Query artifacts

Here, we’ll query artifacts and inspect their metadata.

This guide can be skipped if you are only interested in how to leverage the overall collection.

import lamindb as ln
import bionty as bt

💡 connected lamindb: testuser1/test-scrna

ln.settings.transform.stem_uid = "agayZTonayqA"
ln.settings.transform.version = "1"
ln.track()

💡 notebook imports: bionty==0.47.1 lamindb==0.75.0

💡 saved: Transform(uid='agayZTonayqA5zKv', version='1', name='Query artifacts', key='scrna3', type='notebook', created_by_id=1, updated_at='2024-08-06 18:32:00 UTC')

💡 saved: Run(uid='qwrqQI8IBHeJUUzeFy9C', transform_id=3, created_by_id=1)

Run(uid='qwrqQI8IBHeJUUzeFy9C', started_at='2024-08-06 18:32:00 UTC', is_consecutive=True, transform_id=3, created_by_id=1)

Query artifacts by provenance metadata

users = ln.User.lookup()

ln.Transform.filter(created_by=users.testuser1).search("scrna").df()

	uid	version	name	key	description	type	source_code	hash	reference	reference_type	_source_code_artifact_id	created_by_id	updated_at
id
1	Nv48yAceNSh85zKv	1	scRNA-seq	scrna	None	notebook	None	None	None	None	None	1	2024-08-06 18:30:12.281058+00:00
2	ManDYgmftZ8C5zKv	1	Standardize and append a batch of data	scrna2	None	notebook	None	None	None	None	None	1	2024-08-06 18:31:33.936206+00:00
3	agayZTonayqA5zKv	1	Query artifacts	scrna3	None	notebook	None	None	None	None	None	1	2024-08-06 18:32:00.417366+00:00

transform = ln.Transform.filter(uid="Nv48yAceNSh85zKv").one()

ln.Artifact.filter(transform=transform).df()

	uid	version	description	key	suffix	type	_accessor	size	hash	_hash_type	n_objects	n_observations	visibility	_key_is_virtual	storage_id	transform_id	run_id	created_by_id	updated_at
id
1	0Kn1SeheIkd74eWJeKbm	None	Human immune cells from Conde22	None	.h5ad	dataset	AnnData	57612943	9sXda5E7BYiVoDOQkTC0KB	sha1-fl	None	1648	1	True	1	1	1	1	2024-08-06 18:31:27.737268+00:00

Query artifacts by biological metadata

organism = bt.Organism.lookup()
tissues = bt.Tissue.lookup()

query = ln.Artifact.filter(
    organisms=organism.human,
    tissues=tissues.bone_marrow,
)

query.df()

	uid	version	description	key	suffix	type	_accessor	size	hash	_hash_type	n_objects	n_observations	visibility	_key_is_virtual	storage_id	transform_id	run_id	created_by_id	updated_at
id

Inspect artifact metadata

query_set = ln.Artifact.filter().all()
artifact1, artifact2 = query_set[0], query_set[1]

artifact1.describe()

Artifact(uid='0Kn1SeheIkd74eWJeKbm', description='Human immune cells from Conde22', suffix='.h5ad', type='dataset', _accessor='AnnData', size=57612943, hash='9sXda5E7BYiVoDOQkTC0KB', _hash_type='sha1-fl', n_observations=1648, visibility=1, _key_is_virtual=True, updated_at='2024-08-06 18:31:27 UTC')
  Provenance
    .created_by = 'testuser1'
    .storage = '/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna'
    .transform = 'scRNA-seq'
    .run = '2024-08-06 18:30:12 UTC'
    .input_of_runs = ["'2024-08-06 18:31:33 UTC'"]
  Labels
    .tissues = 'blood', 'thoracic lymph node', 'spleen', 'lung', 'mesenteric lymph node', 'lamina propria', 'liver', 'jejunal epithelium', 'omentum', 'bone marrow', ...
    .cell_types = 'classical monocyte', 'T follicular helper cell', 'memory B cell', 'alveolar macrophage', 'naive thymus-derived CD4-positive, alpha-beta T cell', 'effector memory CD8-positive, alpha-beta T cell, terminally differentiated', 'alpha-beta T cell', 'CD4-positive helper T cell', 'naive thymus-derived CD8-positive, alpha-beta T cell', 'macrophage', ...
    .experimental_factors = '10x 3' v3', '10x 5' v2', '10x 5' v1'
    .ulabels = 'D496', '621B', 'A29', 'A36', 'A35', '637C', 'A52', 'A37', 'D503', '640C', ...
  Features
    'assay' = '10x 3' v3', '10x 5' v2', '10x 5' v1'
    'cell_type' = 'classical monocyte', 'T follicular helper cell', 'memory B cell', 'alveolar macrophage', 'naive thymus-derived CD4-positive, alpha-beta T cell', 'effector memory CD8-positive, alpha-beta T cell, terminally differentiated', 'alpha-beta T cell', 'CD4-positive helper T cell', 'naive thymus-derived CD8-positive, alpha-beta T cell', 'macrophage', ...
    'donor' = 'D496', '621B', 'A29', 'A36', 'A35', '637C', 'A52', 'A37', 'D503', '640C', ...
    'tissue' = 'blood', 'thoracic lymph node', 'spleen', 'lung', 'mesenteric lymph node', 'lamina propria', 'liver', 'jejunal epithelium', 'omentum', 'bone marrow', ...
  Feature sets
    'var' = 'MIR1302-2HG', 'FAM138A', 'OR4F5', 'None', 'OR4F29', 'OR4F16', 'LINC01409', 'FAM87B', 'LINC01128', 'LINC00115', 'FAM41C'
    'obs' = 'donor', 'tissue', 'cell_type', 'assay'

