Leaf stalk-stem angle is an important agronomic trait influencing melon architecture, photosynthetic efficiency, and crop yield. However, the mechanisms governing leaf stalk-stem angle, particularly in melon, are not well understood. In this study, we explored the comparative transcriptome in the expanded architecture line Y164 and the compact plant architecture line Z151 at 30 days after pollination. Phytohormones were measured at the leaf stalk-angle site at the same time in these two lines using liquid chromatography (LC) tandem mass spectrometry (MS) (LC-MS/MS). The phytohormones and transcriptomes were jointly analyzed. Differential hormone profiling revealed that the levels of 1-aminocyclopropane-1-carboxylate (ACC) and 12-oxophytodienoic acid (OPDA) in the large-angled line Y164 were significantly higher than those in the small-angled line Z151. These differences were quantified as 2.1- and 2.8-fold increases, respectively. Conversely, the content of isopentenyl adenosine (IPA) was significantly elevated in Z151, with a 3.8-fold higher concentration relative to Y164. Transcriptome analysis identified a total of 1709 differently expressed genes (DEGs), with a predominant enrichment in the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways related to photosynthesis and plant hormone signal transduction. Similarly, photosynthesis and the hormone metabolic process were predominantly enriched in the biological process of Gene Ontology (GO) terms. Further integration of transcriptome and hormone analyses substantiated the close relationship between melon leaf stalk-stem angle and phytohormones, especially ACC, OPDA and IPA. Selected DEGs from phytohormone signal transduction were validated. Detailed analysis of DEGs highlighted the potential role of genes such as GH3s (LOC103490488, LOC103490483), SUARs (LOC107991561, LOC103497281 and LOC103489067), ARFs (LOC103503893, LOC103493078) and five genes in abscisic acid pathway. In summary, our findings strongly suggest a direct correlation between phytohormones and the leaf stalk-stem angles in melon.

To elucidate the genetic factors contributing to melon resistance against Phelipanche aegyptiaca and comprehend the role of differentially resistant materials in responding to changes in P. aegyptiaca parasitisation, we investigated the P. aeg...

Stomatal trait analysis is essential for optimizing crop photosynthesis and transpiration, yet deep learning studies have focused mainly on monocotyledons, leaving dicotyledonous crops such as melon (Cucumis melo L.) understudied. To bridge this gap, we established a dedicated melon stomatal dataset comprising 5,708 training images, 1,631 validation images, and 815 test images. On this basis, we developed an improved Mask R-CNN framework using Vision Transformer (ViT) as the backbone. Specifically, standard Multi-Head Attention (MHA) was replaced with Dynamically Composable Multi-Head Attention (DCMHA), which enhances information exchange across attention heads and alleviates the low-rank limitation of conventional attention. In addition, a modified effective Squeeze-and-Excitation (eSE) module was incorporated into the Feature Pyramid Network (FPN) to strengthen channel dependency modeling and multi-scale feature representation. On the melon dataset, the proposed model achieved a mean average precision (mAP) of 72.40 ± 0.09%, with AP50 and AP75 of 91.93 ± 0.14% and 84.59 ± 0.19%, respectively. Repeated-run statistical analyses showed that eSE significantly and consistently improved the main detection metrics across backbones, whereas DCMHA provided a more moderate gain within the ViT-based setting, with clearer support for AP50 than for mAP or AP75 under the baseline FPN setting. Overall, the combined configuration remained among the top-performing models for stomatal instance segmentation. Ellipse fitting further enabled automated quantification of stomatal length, width, count, area, and circumference, showing strong agreement with manual measurements (Pearson r = 0.978). The model also showed preliminary transferability to cucumber, watermelon, pumpkin, and loofah, with an average species-specific R² of 0.86, although each species was evaluated on a limited sample set.