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 0.54.4)
ln.track()
💡 notebook imports: anndata==0.9.2 lamindb==0.54.4 lnschema_bionty==0.31.2
💡 Transform(id='agayZTonayqAz8', name='Query individual files', short_name='scrna2', version='0', type=notebook, updated_at=2023-10-01 16:43:24, created_by_id='DzTjkKse')
💡 Run(id='dMp7djqemZGyTyWkYRse', run_at=2023-10-01 16:43:24, transform_id='agayZTonayqAz8', created_by_id='DzTjkKse')
Access 
#
Query files by provenance metadata#
users = ln.User.lookup()
ln.Transform.filter(created_by=users.testuser1).search("scrna")
| id | __ratio__ | |
|---|---|---|
| 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(id="Nv48yAceNSh8z8").one()
ln.File.filter(transform=transform).df()
| storage_id | key | suffix | accessor | description | version | size | hash | hash_type | transform_id | run_id | initial_version_id | updated_at | created_by_id | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| id | ||||||||||||||
| vAk7VTi8De3y0rT7H8u9 | mw7lxLgT | None | .h5ad | AnnData | Conde22 | None | 28049505 | WEFcMZxJNmMiUOFrcSTaig | md5 | Nv48yAceNSh8z8 | QbgMTXxxJxPHD0ovcimm | None | 2023-10-01 16:42:46 | DzTjkKse |
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()
| storage_id | key | suffix | accessor | description | version | size | hash | hash_type | transform_id | run_id | initial_version_id | updated_at | created_by_id | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| id | ||||||||||||||
| tKBg5wZP51aKaLiPXbGK | mw7lxLgT | None | .h5ad | AnnData | 10x reference adata | None | 660792 | a2V0IgOjMRHsCeZH169UOQ | md5 | ManDYgmftZ8Cz8 | k9J7cQZqsnA5sK7oIO1S | None | 2023-10-01 16:43:12 | DzTjkKse |
| vAk7VTi8De3y0rT7H8u9 | mw7lxLgT | None | .h5ad | AnnData | Conde22 | None | 28049505 | WEFcMZxJNmMiUOFrcSTaig | md5 | Nv48yAceNSh8z8 | QbgMTXxxJxPHD0ovcimm | None | 2023-10-01 16:42:46 | DzTjkKse |
Transform 
#
Compare gene sets#
Get file objects:
query = ln.File.filter()
file1, file2 = query.list()
file1.describe()
File(id='vAk7VTi8De3y0rT7H8u9', suffix='.h5ad', accessor='AnnData', description='Conde22', size=28049505, hash='WEFcMZxJNmMiUOFrcSTaig', hash_type='md5', updated_at=2023-10-01 16:42:46)
Provenance:
🗃️ storage: Storage(id='mw7lxLgT', root='/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna', type='local', updated_at=2023-10-01 16:42:00, created_by_id='DzTjkKse')
📔 transform: Transform(id='Nv48yAceNSh8z8', name='scRNA-seq', short_name='scrna', version='0', type='notebook', updated_at=2023-10-01 16:42:46, created_by_id='DzTjkKse')
👣 run: Run(id='QbgMTXxxJxPHD0ovcimm', run_at=2023-10-01 16:42:05, transform_id='Nv48yAceNSh8z8', created_by_id='DzTjkKse')
👤 created_by: User(id='DzTjkKse', handle='testuser1', email='testuser1@lamin.ai', name='Test User1', updated_at=2023-10-01 16:42:00)
⬇️ input_of (core.Run): ['2023-10-01 16:42:52']
Features:
var: FeatureSet(id='NbpG08k5MyhtFXpSVTO8', n=36503, type='number', registry='bionty.Gene', hash='dnRexHCtxtmOU81_EpoJ', updated_at=2023-10-01 16:42:37, modality_id='ea9UjVtc', created_by_id='DzTjkKse')
'FILIP1', 'PTGES3L', 'PIGA', 'PSKH1', 'TONSL-AS1', 'None', 'None', 'None', 'IGLV2-8', 'FOXN3', 'None', 'None', 'None', 'LINC03007', 'ASTN1', 'RASSF5', 'TMEM220-AS1', 'LMO7DN', 'None', 'None', ...
obs: FeatureSet(id='eqbPhBQrbb7AoBWu5XY8', n=4, registry='core.Feature', hash='BUgwklP7zIs3Qx8yNIJ1', updated_at=2023-10-01 16:42:41, modality_id='FqWJG3xl', created_by_id='DzTjkKse')
🔗 assay (4, bionty.ExperimentalFactor): 'single-cell RNA sequencing', '10x 5' v1', '10x 3' v3', '10x 5' v2'
🔗 donor (12, core.ULabel): '582C', 'A52', 'A37', 'D496', '640C', '621B', 'A29', 'A35', 'A36', '637C', ...
🔗 tissue (17, bionty.Tissue): 'thoracic lymph node', 'lung', 'duodenum', 'bone marrow', 'blood', 'omentum', 'transverse colon', 'caecum', 'mesenteric lymph node', 'lamina propria', ...
