Annotate data#

While data is the primary information or raw facts that are collected and stored, metadata is the supporting information that provides context and meaning to that data.

LaminDB let’s you annotate data with metadata in two ways: features and labels. (Also see tutorial)

This guide extends Quickstart to explain the details of annotating data.

Setup#

Let us create an instance that has lnschema_bionty mounted:

!lamin init --storage ./test-annotate --schema bionty

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

💡 lamindb instance: testuser1/test-annotate

lb.settings.organism = "human"  # globally set organism
lb.settings.auto_save_parents = False  # ignores ontological hierarchy
ln.settings.verbosity = "info"

Register a dataset#

Let’s use the same example data as in the Quickstart:

df = pd.DataFrame(
    {"CD8A": [1, 2, 3], "CD4": [3, 4, 5], "CD14": [5, 6, 7]},
    index=["sample1", "sample2", "sample3"],
)

In addition to the data, we also have two types of metadata as follows:

# observational metadata (1:1 correspondence with samples)
obs_meta = pd.DataFrame(
    {
        "cell_type": ["T cell", "T cell", "Monocyte"],
        "tissue": ["capillary blood", "arterial blood", "capillary blood"],
    },
    index=["sample1", "sample2", "sample3"],
)

# external metadata (describes the entire dataset)
external_meta = {
    "organism": "human",
    "assay": "scRNA-seq",
    "experiment": "EXP0001",
    "project": "PRJ0001",
}

To store both data and observational metadata, we use an AnnData object:

# note that we didn't add external metadata to adata.uns, because we will use LaminDB to store it
adata = ad.AnnData(df, obs=obs_meta)
adata

AnnData object with n_obs × n_vars = 3 × 3
    obs: 'cell_type', 'tissue'

Now let’s register the AnnData object without annotating with any metadata:

ln.track()

dataset = ln.Dataset(adata, name="my RNA-seq")
dataset.save()

We don’t see any metadata in the registered dataset yet:

dataset.describe()

Dataset(uid='4V0LW9MtlWQLkGjgy19A', name='my RNA-seq', hash='jBNzT3fmTNEcfJ19FK2euw', visibility=1, updated_at=2023-12-08 11:34:17 UTC)

Provenance:
  💫 transform: Transform(uid='sU0y1kF3igepz8', name='Annotate data', short_name='annotate', version='0', type=notebook, updated_at=2023-12-08 11:34:17 UTC, created_by_id=1)
  👣 run: Run(uid='EDK6zUUGvSfryV9Ty383', run_at=2023-12-08 11:34:17 UTC, transform_id=1, created_by_id=1)
  📄 file: File(uid='4V0LW9MtlWQLkGjgy19A', suffix='.h5ad', accessor='AnnData', description='See dataset 4V0LW9MtlWQLkGjgy19A', size=21224, hash='jBNzT3fmTNEcfJ19FK2euw', hash_type='md5', visibility=1, key_is_virtual=True, updated_at=2023-12-08 11:34:17 UTC, storage_id=1, transform_id=1, run_id=1, created_by_id=1)
  👤 created_by: User(uid='DzTjkKse', handle='testuser1', name='Test User1', updated_at=2023-12-08 11:34:14 UTC)

Define features and labels#

Features and labels are records from their respective registries.

You can define them schema-less using Feature and ULabel registries, or schema-full using dedicated registries.

Define data features#

Data features refer to individual measurable properties or characteristics of a phenomenon being observed. In data analysis and machine learning, features are the input variables used to predict or classify an outcome.

Data features are often numeric, but can also be categorical. For example, in the case of gene expression data, the features are the expression levels of individual genes. They are often stored as columns in a data table (adata.var_names for AnnData objects).

