Modeling Cell Dynamics and Interactions with Unbalanced Mean Field Schr\"odinger Bridge
Zhenyi Zhang, Zihan Wang, Yuhao Sun, Tiejun Li, Peijie Zhou

TL;DR
This paper introduces CytoBridge, a deep learning framework based on the Unbalanced Mean-Field Schr"odinger Bridge, to model cellular dynamics and interactions from snapshot data, improving accuracy over existing methods.
Contribution
It formulates the UMFSB framework for unbalanced stochastic cell interactions and develops CytoBridge, a neural network-based algorithm to learn these dynamics directly from data.
Findings
Accurately models cell transitions, proliferation, and interactions.
Eliminates false cell state transitions in data.
Reconstructs developmental landscapes more precisely.
Abstract
Modeling the dynamics from sparsely time-resolved snapshot data is crucial for understanding complex cellular processes and behavior. Existing methods leverage optimal transport, Schr\"odinger bridge theory, or their variants to simultaneously infer stochastic, unbalanced dynamics from snapshot data. However, these approaches remain limited in their ability to account for cell-cell interactions. This integration is essential in real-world scenarios since intercellular communications are fundamental life processes and can influence cell state-transition dynamics. To address this challenge, we formulate the Unbalanced Mean-Field Schr\"odinger Bridge (UMFSB) framework to model unbalanced stochastic interaction dynamics from snapshot data. Inspired by this framework, we further propose CytoBridge, a deep learning algorithm designed to approximate the UMFSB problem. By explicitly modeling…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsSpectroscopy and Quantum Chemical Studies · stochastic dynamics and bifurcation · Terahertz technology and applications
