Tutorial

LaminDB provides a framework to transform datasets into more useful representations: validated & queryable datasets, machine learning models, and analytical insights. The transformations can be notebooks, scripts, pipelines, or functions.

The metadata involved in this process are stored in a LaminDB instance, a database that manages datasets in storage. For the following walk through LaminDB’s core features, we’ll be working with a local instance.

Track a notebook or script

Py

lamin init --storage ./lamin-tutorial --modules bionty

R

library(laminr)
lc <- import_module("lamin_cli")
lc$init(storage = "./lamin-tutorial", modules = "bionty")

Show code cell content Hide code cell content

!lamin init --storage ./lamindb-tutorial --modules bionty

→ initialized lamindb: anonymous/lamindb-tutorial

What else can I configure during setup?

1. You can pass a cloud storage location to --storage (S3, GCP, R2, HF, etc.)

   --storage s3://my-bucket
   

2. Instead of the default SQLite database pass a Postgres connection string to --db:

   --db postgresql://<user>:<pwd>@<hostname>:<port>/<dbname>
   

3. Instead of a default instance name derived from the storage location, provide a custom name:

   --name my-name
   

4. Mount additional schema modules:

   --modules bionty,wetlab,custom1
   

For more info, see Install & setup.

If you decide to connect your instance to the hub, you will see data & metadata in a UI.

Let’s now track the notebook that’s being run.

Py

import lamindb as ln

ln.track()  # track the current notebook or script

R

library(laminr)
ln <- import_module("lamindb")  # instantiate the central `ln` object of the API

ln$track()  # track a run of your notebook or script

Show code cell content Hide code cell content

import lamindb as ln

ln.track()  # track the current notebook or script

→ connected lamindb: anonymous/lamindb-tutorial

→ created Transform('Dlyds3zetI5b0000', key='tutorial.ipynb'), started new Run('0NDdAcEdCctSdsGn') at 2025-11-14 11:41:57 UTC

→ notebook imports: anndata==0.12.5 bionty==1.9.1 lamindb==1.16.2

• recommendation: to identify the notebook across renames, pass the uid: ln.track("Dlyds3zetI5b")

By calling track(), the notebook gets automatically linked as the source of all data that’s about to be saved! You can see all your transforms and their runs in the Transform and Run registries.

Py

ln.Transform.to_dataframe()

R

ln$Transform$df()

Show code cell content Hide code cell content

ln.Transform.to_dataframe()

	uid	key	description	type	source_code	hash	reference	reference_type	version	is_latest	is_locked	created_at	branch_id	space_id	created_by_id	_template_id
id
1	Dlyds3zetI5b0000	tutorial.ipynb	Tutorial	notebook	None	None	None	None	None	True	False	2025-11-14 11:41:57.785000+00:00	1	1	1	None

Py

ln.Run.to_dataframe()

R

ln$Run$df()

Show code cell content Hide code cell content

ln.Run.to_dataframe()

	uid	name	started_at	finished_at	params	reference	reference_type	is_locked	created_at	branch_id	space_id	transform_id	report_id	_logfile_id	environment_id	created_by_id	initiated_by_run_id
id
1	0NDdAcEdCctSdsGn	None	2025-11-14 11:41:57.789857+00:00	None	None	None	None	False	2025-11-14 11:41:57.790000+00:00	1	1	1	None	None	None	1	None

What happened under the hood?

1. The full run environment and imported package versions of current notebook were detected

2. Notebook metadata was detected and stored in a Transform record with a unique id

3. Run metadata was detected and stored in a Run record with a unique id

The Transform registry stores data transformations: scripts, notebooks, pipelines, functions.

The Run registry stores executions of transforms. Many runs can be linked to the same transform if executed with different context (time, user, input data, etc.).

How do I track a pipeline instead of a notebook?

Leverage a pipeline integration, see: /pipelines. Or manually add code as seen below.

transform = ln.Transform(name="My pipeline")
transform.version = "1.2.0"  # tag the version
ln.track(transform)

Why should I care about tracking notebooks?

Because of interactivity & humans are in the loop, most mistakes happen when using notebooks.

track() makes notebooks & derived results reproducible & auditable, enabling to learn from mistakes.

This is important as much insight generated from biological data is driven by computational biologists interacting with it. An early blog post on this is here.

Is this compliant with OpenLineage?

Yes. What OpenLineage calls a “job”, LaminDB calls a “transform”. What OpenLineage calls a “run”, LaminDB calls a “run”.

Manage artifacts

The Artifact class manages datasets & models that are stored as files, folders, or arrays. Artifact is a registry to manage search, queries, validation & storage access.

You can register data objects (DataFrame, AnnData, …) and files or folders in local storage, AWS S3 (s3://), Google Cloud (gs://), Hugging Face (hf://), or any other file system supported by fsspec.

Create an artifact

Let’s first look at an exemplary dataframe.

