The study identifies the AP2/ERF transcription factor GEMMIFER (MpGMFR) as essential for asexual reproduction in the liverwort Marchantia polymorpha, showing that loss of MpGMFR via genome editing or amiRNA abolishes gemma and gemma cup formation, while dexamethasone‑induced activation triggers their development. Transient strong activation of MpGMFR initiates gemma initial cells at the meristem, which mature into functional gemmae, indicating MpGMFR is both necessary and sufficient for meristem‑derived asexual propagule formation.

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.