regimes (10:90) by up to 5.34% from Custom CNN and 5.58% from ResNet50. The framework reduces annotation dependence and with 40% unlabeled data maintains 98.17% diagnostic accuracy, demonstrating its viability for scalable deployment in resource-limited healthcare settings. Conclusions: Statistical Evaluation and Robustness Analysis of SSPLNet Performance confirms that SSPLNet’s lower error rate is not due to chance. The bootstrap results also confirm that SSPLNet’s reported accuracy falls well within the 95% CI of the sampling distribution. Full article

Producing high-quality segmentation masks for medical images is a fundamental challenge in biomedical image analysis. Recent research has investigated the use of supervised learning with large volumes of labeled data to improve segmentation across medical imaging modalities and unsupervised learning with unlabeled data to segment without detailed annotations. However, a significant hurdle remains in constructing a model that can segment diverse medical images in a zero-shot manner without any annotations. In this work, we introduce the attention diffusion zero-shot unsupervised system (ADZUS), a new method that uses self-attention diffusion models to segment biomedical images without needing any prior labels. This method combines self-attention mechanisms to enable context-aware and detail-sensitive segmentations, with the strengths of the pre-trained diffusion model. The experimental results show that ADZUS outperformed state-of-the-art models on various medical imaging datasets, such as skin lesions, chest X-ray infections, and white blood cell segmentations. The model demonstrated significant improvements by achieving Dice scores ranging from 88.7% to 92.9% and IoU scores from 66.3% to 93.3%. The success of the ADZUS model in zero-shot settings could lower the costs of labeling data and help it adapt to new medical imaging tasks, improving the diagnostic capabilities of AI-based medical imaging technologies. Full article

The medical imaging domain frequently encounters the dual challenges of annotation scarcity and class imbalance. A critical issue lies in effectively extracting information from limited labeled data while mitigating the dominance of head classes. The existing approaches often overlook in-depth modeling of sample relationships in low-dimensional spaces, while rigid or suboptimal dynamic thresholding strategies in pseudo-label generation are susceptible to noisy label interference, leading to cumulative bias amplification during the early training phases. To address these issues, we propose a semi-supervised medical image classification framework combining labeled data-contrastive learning with class-adaptive pseudo-labeling (CLCP-MT), comprising two key components: the semantic discrimination enhancement (SDE) module and the class-adaptive pseudo-label refinement (CAPR) module. The former incorporates supervised contrastive learning on limited labeled data to fully exploit discriminative information in latent structural spaces, thereby significantly amplifying the value of sparse annotations. The latter dynamically calibrates pseudo-label confidence thresholds according to real-time learning progress across different classes, effectively reducing head-class dominance while enhancing tail-class recognition performance. These synergistic modules collectively achieve breakthroughs in both information utilization efficiency and model robustness, demonstrating superior performance in class-imbalanced scenarios. Extensive experiments on the ISIC2018 skin lesion dataset and Chest X-ray14 thoracic disease dataset validate CLCP-MT’s efficacy. With only 20% labeled and 80% unlabeled data, our framework achieves a 10.38% F1-score improvement on ISIC2018 and a 2.64% AUC increase on Chest X-ray14 compared to the baselines, confirming its effectiveness and superiority under annotation-deficient and class-imbalanced conditions. Full article

Background: Plastid RNA editing is widespread in angiosperms yet remains underexplored in the medicinal non-model species Glycyrrhiza uralensis. This study aimed to (i) comprehensively identify plastid RNA editing sites in G. uralensis, and (ii) compare the detection performance of three library construction strategies: total RNA-seq, rRNA-depleted RNA-seq, and mRNA-seq. Methods: Leaf tissue was used from three wild-sampled individual plants. Plastomes were assembled with GetOrganelle v1.7.0 and annotated using PGA. Strand-specific RNA-seq libraries were mapped to sample-matched plastomes using HISAT2 v2.2.1. Variants were identified using REDItools v2.0 under uniform thresholds. Candidate sites were visually verified in IGV v2.12.3, and read origins were confirmed by BLAST v2.13.0+; artifacts were removed via strand-specific filtering. Results: After stringent filtering, 38 high-confidence RNA editing sites were identified across 19 genes. Total RNA seq performed the best, detecting 37/38 sites consistently, whereas rRNA-depleted libraries detected fewer genuine sites and produced numerous rRNA-linked, noncanonical, noncoding-strand-dominant artifacts. Despite very low rates of plastid mapping, mRNA seq recovered a large fraction of bona fide sites under stringent, strand-aware filtering. Conclusions: We establish a set of 38 high-confidence plastid RNA editing sites in G. uralensis and suggest potential adaptive implications of editing in ndh-related genes. Methodologically, total RNA-seq is recommended for identification using de novo RNA editing due to its high sensitivity and low false-positive rate; publicly available poly(A)-selected mRNA-seq datasets can be repurposed to reliably retrieve plastid RNA editing sites when stringent strand-specific filtering is applied. Full article