🔗 cell_type (32, bionty.CellType): 'alpha-beta T cell', 'alveolar macrophage', 'macrophage', 'progenitor cell', 'CD4-positive helper T cell', 'lymphocyte', 'effector memory CD4-positive, alpha-beta T cell', 'plasmacytoid dendritic cell', 'CD16-negative, CD56-bright natural killer cell, human', 'classical monocyte', ...
Labels:
🏷️ species (1, bionty.Species): 'human'
🏷️ tissues (17, bionty.Tissue): 'thoracic lymph node', 'lung', 'duodenum', 'bone marrow', 'blood', 'omentum', 'transverse colon', 'caecum', 'mesenteric lymph node', 'lamina propria', ...
🏷️ cell_types (32, bionty.CellType): 'alpha-beta T cell', 'alveolar macrophage', 'macrophage', 'progenitor cell', 'CD4-positive helper T cell', 'lymphocyte', 'effector memory CD4-positive, alpha-beta T cell', 'plasmacytoid dendritic cell', 'CD16-negative, CD56-bright natural killer cell, human', 'classical monocyte', ...
🏷️ experimental_factors (4, bionty.ExperimentalFactor): 'single-cell RNA sequencing', '10x 5' v1', '10x 3' v3', '10x 5' v2'
🏷️ ulabels (12, core.ULabel): '582C', 'A52', 'A37', 'D496', '640C', '621B', 'A29', 'A35', 'A36', '637C', ...
file1.view_flow()
file2.describe()
File(id='tKBg5wZP51aKaLiPXbGK', suffix='.h5ad', accessor='AnnData', description='10x reference adata', size=660792, hash='a2V0IgOjMRHsCeZH169UOQ', hash_type='md5', updated_at=2023-10-01 16:43:12)
Provenance:
🗃️ storage: Storage(id='mw7lxLgT', root='/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna', type='local', updated_at=2023-10-01 16:42:00, created_by_id='DzTjkKse')
📔 transform: Transform(id='ManDYgmftZ8Cz8', name='Append a new batch of data', short_name='scrna1', version='0', type='notebook', updated_at=2023-10-01 16:43:13, created_by_id='DzTjkKse')
👣 run: Run(id='k9J7cQZqsnA5sK7oIO1S', run_at=2023-10-01 16:42:52, transform_id='ManDYgmftZ8Cz8', created_by_id='DzTjkKse')
👤 created_by: User(id='DzTjkKse', handle='testuser1', email='testuser1@lamin.ai', name='Test User1', updated_at=2023-10-01 16:42:00)
Features:
var: FeatureSet(id='2wFhGDUjuAeoU8jTR3XH', n=754, type='number', registry='bionty.Gene', hash='WMDxN7253SdzGwmznV5d', updated_at=2023-10-01 16:43:12, modality_id='ea9UjVtc', created_by_id='DzTjkKse')
'NSUN6', 'S100A6', 'LAG3', 'EIF2AK1', 'DHRS4L2', 'LSM5', 'G0S2', 'CCDC107', 'PSMD7', 'HNRNPF', 'EIF3G', 'PSMC5', 'HLA-DMA', 'MFSD14B', 'OSBPL8', 'CD63', 'DHRS7', 'PNN', 'MRPS33', 'LYPD2', ...
obs: FeatureSet(id='jugdraH3kleI6wzGVAaT', n=1, registry='core.Feature', hash='QFilx9ah7bacDSHBYJOD', updated_at=2023-10-01 16:43:12, modality_id='FqWJG3xl', created_by_id='DzTjkKse')
🔗 cell_type (9, bionty.CellType): 'CD24-positive, CD4 single-positive thymocyte', 'B cell, CD19-positive', 'CD16-positive, CD56-dim natural killer cell, human', 'monocyte', 'gamma-delta T cell', 'cytotoxic T cell', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'dendritic cell', 'CD4-positive, alpha-beta T cell'
external: FeatureSet(id='P1bXXRGZjslUlZiURh3N', n=2, registry='core.Feature', hash='pzAiye3Tiav8qFggirus', updated_at=2023-10-01 16:43:12, modality_id='FqWJG3xl', created_by_id='DzTjkKse')
🔗 species (1, bionty.Species): 'human'
🔗 assay (1, bionty.ExperimentalFactor): 'single-cell RNA sequencing'
Labels:
🏷️ species (1, bionty.Species): 'human'
🏷️ cell_types (9, bionty.CellType): 'CD24-positive, CD4 single-positive thymocyte', 'B cell, CD19-positive', 'CD16-positive, CD56-dim natural killer cell, human', 'monocyte', 'gamma-delta T cell', 'cytotoxic T cell', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'dendritic cell', 'CD4-positive, alpha-beta 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]
['RCSD1',
'SLTM',
'MTCH2',
'ITM2A',
'STUB1',
'ILF3-DT',
'SNX2',
'TOMM7',
'ZNF106',
'TXN']
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']
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 = 187 × 749
obs: 'cell_type', 'file'
obsm: 'X_umap'
adata_concat.obs.value_counts()
cell_type file
CD16-positive, CD56-dim natural killer cell, human Conde22 114
gamma-delta T cell Conde22 66
10x reference adata 4
CD16-positive, CD56-dim natural killer cell, human 10x reference adata 3
dtype: int64