Here we define them using the Gene registry:

data_features = lb.Gene.from_values(adata.var_names)
ln.save(data_features)
data_features

✅ created 3 Gene records from Bionty matching symbol: 'CD8A', 'CD4', 'CD14'

[Gene(uid='P4lun3ltWYs0', symbol='CD8A', ensembl_gene_id='ENSG00000153563', ncbi_gene_ids='925', biotype='protein_coding', description='CD8 subunit alpha [Source:HGNC Symbol;Acc:HGNC:1706]', synonyms='CD8|P32|CD8ALPHA', updated_at=2023-12-08 11:34:21 UTC, organism_id=1, bionty_source_id=9, created_by_id=1),
 Gene(uid='GL7Rh969kHgO', symbol='CD4', ensembl_gene_id='ENSG00000010610', ncbi_gene_ids='920', biotype='protein_coding', description='CD4 molecule [Source:HGNC Symbol;Acc:HGNC:1678]', synonyms='', updated_at=2023-12-08 11:34:21 UTC, organism_id=1, bionty_source_id=9, created_by_id=1),
 Gene(uid='apu1qTgmYDyi', symbol='CD14', ensembl_gene_id='ENSG00000170458', ncbi_gene_ids='929', biotype='protein_coding', description='CD14 molecule [Source:HGNC Symbol;Acc:HGNC:1628]', synonyms='', updated_at=2023-12-08 11:34:21 UTC, organism_id=1, bionty_source_id=9, created_by_id=1)]

Define metadata features#

Metadata features refer to descriptive or contextual information about the data. They don’t directly describe the content of the data but rather its characteristics.

In this example, the metadata features are “cell_type”, “tissue” that describe observations (stored in adata.obs.columns) and “organism”, “assay”, “experiment” that describe the entire dataset.

Here we define them using the Feature registry:

# obs metadata features
obs_meta_features = ln.Feature.from_df(adata.obs)
ln.save(obs_meta_features)
obs_meta_features

[Feature(uid='7Dp01ydm9P2x', name='cell_type', type='category', updated_at=2023-12-08 11:34:21 UTC, created_by_id=1),
 Feature(uid='ZJCkvCwZgdUd', name='tissue', type='category', updated_at=2023-12-08 11:34:21 UTC, created_by_id=1)]

# external metadata features
external_meta_features = [
    ln.Feature(name=name, type="category") for name in external_meta.keys()
]
ln.save(external_meta_features)
external_meta_features

[Feature(uid='s3i27SReq7jn', name='organism', type='category', updated_at=2023-12-08 11:34:21 UTC, created_by_id=1),
 Feature(uid='Ku8Q4liXttUa', name='assay', type='category', updated_at=2023-12-08 11:34:21 UTC, created_by_id=1),
 Feature(uid='G6zprsmhgaOZ', name='experiment', type='category', updated_at=2023-12-08 11:34:21 UTC, created_by_id=1),
 Feature(uid='Qlld6tbwQE5u', name='project', type='category', updated_at=2023-12-08 11:34:21 UTC, created_by_id=1)]

Define metadata labels#

Metadata labels are the categorical values of metadata features. They are more specific than features and are often used in classification.

In this example, the metadata labels of feature “cell_type” are “T cell” and “Monocyte”; the metadata labels of feature “tissue” are “capillary blood”, “arterial blood”; the metadata labels of feature “organism” is “human”; and so on.

Let’s define them with their respective registries:

cell_types = lb.CellType.from_values(adata.obs["cell_type"])
ln.save(cell_types)
cell_types

✅ created 1 CellType record from Bionty matching name: 'T cell'

✅ created 1 CellType record from Bionty matching synonyms: 'Monocyte'

[CellType(uid='BxNjby0x', name='T cell', ontology_id='CL:0000084', synonyms='T-cell|T-lymphocyte|T lymphocyte', description='A Type Of Lymphocyte Whose Defining Characteristic Is The Expression Of A T Cell Receptor Complex.', updated_at=2023-12-08 11:34:22 UTC, bionty_source_id=21, created_by_id=1),
 CellType(uid='YzV7Qgmj', name='monocyte', ontology_id='CL:0000576', description='Myeloid Mononuclear Recirculating Leukocyte That Can Act As A Precursor Of Tissue Macrophages, Osteoclasts And Some Populations Of Tissue Dendritic Cells.', updated_at=2023-12-08 11:34:22 UTC, bionty_source_id=21, created_by_id=1)]

tissues = lb.Tissue.from_values(adata.obs["tissue"])
ln.save(tissues)
tissues

✅ created 2 Tissue records from Bionty matching name: 'capillary blood', 'arterial blood'

