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.

The study generated a high-quality genome assembly for Victoria cruziana and used comparative transcriptomics to identify anthocyanin biosynthesis genes and their transcriptional regulators that are differentially expressed between white and light pinkish flower stages. Differential expression of structural genes (VcrF3H, VcrF35H, VcrDFR, VcrANS, VcrarGST) and transcription factors (VcrMYB123, VcrMYB-SG6_a, VcrMYB-SG6_b, VcrTT8, VcrTTG1) correlates with the observed flower color change.

The study demonstrates that RNA extracted from herbarium specimens can be used to generate high‑quality transcriptomes, comparable to those from fresh or silica‑dried samples. By assembling and comparing transcriptomes across specimen types, the authors validated a plant immune receptor synthesized from a 1956 collection, proving archival RNA’s utility for functional genomics. These findings challenge the prevailing view that herbarium RNA is unsuitable for transcriptomic analyses.