Skip to content
DraconiticResearch
Search Sources API
194,230 studies31 sourcesUpdated 12 min ago
Peer-reviewedCC BYCell

RegVelo: Gene-regulatory-informed dynamics of single cells

  • Weixu Wang1,2,3
  • Zhiyuan Hu4,5,6,7,8
  • Philipp Weiler9,2,10,3
  • Sarah Mayes11,5,7
  • Marius Lange12,13,2
  • Daniel Mark Fountain11,14,15
  • Julianna O. Haug16,17,10
  • Jingye Wang18,19,5,7,16
  • Zhengyuan Xue20,2,10,3
  • Tatjana Sauka‐Spengler21
  • Fabian Joachim Theis22
22 affiliations
  1. 1Institute of Computational Biology, Computational Health Center, Helmholtz Munich, Munich, Germany; TUM School of Life Sciences Weihenstephan, Technical University of Munich, Munich, Germany
  2. 2Institute of Computational Biology, Computational Health Center, Helmholtz Munich, Munich, Germany
  3. 3TUM School of Life Sciences Weihenstephan, Technical University of Munich, Germany
  4. 4MRC Weatherall Institute of Molecular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK; Reproductive Medicine Center, Medical Research Institute, Frontier Science Center for Immunology and Metabolism, Zhongnan Hospital, Wuhan University, Wuhan, China
  5. 5MRC Weatherall Institute of Molecular Medicine, Radcliffe Department of Medicine, University of Oxford
  6. 6Medical Research Institute, Frontier Science Center for Immunology and Metabolism, Wuhan University
  7. 7Oxford, United Kingdom
  8. 8Wuhan, China
  9. 9Institute of Computational Biology, Computational Health Center, Helmholtz Munich, Munich, Germany; TUM School of Life Sciences Weihenstephan, Technical University of Munich, Munich, Germany; School of Computation, Information and Technology, Technical University of Munich, Munich, Germany
  10. 10School of Computation, Information and Technology, Technical University of Munich, Munich, Germany
  11. 11MRC Weatherall Institute of Molecular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
  12. 12Institute of Computational Biology, Computational Health Center, Helmholtz Munich, Munich, Germany; Department of Biosystems Science and Engineering, ETH Zürich, Basel, Switzerland
  13. 13Department of Biosystems Science and Engineering, ETH Zürich, Basel, Switzerland
  14. 14Department of Biology, New York University, New York, NY, USA
  15. 15Institute for Systems Genetics, NYU Grossman School of Medicine, New York, NY, USA
  16. 16Stowers Institute for Medical Research, Kansas City, MO, USA
  17. 17Institute of Translational Genomics, Helmholtz Munich, Germany
  18. 18Institute for Systems Genetics, NYU Grossman School of Medicine, New York, NY, USA; Department of Biology, New York University, New York, NY, USA
  19. 19MRC WIMM Centre for Computational Biology, MRC Weatherall Institute of Molecular Medicine, University of Oxford, Oxford, United Kingdom
  20. 20School of Computation, Information and Technology, Technical University of Munich, Munich, Germany; Institute of Translational Genomics, Helmholtz Munich, Munich, Germany
  21. 21MRC Weatherall Institute of Molecular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK; Stowers Institute for Medical Research, Kansas City, MO, USA; MRC WIMM Centre for Computational Biology, MRC Weatherall Institute of Molecular Medicine, University of Oxford, Oxford, UK. Electronic address: [email protected]
  22. 22Institute of Computational Biology, Computational Health Center, Helmholtz Munich, Munich, Germany; TUM School of Life Sciences Weihenstephan, Technical University of Munich, Munich, Germany; School of Computation, Information and Technology, Technical University of Munich, Munich, Germany. Electronic address: [email protected]
Open at sourceDOICite

Abstract

RNA velocity has emerged as a popular approach for modeling cellular change along the phenotypic landscape but routinely omits regulatory interactions between genes. Conversely, methods that infer gene regulatory networks (GRNs) do not consider the dynamically changing nature of biological systems. To integrate these two currently disconnected fields, we present RegVelo, an end-to-end dynamic, interpretable, and actionable deep learning model that learns a joint model of splicing kinetics and gene regulatory relationships and allows us to perform in silico perturbation predictions. When applied to datasets of the cell cycle, human hematopoiesis, and murine pancreatic endocrinogenesis, RegVelo demonstrates superior predictive power for interactions and perturbation simulations, for example, compared to methods that focus solely on dynamics or GRN inference. To leverage RegVelo’s full potential, we studied the dynamics of zebrafish neural crest development and underlying regulatory mechanisms using our Smart-seq3 dataset and shared gene expression and chromatin accessibility measurements. Using RegVelo’s in silico perturbation predictions, validated by CRISPR/Cas9-mediated knockout and single-cell Perturb-seq, we establish transcription factor tfec as an early driver and elf1 as a novel regulator of pigment cell fate and propose a gene-regulatory circuit involving tfec and elf1 interactions via the toggle-switch model.

