Query using tiledbsoma

The first guide queried metadata and h5ad artifacts directly through LaminDB.

This guide uses the TileDB-SOMA API to run similar queries.

Setup

Load your LaminDB instance for quering data:

!lamin load laminlabs/cellxgene

💡 connected lamindb: laminlabs/cellxgene

import lamindb as ln
import bionty as bt
import tiledbsoma

census_version = "2024-07-01"

💡 connected lamindb: laminlabs/cellxgene

Create lookup objects

We use metadata records in the laminlabs/cellxgene instance to generate lookups:

human = "homo_sapiens"

features = ln.Feature.lookup(return_field="name")
assays = bt.ExperimentalFactor.lookup(return_field="name")
cell_types = bt.CellType.lookup(return_field="name")
tissues = bt.Tissue.lookup(return_field="name")
ulabels = ln.ULabel.lookup()
suspension_types = ulabels.is_suspension_type.children.all().lookup(return_field="name")

Query data

value_filter = (
    f'{features.tissue} == "{tissues.brain}" and {features.cell_type} in'
    f' ["{cell_types.microglial_cell}", "{cell_types.neuron}"] and'
    f' {features.suspension_type} == "{suspension_types.cell}" and {features.assay} =='
    f' "{assays.ln_10x_3_v3}"'
)

value_filter

'tissue == "brain" and cell_type in ["microglial cell", "neuron"] and suspension_type == "cell" and assay == "10x 3\' v3"'

census_artifact = ln.Artifact.filter(description="Census "+census_version).one()

with census_artifact.open() as census:
    # Reads SOMADataFrame as a slice
    cell_metadata = census["census_data"][human].obs.read(value_filter=value_filter)

    # Concatenates results to pyarrow.Table
    cell_metadata = cell_metadata.concat()

    # Converts to pandas.DataFrame
    cell_metadata = cell_metadata.to_pandas()

cell_metadata.shape

(66418, 28)

cell_metadata.head()

	soma_joinid	dataset_id	assay	assay_ontology_term_id	cell_type	cell_type_ontology_term_id	development_stage	development_stage_ontology_term_id	disease	disease_ontology_term_id	...	tissue	tissue_ontology_term_id	tissue_type	tissue_general	tissue_general_ontology_term_id	raw_sum	nnz	raw_mean_nnz	raw_variance_nnz	n_measured_vars
0	48182177	c888b684-6c51-431f-972a-6c963044cef0	10x 3' v3	EFO:0009922	microglial cell	CL:0000129	68-year-old human stage	HsapDv:0000162	glioblastoma	MONDO:0018177	...	brain	UBERON:0000955	tissue	brain	UBERON:0000955	15204.0	3959	3.840364	209.374207	27229
1	48182178	c888b684-6c51-431f-972a-6c963044cef0	10x 3' v3	EFO:0009922	microglial cell	CL:0000129	68-year-old human stage	HsapDv:0000162	glioblastoma	MONDO:0018177	...	brain	UBERON:0000955	tissue	brain	UBERON:0000955	39230.0	5885	6.666100	875.502870	27229
2	48182185	c888b684-6c51-431f-972a-6c963044cef0	10x 3' v3	EFO:0009922	microglial cell	CL:0000129	68-year-old human stage	HsapDv:0000162	glioblastoma	MONDO:0018177	...	brain	UBERON:0000955	tissue	brain	UBERON:0000955	9576.0	2738	3.497443	121.333753	27229
3	48182187	c888b684-6c51-431f-972a-6c963044cef0	10x 3' v3	EFO:0009922	microglial cell	CL:0000129	68-year-old human stage	HsapDv:0000162	glioblastoma	MONDO:0018177	...	brain	UBERON:0000955	tissue	brain	UBERON:0000955	19374.0	4096	4.729980	464.331956	27229
4	48182188	c888b684-6c51-431f-972a-6c963044cef0	10x 3' v3	EFO:0009922	microglial cell	CL:0000129	68-year-old human stage	HsapDv:0000162	glioblastoma	MONDO:0018177	...	brain	UBERON:0000955	tissue	brain	UBERON:0000955	8466.0	2477	3.417844	162.555950	27229

5 rows × 28 columns

Create AnnData

with census_artifact.open() as census:
    
    experiment = census["census_data"][human]
    
    adata = experiment.axis_query(
        "RNA",
        obs_query=tiledbsoma.AxisQuery(value_filter=value_filter)
    ).to_anndata(
        X_name="raw",
        column_names={
            "obs": [
                features.assay,
                features.cell_type,
                features.tissue,
                features.disease,
                features.suspension_type,
            ]
        }
    )

adata.var = adata.var.set_index("feature_id")

adata

AnnData object with n_obs × n_vars = 66418 × 60530
    obs: 'assay', 'cell_type', 'tissue', 'disease', 'suspension_type'
    var: 'soma_joinid', 'feature_name', 'feature_length', 'nnz', 'n_measured_obs'

adata.var.head()

	soma_joinid	feature_name	feature_length	nnz	n_measured_obs
feature_id
ENSG00000000003	0	TSPAN6	4530	4530448	73855064
ENSG00000000005	1	TNMD	1476	236059	61201828
ENSG00000000419	2	DPM1	9276	17576462	74159149
ENSG00000000457	3	SCYL3	6883	9117322	73988868
ENSG00000000460	4	C1orf112	5970	6287794	73636201

adata.obs.head()

	assay	cell_type	tissue	disease	suspension_type
0	10x 3' v3	microglial cell	brain	glioblastoma	cell
1	10x 3' v3	microglial cell	brain	glioblastoma	cell
2	10x 3' v3	microglial cell	brain	glioblastoma	cell
3	10x 3' v3	microglial cell	brain	glioblastoma	cell
4	10x 3' v3	microglial cell	brain	glioblastoma	cell