[Tissue(uid='40Y1BZYd', name='capillary blood', ontology_id='UBERON:0013757', synonyms='portion of capillary blood|blood in capillary|portion of blood in capillary', description='A Blood That Is Part Of A Capillary.', updated_at=2023-12-08 11:34:24 UTC, bionty_source_id=25, created_by_id=1),
 Tissue(uid='4qSHAbwT', name='arterial blood', ontology_id='UBERON:0013755', synonyms='portion of arterial blood|arterial blood|blood in artery', description='A Blood That Is Part Of A Artery.', updated_at=2023-12-08 11:34:24 UTC, bionty_source_id=25, created_by_id=1)]

organism = lb.Organism.from_bionty(name=external_meta["organism"])
organism.save()
organism

Organism(uid='EeBGvIYd', name='human', ontology_id='NCBITaxon:9606', scientific_name='homo_sapiens', updated_at=2023-12-08 11:34:24 UTC, bionty_source_id=1, created_by_id=1)

assay = lb.ExperimentalFactor.from_bionty(name=external_meta["assay"])
assay.save()
assay

✅ created 1 ExperimentalFactor record from Bionty matching synonyms: 'scRNA-seq'

ExperimentalFactor(uid='068T1Df6', name='single-cell RNA sequencing', ontology_id='EFO:0008913', synonyms='scRNA-seq|single cell RNA sequencing|single-cell transcriptome sequencing|single-cell RNA-seq', description='A Protocol That Provides The Expression Profiles Of Single Cells Via The Isolation And Barcoding Of Single Cells And Their Rna, Reverse Transcription, Amplification, Library Generation And Sequencing.', molecule='RNA assay', instrument='single cell sequencing', updated_at=2023-12-08 11:34:26 UTC, bionty_source_id=35, created_by_id=1)

experiment = ln.ULabel(name=external_meta["experiment"], description="An experiment")
experiment.save()
experiment

ULabel(uid='zO3AzrKC', name='EXP0001', description='An experiment', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)

project = ln.ULabel(name=external_meta["project"], description="A project")
project.save()
project

ULabel(uid='rz6OXKUv', name='PRJ0001', description='A project', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)

Annotate with features#

Non-external features are annotated when registering datasets using .from_df or .from_anndata methods:

(See the below “Annotate with labels stratified by metadata features” session for adding external features.)

dataset = ln.Dataset.from_anndata(
    adata,
    name="my RNA-seq",
    field=lb.Gene.symbol,  # the registry field to use for the data features
)
dataset.save()

This dataset is now annotated with features:

dataset.describe()

Dataset(uid='4V0LW9MtlWQLkGjgy19A', name='my RNA-seq', hash='jBNzT3fmTNEcfJ19FK2euw', visibility=1, updated_at=2023-12-08 11:34:26 UTC)

Provenance:
  📔 transform: Transform(uid='sU0y1kF3igepz8', name='Annotate data', short_name='annotate', version='0', type='notebook', updated_at=2023-12-08 11:34:17 UTC, created_by_id=1)
  👣 run: Run(uid='EDK6zUUGvSfryV9Ty383', run_at=2023-12-08 11:34:17 UTC, transform_id=1, created_by_id=1)
  📄 file: File(uid='4V0LW9MtlWQLkGjgy19A', suffix='.h5ad', accessor='AnnData', description='See dataset 4V0LW9MtlWQLkGjgy19A', size=21224, hash='jBNzT3fmTNEcfJ19FK2euw', hash_type='md5', visibility=1, key_is_virtual=True, updated_at=2023-12-08 11:34:26 UTC, storage_id=1, transform_id=1, run_id=1, created_by_id=1)
  👤 created_by: User(uid='DzTjkKse', handle='testuser1', name='Test User1', updated_at=2023-12-08 11:34:14 UTC)
Features:
  var: FeatureSet(uid='ldfeFgsaNa4zgKei0y1g', n=3, type='number', registry='bionty.Gene', hash='7wsvCyRhtmkNeD2dpTHg', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    'CD8A', 'CD4', 'CD14'
  obs: FeatureSet(uid='eq9NxlLcTZSdjqTOV42S', n=2, registry='core.Feature', hash='Gneowc4mRTgy6p-nfyfb', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    cell_type (category)
    tissue (category)

