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 generated a high‑resolution 1.45‑billion‑contact Micro‑C map for cultivated tomato (Solanum lycopersicum), identifying ~4,600 long‑range chromatin loops that fall into promoter‑centered and Polycomb/heterochromatin‑associated classes. Comparative Micro‑C in wild tomatoes showed conserved loop anchors despite sequence turnover, and integration with transcriptomics revealed that promoter‑anchored loops can either activate or repress gene expression depending on the chromatin state of distal anchors.