SIMVI (Spatial Interaction Modelling using Variational Inference) is a deep generative framework for disentangling intrinsic variation and spatially-induced variation in spatial omics data. SIMVI enables novel downstream analyses, including clustering and differential expression analysis based on disentangled representations, spatial effect identification, spatial effect attribution, and transfer learning on new measurements / modalities. SIMVI is implemented with scvi-tools.
Read our preprint on BioRxiv:
- Dong, Mingze, et al. "SIMVI reveals intrinsic and spatial-induced states in spatial omics data". bioRxiv (2023). Link
The SIMVI package is supported for all OS in principle. The package has been tested on the following systems:
- macOS: Monterey (12.4)
- Linux: Ubantu (20.04.5)
See setup.cfg for details.
SIMVI requires python version 3.7+. Install directly from pip with:
pip install simvi
The installation should take no more than a few minutes on a normal desktop computer.
For detailed usage, follow our step-by-step tutorial here. The tutorial should take several minutes to compile, depending on the computational capacity.
Download the dataset used for the tutorial here: