Query individual files

Here, we’ll query individual files and inspect their metadata.

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

import lamindb as ln
import lnschema_bionty as lb
import anndata as ad

💡 loaded instance: testuser1/test-scrna (lamindb 0.59.0)

ln.track()

💡 notebook imports: anndata==0.9.2 lamindb==0.59.0 lnschema_bionty==0.34.0

💡 Transform(uid='agayZTonayqAz8', name='Query individual files', short_name='scrna3', version='0', type=notebook, updated_at=2023-10-27 14:09:44, created_by_id=1)

💡 Run(uid='WudOf34xwirCTrE9FU3W', run_at=2023-10-27 14:09:44, transform_id=3, created_by_id=1)

Query files by provenance metadata

users = ln.User.lookup()

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

	uid	score
name
scRNA-seq	Nv48yAceNSh8z8	90.0
Append a new batch of data	ManDYgmftZ8Cz8	36.0
Query individual files	agayZTonayqAz8	36.0

transform = ln.Transform.filter(uid="Nv48yAceNSh8z8").one()

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

	uid	storage_id	key	suffix	accessor	description	version	size	hash	hash_type	transform_id	run_id	initial_version_id	visibility	key_is_virtual	updated_at	created_by_id
id
1	OmLkMWSbDuMAxFj7BqyV	1	None	.h5ad	AnnData	Conde22	None	57612943	9sXda5E7BYiVoDOQkTC0KB	sha1-fl	1	1	None	0	True	2023-10-27 14:08:58	1

Query files by biological metadata

assays = lb.ExperimentalFactor.lookup()
organism = lb.Organism.lookup()
cell_types = lb.CellType.lookup()

query = ln.File.filter(
    experimental_factors=assays.single_cell_rna_sequencing,
    organism=organism.human,
    cell_types=cell_types.gamma_delta_t_cell,
)

query.df()

	uid	storage_id	key	suffix	accessor	description	version	size	hash	hash_type	transform_id	run_id	initial_version_id	visibility	key_is_virtual	updated_at	created_by_id
id
1	OmLkMWSbDuMAxFj7BqyV	1	None	.h5ad	AnnData	Conde22	None	57612943	9sXda5E7BYiVoDOQkTC0KB	sha1-fl	1	1	None	0	True	2023-10-27 14:08:58	1
2	viuAb9psg6SVruytRK7P	1	None	.h5ad	AnnData	10x reference adata	None	857752	U4UmKxr_rN8KlwVK4WYKjw	md5	2	2	None	0	True	2023-10-27 14:09:34	1

Inspect file metadata

query_set = ln.File.filter().all()

file1, file2 = query_set[0], query_set[1]

file1.describe()

File(uid='OmLkMWSbDuMAxFj7BqyV', suffix='.h5ad', accessor='AnnData', description='Conde22', size=57612943, hash='9sXda5E7BYiVoDOQkTC0KB', hash_type='sha1-fl', visibility=0, key_is_virtual=True, updated_at=2023-10-27 14:08:58)

Provenance:
  🗃️ storage: Storage(uid='u254wjlq', root='/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna', type='local', updated_at=2023-10-27 14:08:02, created_by_id=1)
  📔 transform: Transform(uid='Nv48yAceNSh8z8', name='scRNA-seq', short_name='scrna', version='0', type='notebook', updated_at=2023-10-27 14:08:07, created_by_id=1)
  👣 run: Run(uid='T5xPTY12UVw6rOOjgE7H', run_at=2023-10-27 14:08:07, transform_id=1, created_by_id=1)
  👤 created_by: User(uid='DzTjkKse', handle='testuser1', name='Test User1', updated_at=2023-10-27 14:08:02)
  ⬇️ input_of (core.Run): ['2023-10-27 14:09:05']
Features:
  var: FeatureSet(uid='6qRKjbpfuxhgYAbbyN5d', n=36503, type='number', registry='bionty.Gene', hash='dnRexHCtxtmOU81_EpoJ', updated_at=2023-10-27 14:08:52, modality_id=1, created_by_id=1)
    'MIR1302-2HG', 'FAM138A', 'OR4F5', 'None', 'None', 'None', 'None', 'None', 'None', 'None', 'OR4F29', 'None', 'OR4F16', 'None', 'LINC01409', 'FAM87B', 'LINC01128', 'LINC00115', 'FAM41C', 'None', ...
  obs: FeatureSet(uid='BCo5J2bFOheDRHdwQ4Zd', n=4, registry='core.Feature', hash='JsxufswT1GUhRPy_OR3-', updated_at=2023-10-27 14:08:53, modality_id=2, created_by_id=1)
    🔗 cell_type (32, bionty.CellType): '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', ...
    🔗 assay (4, bionty.ExperimentalFactor): 'single-cell RNA sequencing', '10x 3' v3', '10x 5' v2', '10x 5' v1'
    🔗 tissue (17, bionty.Tissue): 'blood', 'thoracic lymph node', 'spleen', 'lung', 'mesenteric lymph node', 'lamina propria', 'liver', 'jejunal epithelium', 'omentum', 'bone marrow', ...
    🔗 donor (12, core.ULabel): 'D496', '621B', 'A29', 'A36', 'A35', '637C', 'A52', 'A37', 'D503', '640C', ...
Labels:
  🏷️ organism (1, bionty.Organism): 'human'
  🏷️ tissues (17, bionty.Tissue): 'blood', 'thoracic lymph node', 'spleen', 'lung', 'mesenteric lymph node', 'lamina propria', 'liver', 'jejunal epithelium', 'omentum', 'bone marrow', ...
  🏷️ cell_types (32, bionty.CellType): '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 (4, bionty.ExperimentalFactor): 'single-cell RNA sequencing', '10x 3' v3', '10x 5' v2', '10x 5' v1'
  🏷️ ulabels (12, core.ULabel): 'D496', '621B', 'A29', 'A36', 'A35', '637C', 'A52', 'A37', 'D503', '640C', ...