You see two types of features are annotated and organized as featuresets by slot:

“var”: data features
“obs”: observational metadata features

dataset.features

Features:
  var: FeatureSet(uid='ldfeFgsaNa4zgKei0y1g', n=3, type='number', registry='bionty.Gene', hash='7wsvCyRhtmkNeD2dpTHg', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    'CD8A', 'CD4', 'CD14'
  obs: FeatureSet(uid='eq9NxlLcTZSdjqTOV42S', n=2, registry='core.Feature', hash='Gneowc4mRTgy6p-nfyfb', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    cell_type (category)
    tissue (category)

Use slots to retrieve corresponding annotated features:

dataset.features["var"].df()

	uid	symbol	stable_id	ensembl_gene_id	ncbi_gene_ids	biotype	description	synonyms	organism_id	bionty_source_id	updated_at	created_by_id
id
1	P4lun3ltWYs0	CD8A	None	ENSG00000153563	925	protein_coding	CD8 subunit alpha [Source:HGNC Symbol;Acc:HGNC...	CD8\|P32\|CD8ALPHA	1	9	2023-12-08 11:34:21.044601+00:00	1
2	GL7Rh969kHgO	CD4	None	ENSG00000010610	920	protein_coding	CD4 molecule [Source:HGNC Symbol;Acc:HGNC:1678]		1	9	2023-12-08 11:34:21.044676+00:00	1
3	apu1qTgmYDyi	CD14	None	ENSG00000170458	929	protein_coding	CD14 molecule [Source:HGNC Symbol;Acc:HGNC:1628]		1	9	2023-12-08 11:34:21.044744+00:00	1

dataset.features["obs"].df()

	uid	name	type	unit	description	registries	synonyms	updated_at	created_by_id
id
1	7Dp01ydm9P2x	cell_type	category	None	None	None	None	2023-12-08 11:34:21.059371+00:00	1
2	ZJCkvCwZgdUd	tissue	category	None	None	None	None	2023-12-08 11:34:21.059432+00:00	1

Annotate with labels#

If you simply want to tag a dataset with some descriptive labels, you can pass them to .labels.add. For example, let’s add the experiment label “EXP0001” and project label “PRJ0001” to the dataset:

dataset.labels.add(experiment)
dataset.labels.add(project)

Now you see the dataset is annotated with ‘EXP0001’, ‘PRJ0001’ labels:

dataset.describe()

Dataset(uid='4V0LW9MtlWQLkGjgy19A', name='my RNA-seq', hash='jBNzT3fmTNEcfJ19FK2euw', visibility=1, updated_at=2023-12-08 11:34:26 UTC)

Provenance:
  📔 transform: Transform(uid='sU0y1kF3igepz8', name='Annotate data', short_name='annotate', version='0', type='notebook', updated_at=2023-12-08 11:34:17 UTC, created_by_id=1)
  👣 run: Run(uid='EDK6zUUGvSfryV9Ty383', run_at=2023-12-08 11:34:17 UTC, transform_id=1, created_by_id=1)
  📄 file: File(uid='4V0LW9MtlWQLkGjgy19A', suffix='.h5ad', accessor='AnnData', description='See dataset 4V0LW9MtlWQLkGjgy19A', size=21224, hash='jBNzT3fmTNEcfJ19FK2euw', hash_type='md5', visibility=1, key_is_virtual=True, updated_at=2023-12-08 11:34:26 UTC, storage_id=1, transform_id=1, run_id=1, created_by_id=1)
  👤 created_by: User(uid='DzTjkKse', handle='testuser1', name='Test User1', updated_at=2023-12-08 11:34:14 UTC)
Features:
  var: FeatureSet(uid='ldfeFgsaNa4zgKei0y1g', n=3, type='number', registry='bionty.Gene', hash='7wsvCyRhtmkNeD2dpTHg', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    'CD8A', 'CD4', 'CD14'
  obs: FeatureSet(uid='eq9NxlLcTZSdjqTOV42S', n=2, registry='core.Feature', hash='Gneowc4mRTgy6p-nfyfb', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    cell_type (category)
    tissue (category)
Labels:
  🏷️ ulabels (2, core.ULabel): 'EXP0001', 'PRJ0001'

To view all annotated labels:

dataset.labels

Labels:
  🏷️ ulabels (2, core.ULabel): 'EXP0001', 'PRJ0001'

Since we didn’t specify which features the labels belongs to, they are accessible only through the default accessor “.ulabels” for ULabel Registry.

