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

ln.track("agayZTonayqA0000")

Query artifacts by provenance metadata¶

Query the transform, e.g., by uid:

transform = ln.Transform.get(uid="Nv48yAceNSh80003")

Query the artifact:

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

Show code cell output Hide code cell output

	uid	version	is_latest	description	key	suffix	type	size	hash	n_objects	n_observations	_hash_type	_accessor	visibility	_key_is_virtual	storage_id	transform_id	run_id	created_at	created_by_id
id
1	AE158pvBDEQbQeOj0000	None	True	Human immune cells from Conde22	None	.h5ad	dataset	57612943	t_YJQpYrAyAGhs7Ir68zKj	None	1648	sha1-fl	AnnData	1	True	1	1	1	2024-11-21 06:53:36.460292+00:00	1

Query artifacts by biological metadata¶

tissues = bt.Tissue.lookup()

query = ln.Artifact.filter(
    tissues=tissues.blood,
)
query.df()

Show code cell output Hide code cell output

	uid	version	is_latest	description	key	suffix	type	size	hash	n_objects	n_observations	_hash_type	_accessor	visibility	_key_is_virtual	storage_id	transform_id	run_id	created_at	created_by_id
id
1	AE158pvBDEQbQeOj0000	None	True	Human immune cells from Conde22	None	.h5ad	dataset	57612943	t_YJQpYrAyAGhs7Ir68zKj	None	1648	sha1-fl	AnnData	1	True	1	1	1	2024-11-21 06:53:36.460292+00:00	1

Inspect artifact metadata¶

Query all artifacts that measured the “cell_type” feature:

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

artifact1.describe()

Show code cell output Hide code cell output

Artifact(uid='AE158pvBDEQbQeOj0000', is_latest=True, description='Human immune cells from Conde22', suffix='.h5ad', type='dataset', size=57612943, hash='t_YJQpYrAyAGhs7Ir68zKj', n_observations=1648, _hash_type='sha1-fl', _accessor='AnnData', visibility=1, _key_is_virtual=True, created_at=2024-11-21 06:53:36 UTC)
  Provenance
    .storage = '/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna'
    .transform = 'scRNA-seq'
    .run = 2024-11-21 06:52:53 UTC
    .created_by = 'testuser1'
  Usage
    .input_of_runs = 2024-11-21 06:53:45 UTC
  Labels
    .tissues = 'duodenum', 'lamina propria', 'sigmoid colon', 'jejunal epithelium', 'thymus', 'skeletal muscle tissue', 'caecum', 'mesenteric lymph node', 'spleen', 'omentum', ...
    .cell_types = 'megakaryocyte', 'effector memory CD4-positive, alpha-beta T cell', 'plasmacytoid dendritic cell', 'alveolar macrophage', 'naive B cell', 'alpha-beta T cell', 'CD8-positive, alpha-beta memory T cell, CD45RO-positive', 'progenitor cell', 'gamma-delta T cell', 'CD4-positive helper T cell', ...
    .experimental_factors = '10x 3' v3', '10x 5' v1', '10x 5' v2'
    .ulabels = 'A52', 'A29', '582C', 'D496', 'A35', '640C', 'A36', '637C', '621B', 'A37', ...
  Features
    'assay' = '10x 3' v3', '10x 5' v1', '10x 5' v2'
    'cell_type' = 'CD16-negative, CD56-bright natural killer cell, human', 'CD16-positive, CD56-dim natural killer cell, human', 'CD4-positive helper T cell', 'CD8-positive, alpha-beta memory T cell', 'CD8-positive, alpha-beta memory T cell, CD45RO-positive', 'T follicular helper cell', 'alpha-beta T cell', 'alveolar macrophage', 'animal cell', 'classical monocyte', ...
    'donor' = '582C', '621B', '637C', '640C', 'A29', 'A31', 'A35', 'A36', 'A37', 'A52', ...
    'tissue' = 'blood', 'bone marrow', 'caecum', 'duodenum', 'ileum', 'jejunal epithelium', 'lamina propria', 'liver', 'lung', 'mesenteric lymph node', ...
  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()

Show code cell output Hide code cell output

Artifact(uid='b7dQMbVcWW7iNJzH0001', is_latest=True, description='10x reference adata, trusted cell type annotation', suffix='.h5ad', type='dataset', size=851664, hash='iETHP3Lw-tVqZxYAuEC-SA', n_observations=70, _hash_type='md5', _accessor='AnnData', visibility=1, _key_is_virtual=True, created_at=2024-11-21 06:54:05 UTC)
  Provenance
    .storage = '/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna'
    .transform = 'Standardize and append a dataset'
    .run = 2024-11-21 06:53:45 UTC
    .created_by = 'testuser1'
  Labels
    .cell_types = 'CD16-positive, CD56-dim natural killer cell, human', 'dendritic cell', 'B cell, CD19-positive', 'effector memory CD4-positive, alpha-beta T cell, terminally differentiated', 'cytotoxic T cell', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'CD14-positive, CD16-negative classical monocyte', 'CD38-positive naive B cell', 'CD38-high pre-BCR positive cell'
  Features
    'cell_type' = 'B cell, CD19-positive', 'CD14-positive, CD16-negative classical monocyte', 'CD16-positive, CD56-dim natural killer cell, human', 'CD38-high pre-BCR positive cell', 'CD38-positive naive B cell', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'cytotoxic T cell', 'dendritic cell', 'effector memory CD4-positive, alpha-beta T cell, terminally differentiated'
    'cell_type_untrusted' = 'B cell, CD19-positive', 'CD14-positive, CD16-negative classical monocyte', 'CD16-positive, CD56-dim natural killer cell, human', 'CD38-high pre-BCR positive cell', 'CD38-positive naive B cell', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'cytotoxic T cell', 'dendritic cell', 'effector memory CD4-positive, alpha-beta T cell, terminally differentiated'
  Feature sets
    'var' = 'HES4', 'TNFRSF4', 'SSU72', 'PARK7', 'RBP7', 'SRM', 'MAD2L2', 'AGTRAP', 'TNFRSF1B', 'EFHD2', 'NECAP2', 'HP1BP3', 'C1QA', 'C1QB', 'HNRNPR', 'GALE', 'STMN1', 'CD52', 'FGR', 'ATP5IF1'
    'obs' = 'cell_type', 'cell_type_untrusted'

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)

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

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

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:

adata2

AnnData object with n_obs × n_vars = 70 × 754
    obs: 'cell_type_untrusted', 'n_genes', 'percent_mito', 'louvain', 'cell_type_untrusted_original', 'cell_type'
    var: 'symbol', 'n_counts', 'highly_variable'
    uns: 'louvain', 'louvain_colors', 'neighbors', 'pca'
    obsm: 'X_pca', 'X_umap'
    varm: 'PCs'
    obsp: 'connectivities', 'distances'

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