Py

df = ln.examples.datasets.mini_immuno.get_dataset1(with_typo=True)
df

R

df <- ln$core$datasets$mini_immuno$get_dataset1(otype = "DataFrame", with_typo = TRUE)
df

Show code cell content Hide code cell content

df = ln.examples.datasets.mini_immuno.get_dataset1(with_typo=True)
df

	ENSG00000153563	ENSG00000010610	ENSG00000170458	perturbation	sample_note	cell_type_by_expert	cell_type_by_model	assay_oid	concentration	treatment_time_h	donor	donor_ethnicity
sample1	1	3	5	DMSO	was ok	B cell	B cell	EFO:0008913	0.1%	24	D0001	[Chinese, Singaporean Chinese]
sample2	2	4	6	IFNJ	looks naah	CD8-positive, alpha-beta T cell	T cell	EFO:0008913	200 nM	24	D0002	[Chinese, Han Chinese]
sample3	3	5	7	DMSO	pretty! 🤩	CD8-positive, alpha-beta T cell	T cell	EFO:0008913	0.1%	6	None	[Chinese]

This is how you create an artifact from a dataframe.

Py

artifact = ln.Artifact.from_dataframe(df, key="my_datasets/rnaseq1.parquet").save()  # create & save
artifact.describe()  # describe

R

artifact <- ln$Artifact$from_dataframe(df, key = "my_datasets/rnaseq1.parquet")$save()  # create & save
artifact$describe()  # describe

Show code cell content Hide code cell content

artifact = ln.Artifact.from_dataframe(df, key="my_datasets/rnaseq1.parquet").save()
artifact.describe()

→ writing the in-memory object into cache

Artifact: my_datasets/rnaseq1.parquet (0000)
├── uid: MKDxZXP4LNmKxFYl0000            run: 0NDdAcE (tutorial.ipynb)
│   kind: dataset                        otype: DataFrame             
│   hash: GcJ1rNzrCi3V98GQmSpsXg         size: 10.1 KB                
│   branch: main                         space: all                   
│   created_at: 2025-11-14 11:41:58 UTC  created_by: anonymous        
│   n_observations: 3                                                 
└── storage/path: 
    /home/runner/work/lamin-docs/lamin-docs/docs/lamindb-tutorial/.lamindb/MKDxZXP4LNmKxFYl0000.parquet

Access artifacts

Get the artifact by key.

Py

artifact = ln.Artifact.get(key="my_datasets/rnaseq1.parquet")

R

artifact <- ln$Artifact$get(key = "my_datasets/rnaseq1.parquet")

Show code cell content Hide code cell content

artifact = ln.Artifact.get(key="my_datasets/rnaseq1.parquet")

And this is how you load it back into memory.

Py

artifact.load()

R

artifact$load()

Show code cell content Hide code cell content

artifact.load()

	ENSG00000153563	ENSG00000010610	ENSG00000170458	perturbation	sample_note	cell_type_by_expert	cell_type_by_model	assay_oid	concentration	treatment_time_h	donor	donor_ethnicity
sample1	1	3	5	DMSO	was ok	B cell	B cell	EFO:0008913	0.1%	24	D0001	[Chinese, Singaporean Chinese]
sample2	2	4	6	IFNJ	looks naah	CD8-positive, alpha-beta T cell	T cell	EFO:0008913	200 nM	24	D0002	[Chinese, Han Chinese]
sample3	3	5	7	DMSO	pretty! 🤩	CD8-positive, alpha-beta T cell	T cell	EFO:0008913	0.1%	6	None	[Chinese]

Typically your artifact is in a cloud storage location. To get a local file path to it, call cache().

Py

artifact.cache()

R

artifact$cache()

Show code cell content Hide code cell content

artifact.cache()

PosixUPath('/home/runner/work/lamin-docs/lamin-docs/docs/lamindb-tutorial/.lamindb/MKDxZXP4LNmKxFYl0000.parquet')

If the data is large, you might not want to cache but stream it via open(). For more on this, see: Slice & stream arrays.

Trace data lineage

You can understand where an artifact comes from by looking at its Transform & Run records.

Py

artifact.transform

R

artifact$transform

Show code cell content Hide code cell content

artifact.transform

Transform(uid='Dlyds3zetI5b0000', version=None, is_latest=True, key='tutorial.ipynb', description='Tutorial', type='notebook', hash=None, reference=None, reference_type=None, branch_id=1, space_id=1, created_by_id=1, created_at=2025-11-14 11:41:57 UTC, is_locked=False)

Py

artifact.run

R

artifact$run

Show code cell content Hide code cell content

artifact.run

Run(uid='0NDdAcEdCctSdsGn', name=None, started_at=2025-11-14 11:41:57 UTC, finished_at=None, params=None, reference=None, reference_type=None, branch_id=1, space_id=1, transform_id=1, report_id=None, environment_id=None, created_by_id=1, initiated_by_run_id=None, created_at=2025-11-14 11:41:57 UTC, is_locked=False)

Or visualize deeper data lineage with the view_lineage() method. Here we’re only one step deep.

Py

artifact.view_lineage()

R

artifact$view_lineage()

Show code cell content Hide code cell content

artifact.view_lineage()

! calling anonymously, will miss private instances

Show me a more interesting example, please!

Py

Explore and load the notebook from here.

Hub

Explore data lineage interactively here.

Once you’re done, at the end of your notebook or script, call finish(). Here, we’re not yet done so we’re commenting it out.

