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=2023-10-02 10:19:49, created_by_id='DzTjkKse')
💡 Run(id='j9Njg6IoNhlhnpu6Y4am', run_at=2023-10-02 10:19:49, 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 | ||||||||||||||
| p563WE4VtMIf6FQfXJmN | 7ZVN6khD | None | .h5ad | AnnData | Conde22 | None | 28049505 | WEFcMZxJNmMiUOFrcSTaig | md5 | Nv48yAceNSh8z8 | zfuVcVfil2w5LqYdHn2K | None | 2023-10-02 10:18:54 | 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 | ||||||||||||||
| be3FZ3wa9dpwAGDafjLI | 7ZVN6khD | None | .h5ad | AnnData | 10x reference adata | None | 660792 | a2V0IgOjMRHsCeZH169UOQ | md5 | ManDYgmftZ8Cz8 | BJevtAUNru8jYr9cO093 | None | 2023-10-02 10:19:35 | DzTjkKse |
| p563WE4VtMIf6FQfXJmN | 7ZVN6khD | None | .h5ad | AnnData | Conde22 | None | 28049505 | WEFcMZxJNmMiUOFrcSTaig | md5 | Nv48yAceNSh8z8 | zfuVcVfil2w5LqYdHn2K | None | 2023-10-02 10:18:54 | DzTjkKse |
Transform 
#
Compare gene sets#
Get file objects:
query = ln.File.filter()
file1, file2 = query.list()
file1.describe()
File(id='p563WE4VtMIf6FQfXJmN', suffix='.h5ad', accessor='AnnData', description='Conde22', size=28049505, hash='WEFcMZxJNmMiUOFrcSTaig', hash_type='md5', updated_at=2023-10-02 10:18:54)
Provenance:
🗃️ storage: Storage(id='7ZVN6khD', root='/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna', type='local', updated_at=2023-10-02 10:18:00, created_by_id='DzTjkKse')
📔 transform: Transform(id='Nv48yAceNSh8z8', name='scRNA-seq', short_name='scrna', version='0', type='notebook', updated_at=2023-10-02 10:18:54, created_by_id='DzTjkKse')
👣 run: Run(id='zfuVcVfil2w5LqYdHn2K', run_at=2023-10-02 10:18:06, transform_id='Nv48yAceNSh8z8', created_by_id='DzTjkKse')
👤 created_by: User(id='DzTjkKse', handle='testuser1', email='testuser1@lamin.ai', name='Test User1', updated_at=2023-10-02 10:18:00)
⬇️ input_of (core.Run): ['2023-10-02 10:19:02']
Features:
var: FeatureSet(id='bDDl0r5yF0f3NAADRbV1', n=36503, type='number', registry='bionty.Gene', hash='dnRexHCtxtmOU81_EpoJ', updated_at=2023-10-02 10:18:44, modality_id='Z4a7WYsI', created_by_id='DzTjkKse')
'CAPN2', 'RAD1', 'None', 'ENOX2', 'None', 'None', 'None', 'UQCR11', 'None', 'None', 'LINC02719', 'ABCD4', 'GASK1A', 'None', 'IGHV3OR16-8', 'None', 'None', 'None', 'NUP133', 'RIN1', ...
obs: FeatureSet(id='rDCwyTehbqggk8V1Jxey', n=4, registry='core.Feature', hash='s4COhCi1Xv9Ks3BjuSO9', updated_at=2023-10-02 10:18:48, modality_id='9FuQHsY3', created_by_id='DzTjkKse')
🔗 donor (12, core.ULabel): 'A37', 'A31', 'A36', 'A29', '637C', 'D503', '640C', 'D496', '621B', '582C', ...
🔗 cell_type (32, bionty.CellType): 'animal cell', 'mast cell', 'group 3 innate lymphoid cell', 'plasma cell', 'plasmablast', 'memory B cell', 'naive thymus-derived CD4-positive, alpha-beta T cell', 'megakaryocyte', 'macrophage', 'regulatory T cell', ...
🔗 assay (4, bionty.ExperimentalFactor): 'single-cell RNA sequencing', '10x 5' v1', '10x 3' v3', '10x 5' v2'
🔗 tissue (17, bionty.Tissue): 'thymus', 'ileum', 'duodenum', 'spleen', 'transverse colon', 'jejunal epithelium', 'lamina propria', 'mesenteric lymph node', 'bone marrow', 'thoracic lymph node', ...
