Analyze the collection and save a result¶

import lamindb as ln
import bionty as bt

ln.track("zzJzdgJ763Dy0000")

ln.Collection.to_dataframe()

Show code cell output Hide code cell output

	uid	key	description	hash	reference	reference_type	version_tag	is_latest	is_locked	created_at	branch_id	space_id	created_by_id	run_id	meta_artifact_id
id
2	0PXsYmFARTOStjFP0001	My versioned cytometry collection	None	eNSQbRNsjg278G1RwXmqCw	None	None	2	True	False	2026-01-29 23:14:13.081000+00:00	1	1	3	2	None
1	0PXsYmFARTOStjFP0000	My versioned cytometry collection	None	jZ8YvUdZGRwPgfoBQbOg_Q	None	None	1	False	False	2026-01-29 23:14:02.233000+00:00	1	1	3	1	None

collection = ln.Collection.get(key="My versioned cytometry collection", version="2")

adata = collection.load(join="inner")

The AnnData has the reference to the individual files in the .obs annotations:

adata.obs.artifact_uid.cat.categories

By default, the intersection of features is used:

adata.var.index

Let us create a plot:

markers = bt.CellMarker.lookup()

import scanpy as sc

sc.pp.pca(adata)
sc.pl.pca(adata, color=markers.cd8.name, save="_cd8")

artifact = ln.Artifact("./figures/pca_cd8.pdf", description="My result on CD8").save()
artifact.view_lineage()

Given the image is part of the notebook, there isn’t an actual need to save it and you can also rely on the report that you’ll create when saving the notebook:

ln.finish()

# clean up test instance
!rm -r test-flow
!lamin delete --force test-facs