The authors used a bottom‑up thermodynamic modelling framework to investigate how plants decode calcium signals, starting from Ca2+ binding to EF‑hand proteins and extending to higher‑order decoding modules. They identified six universal Ca2+-decoding modules that can explain variations in calcium sensitivity among kinases and provide a theoretical basis for interpreting calcium signal amplitude and frequency in plant cells.

The authors developed a high‑throughput, semi‑automated image analysis pipeline that couples a Blackbird CNC microscopy robot with YOLO11‑based computer‑vision models to identify life stages of the two‑spotted spider mite across multiple host plants. The three‑class detection model achieved >87% precision and recall, enabling reliable fecundity measurements for resistance breeding, though mortality assessment was less accurate at high mite densities or on unseen host backgrounds.

The study reveals that leaf wounding in Arabidopsis triggers localized cooling and activation of cold-responsive genes, with the subsequent loss of cooling marking wound healing. It identifies CBF transcription factors as mediators of this cooling signal and introduces a computer‑vision and deep‑learning workflow to quantitatively monitor healing dynamics.

The study examined how white lupin (Lupinus albus) cotyledons mobilize nitrogen and minerals during early seedling growth under nitrogen‑deficient conditions, revealing that 60 % of stored proteins degrade within eight days and are redirected to support development. Proteomic analyses showed dynamic shifts in nutrient transport, amino acid metabolism, and stress responses, and premature cotyledon removal markedly impaired growth, highlighting the cotyledon's essential role in nutrient supply and transient photosynthetic activity.

The Global Wheat Dataset Consortium released a comprehensive semantic segmentation dataset (GWFSS) of wheat organs across developmental stages, comprising 1,096 fully annotated images and 52,078 unannotated images from 11 institutions. Models based on DeepLabV3Plus and Segformer were trained, with Segformer achieving ≈90% mIoU for leaves and spikes but lower precision (54%) for stems, while also enabling weed exclusion and discrimination of necrotic, senescent, and residue tissues.