.png){kind=icon}
Return
HyperDiffuseNet: A Deep Hyperbolic Manifold Learning Method for Dimensionality Reduction in Spatial Transcriptomics
.png){kind=icon}
PRE
AI
DOI：10.1177/15578666251377097.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Spatial transcriptomics (ST) reveals tissue organization but presents analytical challenges due to high dimensionality and complex spatial-hierarchical structures, which are often distorted by Euclidean-based dimensionality reduction methods. Here, we introduce HyperDiffuseNet, a deep geometric learning framework designed for ST data representation. HyperDiffuseNet utilizes a variational autoencoder with a hyperbolic latent space to effectively capture hierarchical relationships. It integrates spatial context by first employing graph convolutional networks on the spatial graph to learn multi-scale dependencies, which inform the computation of a diffusion matrix. This graph-derived diffusion information is then efficiently incorporated into the hyperbolic embeddings via linear mixing in the ambient Minkowski space. The model uses negative binomial reconstruction loss and is optimized with a composite objective function balancing reconstruction fidelity, Kullback-Leibler divergence regularization, attention-weighted spatial regularization, diffusion consistency, and local structure preservation. Empirical evaluations on multiple ST datasets demonstrate that HyperDiffuseNet achieves competitive clustering performance. The hyperbolic embedding approach shows notable improvements in Silhouette coefficient and adjusted rand index metrics across most tested datasets, while maintaining comparable performance in structure preservation.
Keywords:
dimensionality reduction
hyperbolic geometry
Minkowski space
spatial transcriptomics
variational autoencoder
Journal
J
IF:
1.6
Papers:
54
Citations:
5.1K
Organization
No organization information available
Cited Papers
ShareSaveIdentifying temporal and spatial patterns of variation from multimodal data using MEFISTO.png)
NATURE METHODS
OAAI
NATURE METHODSIF32.1
OAAIShareSaveThe dynamics and regulators of cell fate decisions are revealed by pseudotemporal ordering of single cellsNATURE BIOTECHNOLOGYOAAI
NATURE BIOTECHNOLOGYIF41.7
OAAIShareSaveSlide-seq: A scalable technology for measuring genome-wide expression at high spatial resolutionScienceOAAI
ScienceIF0
OAAIShareSaveShareSavespatialLIBD: an R/Bioconductor package to visualize spatially-resolved transcriptomics dataBMC GENOMICSOAAI
BMC GENOMICSIF3.7
OAAIShareSaveInterpretable dimensionality reduction of single cell transcriptome data with deep generative modelsNATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAIShareSaveComplex hierarchical structures in single-cell genomics data unveiled by deep hyperbolic manifold learningGENOME RESEARCH
OAAI
GENOME RESEARCHIF5.5
OAAIShareSave
View more