Scanpy analysis
¶
Agentic re-implementation of the classic PBMC3k Scanpy tutorial: QC, clustering, marker discovery, and cell-type annotation — with cutoffs and labels chosen from the data, not hard-coded from the docs.
Instance: laminlabs/lamindata · Branch: scanpy-k-dense · Agent run: Claude Code
Write-up: analysis report
Agentic analysis¶
Step |
Transform |
Outputs |
|---|---|---|
QC |
||
Cluster |
clustered h5ad · HVG · PCA · UMAP |
|
Markers |
||
Canonical check |
||
Annotate |
||
Final plots |
UMAP cell types · UMAP clusters · UMAP markers · cell-type heatmap |
The 10 cell-type labels live on the annotated AnnData; methods, results, and figures are in the report.