View in EDS

stVCR: spatiotemporal dynamics of single cells.

Saved in:
Bibliographic Details
Title: stVCR: spatiotemporal dynamics of single cells.
Authors: Peng Q; LMAM and School of Mathematical Sciences, Peking University, Beijing, China., Zhou P; Center for Machine Learning Research, Peking University, Beijing, China. pjzhou@pku.edu.cn.; Center for Quantitative Biology, Peking University, Beijing, China. pjzhou@pku.edu.cn.; National Engineering Laboratory for Big Data Analysis and Applications, Beijing, China. pjzhou@pku.edu.cn.; AI for Science Institute, Beijing, China. pjzhou@pku.edu.cn., Li T; LMAM and School of Mathematical Sciences, Peking University, Beijing, China. tieli@pku.edu.cn.; Center for Machine Learning Research, Peking University, Beijing, China. tieli@pku.edu.cn.; National Engineering Laboratory for Big Data Analysis and Applications, Beijing, China. tieli@pku.edu.cn.
Source: Nature methods [Nat Methods] 2026 Mar; Vol. 23 (3), pp. 542-553. Date of Electronic Publication: 2026 Mar 12.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: Nature Pub. Group Country of Publication: United States NLM ID: 101215604 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1548-7105 (Electronic) Linking ISSN: 15487091 NLM ISO Abbreviation: Nat Methods Subsets: MEDLINE
Imprint Name(s): Original Publication: New York, NY : Nature Pub. Group, c2004-
MeSH Terms: Single-Cell Analysis*/methods , Video Recording*/methods , Deep Learning*, Drosophila/embryology ; Brain/physiology ; Brain/cytology ; Animals ; Cell Differentiation ; Cell Proliferation ; Spatio-Temporal Analysis ; Cell Movement ; Embryo, Nonmammalian
Abstract: Time-series spatial transcriptomics with single-cell resolution provides an opportunity to study cell differentiation, proliferation and migration in physical space over time. However, because sequencing is destructive, reconstructing spatiotemporal dynamics from snapshots remains challenging. In particular, inferring migration is difficult because samples collected at different time points often lie in different coordinate systems across biological replicates. Here we show that spatiotemporal video cassette recorder (stVCR), a generative deep-learning framework, can reconstruct continuous cell differentiation, proliferation, physical-space migration and spatial alignment in an end-to-end manner. The model integrates dynamical optimal transport in an unbalanced setting, density matching that is invariant to rigid transformations, and biologically informed priors to preserve spatial structure. stVCR also enables interpretable analysis of how phenotype transitions interact with spatial migration and proliferation. Using both simulated and real datasets, we demonstrate that stVCR is effective and robust, and we apply it to uncover spatiotemporal dynamics in axolotl brain regeneration and 3D Drosophila embryo development.
(© 2026. The Author(s), under exclusive licence to Springer Nature America, Inc.)
Competing Interests: Competing interests: The authors declare no competing interests.
References: Gerri, C., Menchero, S., Mahadevaiah, S. K., Turner, J. M. & Niakan, K. K. Human embryogenesis: a comparative perspective. Annu. Rev. Cell Dev. Biol. 36, 411–440 (2020). (PMID: 3302182610.1146/annurev-cellbio-022020-024900)
Briggs, J. A. et al. The dynamics of gene expression in vertebrate embryogenesis at single-cell resolution. Science 360, eaar5780 (2018). (PMID: 29700227603814410.1126/science.aar5780)
Farrell, J. A. et al. Single-cell reconstruction of developmental trajectories during zebrafish embryogenesis. Science 360, eaar3131 (2018). (PMID: 29700225624791610.1126/science.aar3131)
Tyser, R. C. et al. Single-cell transcriptomic characterization of a gastrulating human embryo. Nature 600, 285–289 (2021). (PMID: 34789876761535310.1038/s41586-021-04158-y)
Lauffenburger, D. A. & Horwitz, A. F. Cell migration: a physically integrated molecular process. Cell 84, 359–369 (1996). (PMID: 860858910.1016/S0092-8674(00)81280-5)
Yamada, K. M. & Sixt, M. Mechanisms of 3D cell migration. Nat. Rev. Mol. Cell Biol. 20, 738–752 (2019). (PMID: 3158285510.1038/s41580-019-0172-9)
Ståhl, P. L. et al. Visualization and analysis of gene expression in tissue sections by spatial transcriptomics. Science 353, 78–82 (2016). (PMID: 2736544910.1126/science.aaf2403)
Rodriques, S. G. et al. Slide-seq: a scalable technology for measuring genome-wide expression at high spatial resolution. Science 363, 1463–1467 (2019). (PMID: 30923225692720910.1126/science.aaw1219)
Stickels, R. R. et al. Highly sensitive spatial transcriptomics at near-cellular resolution with Slide-seqV2. Nat. Biotechnol. 39, 313–319 (2021). (PMID: 3328890410.1038/s41587-020-0739-1)
Chen, A. et al. Spatiotemporal transcriptomic atlas of mouse organogenesis using DNA nanoball-patterned arrays. Cell 185, 1777–1792 (2022). (PMID: 3551270510.1016/j.cell.2022.04.003)
Oliveira, M. F. et al. Characterization of immune cell populations in the tumor microenvironment of colorectal cancer using high definition spatial profiling. Preprint at bioRxiv https://doi.org/10.1101/2024.06.04.597233 (2024).
