EUVIMEDEUVIMED entdecken
Open Access

Deep manifold learning reveals hidden developmental dynamics of a human embryo model

Kejie Chen iD, Kai-Rong Qin iD, Jing Na iD, Guanbin Gao iD, Chunxi Yang iD, Jianping Fu iD

Science Advances · 08.08.2025 · 11 (32)

DOI: 10.1126/sciadv.adr8901 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 08.08.2025. Verfasst von Kejie Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, Yunnan, China. Hauptthemen laut MEDLINE: Deep Learning, Embryonic Development, Models, Biological, Embryo, Mammalian. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this study, postimplantation human epiblast and amnion development are modeled using a stem cell–based embryoid system. A dataset of 3697 fluorescent images, along with tissue, cavity, and cell masks, is generated from experimental data. A computational pipeline analyzes morphological and marker expression features, revealing key developmental processes such as tissue growth, cavity expansion, and cell differentiation. To uncover hidden developmental dynamics, a deep manifold learning framework is introduced. This framework uses an autoencoder to project embryoid images into a twenty-dimensional (20D) latent space and models the dynamics using a mean-reverting stochastic process of mixed Gaussians. The approach accurately captures phenotypic changes observed at discrete experimental time points. Moreover, it enables the generation of artificial yet realistic embryoid images at finer temporal resolutions, providing deeper insights into the progression of early human development.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningEmbryonic DevelopmentModels, BiologicalEmbryo, MammalianHumansCell DifferentiationEmbryoid Bodies

Autor:innen und Institutionen

  • Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, Yunnan, China.
  • Yunnan Key Laboratory of Intelligent Control and Application, Kunming, Yunnan, China.
  • School of Biomedical Engineering, Faculty of Medicine, Dalian University of Technology, Dalian, Liaoning, China.
  • Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, USA.
  • Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI, USA.
  • Department of Cell & Developmental Biology, University of Michigan Medical School, Ann Arbor, MI, USA.

ORCID-Profile: Kejie Chen, Kai-Rong Qin, Jing Na, Guanbin Gao, Chunxi Yang, Jianping Fu

Zitieren

APA

Chen, K., Qin, K. R., Na, J., Gao, G., Yang, C., & Fu, J. (2025). Deep manifold learning reveals hidden developmental dynamics of a human embryo model. Science Advances, 11(32). https://doi.org/10.1126/sciadv.adr8901

Vancouver

Chen K, Qin KR, Na J, Gao G, Yang C, Fu J. Deep manifold learning reveals hidden developmental dynamics of a human embryo model. Science Advances. 2025;11(32). doi:10.1126/sciadv.adr8901

BibTeX
@article{Chen2025,
  author = {Chen, Kejie and Qin, Kai-Rong and Na, Jing and Gao, Guanbin and Yang, Chunxi and Fu, Jianping},
  title = {Deep manifold learning reveals hidden developmental dynamics of a human embryo model},
  journal = {Science Advances},
  year = {2025},
  volume = {11},
  number = {32},
  doi = {10.1126/sciadv.adr8901}
}
Kostenlos starten →