Labels:
🏷️ species (1, bionty.Species): 'human'
🏷️ tissues (17, bionty.Tissue): 'thymus', 'ileum', 'duodenum', 'spleen', 'transverse colon', 'jejunal epithelium', 'lamina propria', 'mesenteric lymph node', 'bone marrow', 'thoracic lymph node', ...
🏷️ cell_types (32, bionty.CellType): 'animal cell', 'mast cell', 'group 3 innate lymphoid cell', 'plasma cell', 'plasmablast', 'memory B cell', 'naive thymus-derived CD4-positive, alpha-beta T cell', 'megakaryocyte', 'macrophage', 'regulatory T cell', ...
🏷️ experimental_factors (4, bionty.ExperimentalFactor): 'single-cell RNA sequencing', '10x 5' v1', '10x 3' v3', '10x 5' v2'
🏷️ ulabels (12, core.ULabel): 'A37', 'A31', 'A36', 'A29', '637C', 'D503', '640C', 'D496', '621B', '582C', ...
file1.view_flow()
file2.describe()
File(id='be3FZ3wa9dpwAGDafjLI', suffix='.h5ad', accessor='AnnData', description='10x reference adata', size=660792, hash='a2V0IgOjMRHsCeZH169UOQ', hash_type='md5', updated_at=2023-10-02 10:19:35)
Provenance:
🗃️ storage: Storage(id='7ZVN6khD', root='/home/runner/work/lamin-usecases/lamin-usecases/docs/test-scrna', type='local', updated_at=2023-10-02 10:18:00, created_by_id='DzTjkKse')
📔 transform: Transform(id='ManDYgmftZ8Cz8', name='Append a new batch of data', short_name='scrna1', version='0', type='notebook', updated_at=2023-10-02 10:19:37, created_by_id='DzTjkKse')
👣 run: Run(id='BJevtAUNru8jYr9cO093', run_at=2023-10-02 10:19:02, transform_id='ManDYgmftZ8Cz8', created_by_id='DzTjkKse')
👤 created_by: User(id='DzTjkKse', handle='testuser1', email='testuser1@lamin.ai', name='Test User1', updated_at=2023-10-02 10:18:00)
Features:
var: FeatureSet(id='JH4lHm0bKOjJwld8gvuS', n=754, type='number', registry='bionty.Gene', hash='WMDxN7253SdzGwmznV5d', updated_at=2023-10-02 10:19:35, modality_id='Z4a7WYsI', created_by_id='DzTjkKse')
'PTPRC', 'COX17', 'HIGD2A', 'LINC01857', 'MRPS6', 'GZMH', 'TPD52', 'TMEM256', 'SNX2', 'CCT8', 'TBC1D10C', 'FCN1', 'MATK', 'PRDX6', 'APEX1', 'TINF2', 'HSD17B8', 'DEK', 'NCL', 'GZMK', ...
obs: FeatureSet(id='iJO8vTcbKF2WmUE5abJn', n=1, registry='core.Feature', hash='N2S5inpQSO0LupVR9d63', updated_at=2023-10-02 10:19:35, modality_id='9FuQHsY3', created_by_id='DzTjkKse')
🔗 cell_type (9, bionty.CellType): 'dendritic cell', 'B cell, CD19-positive', 'cytotoxic T cell', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'monocyte', 'CD4-positive, alpha-beta T cell', 'CD16-positive, CD56-dim natural killer cell, human', 'gamma-delta T cell', 'CD24-positive, CD4 single-positive thymocyte'
external: FeatureSet(id='Tb1kUtpJdIBsnA90OVZ7', n=2, registry='core.Feature', hash='K0Hptsob4fESZu-GTvkj', updated_at=2023-10-02 10:19:35, modality_id='9FuQHsY3', created_by_id='DzTjkKse')
🔗 assay (1, bionty.ExperimentalFactor): 'single-cell RNA sequencing'
🔗 species (1, bionty.Species): 'human'
Labels:
🏷️ species (1, bionty.Species): 'human'
🏷️ cell_types (9, bionty.CellType): 'dendritic cell', 'B cell, CD19-positive', 'cytotoxic T cell', 'CD8-positive, CD25-positive, alpha-beta regulatory T cell', 'monocyte', 'CD4-positive, alpha-beta T cell', 'CD16-positive, CD56-dim natural killer cell, human', 'gamma-delta T cell', 'CD24-positive, CD4 single-positive thymocyte'
🏷️ 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]
['CAPN2',
'NDUFAF3',
'PRKCQ-AS1',
'PNISR',
'CFD',
'CWC25',
'LCK',
'LIMS1',
'NSA2',
'EBPL']
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