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 adapted OpenPlant kit CRISPR/Cas9 tools to enable multiplex gRNA expression from a single transcript using tRNA sequences in the liverwort Marchantia polymorpha, markedly enhancing editing efficiency and scalability. They coupled this vector system with a simplified, optimized thallus transformation protocol, providing a rapid and versatile platform for generating CRISPR/Cas9 mutants and advancing functional genomics in this model species.