Related

  1. A droplet-based long-read single-cell epigenome sequencing method for the high-throughput profiling of multidimensional regulatory elements within individual cells
    Jiansen Lu, Kexuan Chen, Shengtao Jia +3
    Cell DiscoveryPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationPMCDOAJ
  2. Deciphering global transcriptional dynamics coordinated by gene-gene regulatory interactions using single-cell data
    Liying Zhou, Songhao Luo, Zhiwei Huang +3
    Molecular Systems BiologyPeer-reviewedCC BY 4.0Full text1 citedMolecular biology & gene regulationPMC
  3. Single-cell multimodal analysis reveals enhancer and transcription factor regulatory dynamics during human iPSC-derived cardiomyocyte differentiation
    Hyejin Kim, Sun-Ho Lee, Chul Min Yang +4
    BMB ReportsPeer-reviewedCC BY-NC 4.0Full textMolecular biology & gene regulationPMC
  4. A spatiotemporal single‐cell atlas of porcine development reveals regulatory dynamics and cellular targets of domestication
    R J Zhou, Zishuai Wang, Chenghao Hu +6
    iMetaPeer-reviewedCC BY7 citedMolecular biology & gene regulationOpenAlex
  5. Single-molecule Analysis of DNA Replication Dynamics in Budding Yeast and Human Cells by DNA Combing
    Hélène Tourrière, Julie Saksouk, Armelle Lengronne +1
    Bio-protocolPeer-reviewedLicence not stated13 citedMolecular biology & gene regulationHAL

Cite

BibTeXRIS
BibTeX
@article{wang2026regvelo,
  title = {{RegVelo: Gene-regulatory-informed dynamics of single cells}},
  author = {Weixu Wang and Zhiyuan Hu and Philipp Weiler and Sarah Mayes and Marius Lange and Daniel Mark Fountain and Julianna O. Haug and Jingye Wang and Zhengyuan Xue and Tatjana Sauka‐Spengler and Fabian Joachim Theis},
  journal = {Cell},
  year = {2026},
  month = may,
  doi = {10.1016/j.cell.2026.04.022},
  url = {https://doi.org/10.1016/j.cell.2026.04.022},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - RegVelo: Gene-regulatory-informed dynamics of single cells
AU  - Weixu Wang
AU  - Zhiyuan Hu
AU  - Philipp Weiler
AU  - Sarah Mayes
AU  - Marius Lange
AU  - Daniel Mark Fountain
AU  - Julianna O. Haug
AU  - Jingye Wang
AU  - Zhengyuan Xue
AU  - Tatjana Sauka‐Spengler
AU  - Fabian Joachim Theis
PY  - 2026
DA  - 2026/05/12
JO  - Cell
DO  - 10.1016/j.cell.2026.04.022
UR  - https://doi.org/10.1016/j.cell.2026.04.022
AB  - RNA velocity has emerged as a popular approach for modeling cellular change along the phenotypic landscape but routinely omits regulatory interactions between genes. Conversely, methods that infer gene regulatory networks (GRNs) do not consider the dynamically changing nature of biological systems. To integrate these two currently disconnected fields, we present RegVelo, an end-to-end dynamic, interpretable, and actionable deep learning model that learns a joint model of splicing kinetics and gene regulatory relationships and allows us to perform in silico perturbation predictions. When applied to datasets of the cell cycle, human hematopoiesis, and murine pancreatic endocrinogenesis, RegVelo demonstrates superior predictive power for interactions and perturbation simulations, for example, compared to methods that focus solely on dynamics or GRN inference. To leverage RegVelo’s full potential, we studied the dynamics of zebrafish neural crest development and underlying regulatory mechanisms using our Smart-seq3 dataset and shared gene expression and chromatin accessibility measurements. Using RegVelo’s in silico perturbation predictions, validated by CRISPR/Cas9-mediated knockout and single-cell Perturb-seq, we establish transcription factor tfec as an early driver and elf1 as a novel regulator of pigment cell fate and propose a gene-regulatory circuit involving tfec and elf1 interactions via the toggle-switch model.
SN  - 0092-8674
SN  - 1097-4172
ER  -