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 0.56a1)
ln.track()
💡 notebook imports: anndata==0.9.2 lamindb==0.56a1 lnschema_bionty==0.32.0
💡 Transform(id=3, uid='agayZTonayqAz8', name='Query individual files', short_name='scrna3', version='0', type=notebook, updated_at=2023-10-16 21:47:54, created_by_id=1)
💡 Run(id=3, uid='1z1pcGU3opPZ1kawQaj8', run_at=2023-10-16 21:47:54, transform_id=3, created_by_id=1)
Access 
#
Query files by provenance metadata#
users = ln.User.lookup()
ln.Transform.filter(created_by=users.testuser1).search("scrna")
| id | __ratio__ | |
|---|---|---|
| name | ||
| scRNA-seq | 1 | 90.0 |
| Append a new batch of data | 2 | 36.0 |
| Query individual files | 3 | 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 | updated_at | created_by_id | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| id | |||||||||||||||
| 1 | MpmFBPjOegAuuyRzbGAq | 1 | None | .h5ad | AnnData | Conde22 | None | 57615999 | 6Hu1BywwK6bfIU2Dpku2xZ | sha1-fl | 1 | 1 | None | 2023-10-16 21:47:05 | 1 |
Query files based on biological metadata#
assays = lb.ExperimentalFactor.lookup()
species = lb.Species.lookup()
cell_types = lb.CellType.lookup()
query = ln.File.filter(
experimental_factors=assays.single_cell_rna_sequencing,
species=species.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 | updated_at | created_by_id | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| id | |||||||||||||||
| 1 | MpmFBPjOegAuuyRzbGAq | 1 | None | .h5ad | AnnData | Conde22 | None | 57615999 | 6Hu1BywwK6bfIU2Dpku2xZ | sha1-fl | 1 | 1 | None | 2023-10-16 21:47:05 | 1 |
Transform 
#
Compare gene sets#
Get file objects:
query = ln.File.filter()
file1, file2 = query.list()
file1.describe()
File(id=1, uid='MpmFBPjOegAuuyRzbGAq', suffix='.h5ad', accessor='AnnData', description='Conde22', size=57615999, hash='6Hu1BywwK6bfIU2Dpku2xZ', hash_type='sha1-fl', updated_at=2023-10-16 21:47:05)
Provenance:
🗃️ storage: Storage(id=1, uid='bEvhinvc', root='/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna', type='local', updated_at=2023-10-16 21:45:55, created_by_id=1)
📔 transform: Transform(id=1, uid='Nv48yAceNSh8z8', name='scRNA-seq', short_name='scrna', version='0', type='notebook', updated_at=2023-10-16 21:46:01, created_by_id=1)
👣 run: Run(id=1, uid='Tcf2JasApz9P8RE7gqna', run_at=2023-10-16 21:46:01, transform_id=1, created_by_id=1)
👤 created_by: User(id=1, uid='DzTjkKse', handle='testuser1', email='testuser1@lamin.ai', name='Test User1', updated_at=2023-10-16 21:45:55)
⬇️ input_of (core.Run): ['2023-10-16 21:47:14']
Features:
var: FeatureSet(id=1, uid='ISCdUu2vePwTzsv99UmG', n=36503, type='number', registry='bionty.Gene', hash='dnRexHCtxtmOU81_EpoJ', updated_at=2023-10-16 21:46:57, 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(id=2, uid='AeMRCgTDsUFRNwXFlqD9', n=4, registry='core.Feature', hash='xPTyeKYm-_4RH5MEI97t', updated_at=2023-10-16 21:46:58, 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:
🏷️ species (1, bionty.Species): '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(id=2, uid='qscOv2TpO4PaevwVlwRs', suffix='.h5ad', accessor='AnnData', description='10x reference adata', size=857752, hash='j6o6e27xPdqHQyT7Em_7MQ', hash_type='md5', updated_at=2023-10-16 21:47:42)
Provenance:
🗃️ storage: Storage(id=1, uid='bEvhinvc', root='/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna', type='local', updated_at=2023-10-16 21:45:55, created_by_id=1)
📔 transform: Transform(id=2, uid='ManDYgmftZ8Cz8', name='Append a new batch of data', short_name='scrna2', version='0', type='notebook', updated_at=2023-10-16 21:47:14, created_by_id=1)
👣 run: Run(id=2, uid='xkYC1M6aAdWdAwNLWCmV', run_at=2023-10-16 21:47:14, transform_id=2, created_by_id=1)
👤 created_by: User(id=1, uid='DzTjkKse', handle='testuser1', email='testuser1@lamin.ai', name='Test User1', updated_at=2023-10-16 21:45:55)
Features:
var: FeatureSet(id=4, uid='tPDeC1XYr2fGU3UipJot', n=754, type='number', registry='bionty.Gene', hash='WMDxN7253SdzGwmznV5d', updated_at=2023-10-16 21:47:42, 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(id=5, uid='6AEOiT1l8HTdqkAVleqZ', n=1, registry='core.Feature', hash='PFicj8Uq94k6vPsRmJvl', updated_at=2023-10-16 21:47:42, modality_id=2, created_by_id=1)
🔗 cell_type (9, bionty.CellType): 'B cell, CD19-positive', 'dendritic cell', 'central memory CD8-positive, alpha-beta T cell', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'CD8-positive, alpha-beta memory T cell', 'CD16-positive, CD56-dim natural killer cell, human', 'Cd4-negative, CD8_alpha-negative, CD11b-positive dendritic cell', 'monocyte', 'mature T cell'
external: FeatureSet(id=6, uid='unwxLOfuEVBcpuW10Uhu', n=2, registry='core.Feature', hash='m_3u0np1BS5T5HSnawJY', updated_at=2023-10-16 21:47:42, modality_id=2, created_by_id=1)
🔗 assay (1, bionty.ExperimentalFactor): 'single-cell RNA sequencing'
🔗 species (1, bionty.Species): 'human'
Labels:
🏷️ species (1, bionty.Species): 'human'
🏷️ cell_types (9, bionty.CellType): 'B cell, CD19-positive', 'dendritic cell', 'central memory CD8-positive, alpha-beta T cell', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'CD8-positive, alpha-beta memory T cell', 'CD16-positive, CD56-dim natural killer cell, human', 'Cd4-negative, CD8_alpha-negative, CD11b-positive dendritic cell', 'monocyte', 'mature T cell'
🏷️ experimental_factors (1, bionty.ExperimentalFactor): 'single-cell RNA sequencing'
file2.view_flow()
Load files into memory:
file1_adata = file1.load()
file2_adata = file2.load()
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
['CD8-positive, alpha-beta memory T cell',
'CD16-positive, CD56-dim natural killer cell, human']
We can now subset the two datasets by shared cell types:
file1_adata_subset = file1_adata[
file1_adata.obs["cell_type"].isin(shared_celltypes_names)
]
file2_adata_subset = file2_adata[
file2_adata.obs["cell_type"].isin(shared_celltypes_names)
]
Concatenate subsetted datasets:
adata_concat = ad.concat(
[file1_adata_subset, file2_adata_subset],
label="file",
keys=[file1.description, file2.description],
)
adata_concat
AnnData object with n_obs × n_vars = 244 × 749
obs: 'cell_type', 'file'
obsm: 'X_umap'
adata_concat.obs.value_counts()
cell_type file
CD8-positive, alpha-beta memory T cell Conde22 120
CD16-positive, CD56-dim natural killer cell, human Conde22 114
CD8-positive, alpha-beta memory T cell 10x reference adata 7
CD16-positive, CD56-dim natural killer cell, human 10x reference adata 3
dtype: int64