This project implements an end-to-end pipeline for spatial transcriptomics data analysis using Scanpy and Squidpy.
- Quality control (QC)
- Normalization and log transformation
- PCA, UMAP, Leiden clustering
- Marker gene analysis
- Cell type annotation
- Spatial visualization
This project uses a sample Visium dataset provided by Scanpy for demonstration purposes.
src/ # pipeline code results/ # generated figures data/ # input data (not included)
python main.py
Output
UMAP plot of clusters
Spatial distribution of cell types