Research map / Probabilistic and scientific modeling / Dynamical systems
CellStream: Dynamical Optimal Transport Informed Embeddings for Reconstructing Cellular Trajectories from Snapshots Data
Yue Ling, Peiqi Zhang, Zhenyi Zhang, Peijie Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| jointly learn embedding and dynamics with unbalanced OT (CellStream vs best baseline VC) | embedding for trajectory inference · EMT | velocity consistency: 0.96 -> 0.97 | Improved |
| CellStream vs TIGON+t-SNE on temporal consistency | embedding for trajectory inference · EMT | temporal consistency: 0.94 -> 0.99 | Mixed |
| CellStream vs MIOFlow on iPSC velocity consistency | embedding for trajectory inference · iPSC | velocity consistency: 0.98 -> 0.97 | No clear effect |
| CellStream vs TIGON+PCA on iPSC | embedding for trajectory inference · iPSC | velocity consistency: 0.32 -> 0.97 | Improved |
| CellStream vs MIOFlow on MOSTA | embedding for trajectory inference · MOSTA | velocity consistency: 0.42 -> 0.98 | Improved |
| CellStream vs diffusion-map embedding on MOSTA | embedding for trajectory inference · MOSTA | velocity consistency / temporal consistency: VC 0.98 vs 0.98; TC 0.99 vs 0.99 | No clear effect |
| CellStream under increasing simulated noise | embedding for trajectory inference · simulated bifurcation data | velocity accuracy / temporal consistency | Improved |
Closest papers by meaning
- Unsupervised Gene-Cell Collective Representation Learning with Optimal Transport (AAAI 2024 · similarity 0.87)
- TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics (NeurIPS 2026 · similarity 0.87)
- Joint Velocity-Growth Flow Matching for Single-Cell Dynamics Modeling (NeurIPS 2025 · similarity 0.86)
- GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics (NeurIPS 2024 · similarity 0.85)
- Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport (ICLR 2025 · similarity 0.85)
- sciLaMA: A Single-Cell Representation Learning Framework to Leverage Prior Knowledge from Large Language Models (ICML 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