Py

# ln.finish()  # mark run as finished, save execution report, source code & environment

R

# ln$finish()  # mark run as finished, save execution report & source code

If you did not use RStudio’s notebook mode, you have to render an HTML externally.

1. Render the notebook to HTML via one of:

   • In RStudio, click the “Knit” button

   • From the command line, run

     Rscript -e 'rmarkdown::render("tutorial.Rmd")'
     

   • Use the rmarkdown package in R

     rmarkdown::render("tutorial.Rmd")
     

2. Save it to your LaminDB instance via one of:

   • Using the save() command in the lamin_cli module from R

     lc <- import_module("lamin_cli")
     lc$save("tutorial.Rmd")
     

   • Using the lamin CLI

     lamin save tutorial.Rmd
     

Here is how a notebook looks on the hub.

Explore.

To create a new version of a notebook or script, run lamin load on the terminal, e.g.,

$ lamin load https://lamin.ai/laminlabs/lamindata/transform/13VINnFk89PE0004
→ notebook is here: mcfarland_2020_preparation.ipynb

Note that data lineage also helps to understand what a dataset is being used for, not only where it comes from. Many datasets are being used over and over for different purposes and it’s often useful to understand how.

Annotate an artifact

You can annotate artifacts with features and labels. Features are measurement dimensions (e.g. "organism", "temperature") and labels are measured categories (e.g. "human", "mouse").

Let’s annotate an artifact with a Record, a built-in universal label ontology.

Py

# create a label
my_experiment = ln.Record(name="My experiment").save()

# annotate the artifact with a label
artifact.records.add(my_experiment)

# describe the artifact
artifact.describe()

R

# create a label
my_experiment <- ln$Record(name = "My experiment")$save()

# annotate the artifact with a label
artifact$records$add(my_experiment)

# describe the artifact
artifact$describe()

Show code cell content Hide code cell content

# create & save a record
my_experiment = ln.Record(name="My experiment").save()

# annotate the artifact with a record
artifact.records.add(my_experiment)

# describe the artifact
artifact.describe()

Artifact: my_datasets/rnaseq1.parquet (0000)
├── uid: MKDxZXP4LNmKxFYl0000            run: 0NDdAcE (tutorial.ipynb)
│   kind: dataset                        otype: DataFrame             
│   hash: GcJ1rNzrCi3V98GQmSpsXg         size: 10.1 KB                
│   branch: main                         space: all                   
│   created_at: 2025-11-14 11:41:58 UTC  created_by: anonymous        
│   n_observations: 3                                                 
├── storage/path: 
│   /home/runner/work/lamin-docs/lamin-docs/docs/lamindb-tutorial/.lamindb/MKDxZXP4LNmKxFYl0000.parquet
└── Labels
    └── .records                        Record                             My experiment                           

This is how you query artifacts based on the annotation.

Py

ln.Artifact.filter(records=my_experiment).to_dataframe()

R

ln$Artifact$filter(records = my_experiment)$df()

Show code cell content Hide code cell content

ln.Artifact.filter(records=my_experiment).to_dataframe()

	uid	key	description	suffix	kind	otype	size	hash	n_files	n_observations	version	is_latest	is_locked	created_at	branch_id	space_id	storage_id	run_id	schema_id	created_by_id
id
1	MKDxZXP4LNmKxFYl0000	my_datasets/rnaseq1.parquet	None	.parquet	dataset	DataFrame	10354	GcJ1rNzrCi3V98GQmSpsXg	None	3	None	True	False	2025-11-14 11:41:58.367000+00:00	1	1	1	1	None	1

You can also annotate with labels from other registries, e.g., the biological ontologies in bionty.

Py

import bionty as bt

# create a cell type label from the source ontology
cell_type = bt.CellType.from_source(name="effector T cell").save()

# annotate the artifact with a cell type
artifact.cell_types.add(cell_type)

# describe the artifact
artifact.describe()

R

bt <- import_module("bionty")

# create a cell type label from the source ontology
cell_type <- bt$CellType$from_source(name = "effector T cell")$save()

# annotate the artifact with a cell type
artifact$cell_types$add(cell_type)

# describe the artifact
artifact$describe()

Show code cell content Hide code cell content

import bionty as bt

# create a cell type label from the source ontology
cell_type = bt.CellType.from_source(name="effector T cell").save()

# annotate the artifact with a cell type
artifact.cell_types.add(cell_type)

# describe the artifact
artifact.describe()

Artifact: my_datasets/rnaseq1.parquet (0000)
├── uid: MKDxZXP4LNmKxFYl0000            run: 0NDdAcE (tutorial.ipynb)
│   kind: dataset                        otype: DataFrame             
│   hash: GcJ1rNzrCi3V98GQmSpsXg         size: 10.1 KB                
│   branch: main                         space: all                   
│   created_at: 2025-11-14 11:41:58 UTC  created_by: anonymous        
│   n_observations: 3                                                 
├── storage/path: 
│   /home/runner/work/lamin-docs/lamin-docs/docs/lamindb-tutorial/.lamindb/MKDxZXP4LNmKxFYl0000.parquet
└── Labels
    └── .records                        Record                             My experiment                           
        .cell_types                     bionty.CellType                    effector T cell                         

This is how you query artifacts by cell type annotations.

