The study investigates the gene regulatory network (GRN) controlling flowering time in the allotetraploid crop Brassica napus by comparing its transcriptome to that of Arabidopsis thaliana. While most orthologous gene pairs show conserved expression dynamics, several flowering‑time genes display regulatory divergence, especially under cold conditions, indicating subfunctionalisation among paralogues. Despite these differences, the overall GRN topology remains similar to Arabidopsis, likely due to retention of multiple paralogues.

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 study examined how soil phosphorus and nitrogen availability influence wheat root-associated arbuscular mycorrhizal fungal (AMF) communities and the expression of mycorrhizal nutrient transporters. Field sampling across two years combined with controlled pot experiments showed that P and N jointly affect AMF colonisation, community composition (with Funneliformis dominance under high P), and regulation of phosphate, ammonium, and nitrate transporters. Integrating metabarcoding and RT‑qPCR provides a framework to assess AMF contributions to crop nutrition.