CellStream: Dynamical Optimal Transport Informed Embeddings for Reconstructing Cellular Trajectories from Snapshots Data

• URL: http://arxiv.org/abs/2511.13786v1
• Date: Sun, 16 Nov 2025 13:18:45 GMT
• Title: CellStream: Dynamical Optimal Transport Informed Embeddings for Reconstructing Cellular Trajectories from Snapshots Data
• Authors: Yue Ling, Peiqi Zhang, Zhenyi Zhang, Peijie Zhou,
• Abstract summary: We introduce CellStream, a novel deep learning framework that learns embedding and cellular dynamics from single-cell snapshot data.<n>Compared to existing methods, CellStream generates dynamics-informed embeddings that robustly capture temporal developmental processes.<n>Our experiments indicate significant improvements over state-of-the-art methods in representing cellular trajectories.
• Score: 4.4456485008754685
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Single-cell RNA sequencing (scRNA-seq), especially temporally resolved datasets, enables genome-wide profiling of gene expression dynamics at single-cell resolution across discrete time points. However, current technologies provide only sparse, static snapshots of cell states and are inherently influenced by technical noise, complicating the inference and representation of continuous transcriptional dynamics. Although embedding methods can reduce dimensionality and mitigate technical noise, the majority of existing approaches typically treat trajectory inference separately from embedding construction, often neglecting temporal structure. To address this challenge, here we introduce CellStream, a novel deep learning framework that jointly learns embedding and cellular dynamics from single-cell snapshot data by integrating an autoencoder with unbalanced dynamical optimal transport. Compared to existing methods, CellStream generates dynamics-informed embeddings that robustly capture temporal developmental processes while maintaining high consistency with the underlying data manifold. We demonstrate CellStream's effectiveness on both simulated datasets and real scRNA-seq data, including spatial transcriptomics. Our experiments indicate significant quantitative improvements over state-of-the-art methods in representing cellular trajectories with enhanced temporal coherence and reduced noise sensitivity. Overall, CellStream provides a new tool for learning and representing continuous streams from the noisy, static snapshots of single-cell gene expression.

Related papers

• Latent Causal Diffusions for Single-Cell Perturbation Modeling [83.47931153555321]
  We present a generative model that frames single-cell gene expression as a stationary diffusion process observed under measurement noise.<n> LCD outperforms established approaches in predicting the distributional shifts of unseen perturbation combinations in single-cell RNA-sequencing screens.<n>We develop an approach we call causal linearization via perturbation responses (CLIPR), which yields an approximation of the direct causal effects between all genes.
  arXiv  Detail & Related papers  (2026-01-20T16:15:38Z)
• Simulating Distribution Dynamics: Liquid Temporal Feature Evolution for Single-Domain Generalized Object Detection [58.25418970608328]
  Single-Domain Generalized Object Detection (Single-DGOD) aims to transfer a detector trained on one source domain to multiple unknown domains.<n>Existing methods for Single-DGOD typically rely on discrete data augmentation or static perturbation methods to expand data diversity.<n>We propose a new method, which simulates the progressive evolution of features from the source domain to simulated latent distributions.
  arXiv  Detail & Related papers  (2025-11-13T03:10:39Z)
• scAGC: Learning Adaptive Cell Graphs with Contrastive Guidance for Single-Cell Clustering [26.506077979458908]
  We propose scAGC, a single-cell clustering method that learns adaptive cell graphs with contrastive guidance.<n> scAGC consistently outperforms other state-of-the-art methods, yielding the best NMI and ARI scores on 9 and 7 datasets, respectively.
  arXiv  Detail & Related papers  (2025-08-07T10:55:52Z)
• Uncovering smooth structures in single-cell data with PCS-guided neighbor embeddings [14.708144124501635]
  Single-cell sequencing is revolutionizing biology by enabling detailed investigations of cell-state transitions.<n>It remains challenging to extract smooth, low-dimensional representations from noisy, high-dimensional single-cell data.<n>We introduce NESS, a principled and interpretable machine learning approach to improve NE representations.
  arXiv  Detail & Related papers  (2025-06-27T13:45:55Z)
• Inferring stochastic dynamics with growth from cross-sectional data [3.3748750222488657]
  We present a novel approach, emphunbalanced probability flow inference, that addresses the challenge for biological processes modelled as dynamics with growth.<n>By leveraging a Lagrangian formulation of the Fokker-Planck equation, our method accurately disentangles drift from intrinsic noise and growth.
  arXiv  Detail & Related papers  (2025-05-19T14:51:47Z)
• A scalable gene network model of regulatory dynamics in single cells [88.48246132084441]
  We introduce a Functional Learnable model of Cell dynamicS, FLeCS, that incorporates gene network structure into coupled differential equations to model gene regulatory functions.<n>Given (pseudo)time-series single-cell data, FLeCS accurately infers cell dynamics at scale.
  arXiv  Detail & Related papers  (2025-03-25T19:19:21Z)
• Integrating Dynamical Systems Modeling with Spatiotemporal scRNA-seq Data Analysis [2.4832894642382195]
  Single-cell RNA sequencing (scRNA-seq) has provided static snapshots of gene expression.<n>temporally resolved scRNA-seq, spatial transcriptomics (ST), and time-series transcriptomics (temporal-ST) have further revolutionized our ability to study dynamics of individual cells.
  arXiv  Detail & Related papers  (2025-03-14T12:25:27Z)
• DynaCLR: Contrastive Learning of Cellular Dynamics with Temporal Regularization [0.5385157903509136]
  DynaCLR is a self-supervised method for embedding cell and organelle Dynamics via Contrastive Learning of Representations of time-lapse images.<n>We integrate single-cell tracking and time-aware contrastive sampling to learn robust, temporally regularized representations of cell dynamics.
  arXiv  Detail & Related papers  (2024-10-15T05:01:25Z)
• Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen [76.02070962797794]
  This work introduces CellFlow for Generation (CFGen), a flow-based conditional generative model that preserves the inherent discreteness of single-cell data.<n>CFGen generates whole-genome multi-modal single-cell data reliably, improving the recovery of crucial biological data characteristics.
  arXiv  Detail & Related papers  (2024-07-16T14:05:03Z)
• Geodesic Sinkhorn for Fast and Accurate Optimal Transport on Manifolds [53.110934987571355]
  We propose Geodesic Sinkhorn -- based on a heat kernel on a manifold graph. We apply our method to the computation of barycenters of several distributions of high dimensional single cell data from patient samples undergoing chemotherapy.
  arXiv  Detail & Related papers  (2022-11-02T00:51:35Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics [74.43710101147849]
  We present TrajectoryNet, which controls the continuous paths taken between distributions to produce dynamic optimal transport. We show how this is particularly applicable for studying cellular dynamics in data from single-cell RNA sequencing (scRNA-seq) technologies.
  arXiv  Detail & Related papers  (2020-02-09T21:00:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.