Search

Abstract Maritime objects frequently exhibit low-quality and insufficient feature information, particularly in complex maritime environments characterized by challenges such as small objects, waves, and reflections. This situation poses significant challenges to the development of reliable object detection including the strategies of loss function and the feature understanding capabilities in common YOLOv8 (You Only Look Once) detectors. Furthermore, the widespread adoption and unmanned operation of intelligent ships have generated increasing demands on the computational efficiency and cost of object detection hardware, necessitating the development of more lightweight network architectures. This study proposes the EL-YOLO (Efficient Lightweight You Only Look Once) algorithm based on YOLOv8, designed specifically for intelligent ship object detection. EL-YOLO incorporates novel features, including adequate wise IoU (AWIoU) for improved bounding box regression, shortcut multi-fuse neck (SMFN) for a comprehensive analysis of features, and greedy-driven filter pruning (GDFP) to achieve a streamlined and lightweight network design. The findings of this study demonstrate notable advancements in both detection accuracy and lightweight characteristics across diverse maritime scenarios. EL-YOLO exhibits superior performance in intelligent ship object detection using RGB cameras, showcasing a significant improvement compared to standard YOLOv8 models.

Abstract The article presents a comprehensive summary of Intelligent Ship Marine Object Detection (ISMOD) based on the RGB Camera. Marine object detection plays a pivotal role in enabling intelligent ships to acquire crucial data and security assurances for autonomous navigation. Among the various detection sensors, the RGB Camera is an informative and cost‐effective tool with a wide range of civil applications. In the beginning, the ISMOD metrics based on the RGB camera is analyzed from three significant aspects, namely accuracy, speed, and robustness. Subsequently, the latest research status and comparative overview are presented, encompassing three mainstream detection methods: traditional detection, deep learning detection, and sensor fusion detection. Finally, the existing challenges of ISMOD are discussed and future development trends are recommended. The results demonstrate that forthcoming development will predominantly concentrate on deep learning approaches, complemented by other techniques. It is imperative to advance detection performance in domains such as deep fusion, multi‐feature extraction, multi‐fusion technology, and lightweight detection architecture.

Abstract CRISPR‐based gene therapies are making remarkable strides toward the clinic. But the large size of most widely used Cas endonucleases including Cas9 and Cas12a restricts their efficient delivery by the adeno‐associated virus (AAV) for in vivo gene editing. Being exceptionally small, the recently engineered type V‐F CRISPR‐Cas12f1 systems can overcome the cargo packaging bottleneck and present as strong candidates for therapeutic applications. In this study, the pairwise editing efficiencies of different engineered Cas12f1/sgRNA scaffold combinations are systemically screened and optimized, and the CasMINI_v3.1/ge4.1 system is identified as being able to significantly boost the gene editing activity. Moreover, packaged into single AAV vectors and delivered via subretinal injection, CasMINI_v3.1/ge4.1 achieves remarkably high in vivo editing efficiencies, over 70% in transduced retinal cells. Further, the efficacy of this Cas12f1 system‐based gene therapy to treat retinitis pigmentosa in RhoP23H mice is demonstrated by the therapeutic benefits achieved including rescued visual function and structural preservation. And minimal bystander editing activity is detected. This work advances and expands the therapeutic potential of the miniature Cas12f1 system to support efficient and accurate in vivo gene therapy.

Nitrogen is a crucial element for the growth and development of plants, directly affecting crop growth and yield. To investigate the physiological and molecular mechanism of nitrogen-deficiency stress, we conducted an investigation into the effects of different nitrogen levels on the growth, photosynthetic characteristics, and gene transcription levels of banana seedlings. Compared with the control group with normal nitrogen levels (NN), the height of plants receiving Reduced-N (NR), Low-N (LN), and N-Free (NF) treatments was decreased by 0.45 cm, 2.5 cm, and 3.25 cm, respectively. Their dry weight was reduced by 1.63 g, 2.99 g, and 2.88 g, respectively. Conversely, the dry weight of the underground plant part in the LN and NF treatment groups exhibited an increase of 0.13 g and 0.16 g, respectively. Regarding photosynthetic characteristics, the Specialty Products Agricultural Division (SPAD) values of the NR, LN, and NF treatments showed reductions of 15.5%, 30.4%, and 35.9%, respectively, compared with those of the control treatments. The values of maximum photosynthetic efficiency (Fv/Fm), actual photosynthetic efficiency (Y(Ⅱ)), and relative electron transfer (ETR) of the banana seedlings decreased to different degrees after NR, LN, and NF treatment, and their values were positively correlated with N levels. Gene transcription analysis showed that N transport-related proteins, including NRT1.7, NRT2.3a, NRT2.3b, and NRT2.5, were significantly up-regulated to increase the nitrogen absorption capacity of plant roots. On the other hand, various transcription factors including GRAS, MYB, and WRKY were notably up-regulated, facilitating root growth and the expanding root absorption area, thereby enhancing nitrogen uptake. Furthermore, genes associated with endogenous hormone metabolic pathways such as gibberellin (GA), strigolactone (SL), and brassinosteroids (BR) were activated in banana plants subjected to low nitrogen stress, enhancing the plant’s ability to adapt to nitrogen-deficient conditions. These findings offer valuable insights into understanding the transcriptional regulatory mechanisms governing banana responses to low nitrogen stress and breeding new varieties with improved nutrient utilization.

