The study introduces a hybrid modeling framework that integrates a logistic ordinary differential equation with a Long Short-Term Memory neural network to form a Physics-Informed Neural Network (PINN) for predicting wheat plant height. Using only time and temperature as inputs, the PINN outperformed other longitudinal growth models, achieving the lowest average RMSE and reduced variability across multiple random initializations. The results suggest that embedding biological growth constraints within data‑driven models can substantially improve prediction accuracy for plant traits.

The authors compiled and standardized published data on Rubisco dark inhibition for 157 flowering plant species, categorizing them into four inhibition levels and analyzing phylogenetic trends. Their meta‑analysis reveals a complex, uneven distribution of inhibition across taxa, suggesting underlying chloroplast microenvironment drivers and providing a new resource for future photosynthesis improvement efforts.

The study sequenced 226 finger millet‑infecting Magnaporthe oryzae isolates from East Africa, revealing two genetically distinct populations correlated with climate and differing in effector repertoires and virulence. It shows that homologous recombination between transposable elements drives effector loss, and transcript profiling identifies a subset of effectors up‑regulated in incompatible interactions, highlighting candidates for resistance breeding.

Six new Viola species and two reinstated species from China were identified using field surveys, detailed morphological comparison, and phylogenetic analysis of ITS and GPI gene sequences, placing them in section Plagiostigma subsect. Diffusae. The GPI data offered higher resolution, indicating complex relationships possibly due to ancient hybridization or incomplete lineage sorting, thereby clarifying species boundaries and evolutionary patterns in Chinese Viola.

The study examined infection phenotypes and cross‑kingdom transcriptomes of the root‑knot nematode Meloidogyne incognita across nine host interactions representing six orders of flowering plants 25 days post‑infection. While host phylogeny did not predict parasitic outcomes, the nematode displayed three distinct transcriptional programmes with differential effector deployment, suggesting that host specificity arises from variable effector expression rather than a conserved gall transcriptome.

Researchers isolated a fungal pathogen from a naturally infected Rumex crispus leaf in Japan and identified it as Teratoramularia rumicicola using morphological traits and phylogenetic analysis of ITS and LSU rDNA sequences. Host range tests showed the isolate (TR4) caused disease and reduced biomass in three Rumex species but was harmless to five tested forage crops, indicating its potential as a selective bioherbicide for pasture systems.

Eighty-eight herbarium specimens of the Galapagos mistletoe Phoradendron berteroanum were measured for eight vegetative and floral traits, and univariate and multivariate analyses were conducted across altitude, island, host, and vegetation cover. Leaf size and internode length peaked at mid‑elevations while floral segment number declined with altitude, and flower number varied with host species, but no distinct island‑specific morphotypes were detected, indicating a single species responding to local environmental conditions.