Waterlogging poses a grave abiotic stress that hampers crop productivity and survival due to reduced oxygen availability in the impacted tissues. To adapt to this hypoxic environment, the hypocotyls of melon (Cucumis melo L.) seedlings can produce a profusion of adventitious roots when exposed to waterlogging stress. However, research on the significance of these adventitious roots under waterlogging stress has been limited. The present study aimed to elucidate the critical role of adventitious roots by investigating the physiological, biochemical, and metabolic changes that occur following their removal during waterlogging stress. The removal of adventitious roots compromised the normal growth of melon seedlings, resulting in phenotypic abnormalities such as chlorotic and withered leaves. Our results indicated that the removal of adventitious roots led to significant reductions in total chlorophyll levels by 62.89% and 43.60% compared to the normal control condition and waterlogging stress alone, respectively. Additionally, in the adventitious root removal treatment, higher malondialdehyde (MDA) content, O₂^•− production rate, monodehydroascorbate reductase (MDHAR) activity, alcohol dehydrogenase (ADH) activity, the AsA/DHA ratio, proline content, jasmonic acid (JA) content, and 1-aminocyclopropane-1-carboxylic acid (ACC) content were observed. Specifically, JA levels were significantly enhanced by 180.54% and 52.05%, and ACC levels were significantly increased by 519.23% and 125.16% compared to the control and waterlogging stress conditions, respectively. Through untargeted metabolomic analysis, a total of 447 differentially accumulated metabolites (DAMs) were identified. Notably, jasmonic acid and brassinolide, which are involved in plant hormone signal transduction, along with cyanidin 3-(2G-xylosylrutinoside) classified as flavonoids, (2S,3′S)-α-amino-2-carboxy-5-oxo-1-pyrrolidinebutanoic acid categorized as proline and derivatives, and ligstroside-aglycone and foeniculoside VII annotated as terpenoids, exhibited key roles in the waterlogging response. This research enhances our understanding of the mechanisms underlying the removal of adventitious roots during waterlogging stress, as well as the associated physiological, biochemical, and metabolic changes. These findings provide valuable insights into the crucial role of adventitious roots in melon seedlings subjected to waterlogging stress and may inform strategies for enhancing waterlogging tolerance in breeding practices. Full article

Facial beauty prediction (FBP) is a cutting-edge task in deep learning that aims to equip machines with the ability to assess facial attractiveness in a human-like manner. In human perception, facial beauty is strongly associated with facial symmetry, where balanced structures often reflect aesthetic appeal. Leveraging symmetry provides an interpretable prior for FBP and offers geometric constraints that enhance feature learning. However, existing multi-task FBP models still face challenges such as limited annotated data, insufficient frequency–temporal modeling, and feature conflicts from task heterogeneity. The Mamba model excels in feature extraction and long-range dependency modeling but encounters difficulties in parameter sharing and computational efficiency in multi-task settings. In contrast, mixture-of-experts (MoE) enables adaptive expert selection, reducing redundancy while enhancing task specialization. This paper proposes MoMamba, a multi-task decoder combining Mamba’s state-space modeling with MoE’s dynamic routing to improve multi-scale feature fusion and adaptability. A detail enhancement module fuses high- and low-frequency components from discrete cosine transform with temporal features from Mamba, and a state-aware MoE module incorporates low-rank expert modeling and task-specific decoding. Experiments on SCUT-FBP and SCUT-FBP5500 demonstrate superior performance in both classification and regression, particularly in symmetry-related perception modeling. Full article

