As a crop with significant medicinal value and nutritional components, the market demand for bitter melon continues to grow. The diversity of bitter melon shapes has a direct impact on its market acceptance and consumer preferences, making precise identification of bitter melon germplasm resources crucial for breeding work. To address the limitations of time-consuming and less accurate traditional manual identification methods, there is a need to enhance the automation and intelligence of bitter melon phenotype detection. This study developed a bitter melon phenotype detection model named CSW-YOLO. By incorporating the ConvNeXt V2 module to replace the backbone network of YOLOv8, the model’s focus on critical target features is enhanced. Additionally, the SimAM attention mechanism was introduced to compute attention weights for neurons without increasing the parameter count, further enhancing the model’s recognition accuracy. Finally, WIoUv3 was introduced as the bounding box loss function to improve the model’s convergence speed and positioning capabilities. The model was trained and tested on a bitter melon image dataset, achieving a precision of 94.6%, a recall of 80.6%, a mAP50 of 96.7%, and an F1 score of 87.04%. These results represent improvements of 8.5%, 0.4%, 11.1%, and 4% in precision, recall, mAP50, and F1 score, respectively, over the original YOLOv8 model. Furthermore, the effectiveness of the improvements was validated through heatmap analysis and ablation experiments, demonstrating that the CSW-YOLO model can more accurately focus on target features, reduce false detection rates, and enhance generalization capabilities. Comparative tests with various mainstream deep learning models also proved the superior performance of CSW-YOLO in bitter melon phenotype detection tasks. This research provides an accurate and reliable method for bitter melon phenotype identification and also offers technical support for the visual detection technologies of other agricultural products.

Light quality optimization is a cost-effective method for increasing leafy vegetable quality in plant factories. Light-emitting diodes (LEDs) that enable the precise modulation of light quality were used in this study to examine the effects of red-blue (RB), red-blue-green (RBG), red-blue-purple (RBP), and red-blue-far-red (RBF) lights on the growth, antioxidant capacity, and nitrogen metabolism of Chinese cabbage leaves, while white light served as the control (CK). Results showed that the chlorophyll, carotenoid, vitamin C, amino acid, total flavonoid, and antioxidant levels of Chinese cabbage were all significantly increased under RBP combined light treatment. Meanwhile, RBG combined light treatment significantly increased the levels of amino acids but decreased the nitrite content of Chinese cabbage. In addition, RBF combined light treatment remarkably increased the amino acid levels but decreased the antioxidant capacity of Chinese cabbage. In conclusion, the addition of purple light to red-blue light was effective in improving the nutritional value and antioxidant capacity of Chinese cabbage. This light condition can be used as a model for a supplemental lighting strategy for leafy vegetables in plant factory production.

Bitter melon, an important medicinal and edible economic crop, is often threatened by diseases such as downy mildew, powdery mildew, viral diseases, anthracnose, and blight during its growth. Efficient and accurate disease detection is of significant importance for achieving sustainable disease management in bitter melon cultivation. To address the issues of weak generalization ability and high computational demands in existing deep learning models in complex field environments, this study proposes an improved lightweight YOLOv8-LSW model. The model incorporates the inverted bottleneck structure of LeYOLO-small to design the backbone network, utilizing depthwise separable convolutions and cross-stage feature reuse modules to achieve lightweight design, reducing the number of parameters while enhancing multi-scale feature extraction capabilities. It also integrates the ShuffleAttention mechanism, strengthening the feature response in lesion areas through channel shuffling and spatial attention dual pathways. Finally, WIoUv3 replaces the original loss function, optimizing lesion boundary regression based on a dynamic focusing mechanism. The results show that YOLOv8-LSW achieves a precision of 95.3%, recall of 94.3%, mAP50 of 98.1%, mAP50-95h of 95.6%, and F1-score of 94.80%, which represent improvements of 2.2%, 2.7%, 1.2%, 2.2%, and 2.46%, respectively, compared to the original YOLOv8n. The effectiveness of the improvements was verified through heatmap analysis and ablation experiments. The number of parameters and GFLOPS were reduced by 20.58% and 20.29%, respectively, with an FPS of 341.58. Comparison tests with various mainstream deep learning models also demonstrated that YOLO-LSW performs well in the bitter melon disease detection task. This research provides a technical solution with both lightweight design and strong generalization ability for real-time detection of bitter melon diseases in complex environments, which holds significant application value in promoting precision disease control in smart agriculture.

Infection by Sclerotium rolfsii will cause serious disease and lead to significant economic losses in chili pepper. In this study, the response of pepper during S. rolfsii infection was explored by electron microscopy, physiological determination and integrated proteome and metabolome analyses. Our results showed that the stomata of pepper stems were important portals for S. rolfsii infection. The plant cell morphology was significantly changed at the time of the fungal hyphae just contacting (T1) or surrounding (T2) the pepper. The chlorophyll, carotenoid, and MDA contents and the activities of POD, SOD, and CAT were markedly upregulated at T1 and T2. Approximately 4129 proteins and 823 metabolites were clearly identified in proteome and metabolome analyses, respectively. A change in 396 proteins and 54 metabolites in pepper stem tissues was observed at T1 compared with 438 proteins and 53 metabolites at T2. The proteins and metabolites related to photosynthesis and antioxidant systems in chloroplasts and mitochondria were disproportionally affected by S. rolfsii infection, impacting carbohydrate and amino acid metabolism. This study provided new insights into the response mechanism in pepper stems during S. rolfsii infection, which can guide future work on fungal disease resistance breeding in pepper.

Capsicum (pepper) is an economically vital genus in the Solanaceae family, with most species possessing about 3 Gb genomes. However, the recently sequenced Capsicum rhomboideum (~1.7 Gb) represents the first reported case of an extremely compact genome in Capsicum, providing a unique and ideal model for studying genome size evolution. To elucidate the mechanisms driving this variation, we performed comparative genomic analyses between the compact Capsicum rhomboideum and the reference Capsicum annuum cv. CM334 (~2.9 Gb). Although their genome size differences initially suggested whole-genome duplication (WGD) as a potential driver, both species shared two ancient WGD events with identical timing, predating their divergence and thus ruling out WGD as a direct contributor to their size difference. Instead, transposable elements (TEs), particularly long terminal repeat retrotransposons (LTR-RTs), emerged as the dominant force shaping genome size variation. Genome size strongly correlated with LTR-RT abundance, and multiple LTR-RT burst events aligned with major phases of genome expansion. Notably, the integrity and transcriptional activity of LTR-RTs decline over evolutionary time; older insertions exhibit greater structural degradation and reduced activity, reflecting their dynamic nature. This study systematically delineated the evolutionary trajectory of LTR-RTs—from insertion and proliferation to decay–uncovering their pivotal role in driving Capsicum genome size evolution. Our findings advance the understanding of plant genome dynamics and provide a framework for studying genome size variation across diverse plant lineages.