Add SpaGFT-like method for identification of SVGs
Open
@LLehner is already working on this.
Since Oct 28, 2024.
enhancement :sparkles:
graph :spider_web:
squidpy2.0
- Dominant language
- Python
- Stars
- 598
- Forks
- 121
- Avg merge
- 3d 11h
- Merged PRs (30d)
- 3
Description
SpaGFT (Spatial omics representation and functional tissue module inference using graph Fourier transform) uses Fourier transforms to identify SVGs (and then groups them into "tissue modules". At SBI2 the presenter said their method is "similar but better than Moran's I" - so we could potentially implement it as another flavor in https://squidpy.readthedocs.io/en/stable/api/squidpy.gr.spatial_autocorr.html.
The implementation already used AnnData and looks to be low on dependencies:
https://github.com/jxLiu-bio/SpaGFT/blob/master/SpaGFT/gft.py
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.