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

Joao F. Rocha, Ke Xu, Xingzhi Sun, Ananya Krishna, Dhananjay Bhaskar, Blanche Mongeon, Morgan Craig, Mark Gerstein, Smita Krishnaswamy
Proceedings of the 20th Machine Learning in Computational Biology meeting, PMLR 311:336-346, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v311-rocha25a, title = {STAGED: A Multi-Agent Neural Network for Learning Cellular Interaction Dynamics}, author = {Rocha, Joao F. and Xu, Ke and Sun, Xingzhi and Krishna, Ananya and Bhaskar, Dhananjay and Mongeon, Blanche and Craig, Morgan and Gerstein, Mark and Krishnaswamy, Smita}, booktitle = {Proceedings of the 20th Machine Learning in Computational Biology meeting}, pages = {336--346}, year = {2025}, editor = {Knowles, David A and Koo, Peter K}, volume = {311}, series = {Proceedings of Machine Learning Research}, month = {10--11 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v311/main/assets/rocha25a/rocha25a.pdf}, url = {https://proceedings.mlr.press/v311/rocha25a.html}, 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.} }
Endnote
%0 Conference Paper %T STAGED: A Multi-Agent Neural Network for Learning Cellular Interaction Dynamics %A Joao F. Rocha %A Ke Xu %A Xingzhi Sun %A Ananya Krishna %A Dhananjay Bhaskar %A Blanche Mongeon %A Morgan Craig %A Mark Gerstein %A Smita Krishnaswamy %B Proceedings of the 20th Machine Learning in Computational Biology meeting %C Proceedings of Machine Learning Research %D 2025 %E David A Knowles %E Peter K Koo %F pmlr-v311-rocha25a %I PMLR %P 336--346 %U https://proceedings.mlr.press/v311/rocha25a.html %V 311 %X 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.
APA
Rocha, J.F., Xu, K., Sun, X., Krishna, A., Bhaskar, D., Mongeon, B., Craig, M., Gerstein, M. & Krishnaswamy, S.. (2025). STAGED: A Multi-Agent Neural Network for Learning Cellular Interaction Dynamics. Proceedings of the 20th Machine Learning in Computational Biology meeting, in Proceedings of Machine Learning Research 311:336-346 Available from https://proceedings.mlr.press/v311/rocha25a.html.

Related Material