La Manno, G. et al. RNA velocity of single cells. Nature 560, 494–498 (2018). (PMID: 30089906613080110.1038/s41586-018-0414-6)
Bergen, V., Lange, M., Peidli, S., Wolf, F. A. & Theis, F. J. Generalizing RNA velocity to transient cell states through dynamical modeling. Nat. Biotechnol. 38, 1408–1414 (2020). (PMID: 3274775910.1038/s41587-020-0591-3)
Gao, M., Qiao, C. & Huang, Y. UniTVelo: temporally unified RNA velocity reinforces single-cell trajectory inference. Nat. Commun. 13, 6586 (2022). (PMID: 36329018963379010.1038/s41467-022-34188-7)
Cui, H. et al. DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kinetics. Genome Biol. 25, 27 (2024). (PMID: 382433131079943110.1186/s13059-023-03148-9)
Li, S. et al. A relay velocity model infers cell-dependent RNA velocity. Nat. Biotechnol. 42, 99–108 (2024). (PMID: 3701244810.1038/s41587-023-01728-5)
Gayoso, A. et al. Deep generative modeling of transcriptional dynamics for RNA velocity analysis in single cells. Nat. Methods 21, 50–59 (2024). (PMID: 3773556810.1038/s41592-023-01994-w)
Farrell, S., Mani, M. & Goyal, S. Inferring single-cell transcriptomic dynamics with structured latent gene expression dynamics. Cell Rep. Methods 3, 100581 (2023). (PMID: 377088941054594410.1016/j.crmeth.2023.100581)
Li, T., Shi, J., Wu, Y. & Zhou, P. On the mathematics of RNA velocity I: theoretical analysis. CSIAM Trans. Appl. Math. 2, 1–55 (2021). (PMID: 10.4208/csiam-am.SO-2020-0001)
Battich, N. et al. Sequencing metabolically labeled transcripts in single cells reveals mRNA turnover strategies. Science 367, 1151–1156 (2020). (PMID: 3213954710.1126/science.aax3072)
Erhard, F. et al. scSLAM-seq reveals core features of transcription dynamics in single cells. Nature 571, 419–423 (2019). (PMID: 3129254510.1038/s41586-019-1369-y)
Qiu, Q. et al. Massively parallel and time-resolved RNA sequencing in single cells with scNT-seq. Nat. Methods 17, 991–1001 (2020). (PMID: 32868927810379710.1038/s41592-020-0935-4)
Cao, J., Zhou, W., Steemers, F., Trapnell, C. & Shendure, J. Sci-fate characterizes the dynamics of gene expression in single cells. Nat. Biotechnol. 38, 980–988 (2020). (PMID: 32284584741649010.1038/s41587-020-0480-9)
Hendriks, G.-J. et al. NASC-seq monitors RNA synthesis in single cells. Nat. Commun. 10, 3138 (2019). (PMID: 31316066663724010.1038/s41467-019-11028-9)
Lin, S. et al. Well-TEMP-seq as a microwell-based strategy for massively parallel profiling of single-cell temporal RNA dynamics. Nat. Commun. 14, 1272 (2023). (PMID: 36882403999236110.1038/s41467-023-36902-5)
Qiu, X. et al. Mapping transcriptomic vector fields of single cells. Cell 185, 690–711 (2022). (PMID: 35108499933214010.1016/j.cell.2021.12.045)
Peng, Q., Qiu, X. & Li, T. Storm: incorporating transient stochastic dynamics to infer the RNA velocity with metabolic labeling information. PLoS Comput. Biol. 20, e1012606 (2024). (PMID: 395566171161127010.1371/journal.pcbi.1012606)
Schiebinger, G. et al. Optimal-transport analysis of single-cell gene expression identifies developmental trajectories in reprogramming. Cell 176, 928–943 (2019). (PMID: 30712874640280010.1016/j.cell.2019.01.006)