α-L-fucosidases (EC 3.2.1.51) are of particular interest due to their ability to cleave terminal α-L-fucose residues from glycoconjugates, a property associated with numerous biological and therapeutic effects. They have also been investigated for their potential use in glycan remodeling, disease biomarker analysis, and particularly as therapeutic agents in the context of fucosidosis, a rare lysosomal storage disorder, caused by a deficiency in α-L-fucosidase activity. However, limitations in enzyme availability, stability, and substrate specificity highlight the need for novel and more efficient enzyme sources. Bifidobacterium castoris (B. castor is) is a newly identified species first discovered in the beaver gut microbiota in 2019. Phylogenetic studies have revealed its advanced metabolic capacity, and genomic analyses have demonstrated its extensive carbohydrate metabolism potential. This research article focuses on the recombinant production and biochemical characterization of a novel α-L-fucosidase from B. castoris LMG (Laboratorium voor Microbiologie Gent) 30937, predicted to belong to glycoside hydrolase family 29 (GH29) according to Universal Protein Resource (UniProt) annotation. Under optimized reaction conditions the recombinant α-L-fucosidase exhibited a specific activity of 0.264 U/mg to pNP-Fuc (4-Nitrophenyl-α-L-fucopyranoside). The results indicate that the enzyme is active in the pH range of 3.0–8.0 and temperatures of 24–42 °C, but its optimum conditions are the slightly acidic pH of 5.5 and the elevated temperature of 42 °C. This profile suggests that the enzyme is adapted to acidic intestinal-like environments. This novel enzyme expands the GH29 α-L-fucosidase repertoire and offers a promising new candidate for future biotechnological applications. Full article

Accurate and efficient detection of underwater targets in sonar imagery is critical for applications such as marine exploration, infrastructure inspection, and autonomous navigation. However, sonar-based object detection remains challenging due to low resolution, high noise, cluttered backgrounds, and the scarcity of annotated data. To address these issues, we propose UWS-YOLO, a novel detection framework specifically designed for underwater sonar images. The model integrates three key innovations: (1) a C2F-Ortho module that enhances multi-scale feature representation through orthogonal channel attention, improving sensitivity to small and low-contrast targets; (2) a DySnConv module that employs Dynamic Snake Convolution to adaptively capture elongated and irregular structures such as pipelines and cables; and (3) a cross-modal transfer learning strategy that pre-trains on large-scale optical underwater imagery before fine-tuning on sonar data, effectively mitigating overfitting and bridging the modality gap. Extensive evaluations on real-world sonar datasets demonstrate that UWS-YOLO achieves a mAP@0.5 of 87.1%, outperforming the YOLOv8n baseline by 3.5% and seven state-of-the-art detectors in accuracy while maintaining real-time performance at 158 FPS with only 8.8 GFLOPs. The framework exhibits strong generalization across datasets, robustness to noise, and computational efficiency on embedded devices, confirming its suitability for deployment in resource-constrained underwater environments. Full article

Timely detection of road surface defects such as cracks and potholes is critical for ensuring traffic safety and reducing infrastructure maintenance costs. While recent advances in image-based deep learning techniques have shown promise for automated road defect detection, existing models remain limited to closed-set detection settings, making it difficult to recognize newly emerging or fine-grained defect types. To address this limitation, we propose an attribute-aware open-vocabulary crack detection (AOVCD) framework, which leverages the alignment capability of pretrained vision–language models to generalize beyond fixed class labels. In this framework, crack types are represented as combinations of visual attributes, enabling semantic grounding between image regions and natural language descriptions. To support this, we extend the existing PPDD dataset with attribute-level annotations and incorporate a multi-label attribute recognition task as an auxiliary objective. Experimental results demonstrate that the proposed AOVCD model outperforms existing baselines. In particular, compared to CLIP-based zero-shot inference, the proposed model achieves approximately a 10-fold improvement in average precision (AP) for novel crack categories. Attribute classification performance—covering geometric, spatial, and textural features—also increases by 40% in balanced accuracy (BACC) and 23% in AP. These results indicate that integrating structured attribute information enhances generalization to previously unseen defect types, especially those involving subtle visual cues. Our study suggests that incorporating attribute-level alignment within a vision–language framework can lead to more adaptive and semantically grounded defect recognition systems. Full article

