The study assessed how well common deep learning models (ResNet, EfficientNet, Inception, MobileNet) generalize across different tomato pest and disease image datasets. While models performed well on the dataset they were trained on, they suffered substantial accuracy drops when applied to other datasets, indicating that architectural changes alone cannot overcome dataset variability. The results highlight the necessity for more diverse, representative training data to improve real-world deployment of PPD diagnostic tools.

The study demonstrates that hyperspectral imaging can non‑destructively differentiate active nitrogen‑fixing root nodules from non‑fixing nodules and root tissue based on distinct spectral signatures. By integrating deep‑learning models, the authors created an automated nodule counting pipeline that works across multiple legume species and growth conditions, eliminating labor‑intensive manual counting and reliably detecting nodules within dense root systems.

The study identifies two maize genes, Discordia3a and Discordia3b, that encode the microtubule‑severing protein KATANIN. Loss‑of‑function allele combinations reduce microtubule severing, impair cell elongation, delay mitotic entry, and disrupt preprophase band and nuclear positioning, leading to dwarfed, misshapen plants.

The study identified lineage-specific long non‑coding RNAs (lncRNAs) from the aphid‑specific Ya gene family in Rhopalosiphum maidis and R. padi, demonstrating that these Ya lncRNAs are secreted into maize, remain stable, and move systemically. RNA interference of Ya genes reduced aphid fecundity, while ectopic expression of Ya lncRNAs in maize enhanced aphid colonization, indicating that Ya lncRNAs act as cross‑kingdom effectors that influence aphid virulence.

The study used a computer‑vision phenotyping pipeline (EarVision.v2) based on Faster R-CNN to map Ds‑GFP mutant kernels on maize ears and a statistical framework (EarScape) to assess spatial patterns of allele transmission from the apex to the base. They found that alleles causing pollen‑specific transmission defects often show significant spatial biases, whereas Mendelian alleles do not, indicating that reduced pollen fitness can shape the spatial distribution of progeny genotypes in Zea mays.

The study introduces the Botanical Spectrum Analyzer (BSA), a GUI that incorporates a modified U‑Net deep neural network for accurate segmentation of plant images from RGB and hyperspectral (VNIR and SWIR) data. BSA was tested on wheat, barley, and Arabidopsis datasets, achieving >99% accuracy and F1‑scores above 98%, and markedly outperformed commercial tools on root segmentation tasks.

The study investigates how the pleiotropic maize genes GRASSY TILLERS1 (GT1) and RAMOSA3 (RA3) are differentially regulated to suppress axillary meristems and floral organs, using a newly developed high-throughput quantitative phenotyping method for grass flowers. Distinct environmental mechanisms were found to control each suppression process, and upstream regulatory pathways of GT1 and RA3 have diverged, illustrating how ancient developmental genes can be redeployed to increase genetic pleiotropy during evolution.

The study reveals that the maize catalytic trehalose-6-phosphate phosphatase RA3 interacts with the non‑catalytic TPS ZmTPS1, and together with the catalytic TPS ZmTPS14 they form a protein complex that enhances enzymatic activity. Genetic analyses show that mutations in ZmTPS1 and its paralog ZmTPS12 exacerbate ra3 branching phenotypes, while loss of the catalytic TPSs ZmTPS11 and ZmTPS14 causes embryonic lethality, indicating essential and regulatory roles for both catalytic and non‑catalytic TPS/TPP proteins in plant development.

The study shows that the membrane lipids PI4P, PI(4,5)P2, and phosphatidylserine have distinct spatial and temporal dynamics during lateral root primordium formation in Arabidopsis thaliana, with PI4P acting as a stable basal lipid, PI(4,5)P2 serving as a negative regulator of initiation, and phosphatidylserine increasing after founder cell activation. Using live-cell biosensors, genetic mutants, and an inducible PI(4,5)P2 depletion system, the authors demonstrate that reducing PI(4,5)P2 enhances lateral root initiation and development.

Using CRISPR‑Cas9‑generated Zmcry mutants, the study shows that maize cryptochromes redundantly mediate blue‑light signaling, suppress mesocotyl elongation, and enhance UV‑B stress tolerance by upregulating genes for phenylpropanoid, flavonoid, and fatty‑acid pathways. Blue light also promotes epidermal wax accumulation, and ZmCRY1 directly interacts with GLOSSY2 in a light‑dependent manner to drive C32 aldehyde synthesis, linking cryptochrome activity to wax biosynthesis and UV‑B resistance.