Bunne, C., Schiebinger, G., Krause, A., Regev, A. & Cuturi, M. Optimal transport for single-cell and spatial omics. Nat. Rev. Methods Prim. 4, 58 (2024). (PMID: 10.1038/s43586-024-00334-2)
Zhang, Z., Sun, Y., Peng, Q., Li, T. & Zhou, P. Integrating dynamical systems modeling with spatiotemporal scRNA-seq data analysis. Entropy 27, 453 (2025). (PMID: 404224081210981310.3390/e27050453)
Zhang, Z. et al. Deciphering cell-fate trajectories using spatiotemporal single-cell transcriptomic data. NPJ Syst. Biol. Appl. 12, 2 (2025).
Tong, A., Huang, J., Wolf, G., Van Dijk, D. & Krishnaswamy, S. TrajectoryNet: a dynamic optimal transport network for modeling cellular dynamics. Int. Conf. Mach. Learn. 119, 9526–9536 (2020).
Tong, A. et al. Learning transcriptional and regulatory dynamics driving cancer cell plasticity using neural ODE-based optimal transport. Preprint at bioRxiv https://doi.org/10.1101/2023.03.28.534644 (2023).
Benamou, J.-D. & Brenier, Y. A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem. Numerische Mathematik 84, 375–393 (2000). (PMID: 10.1007/s002110050002)
Huguet, G. et al. Manifold interpolating optimal-transport flows for trajectory inference. Adv. Neural Inf. Process. Syst. 35, 29705–29718 (2022). (PMID: 3739778610312391)
Tong, A. et al. Improving and generalizing flow-based generative models with minibatch optimal transport. Trans. Mach. Learn. Res. 1–34 (2024).
Neklyudov, K., Brekelmans, R., Severo, D. & Makhzani, A. Action matching: learning stochastic dynamics from samples. In Proc. 40th International Conference on Machine Learning (eds Krause, A. et al.) 25858–25889 (PMLR, 2023).
Neklyudov, K. et al. A computational framework for solving Wasserstein Lagrangian flows. In Proc. 41st International Conference on Machine Learning (eds Salakhutdinov, R. et al.) 37461–37485 (PMLR, 2024).
Zhang, K., Zhu, J., Kong, D. & Zhang, Z. Modeling single cell trajectory using forward-backward stochastic differential equations. PLoS Comput. Biol. 20, e1012015 (2024). (PMID: 386200171101828710.1371/journal.pcbi.1012015)
Jiang, Q. & Wan, L. A physics-informed neural SDE network for learning cellular dynamics from time-series scRNA-seq data. Bioinformatics 40, ii120–ii127 (2024). (PMID: 392307051137333810.1093/bioinformatics/btae400)
Tong, A. Y. et al. Simulation-free Schrödinger bridges via score and flow matching. In Proc. 27th International Conference on Artificial Intelligence and Statistics (eds Dasgupta, S. et al.) 1279–1287 (PMLR, 2024).
Pariset, M., Hsieh, Y.-P., Bunne, C., Krause, A. & De Bortoli, V. Unbalanced diffusion Schrödinger bridge. ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems (2023).
Sha, Y., Qiu, Y., Zhou, P. & Nie, Q. Reconstructing growth and dynamic trajectories from single-cell transcriptomics data. Nat. Mach. Intell. 6, 25–39 (2024). (PMID: 3827436410.1038/s42256-023-00763-w)
Chizat, L., Peyré, G., Schmitzer, B. & Vialard, F.-X. An interpolating distance between optimal transport and Fisher–Rao metrics. Found. Computational Math. 18, 1–44 (2018). (PMID: 10.1007/s10208-016-9331-y)
Wang, D. et al. Joint velocity-growth flow matching for single-cell dynamics modeling. In Proc. 39th Conference on Neural Information Processing Systems (2025); https://openreview.net/forum?id=aXAkNlbnGa.