You may already notice that it could be difficult to interpret labels without features if they belong to the same registry.

dataset.ulabels.df()

	uid	name	description	reference	reference_type	updated_at	created_by_id
id
1	zO3AzrKC	EXP0001	An experiment	None	None	2023-12-08 11:34:26.139284+00:00	1
2	rz6OXKUv	PRJ0001	A project	None	None	2023-12-08 11:34:26.158474+00:00	1

Annotate with labels stratified by metadata features#

For labels associated with metadata features, you can pass “feature” to .labels.add to stratified them by feature. (Another way to stratify labels is through ontological hierarchy, which is covered in the Quickstart)

Let’s add the experiment label “EXP0001” and project label “PRJ0001” to the dataset again, this time specifying their features:

# an auto-complete object of registered features
features = ln.Feature.lookup()

dataset.labels.add(experiment, feature=features.experiment)
dataset.labels.add(project, feature=features.project)

You now see a 3rd featureset is added to the dataset at slot “external”, and the labels are stratified by two features:

dataset.describe()

Dataset(uid='4V0LW9MtlWQLkGjgy19A', name='my RNA-seq', hash='jBNzT3fmTNEcfJ19FK2euw', visibility=1, updated_at=2023-12-08 11:34:26 UTC)

Provenance:
  📔 transform: Transform(uid='sU0y1kF3igepz8', name='Annotate data', short_name='annotate', version='0', type='notebook', updated_at=2023-12-08 11:34:17 UTC, created_by_id=1)
  👣 run: Run(uid='EDK6zUUGvSfryV9Ty383', run_at=2023-12-08 11:34:17 UTC, transform_id=1, created_by_id=1)
  📄 file: File(uid='4V0LW9MtlWQLkGjgy19A', suffix='.h5ad', accessor='AnnData', description='See dataset 4V0LW9MtlWQLkGjgy19A', size=21224, hash='jBNzT3fmTNEcfJ19FK2euw', hash_type='md5', visibility=1, key_is_virtual=True, updated_at=2023-12-08 11:34:26 UTC, storage_id=1, transform_id=1, run_id=1, created_by_id=1)
  👤 created_by: User(uid='DzTjkKse', handle='testuser1', name='Test User1', updated_at=2023-12-08 11:34:14 UTC)
Features:
  var: FeatureSet(uid='ldfeFgsaNa4zgKei0y1g', n=3, type='number', registry='bionty.Gene', hash='7wsvCyRhtmkNeD2dpTHg', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    'CD8A', 'CD4', 'CD14'
  obs: FeatureSet(uid='eq9NxlLcTZSdjqTOV42S', n=2, registry='core.Feature', hash='Gneowc4mRTgy6p-nfyfb', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    cell_type (category)
    tissue (category)
  external: FeatureSet(uid='OVg4oE93Z7tg2RRnVEBa', n=2, registry='core.Feature', hash='gJcv0-y8HW_LnugAxVQ5', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    🔗 experiment (1, core.ULabel): 'EXP0001'
    🔗 project (1, core.ULabel): 'PRJ0001'
Labels:
  🏷️ ulabels (2, core.ULabel): 'EXP0001', 'PRJ0001'

With feature-stratified labels, you can retrieve labels by feature:

dataset.labels.get(features.experiment).df()

	uid	name	description	reference	reference_type	updated_at	created_by_id
id
1	zO3AzrKC	EXP0001	An experiment	None	None	2023-12-08 11:34:26.139284+00:00	1

Note that adding feature-stratified labels will also allow you to retrieve labels with the default accessor of respective registries:

dataset.labels.add(assay, feature=features.assay)

