StressNET: an adaptable deep-learning model for mechanical stress inference in tissues
- 1University of Nottingham School of Biosciences
Abstract
Mechanical interactions between cells are fundamental to tissue morphogenesis during development and regeneration. Computational methods that infer intercellular stresses from microscopy images of cell shapes offer a non-invasive alternative to experimental perturbation techniques, yet all existing approaches rely on explicit physical models. Here we present StressNET, a Graph Neural Network (GNN) that infers intercellular mechanical stresses directly from tissue geometry, without assuming any underlying physical model. We generated synthetic datasets to train and benchmark StressNET, and demonstrate that its predictions achieve state-of-the-art correlation with experimental stress proxies in zebrafish neuromasts and Xenopus embryos. Analysis of the network's latent space reveals that StressNET learns global organizational principles of mechanical stress distribution, beyond local cell-cell interactions. StressNET is open-source and provides pre-trained models that can be fine-tuned on in vivo data, making it a broadly adaptable tool for studying tissue mechanics across biological systems.
Related
- Extracellular matrix composition is associated with tissue-specific decellularization susceptibility and mechanical remodeling across human urogenital tissues
- Cell Geometry and Junction Arrangement Define the Mechanical Robustness of Plant Tissues
- When Does Depth Matter For In-Context Learning? Adaptive Inference in Deep Transformers
- Mitochondrial dynamics resolve physical-social tensions and challenges through adaptable multi-objective optimisation
- Deep learning for mass extinction detection on fossilized phylogenies: power, limitations and lessons for simulation-based birth–death inference
BibTeX
@misc{chara2026stressnet,
title = {{StressNET: an adaptable deep-learning model for mechanical stress inference in tissues}},
author = {O. Chara and N. Aldecoa Rodrigo and A. Borges and J. R. Miranda-Rodriguez and G. Ventura and J. Sedzinski and H. Lopez-Schier},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.14.751456},
url = {https://www.biorxiv.org/content/10.64898/2026.09.14.751456v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - StressNET: an adaptable deep-learning model for mechanical stress inference in tissues
AU - O. Chara
AU - N. Aldecoa Rodrigo
AU - A. Borges
AU - J. R. Miranda-Rodriguez
AU - G. Ventura
AU - J. Sedzinski
AU - H. Lopez-Schier
PY - 2026
DA - 2026/09/14
PB - bioRxiv
DO - 10.64898/2026.09.14.751456
UR - https://www.biorxiv.org/content/10.64898/2026.09.14.751456v1
AB - Mechanical interactions between cells are fundamental to tissue morphogenesis during development and regeneration. Computational methods that infer intercellular stresses from microscopy images of cell shapes offer a non-invasive alternative to experimental perturbation techniques, yet all existing approaches rely on explicit physical models. Here we present StressNET, a Graph Neural Network (GNN) that infers intercellular mechanical stresses directly from tissue geometry, without assuming any underlying physical model. We generated synthetic datasets to train and benchmark StressNET, and demonstrate that its predictions achieve state-of-the-art correlation with experimental stress proxies in zebrafish neuromasts and Xenopus embryos. Analysis of the network's latent space reveals that StressNET learns global organizational principles of mechanical stress distribution, beyond local cell-cell interactions. StressNET is open-source and provides pre-trained models that can be fine-tuned on in vivo data, making it a broadly adaptable tool for studying tissue mechanics across biological systems.
ER -