Peng, Q. et al. WFR-FM: simulation-free dynamic unbalanced optimal transport. In Proc. 14th International Conference on Learning Representations (2026); https://openreview.net/forum?id=1nqu7bK1mm.
Zhang, Z., Li, T. & Zhou, P. Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport. In Proc. 13th International Conference on Learning Representations (2025); https://openreview.net/forum?id=gQlxd3Mtru.
Bunne, C. et al. Learning single-cell perturbation responses using neural optimal transport. Nat. Methods 20, 1759–1768 (2023). (PMID: 377707091063013710.1038/s41592-023-01969-x)
Zeira, R., Land, M., Strzalkowski, A. & Raphael, B. J. Alignment and integration of spatial transcriptomics data. Nat. Methods 19, 567–575 (2022). (PMID: 35577957933402510.1038/s41592-022-01459-6)
Mémoli, F. Gromov–Wasserstein distances and the metric approach to object matching. Found. Comput, Math. 11, 417–487 (2011). (PMID: 10.1007/s10208-011-9093-5)
Klein, D. et al. Mapping cells through time and space with moscot. Nature 638, 1065–1075 (2025). (PMID: 398437461186498710.1038/s41586-024-08453-2)
Scetbon, M. & Cuturi, M. Low-rank optimal transport: approximation, statistics and debiasing. Adv. Neural Inf. Process. Syst. 35, 6802–6814 (2022).
Qiu, X. et al. Spatiotemporal modeling of molecular holograms. Cell 187, 7351–7373 (2024). (PMID: 3953209710.1016/j.cell.2024.10.011)
Halmos, P. et al. DeST-OT: alignment of spatiotemporal transcriptomics data. Cell Syst. 16, 101160 (2025). (PMID: 398749601197245110.1016/j.cels.2024.12.001)
Gu, Y. et al. Topological velocity inference from spatial transcriptomic data. Nat. Biotechnol. https://doi.org/10.1038/s41587-025-02688-8 (2025).
Zhou, P., Bocci, F., Li, T. & Nie, Q. Spatial transition tensor of single cells. Nat. Methods 21, 1053–1062 (2024). (PMID: 387553221116657410.1038/s41592-024-02266-x)
Flamary, R. et al. POT: Python optimal transport. J. Mach. Learn. Res. 22, 1–8 (2021).
Chen, R. T., Rubanova, Y., Bettencourt, J. & Duvenaud, D. K. Neural ordinary differential equations. Adv. Neural Inf. Process. Syst. 31, 6572–6583 (2018).
Wei, X. et al. Single-cell stereo-seq reveals induced progenitor cells involved in axolotl brain regeneration. Science 377, eabp9444 (2022). (PMID: 3604892910.1126/science.abp9444)
Schönemann, P. H. A generalized solution of the orthogonal procrustes problem. Psychometrika 31, 1–10 (1966). (PMID: 10.1007/BF02289451)
Cheng, M. et al. Three-dimension transcriptomics maps of whole mouse embryo during organogenesis. Preprint at bioRxiv https://doi.org/10.1101/2024.08.17.608366 (2024).
Liu, X., Zeira, R. & Raphael, B. J. Partial alignment of multislice spatially resolved transcriptomics data. Genome Res. 33, 1124–1132 (2023). (PMID: 3755326310538490)
Jin, S. et al. Inference and analysis of cell-cell communication using CellChat. Nat. Commun. 12, 1088 (2021). (PMID: 33597522788987110.1038/s41467-021-21246-9)
Efremova, M., Vento-Tormo, M., Teichmann, S. A. & Vento-Tormo, R. CellPhoneDB: inferring cell–cell communication from combined expression of multi-subunit ligand–receptor complexes. Nat. Protoc. 15, 1484–1506 (2020). (PMID: 3210320410.1038/s41596-020-0292-x)
Zhang, Z., Wang, Z., Sun, Y., Li, T. & Zhou, P. Modeling cell dynamics and interactions with unbalanced mean field Schrödinger bridge. In Proc. 39th Annual Conference on Advances in Neural Information Processing Systems (2025); https://openreview.net/forum?id=Z6DJJIN8IJ.