file1.view_flow()

file2.describe()

File(uid='viuAb9psg6SVruytRK7P', suffix='.h5ad', accessor='AnnData', description='10x reference adata', size=857752, hash='U4UmKxr_rN8KlwVK4WYKjw', hash_type='md5', visibility=0, key_is_virtual=True, updated_at=2023-10-27 14:09:34)

Provenance:
  🗃️ storage: Storage(uid='u254wjlq', root='/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna', type='local', updated_at=2023-10-27 14:08:02, created_by_id=1)
  📔 transform: Transform(uid='ManDYgmftZ8Cz8', name='Append a new batch of data', short_name='scrna2', version='0', type='notebook', updated_at=2023-10-27 14:09:05, created_by_id=1)
  👣 run: Run(uid='y3ZljwUGmUeTdj2jFLJH', run_at=2023-10-27 14:09:05, transform_id=2, created_by_id=1)
  👤 created_by: User(uid='DzTjkKse', handle='testuser1', name='Test User1', updated_at=2023-10-27 14:08:02)
Features:
  var: FeatureSet(uid='3ew3YYt0kI1BeTlYVQA2', n=754, type='number', registry='bionty.Gene', hash='WMDxN7253SdzGwmznV5d', updated_at=2023-10-27 14:09:34, modality_id=1, created_by_id=1)
    'IL18', 'NPM3', 'S100A9', 'S100A8', 'CNN2', 'ARHGAP45', 'RNF34', 'GPX4', 'S100A6', 'ADISSP', 'S100A4', 'FAM174C', 'SIT1', 'CCDC107', 'RSL1D1', 'TLN1', 'HES4', 'TNFRSF17', 'PCNA', 'RAB13', ...
  obs: FeatureSet(uid='2np8n6GtX3ngtJf1cPgm', n=1, registry='core.Feature', hash='o_VeIetTYgrhSdlswoWg', updated_at=2023-10-27 14:09:34, modality_id=2, created_by_id=1)
    🔗 cell_type (9, bionty.CellType): 'B cell, CD19-positive', 'dendritic cell', 'CD24-positive, CD4 single-positive thymocyte', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'CD16-positive, CD56-dim natural killer cell, human', 'gamma-delta T cell', 'monocyte', 'cytotoxic T cell', 'CD4-positive, alpha-beta T cell'
  external: FeatureSet(uid='hFHf5NbOEs6KqsfilEiu', n=2, registry='core.Feature', hash='m7vr-9W9Irr2iGKqfw8p', updated_at=2023-10-27 14:09:35, modality_id=2, created_by_id=1)
    🔗 assay (1, bionty.ExperimentalFactor): 'single-cell RNA sequencing'
    🔗 organism (1, bionty.Organism): 'human'
Labels:
  🏷️ organism (1, bionty.Organism): 'human'
  🏷️ cell_types (9, bionty.CellType): 'B cell, CD19-positive', 'dendritic cell', 'CD24-positive, CD4 single-positive thymocyte', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'CD16-positive, CD56-dim natural killer cell, human', 'gamma-delta T cell', 'monocyte', 'cytotoxic T cell', 'CD4-positive, alpha-beta T cell'
  🏷️ experimental_factors (1, bionty.ExperimentalFactor): 'single-cell RNA sequencing'

file2.view_flow()

Compare features

Here we compute shared genes without loading files:

file1_genes = file1.features["var"]
file2_genes = file2.features["var"]

shared_genes = file1_genes & file2_genes
len(shared_genes)

749

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

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

Compare cell types

file1_celltypes = file1.cell_types.all()
file2_celltypes = file2.cell_types.all()

shared_celltypes = file1_celltypes & file2_celltypes
shared_celltypes_names = shared_celltypes.list("name")
shared_celltypes_names

['CD16-positive, CD56-dim natural killer cell, human', 'gamma-delta T cell']

Load the individual files

We could either load the files into memory or access them in backed mode through .backed() to lazily load their content from the cloud or the disk.display_markdown

Let’s load them into memory:

adata1 = file1.load()
adata2 = file2.load()

We can now subset the two datasets 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)]