Py

ln.Artifact.filter(cell_types=cell_type).to_dataframe()

R

ln$Artifact$filter(cell_types = cell_type)$df()

Show code cell content Hide code cell content

ln.Artifact.filter(cell_types=cell_type).to_dataframe()

	uid	key	description	suffix	kind	otype	size	hash	n_files	n_observations	version	is_latest	is_locked	created_at	branch_id	space_id	storage_id	run_id	schema_id	created_by_id
id
1	MKDxZXP4LNmKxFYl0000	my_datasets/rnaseq1.parquet	None	.parquet	dataset	DataFrame	10354	GcJ1rNzrCi3V98GQmSpsXg	None	3	None	True	False	2025-11-14 11:41:58.367000+00:00	1	1	1	1	None	1

If you want to annotate by non-categorical metadata or indicate the feature for a label, annotate via features.

Py

# define the "temperature" & "experiment" features
ln.Feature(name="temperature", dtype=float).save()
ln.Feature(name="experiment", dtype=ln.Record).save()

# annotate the artifact
artifact.features.add_values({"temperature": 21.6, "experiment": "My experiment"})

# describe the artifact
artifact.describe()

R

# define the "temperature" & "experiment" features
ln$Feature(name = "temperature", dtype = "float")$save()
ln$Feature(name = "experiment", dtype = ln$Record)$save()

# annotate the artifact
artifact$features$add_values(
  list(temperature = 21.6, experiment = "My experiment")
)

# describe the artifact
artifact$describe()

Show code cell content Hide code cell content

# define the "temperature" & "experiment" features
ln.Feature(name="temperature", dtype=float).save()
ln.Feature(name="experiment", dtype=ln.Record).save()

# annotate the artifact
artifact.features.add_values({"temperature": 21.6, "experiment": "My experiment"})

# describe the artifact
artifact.describe()

Artifact: my_datasets/rnaseq1.parquet (0000)
├── uid: MKDxZXP4LNmKxFYl0000            run: 0NDdAcE (tutorial.ipynb)
│   kind: dataset                        otype: DataFrame             
│   hash: GcJ1rNzrCi3V98GQmSpsXg         size: 10.1 KB                
│   branch: main                         space: all                   
│   created_at: 2025-11-14 11:41:58 UTC  created_by: anonymous        
│   n_observations: 3                                                 
├── storage/path: 
│   /home/runner/work/lamin-docs/lamin-docs/docs/lamindb-tutorial/.lamindb/MKDxZXP4LNmKxFYl0000.parquet
├── Features
│   └── experiment                      Record                             My experiment                           
│       temperature                     float                              21.6                                    
└── Labels
    └── .records                        Record                             My experiment                           
        .cell_types                     bionty.CellType                    effector T cell                         

This is how you query artifacts by features.

Py

ln.Artifact.filter(temperature=21.6).to_dataframe()

R

ln$Artifact$filter(temperature = 21.6)$df()

Show code cell content Hide code cell content

ln.Artifact.filter(temperature=21.6).to_dataframe()

	uid	key	description	suffix	kind	otype	size	hash	n_files	n_observations	version	is_latest	is_locked	created_at	branch_id	space_id	storage_id	run_id	schema_id	created_by_id
id
1	MKDxZXP4LNmKxFYl0000	my_datasets/rnaseq1.parquet	None	.parquet	dataset	DataFrame	10354	GcJ1rNzrCi3V98GQmSpsXg	None	3	None	True	False	2025-11-14 11:41:58.367000+00:00	1	1	1	1	None	1

Validate an artifact

Validated datasets are more re-usable by analysts and machine learning models. You can define what a valid artifact should look like by defining a schema.

In lamindb, validation also means annotation with the validated metadata which increases the findability of a dataset.

Can you give me examples for what findability and usability means?

1. Findability: Which datasets measured expression of cell marker CD14? Which characterized cell line K562? Which have a test & train split? Etc.

2. Usability: Are there typos in feature names? Are there typos in labels? Are types and units of features consistent? Etc.

Py

import bionty as bt  # <-- use bionty to access registries with imported public ontologies

# define a few more valid labels
ln.Record(name="DMSO").save()
ln.Record(name="IFNG").save()

# define a few more valid features
ln.Feature(name="perturbation", dtype=ln.Record).save()
ln.Feature(name="cell_type_by_model", dtype=bt.CellType).save()
ln.Feature(name="cell_type_by_expert", dtype=bt.CellType).save()
ln.Feature(name="assay_oid", dtype=bt.ExperimentalFactor.ontology_id).save()
ln.Feature(name="donor", dtype=str, nullable=True).save()
ln.Feature(name="concentration", dtype=str).save()
ln.Feature(name="treatment_time_h", dtype="num", coerce_dtype=True).save()

# define a schema that merely enforces a feature identifier type
schema = ln.Schema(itype=ln.Feature).save()

R

bt <- import_module("bionty")  # <-- use bionty to access registries with imported public ontologies