Ichbiah, S., Delbary, F., McDougall, A., Dumollard, R. & Turlier, H. Embryo mechanics cartography: inference of 3D force atlases from fluorescence microscopy. Nat. Methods 20, 1989–1999 (2023). (PMID: 380575271070367710.1038/s41592-023-02084-7)
Noll, N., Streichan, S. J. & Shraiman, B. I. Variational method for image-based inference of internal stress in epithelial tissues. Phys. Rev. X 10, 011072 (2020). (PMID: 337679097989596)
Wang, K. et al. PhyloVelo enhances transcriptomic velocity field mapping using monotonically expressed genes. Nat. Biotechnol. 42, 778–789 (2024). (PMID: 3752495810.1038/s41587-023-01887-5)
Li, C., Virgilio, M. C., Collins, K. L. & Welch, J. D. Multi-omic single-cell velocity models epigenome–transcriptome interactions and improves cell fate prediction. Nat. Biotechnol. 41, 387–398 (2023). (PMID: 3622960910.1038/s41587-022-01476-y)
Peyré, G. & Cuturi, M. in Foundations and Trends in Machine Learning Vol. 11, 355–607 (Now Publishers, 2019).
Liero, M., Mielke, A. & Savaré, G. Optimal transport in competition with reaction: the Hellinger–Kantorovich distance and geodesic curves. SIAM J. Math. Anal. 48, 2869–2911 (2016). (PMID: 10.1137/15M1041420)
Kondratyev, S., Monsaingeon, L. & Vorotnikov, D. A new optimal transport distance on the space of finite Radon measures. Adv. Differential Equ. 21, 1117 – 1164 (2016).
Cohen, S. & Guibasm, L. The earth mover’s distance under transformation sets. Proc. Seventh IEEE Int. Conf. Computer Vis. 2, 1076–1083 (1999). (PMID: 10.1109/ICCV.1999.790393)
Shi, J., Aihara, K., Li, T. & Chen, L. Energy landscape decomposition for cell differentiation with proliferation effect. Natl. Sci. Rev. 9, nwac116 (2022). (PMID: 35992240938546810.1093/nsr/nwac116)
Bishop, C. M. & Bishop, H. Deep Learning: Foundations and Concepts (Springer Nature, 2024).
Fang, Z., Liu, X. & Peltz, G. GSEApy: a comprehensive package for performing gene set enrichment analysis in Python. Bioinformatics 39, btac757 (2023). (PMID: 36426870980556410.1093/bioinformatics/btac757)
Peng, Q. stVCR: spatiotemporal dynamics of single cell. Code Ocean https://doi.org/10.24433/CO.9796381.v1 (2026).
Entry Date(s): Date Created: 20260313 Date Completed: 20260313 Latest Revision: 20260313
Update Code: 20260313
DOI: 10.1038/s41592-026-03010-3
PMID: 41820580
Database: MEDLINE
Description
Abstract:Time-series spatial transcriptomics with single-cell resolution provides an opportunity to study cell differentiation, proliferation and migration in physical space over time. However, because sequencing is destructive, reconstructing spatiotemporal dynamics from snapshots remains challenging. In particular, inferring migration is difficult because samples collected at different time points often lie in different coordinate systems across biological replicates. Here we show that spatiotemporal video cassette recorder (stVCR), a generative deep-learning framework, can reconstruct continuous cell differentiation, proliferation, physical-space migration and spatial alignment in an end-to-end manner. The model integrates dynamical optimal transport in an unbalanced setting, density matching that is invariant to rigid transformations, and biologically informed priors to preserve spatial structure. stVCR also enables interpretable analysis of how phenotype transitions interact with spatial migration and proliferation. Using both simulated and real datasets, we demonstrate that stVCR is effective and robust, and we apply it to uncover spatiotemporal dynamics in axolotl brain regeneration and 3D Drosophila embryo development.<br /> (© 2026. The Author(s), under exclusive licence to Springer Nature America, Inc.)
ISSN:1548-7105
DOI:10.1038/s41592-026-03010-3