artifact1.view_lineage()

artifact2.describe()

Artifact(uid='g3IiBfOBGmIUtq7CZvoh', description='10x reference adata', suffix='.h5ad', type='dataset', _accessor='AnnData', size=853388, hash='0O3vN1SecMwUGmF-ZbebIg', _hash_type='md5', n_observations=70, visibility=1, _key_is_virtual=True, updated_at='2024-08-06 18:31:54 UTC')
  Provenance
    .created_by = 'testuser1'
    .storage = '/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna'
    .transform = 'Standardize and append a batch of data'
    .run = '2024-08-06 18:31:33 UTC'
  Labels
    .cell_types = 'B cell, CD19-positive', 'CD4-positive helper T cell', 'dendritic cell', 'effector memory CD4-positive, alpha-beta T cell, terminally differentiated', 'cytotoxic T cell', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'CD16-positive, CD56-dim natural killer cell, human', 'CD14-positive, CD16-positive monocyte', 'CD38-positive naive B cell'
  Features
    'cell_type' = 'B cell, CD19-positive', 'CD4-positive helper T cell', 'dendritic cell', 'effector memory CD4-positive, alpha-beta T cell, terminally differentiated', 'cytotoxic T cell', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'CD16-positive, CD56-dim natural killer cell, human', 'CD14-positive, CD16-positive monocyte', 'CD38-positive naive B cell'
  Feature sets
    'var' = 'TLE5', 'S1PR4', 'CD164', 'SMIM24', 'DCAF10', 'RAB13', 'TPM3', 'HES4', 'HAX1', 'ADD3', 'GSTK1', 'GTF3C6', 'SNX2', 'ACAA1', 'MATK', 'ZYX', 'JAML', 'CD3E', 'CD3D', 'EXOG'
    'obs' = 'cell_type'

artifact2.view_lineage()

Compare features

Here we compute shared genes:

artifact1_genes = artifact1.features["var"]
artifact2_genes = artifact2.features["var"]

shared_genes = artifact1_genes & artifact2_genes
len(shared_genes)

749

shared_genes.list("symbol")[:10]

['HES4',
 'TNFRSF4',
 'SSU72',
 'PARK7',
 'RBP7',
 'SRM',
 'MAD2L2',
 'AGTRAP',
 'TNFRSF1B',
 'EFHD2']

Compare cell types

artifact1_celltypes = artifact1.cell_types.all()
artifact2_celltypes = artifact2.cell_types.all()

shared_celltypes = artifact1_celltypes & artifact2_celltypes
shared_celltypes_names = shared_celltypes.list("name")
shared_celltypes_names

['CD4-positive helper T cell',
 'CD16-positive, CD56-dim natural killer cell, human']

Load the individual artifacts

We could either load the artifacts into memory or access them in backed mode through .open() to lazily load their content.

Let’s load them into memory:

adata1 = artifact1.load()
adata2 = artifact2.load()

We can now subset the two collections by shared cell types:

adata1_subset = adata1[adata1.obs["cell_type"].isin(shared_celltypes_names)]
adata2_subset = adata2[adata2.obs["cell_type"].isin(shared_celltypes_names)]