# define a few more valid labels
ln$Record(name = "DMSO")$save()
ln$Record(name = "IFNG")$save()

# define a few more valid features
ln$Feature(name = "perturbation", dtype = ln$Record)$save()
ln$Feature(name = "cell_type_by_model", dtype = bt$CellType)$save()
ln$Feature(name = "cell_type_by_expert", dtype = bt$CellType)$save()
ln$Feature(name = "assay_oid", dtype = bt$ExperimentalFactor$ontology_id)$save()
ln$Feature(name = "donor", dtype = "str", nullable = TRUE)$save()
ln$Feature(name = "concentration", dtype = "str")$save()
ln$Feature(name = "treatment_time_h", dtype = "num", coerce_dtype = TRUE)$save()

# define a schema that merely enforces a feature identifier type
schema <- ln$Schema(itype = ln$Feature)$save()

Show code cell content Hide code cell content

import bionty as bt  # <-- use bionty to access registries with imported public ontologies

# define a few more valid labels
ln.Record(name="DMSO").save()
ln.Record(name="IFNG").save()

# define a few more valid features
ln.Feature(name="perturbation", dtype=ln.Record).save()
ln.Feature(name="cell_type_by_model", dtype=bt.CellType).save()
ln.Feature(name="cell_type_by_expert", dtype=bt.CellType).save()
ln.Feature(name="assay_oid", dtype=bt.ExperimentalFactor.ontology_id).save()
ln.Feature(name="donor", dtype=str, nullable=True).save()
ln.Feature(name="sample_note", dtype=str, nullable=True).save()
ln.Feature(name="concentration", dtype=str).save()
ln.Feature(name="treatment_time_h", dtype="num", coerce_dtype=True).save()

# define a schema that merely enforces a feature identifier type
schema = ln.Schema(itype=ln.Feature).save()

If you pass a schema object to the Artifact constructor, the artifact will be validated & annotated. Let’s try this.

Py

artifact = ln.Artifact.from_dataframe(df, key="my_datasets/rnaseq1.parquet", schema=schema)

R

artifact <- ln$Artifact$from_dataframe(df, key = "my_datasets/rnaseq1.parquet", schema = schema)

Show code cell content Hide code cell content

try:
    artifact = ln.Artifact.from_dataframe(
        df, key="my_datasets/rnaseq1.parquet", schema=schema
    )
except ln.errors.ValidationError as error:
    print(str(error))

→ writing the in-memory object into cache

→ returning artifact with same hash: Artifact(uid='MKDxZXP4LNmKxFYl0000', version=None, is_latest=True, key='my_datasets/rnaseq1.parquet', description=None, suffix='.parquet', kind='dataset', otype='DataFrame', size=10354, hash='GcJ1rNzrCi3V98GQmSpsXg', n_files=None, n_observations=3, branch_id=1, space_id=1, storage_id=1, run_id=1, schema_id=None, created_by_id=1, created_at=2025-11-14 11:41:58 UTC, is_locked=False); to track this artifact as an input, use: ln.Artifact.get()

→ loading artifact into memory for validation

! 4 terms not validated in feature 'columns': 'ENSG00000153563', 'ENSG00000010610', 'ENSG00000170458', 'donor_ethnicity'
    → fix typos, remove non-existent values, or save terms via: curator.cat.add_new_from('columns')

! 1 term not validated in feature 'perturbation': 'IFNJ'
    → fix typos, remove non-existent values, or save terms via: curator.cat.add_new_from('perturbation')

1 term not validated in feature 'perturbation': 'IFNJ'
    → fix typos, remove non-existent values, or save terms via: curator.cat.add_new_from('perturbation')

Because there is a typo in the perturbation column, validation fails. Let’s fix it by making a new version.

Make a new version of an artifact

Py

# fix the "IFNJ" typo
df["perturbation"] = df["perturbation"].cat.rename_categories({"IFNJ": "IFNG"})

# create a new version
artifact = ln.Artifact.from_dataframe(df, key="my_datasets/rnaseq1.parquet", schema=schema).save()

# see the annotations
artifact.describe()

# simplest way to check that artifact was validated
artifact.schema

# see all versions of the artifact
artifact.versions.to_dataframe()

R

# fix the "IFNJ" typo
levels(df$perturbation) <- c("DMSO", "IFNG")
df["sample2", "perturbation"] <- "IFNG"

# create a new version
artifact <- ln$Artifact$from_dataframe(df, key = "my_datasets/rnaseq1.parquet", schema = schema)$save()

# see the annotations
artifact$describe()

# simplest way to check that artifact was validated
artifact$schema

# see all versions of an artifact
artifact$versions$df()

Show code cell content Hide code cell content

# fix the "IFNJ" typo
df["perturbation"] = df["perturbation"].cat.rename_categories({"IFNJ": "IFNG"})

# create a new version
artifact = ln.Artifact.from_dataframe(
    df, key="my_datasets/rnaseq1.parquet", schema=schema
).save()

# see the annotations
artifact.describe()

# see all versions of the artifact
artifact.versions.to_dataframe()

→ writing the in-memory object into cache

→ creating new artifact version for key 'my_datasets/rnaseq1.parquet' in storage '/home/runner/work/lamin-docs/lamin-docs/docs/lamindb-tutorial'