Plant melatonin is widely recognized as a pleiotropic regulator. As a growth-regulating hormone, it extensively participates in various growth and developmental processes and has significant functions in stress responses and disease resistance. Plant melatonin is synthesized primarily through the catalytic actions of five enzymes: TDC (tryptophan decarboxylase), T5H (tryptamine-5-hydroxylase), SNAT (serotonin N-acetyltransferase), ASMT (N-acetylserotonin methyltransferase), and COMT (caffeic acid-O-methyltransferase). There are multiple genes for each of these five enzymes in citrus genomes, however, with the exception of COMT5—whose function has recently been elucidated—and SNAT, which has only been preliminarily identified, the remaining genes have not been unequivocally characterized or functionally annotated. Hence, we carried out a genome-wide analysis of melatonin biosynthesis enzyme-related gene families in trifoliate orange (Poncirus trifoliata), one of the most common citrus rootstock varieties. Through bioinformatics approaches, we identified 96 gene family members encoding melatonin biosynthetic enzymes and characterized their protein sequence properties, phylogenetic relationships, gene structures, chromosomal distributions, and promoter cis-acting elements. Furthermore, by analyzing expression patterns in different tissues and under various stresses, we identified multiple stress-responsive melatonin synthase genes. These genes likely participate in melatonin synthesis under adverse conditions, thereby enhancing stress adaptation. Specifically, PtCOMT5, PtASMT11, and PtTDC9 were significantly induced by low temperature; PtSNAT1, PtSNAT14, PtSNAT18, and PtTDC10 were markedly responsive to drought; and PtASMT15, PtSNAT15, PtASMT16, and PtSNAT3 were strongly induced by ABA. Among them, PtASMT23 expression was induced up to 120-fold under low temperature, while PtSNAT18 showed over 100-fold upregulation under dehydration treatment. These findings strongly suggest that PtASMT23 and PtSNAT18 play critical roles in regulating melatonin biosynthesis in response to cold and drought stress, respectively. Collectively, these findings pinpoint novel genetic targets for enhancing stress resilience in citrus breeding programs and lay the foundation for the functional characterization of specific melatonin biosynthesis pathway gene family members in citrus and other horticultural crop species. Full article

Background/Objectives: The limited availability of labeled data, particularly in the medical domain, poses a significant challenge for training accurate diagnostic models. While deep learning techniques have demonstrated notable efficacy in image-based tasks, they require large annotated datasets. In data-scarce scenarios—especially involving rare diseases—their performance deteriorates significantly. Meta-learning offers a promising alternative by enabling models to adapt quickly to new tasks using prior knowledge and only a few labeled examples. This study aims to evaluate the effectiveness of representative meta-learning models for thoracic disease classification in chest X-rays. Methods: We conduct a comparative evaluation of four meta-learning models: Prototypical Networks, Relation Networks, MAML, and FoMAML. First, we assess five backbone architectures (ConvNeXt, DenseNet-121, ResNet-50, MobileNetV2, and ViT) using a Prototypical Network. The best-performing backbone is then used across all meta-learning models for fair comparison. Experiments are performed on the ChestX-ray14 dataset under a 2-way setting with multiple k-shot configurations. Results: Prototypical Networks combined with DenseNet-121 achieved the best performance, with a recall of 68.1%, an F1-score of 67.4%, and a precision of 0.693 in the 2-way, 10-shot configuration. In a disease-specific analysis, Hernia obtains the best classification results. Furthermore, Prototypical and Relation Networks demonstrate significantly higher computational efficiency, requiring fewer FLOPs and shorter execution times than MAML and FoMAML. Conclusions: Prototype-based meta-learning, particularly with DenseNet-121, proves to be a robust and computationally efficient approach for few-shot chest X-ray disease classification. These findings highlight its potential for real-world clinical applications, especially in scenarios with limited annotated medical data. Full article

The early detection of fire and smoke is essential for mitigating human casualties, property damage, and environmental impact. Traditional sensor-based and vision-based detection systems frequently exhibit high false alarm rates, delayed response times, and limited adaptability in complex or dynamic environments. Recent advances in deep learning and computer vision have enabled more accurate, real-time detection through the automated analysis of flame and smoke patterns. This paper presents a comprehensive review of deep learning techniques for fire and smoke detection, with a particular focus on convolutional neural networks (CNNs), object detection frameworks such as YOLO and Faster R-CNN, and spatiotemporal models for video-based analysis. We examine the benefits of these approaches in terms of improved accuracy, robustness, and deployment feasibility on resource-constrained platforms. Furthermore, we discuss current limitations, including the scarcity and diversity of annotated datasets, susceptibility to false alarms, and challenges in generalization across varying scenarios. Finally, we outline promising research directions, including multimodal sensor fusion, lightweight edge AI implementations, and the development of explainable deep learning models. By synthesizing recent advancements and identifying persistent challenges, this review provides a structured foundation for the design of next-generation intelligent fire detection systems. Full article