MIOFlow 2.0: A unified framework for inferring cellular stochastic dynamics from single cell and spatial transcriptomics data

2026-03-23

AI Summary

This study addresses the challenge of reconstructing continuous cell fate trajectories governed by stochasticity, proliferation dynamics, and microenvironmental cues from discrete single-cell and spatial transcriptomic snapshots. To this end, we propose a unified framework that integrates a PHATE-preserving autoencoder latent space, neural stochastic differential equations, a proliferation model initialized via non-equilibrium optimal transport, and a joint embedding strategy incorporating spatial signals. This approach uniquely enables the simultaneous modeling of stochastic branching events, non-conservative cell proliferation, and spatial microenvironmental influences along developmental trajectories. Experiments on synthetic data, embryoid body differentiation, and axolotl brain regeneration demonstrate that our method substantially improves trajectory inference accuracy and uncovers key microenvironmental signals driving cell fate decisions.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Reasoning under Uncertainty: Stochastic Optimization
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in 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: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Understanding cellular trajectories via time-resolved single-cell transcriptomics is vital for studying development, regeneration, and disease. A key challenge is inferring continuous trajectories from discrete snapshots. Biological complexity stems from stochastic cell fate decisions, temporal proliferation changes, and spatial environmental influences. Current methods often use deterministic interpolations treating cells in isolation, failing to capture the probabilistic branching, population shifts, and niche-dependent signaling driving real biological processes. We introduce Manifold Interpolating Optimal-Transport Flow (MIOFlow) 2.0. This framework learns biologically informed cellular trajectories by integrating manifold learning, optimal transport, and neural differential equations. It models three core processes: (1) stochasticity and branching via Neural Stochastic Differential Equations; (2) non-conservative population changes using a learned growth-rate model initialized with unbalanced optimal transport; and (3) environmental influence through a joint latent space unifying gene expression with spatial features like local cell type composition and signaling. By operating in a PHATE-distance matching autoencoder latent space, MIOFlow 2.0 ensures trajectories respect the data's intrinsic geometry. Empirical comparisons show expressive trajectory learning via neural differential equations outperforms existing generative models, including simulation-free flow matching. Validated on synthetic datasets, embryoid body differentiation, and spatially resolved axolotl brain regeneration, MIOFlow 2.0 improves trajectory accuracy and reveals hidden drivers of cellular transitions, like specific signaling niches. MIOFlow 2.0 thus bridges single-cell and spatial transcriptomics to uncover tissue-scale trajectories.

Problem

• cellular trajectories
• stochastic dynamics
• single-cell transcriptomics
• spatial transcriptomics
• cell fate decisions

Innovation

• Neural Stochastic Differential Equations
• Optimal Transport
• Manifold Learning
• Spatial Transcriptomics
• Cellular Trajectory Inference