→ loading artifact into memory for validation

! 4 terms not validated in feature 'columns': 'ENSG00000153563', 'ENSG00000010610', 'ENSG00000170458', 'donor_ethnicity'
    → fix typos, remove non-existent values, or save terms via: curator.cat.add_new_from('columns')

Artifact: my_datasets/rnaseq1.parquet (0001)
├── uid: MKDxZXP4LNmKxFYl0001            run: 0NDdAcE (tutorial.ipynb)
│   kind: dataset                        otype: DataFrame             
│   hash: ug6ICnjB8oyqescoUDbYKg         size: 10.1 KB                
│   branch: main                         space: all                   
│   created_at: 2025-11-14 11:42:03 UTC  created_by: anonymous        
│   n_observations: 3                                                 
├── storage/path: 
│   /home/runner/work/lamin-docs/lamin-docs/docs/lamindb-tutorial/.lamindb/MKDxZXP4LNmKxFYl0001.parquet
├── Dataset features
│   └── columns (8)                                                                                                
│       assay_oid                       bionty.ExperimentalFactor.ontolo…  EFO:0008913                             
│       cell_type_by_expert             bionty.CellType                    B cell, CD8-positive, alpha-beta T cell 
│       cell_type_by_model              bionty.CellType                    B cell, T cell                          
│       perturbation                    Record                             DMSO, IFNG                              
│       donor                           str                                                                        
│       sample_note                     str                                                                        
│       concentration                   str                                                                        
│       treatment_time_h                num                                                                        
└── Labels
    └── .records                        Record                             DMSO, IFNG                              
        .cell_types                     bionty.CellType                    T cell, B cell, CD8-positive, alpha-bet…
        .experimental_factors           bionty.ExperimentalFactor          single-cell RNA sequencing              

	uid	key	description	suffix	kind	otype	size	hash	n_files	n_observations	version	is_latest	is_locked	created_at	branch_id	space_id	storage_id	run_id	schema_id	created_by_id
id
2	MKDxZXP4LNmKxFYl0001	my_datasets/rnaseq1.parquet	None	.parquet	dataset	DataFrame	10354	ug6ICnjB8oyqescoUDbYKg	None	3	None	True	False	2025-11-14 11:42:03.557000+00:00	1	1	1	1	1.0	1
1	MKDxZXP4LNmKxFYl0000	my_datasets/rnaseq1.parquet	None	.parquet	dataset	DataFrame	10354	GcJ1rNzrCi3V98GQmSpsXg	None	3	None	False	False	2025-11-14 11:41:58.367000+00:00	1	1	1	1	NaN	1

The content of the dataset is now validated and the dataset is richly annotated and queryable by all entities that you defined.

Can I also create new versions without passing key?

That works, too, you can use revises:

artifact_v1 = ln.Artifact.from_dataframe(df, description="Just a description").save()
# below revises artifact_v1
artifact_v2 = ln.Artifact.from_dataframe(df_updated, revises=artifact_v1).save()

The good thing about passing revises: Artifact is that you don’t need to worry about coming up with naming conventions for paths.

The good thing about versioning based on key is that it’s how all data versioning tools are doing it.

Query & search registries

We’ve already seen a few queries. Let’s now walk through the topic systematically.

To get an overview over all artifacts in your instance, call df.

Py

ln.Artifact.to_dataframe()

R

ln$Artifact$df()

Show code cell content Hide code cell content

ln.Artifact.to_dataframe()

	uid	key	description	suffix	kind	otype	size	hash	n_files	n_observations	version	is_latest	is_locked	created_at	branch_id	space_id	storage_id	run_id	schema_id	created_by_id
id
2	MKDxZXP4LNmKxFYl0001	my_datasets/rnaseq1.parquet	None	.parquet	dataset	DataFrame	10354	ug6ICnjB8oyqescoUDbYKg	None	3	None	True	False	2025-11-14 11:42:03.557000+00:00	1	1	1	1	1.0	1
1	MKDxZXP4LNmKxFYl0000	my_datasets/rnaseq1.parquet	None	.parquet	dataset	DataFrame	10354	GcJ1rNzrCi3V98GQmSpsXg	None	3	None	False	False	2025-11-14 11:41:58.367000+00:00	1	1	1	1	NaN	1

The Artifact registry additionally supports seeing all feature annotations of an artifact.

Py

ln.Artifact.to_dataframe(features=True)

R

ln$Artifact$df(features = TRUE)

Show code cell content Hide code cell content

ln.Artifact.to_dataframe(features=True)

→ queried for all categorical features with dtype Record and non-categorical features: (7) ['temperature', 'experiment', 'perturbation', 'donor', 'sample_note', 'concentration', 'treatment_time_h']

	uid	key	temperature	experiment	perturbation
id
2	MKDxZXP4LNmKxFYl0001	my_datasets/rnaseq1.parquet	NaN	NaN	{IFNG, DMSO}
1	MKDxZXP4LNmKxFYl0000	my_datasets/rnaseq1.parquet	21.6	My experiment	NaN

LaminDB’s central classes are registries that store records (SQLRecord objects). If you want to see the fields of a registry, look at the class or auto-complete.

