Analyze a collection in memory

Here, we’ll analyze the growing collection by loading it into memory. This is only possible if it’s not too large. If your data is large, you’ll likely want to iterate over the collection to train a model, the topic of the next page ().

import lamindb as ln
import bionty as bt

ln.track("mfWKm8OtAzp80000")

Show code cell output Hide code cell output

→ connected lamindb: testuser1/test-scrna

→ created Transform('mfWKm8Ot'), started new Run('Pz9zmEkC') at 2024-12-20 15:05:25 UTC

→ notebook imports: bionty==0.53.2 lamindb==0.77.3 scanpy==1.10.4

ln.Collection.df()

Show code cell output Hide code cell output

	uid	name	description	hash	reference	reference_type	visibility	transform_id	meta_artifact_id	version	is_latest	run_id	created_at	created_by_id
id
2	vU9vGhm9ozKWE66f0001	My versioned scRNA-seq collection	None	luH-jPb6eJLsXvc1TWGpUg	None	None	1	2	None	2	True	2	2024-12-20 15:05:15.781635+00:00	1
1	vU9vGhm9ozKWE66f0000	My versioned scRNA-seq collection	None	DuyXxlMxwF92YehyBLbhKg	None	None	1	1	None	None	False	1	2024-12-20 15:04:59.403847+00:00	1

collection = ln.Collection.get(name="My versioned scRNA-seq collection", version="2")

collection.artifacts.df()

Show code cell output Hide code cell output

	uid	key	description	suffix	type	size	hash	n_objects	n_observations	_hash_type	_accessor	visibility	_key_is_virtual	storage_id	transform_id	version	is_latest	run_id	created_at	created_by_id
id
1	NAxy8G7q3xarNdqt0000	None	Human immune cells from Conde22	.h5ad	dataset	57612943	t_YJQpYrAyAGhs7Ir68zKj	None	1648	sha1-fl	AnnData	1	True	1	1	None	True	1	2024-12-20 15:04:55.120402+00:00	1
3	Y0PbHhR9YXSu8sGt0001	None	10x reference adata, trusted cell type annotation	.h5ad	dataset	857336	GK721a-L-fGDI8kXefKMtA	None	70	md5	AnnData	1	True	1	2	None	True	2	2024-12-20 15:05:15.598075+00:00	1

If the collection isn’t too large, we can now load it into memory.

Under-the-hood, the AnnData objects are concatenated during loading.

The amount of time this takes depends on a variety of factors.

If it occurs often, one might consider storing a concatenated version of the collection, rather than the individual pieces.

adata = collection.load()

The default is an outer join during concatenation as in pandas:

adata

Show code cell output Hide code cell output

AnnData object with n_obs × n_vars = 1718 × 36508
    obs: 'donor', 'tissue', 'cell_type', 'assay', 'cell_type_untrusted', 'n_genes', 'percent_mito', 'louvain', 'cell_type_untrusted_original', 'artifact_uid'
    obsm: 'X_umap', 'X_pca'

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

adata.obs.artifact_uid.cat.categories

Show code cell output Hide code cell output

Index(['NAxy8G7q3xarNdqt0000', 'Y0PbHhR9YXSu8sGt0001'], dtype='object')

We can easily obtain ensemble IDs for gene symbols using the look up object:

genes = bt.Gene.lookup(field="symbol")

genes.itm2b.ensembl_gene_id

Show code cell output Hide code cell output

'ENSG00000136156'

Let us create a plot:

import scanpy as sc

sc.pp.pca(adata, n_comps=2)

sc.pl.pca(
    adata,
    color=genes.itm2b.ensembl_gene_id,
    title=(
        f"{genes.itm2b.symbol} / {genes.itm2b.ensembl_gene_id} /"
        f" {genes.itm2b.description}"
    ),
    save="_itm2b",
)

WARNING: saving figure to file figures/pca_itm2b.pdf

We could save a plot as a pdf and then see it in the flow diagram:

artifact = ln.Artifact("./figures/pca_itm2b.pdf", description="My result on ITM2B")
artifact.save()
artifact.view_lineage()

But given the image is part of the notebook, we can also rely on the report that we create when saving the notebook:

ln.finish()