# access labels directly via default accessor "experimental_factors"
dataset.experimental_factors.df()

	uid	name	ontology_id	abbr	synonyms	description	molecule	instrument	measurement	bionty_source_id	updated_at	created_by_id
id
1	068T1Df6	single-cell RNA sequencing	EFO:0008913	None	scRNA-seq\|single cell RNA sequencing\|single-ce...	A Protocol That Provides The Expression Profil...	RNA assay	single cell sequencing	None	35	2023-12-08 11:34:26.125552+00:00	1

# access labels via feature
dataset.labels.get(features.assay).df()

	uid	name	ontology_id	abbr	synonyms	description	molecule	instrument	measurement	bionty_source_id	updated_at	created_by_id
id
1	068T1Df6	single-cell RNA sequencing	EFO:0008913	None	scRNA-seq\|single cell RNA sequencing\|single-ce...	A Protocol That Provides The Expression Profil...	RNA assay	single cell sequencing	None	35	2023-12-08 11:34:26.125552+00:00	1

Let’s finish the rest annotation of labels:

# labels of obs metadata features
dataset.labels.add(cell_types, feature=features.cell_type)
dataset.labels.add(tissues, feature=features.tissue)

# labels of external metadata features
dataset.labels.add(organism, feature=features.organism)

Now you’ve annotated your dataset with all features and labels:

dataset.describe()

Dataset(uid='4V0LW9MtlWQLkGjgy19A', name='my RNA-seq', hash='jBNzT3fmTNEcfJ19FK2euw', visibility=1, updated_at=2023-12-08 11:34:26 UTC)

Provenance:
  📔 transform: Transform(uid='sU0y1kF3igepz8', name='Annotate data', short_name='annotate', version='0', type='notebook', updated_at=2023-12-08 11:34:17 UTC, created_by_id=1)
  👣 run: Run(uid='EDK6zUUGvSfryV9Ty383', run_at=2023-12-08 11:34:17 UTC, transform_id=1, created_by_id=1)
  📄 file: File(uid='4V0LW9MtlWQLkGjgy19A', suffix='.h5ad', accessor='AnnData', description='See dataset 4V0LW9MtlWQLkGjgy19A', size=21224, hash='jBNzT3fmTNEcfJ19FK2euw', hash_type='md5', visibility=1, key_is_virtual=True, updated_at=2023-12-08 11:34:26 UTC, storage_id=1, transform_id=1, run_id=1, created_by_id=1)
  👤 created_by: User(uid='DzTjkKse', handle='testuser1', name='Test User1', updated_at=2023-12-08 11:34:14 UTC)
Features:
  var: FeatureSet(uid='ldfeFgsaNa4zgKei0y1g', n=3, type='number', registry='bionty.Gene', hash='7wsvCyRhtmkNeD2dpTHg', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    'CD8A', 'CD4', 'CD14'
  obs: FeatureSet(uid='eq9NxlLcTZSdjqTOV42S', n=2, registry='core.Feature', hash='Gneowc4mRTgy6p-nfyfb', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    🔗 cell_type (2, bionty.CellType): 'T cell', 'monocyte'
    🔗 tissue (2, bionty.Tissue): 'capillary blood', 'arterial blood'
  external: FeatureSet(uid='8hIR1rmv5m3nItsMP0Sn', n=4, registry='core.Feature', hash='VRBwfJn0S5m6N-uo_QKR', updated_at=2023-12-08 11:34:26 UTC, created_by_id=1)
    🔗 organism (1, bionty.Organism): 'human'
    🔗 assay (1, bionty.ExperimentalFactor): 'single-cell RNA sequencing'
    🔗 experiment (1, core.ULabel): 'EXP0001'
    🔗 project (1, core.ULabel): 'PRJ0001'
Labels:
  🏷️ organism (1, bionty.Organism): 'human'
  🏷️ tissues (2, bionty.Tissue): 'capillary blood', 'arterial blood'
  🏷️ cell_types (2, bionty.CellType): 'T cell', 'monocyte'
  🏷️ experimental_factors (1, bionty.ExperimentalFactor): 'single-cell RNA sequencing'
  🏷️ ulabels (2, core.ULabel): 'EXP0001', 'PRJ0001'