Py

ln.Artifact

R

ln$Artifact

Show code cell content Hide code cell content

ln.Artifact

Artifact
  Simple fields
    .uid: CharField
    .key: CharField
    .description: TextField
    .suffix: CharField
    .kind: CharField
    .otype: CharField
    .size: BigIntegerField
    .hash: CharField
    .n_files: BigIntegerField
    .n_observations: BigIntegerField
    .version: CharField
    .is_latest: BooleanField
    .is_locked: BooleanField
    .created_at: DateTimeField
    .updated_at: DateTimeField
  Relational fields
    .branch: Branch
    .space: Space
    .storage: Storage
    .run: Run
    .schema: Schema
    .created_by: User
    .input_of_runs: Run
    .feature_sets: Schema
    .linked_in_records: Record
    .users: User
    .ulabels: ULabel
    .collections: Collection
    .records: Record
    .references: Reference
    .projects: Project
    .blocks: Block
  Bionty fields
    .organisms: bionty.Organism
    .genes: bionty.Gene
    .proteins: bionty.Protein
    .cell_markers: bionty.CellMarker
    .tissues: bionty.Tissue
    .cell_types: bionty.CellType
    .diseases: bionty.Disease
    .cell_lines: bionty.CellLine
    .phenotypes: bionty.Phenotype
    .pathways: bionty.Pathway
    .experimental_factors: bionty.ExperimentalFactor
    .developmental_stages: bionty.DevelopmentalStage
    .ethnicities: bionty.Ethnicity

Each registry is a table in the relational schema of the underlying database. With view(), you can see the latest records in the database.

Py

ln.view()

R

ln$view()

Show code cell content Hide code cell content

ln.view()

****************

* module: core *

****************

Artifact

	uid	key	description	suffix	kind	otype	size	hash	n_files	n_observations	version	is_latest	is_locked	created_at	branch_id	space_id	storage_id	run_id	schema_id	created_by_id
id
2	MKDxZXP4LNmKxFYl0001	my_datasets/rnaseq1.parquet	None	.parquet	dataset	DataFrame	10354	ug6ICnjB8oyqescoUDbYKg	None	3	None	True	False	2025-11-14 11:42:03.557000+00:00	1	1	1	1	1.0	1
1	MKDxZXP4LNmKxFYl0000	my_datasets/rnaseq1.parquet	None	.parquet	dataset	DataFrame	10354	GcJ1rNzrCi3V98GQmSpsXg	None	3	None	False	False	2025-11-14 11:41:58.367000+00:00	1	1	1	1	NaN	1

Feature

	uid	name	dtype	is_type	unit	description	array_rank	array_size	array_shape	proxy_dtype	synonyms	is_locked	created_at	branch_id	space_id	created_by_id	run_id	type_id
id
10	B8pvfNRDlagD	treatment_time_h	num	None	None	None	0	0	None	None	None	False	2025-11-14 11:42:00.917000+00:00	1	1	1	1	None
9	vmiQ6ygoLjRA	concentration	str	None	None	None	0	0	None	None	None	False	2025-11-14 11:42:00.914000+00:00	1	1	1	1	None
8	uccWpJTFTKCp	sample_note	str	None	None	None	0	0	None	None	None	False	2025-11-14 11:42:00.910000+00:00	1	1	1	1	None
7	wgnozDogmzdG	donor	str	None	None	None	0	0	None	None	None	False	2025-11-14 11:42:00.906000+00:00	1	1	1	1	None
6	yAO6Nxb3yDww	assay_oid	cat[bionty.ExperimentalFactor.ontology_id]	None	None	None	0	0	None	None	None	False	2025-11-14 11:42:00.903000+00:00	1	1	1	1	None
5	8aeU2uUUZk7y	cell_type_by_expert	cat[bionty.CellType]	None	None	None	0	0	None	None	None	False	2025-11-14 11:42:00.899000+00:00	1	1	1	1	None
4	ioA74uyd9kLh	cell_type_by_model	cat[bionty.CellType]	None	None	None	0	0	None	None	None	False	2025-11-14 11:42:00.895000+00:00	1	1	1	1	None

FeatureValue

	value	hash	is_locked	created_at	branch_id	space_id	created_by_id	run_id	feature_id
id
1	21.6	XftFE5byhwPHY-11WjfNAw	False	2025-11-14 11:42:00.816000+00:00	1	1	1	1	1

Record

	uid	name	is_type	description	reference	reference_type	is_locked	created_at	branch_id	space_id	created_by_id	type_id	schema_id	run_id
id
3	KBAG3yQ13jDWTSjN	IFNG	False	None	None	None	False	2025-11-14 11:42:00.887000+00:00	1	1	1	None	None	1
2	C3dmEGNPV6rqv0Bd	DMSO	False	None	None	None	False	2025-11-14 11:42:00.883000+00:00	1	1	1	None	None	1
1	uuKS6foMKSf0ul11	My experiment	False	None	None	None	False	2025-11-14 11:41:59.335000+00:00	1	1	1	None	None	1

Run

	uid	name	started_at	finished_at	params	reference	reference_type	is_locked	created_at	branch_id	space_id	transform_id	report_id	_logfile_id	environment_id	created_by_id	initiated_by_run_id
id
1	0NDdAcEdCctSdsGn	None	2025-11-14 11:41:57.789857+00:00	None	None	None	None	False	2025-11-14 11:41:57.790000+00:00	1	1	1	None	None	None	1	None

