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.
CLPC2 plays specific roles in CLP complex-mediated regulation of growth, photosynthesis, embryogenesis and response to growth-promoting microbial compounds
Authors: Leal-Lopez, J., Bahaji, A., De Diego, N., Tarkowski, P., Baroja-Fernandez, E., Munoz, F. J., Almagro, G., Perez, C. E., Bastidas-Parrado, L. A., Loperfido, D., Caporalli, E., Ezquer, I., Lopez-Serrano, L., Ferez-Gomez, A., Coca-Ruiz, V., Pulido, P., Morcillo, R. J. L., Pozueta-Romero, J.
The study demonstrates that the plastid chaperone CLPC2, but not its paralogue CLPC1, is essential for Arabidopsis responsiveness to microbial volatile compounds and for normal seed and seedling development. Loss of CLPC2 alters the chloroplast proteome, affecting proteins linked to growth, photosynthesis, and embryogenesis, while overexpression of CLPC2 mimics CLPC1 deficiency, highlighting distinct functional roles within the CLP protease complex.