Banana Fusarium wilt caused by Fusarium oxysporum f. sp. cubense tropical race4 (Foc TR4) is one of the most destructive soil-borne fungal diseases and currently threatens banana production around the world. Until now, there is lack of an effective method to control banana Fusarium wilt. Therefore, it is urgent to find an effective and eco-friendly strategy against the fungal disease. In this study, a strain of Trichoderma sp. N4-3 was isolated newly from the rhizosphere soil of banana plants. The isolate was identified as Trichoderma parareesei through analysis of TEF1 and RPB2 genes as well as morphological characterization. In vitro antagonistic assay demonstrated that strain N4-3 had a broad-spectrum antifungal activity against ten selected phytopathogenic fungi. Especially, it demonstrated a strong antifungal activity against Foc TR4. The results of the dual culture assay indicated that strain N4-3 could grow rapidly during the pre-growth period, occupy the growth space, and secrete a series of cell wall-degrading enzymes upon interaction with Foc TR4. These enzymes contributed to the mycelial and spore destruction of the pathogenic fungus by hyperparasitism. Additionally, the sequenced genome proved that strain N4-3 contained 21 genes encoding chitinase and 26 genes encoding β-1,3-glucanase. The electron microscopy results showed that theses cell wall-degrading enzymes disrupted the mycelial, spore, and cell ultrastructure of Foc TR4. A pot experiment revealed that addition of strain N4-3 significantly reduced the amount of Foc TR4 in the rhizosphere soil of bananas at 60 days post inoculation. The disease index was decreased by 45.00% and the fresh weight was increased by 63.74% in comparison to the control. Hence, Trichoderma parareesei N4-3 will be a promising biological control agents for the management of plant fungal diseases.

Plant height is an important and valuable agronomic trait associated with yield and resistance to abiotic and biotic stresses. Dwarfism has positive effects on plant development and field management, especially for tall monocotyledon banana (Musa spp.). However, several key genes and their regulation mechanism of controlling plant height during banana development are unclear. In the present study, the popular cultivar ‘Brazilian banana’ (‘BX’) and its dwarf mutant (‘RK’) were selected to identify plant height-related genes by comparing the phenotypic and transcriptomic data. Banana seedlings with 3–4 leaves were planted in the greenhouse and field. We found that the third and fourth weeks are the key period of plant height development of the selected cultivars. A total of 4563 and 10507 differentially expressed genes (DEGs) were identified in the third and fourth weeks, respectively. Twenty modules were produced by the weighted gene co-expression network analysis (WGCNA). Eight modules were positively correlated with the plant height, and twelve other modules were negatively correlated. Combining with the analysis of DEGs and WGCNA, 13 genes in the signaling pathway of gibberellic acid (GA) and 7 genes in the signaling pathway of indole acetic acid (IAA) were identified. Hub genes related to plant height development were obtained in light of the significantly different expression levels (|log2FC| ≥ 1) at the critical stages. Moreover, GA3 treatment significantly induced the transcription expressions of the selected candidate genes, suggesting that GA signaling could play a key role in plant height development of banana. It provides an important gene resource for the regulation mechanism of banana plant development and assisted breeding of ideal plant architecture.

Banana Fusarium wilt caused by Fusarium oxysporum f. sp. cubense tropical race 4 (Foc TR4) is one of the most destructive banana diseases in the world, which limits the development of the banana industry. Compared with traditional physical and chemical practices, biological control becomes a promising safe and efficient strategy. In this study, strain Y1-14 with strong antagonistic activity against Foc TR4 was isolated from the rhizosphere soil of a banana plantation, where no disease symptom was detected for more than ten years. The strain was identified as Streptomyces according to the morphological, physiological, and biochemical characteristics and the phylogenetic tree of 16S rRNA. Streptomyces sp. Y1-14 also showed a broad-spectrum antifungal activity against the selected 12 plant pathogenic fungi. Its extracts inhibited the growth and spore germination of Foc TR4 by destroying the integrity of the cell membrane and the ultrastructure of mycelia. Twenty-three compounds were identified by gas chromatography–mass spectrometry (GC-MS). The antifungal mechanism was investigated further by metabolomic analysis. Strain Y1-14 extracts significantly affect the carbohydrate metabolism pathway of Foc TR4 by disrupting energy metabolism.