STAGED: A Multi-Agent Neural Network for Learning Cellular Interaction Dynamics

2025-07-15

AI Summary

Existing spatial transcriptomics methods for modeling cell–cell interactions rely heavily on prior biological knowledge, limiting their adaptability and generalizability. Method: We propose STAGED, a data-driven framework that couples graph ordinary differential equations (Graph ODEs) with multi-agent neural networks and introduces cell-type-specific attention to learn dynamic interaction strengths among heterogeneous cells within spatial neighborhoods in an end-to-end manner. A shared-weight graph neural network enables continuous trajectory modeling, capturing the spatial coupling between gene regulatory networks and intercellular communication. Contribution/Results: Evaluated on both synthetic and real spatial transcriptomic datasets, STAGED significantly improves accuracy in modeling cellular state transitions. It provides an interpretable, generalizable computational tool for deciphering coordinated cellular behaviors within tissue microenvironments, advancing mechanistic understanding of spatially resolved cell dynamics.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Multiagent Systems: Modeling other Agents

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

The advent of single-cell technology has significantly improved our understanding of cellular states and subpopulations in various tissues under normal and diseased conditions by employing data-driven approaches such as clustering and trajectory inference. However, these methods consider cells as independent data points of population distributions. With spatial transcriptomics, we can represent cellular organization, along with dynamic cell-cell interactions that lead to changes in cell state. Still, key computational advances are necessary to enable the data-driven learning of such complex interactive cellular dynamics. While agent-based modeling (ABM) provides a powerful framework, traditional approaches rely on handcrafted rules derived from domain knowledge rather than data-driven approaches. To address this, we introduce Spatio Temporal Agent-Based Graph Evolution Dynamics(STAGED) integrating ABM with deep learning to model intercellular communication, and its effect on the intracellular gene regulatory network. Using graph ODE networks (GDEs) with shared weights per cell type, our approach represents genes as vertices and interactions as directed edges, dynamically learning their strengths through a designed attention mechanism. Trained to match continuous trajectories of simulated as well as inferred trajectories from spatial transcriptomics data, the model captures both intercellular and intracellular interactions, enabling a more adaptive and accurate representation of cellular dynamics.

Problem

• Modeling dynamic cell-cell interactions from spatial transcriptomics data
• Integrating agent-based modeling with deep learning for cellular dynamics
• Learning intercellular and intracellular interactions via graph ODE networks

Innovation

• Integrates agent-based modeling with deep learning
• Uses graph ODE networks with shared weights
• Dynamically learns interaction strengths via attention