Learning noisy tissue dynamics across time scales

2025-10-21

AI Summary

This study addresses the challenge of directly modeling and predicting tissue dynamics from highly noisy live multicellular imaging data—critical for understanding biological processes such as wound healing and morphogenesis. We propose a biomimetic Neural Stochastic Differential Equation (Neural SDE) framework that explicitly encodes tissue architecture via a graph neural network, jointly models cellular states and motility on dynamic graph edges, and enhances temporal modeling through normalized flows and WaveNet-based sequence modeling. The method significantly reduces reliance on labeled data and enables multi-timescale prediction. Validated on epithelial tissue data, it accurately recapitulates stochastic cell migration coupled with division cycles; it further generates complex developmental dynamics—including Drosophila wing development and ERK signaling waves—with high fidelity. Our approach establishes an interpretable, data-efficient paradigm for mechanistic biological analysis and clinical digital twin applications.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Bio-inspired Learning
• Computer Vision: Medical and Biological Imaging

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Tissue dynamics play a crucial role in biological processes ranging from wound healing to morphogenesis. However, these noisy multicellular dynamics are notoriously hard to predict. Here, we introduce a biomimetic machine learning framework capable of inferring noisy multicellular dynamics directly from experimental movies. This generative model combines graph neural networks, normalizing flows and WaveNet algorithms to represent tissues as neural stochastic differential equations where cells are edges of an evolving graph. This machine learning architecture reflects the architecture of the underlying biological tissues, substantially reducing the amount of data needed to train it compared to convolutional or fully-connected neural networks. Taking epithelial tissue experiments as a case study, we show that our model not only captures stochastic cell motion but also predicts the evolution of cell states in their division cycle. Finally, we demonstrate that our method can accurately generate the experimental dynamics of developmental systems, such as the fly wing, and cell signaling processes mediated by stochastic ERK waves, paving the way for its use as a digital twin in bioengineering and clinical contexts.

Problem

• Predicting noisy multicellular dynamics from experimental tissue movies
• Reducing data requirements for modeling stochastic cell behaviors
• Generating accurate digital replicas of biological developmental systems

Innovation

• Uses graph neural networks with normalizing flows and WaveNet
• Models tissues as neural stochastic differential equations
• Generates experimental dynamics as digital twin