Schema

	uid	name	description	n	is_type	itype	otype	dtype	hash	minimal_set	ordered_set	maximal_set	slot	is_locked	created_at	branch_id	space_id	created_by_id	run_id	type_id	validated_by_id	composite_id
id
2	0Mg3OQtjlDCLmJGf	None	None	8	False	Feature	None	None	1SotJiS28Qs9O7bjf4cWOA	True	False	False	None	False	2025-11-14 11:42:03.573000+00:00	1	1	1	1	None	None	None
1	0000000000000000	None	None	-1	False	Feature	None	None	kMi7B_N88uu-YnbTLDU-DA	True	False	False	None	False	2025-11-14 11:42:00.920000+00:00	1	1	1	1	None	None	None

Storage

	uid	root	description	type	region	instance_uid	is_locked	created_at	branch_id	space_id	created_by_id	run_id
id
1	IpIww7jFzPYA	/home/runner/work/lamin-docs/lamin-docs/docs/l...	None	local	None	5WCoFhciyw3n	False	2025-11-14 11:41:54.413000+00:00	1	1	1	None

Transform

	uid	key	description	type	source_code	hash	reference	reference_type	version	is_latest	is_locked	created_at	branch_id	space_id	created_by_id	_template_id
id
1	Dlyds3zetI5b0000	tutorial.ipynb	Tutorial	notebook	None	None	None	None	None	True	False	2025-11-14 11:41:57.785000+00:00	1	1	1	None

******************

* module: bionty *

******************

CellType

	uid	name	ontology_id	abbr	synonyms	description	is_locked	created_at	branch_id	space_id	created_by_id	run_id	source_id
id
17	4BEwsp1Q	mature alpha-beta T cell	CL:0000791	None	mature alpha-beta T-cell|mature alpha-beta T l...	A Alpha-Beta T Cell That Has A Mature Phenotype.	False	2025-11-14 11:42:02.382000+00:00	1	1	1	1	16
16	6By01L04	alpha-beta T cell	CL:0000789	None	alpha-beta T-cell|alpha-beta T-lymphocyte|alph...	A T Cell That Expresses An Alpha-Beta T Cell R...	False	2025-11-14 11:42:02.382000+00:00	1	1	1	1	16
15	6IC9NGJE	CD8-positive, alpha-beta T cell	CL:0000625	None	CD8-positive, alpha-beta T-lymphocyte|CD8-posi...	A T Cell Expressing An Alpha-Beta T Cell Recep...	False	2025-11-14 11:42:02.091000+00:00	1	1	1	1	16
14	7GpphKmr	lymphocyte of B lineage	CL:0000945	None	None	A Lymphocyte Of B Lineage With The Commitment ...	False	2025-11-14 11:42:01.774000+00:00	1	1	1	1	16
13	ryEtgi1y	B cell	CL:0000236	None	B-cell|B-lymphocyte|B lymphocyte	A Lymphocyte Of B Lineage That Is Capable Of B...	False	2025-11-14 11:42:01.477000+00:00	1	1	1	1	16
12	u3sr1Gdf	nucleate cell	CL:0002242	None	None	A Cell Containing At Least One Nucleus.	False	2025-11-14 11:42:00.741000+00:00	1	1	1	1	16
11	4Ilrnj9U	hematopoietic cell	CL:0000988	None	haemopoietic cell|haematopoietic cell|hemopoie...	A Cell Of A Hematopoietic Lineage.	False	2025-11-14 11:42:00.741000+00:00	1	1	1	1	16

ExperimentalFactor

	uid	name	ontology_id	abbr	synonyms	description	molecule	instrument	measurement	is_locked	created_at	branch_id	space_id	created_by_id	run_id	source_id
id
6	2zGOHoUs	single cell sequencing	EFO:0007832	None	None	Single Cell Sequencing Examines The Sequence I...	None	single cell sequencing	None	False	2025-11-14 11:42:03.448000+00:00	1	1	1	1	21
5	6dI7vyK2	assay by sequencer	EFO:0003740	None	sequencing assay	An Assay That Exploits A Sequencer As The Inst...	None	assay by sequencer	None	False	2025-11-14 11:42:03.448000+00:00	1	1	1	1	21
4	6oIjaW4X	assay by instrument	EFO:0002773	None	None	None	None	None	None	False	2025-11-14 11:42:03.448000+00:00	1	1	1	1	21
3	1wLRxESw	assay by molecule	EFO:0002772	None	None	None	None	None	None	False	2025-11-14 11:42:03.448000+00:00	1	1	1	1	21
2	789nVHwo	RNA assay	EFO:0001457	None	None	An Assay With Input Rna	RNA assay	None	None	False	2025-11-14 11:42:03.448000+00:00	1	1	1	1	21
1	4WYv9kl0	single-cell RNA sequencing	EFO:0008913	None	single-cell RNA-seq|scRNA-seq|single cell RNA ...	A Protocol That Provides The Expression Profil...	RNA assay	single cell sequencing	None	False	2025-11-14 11:42:03.111000+00:00	1	1	1	1	21

Source

	uid	entity	organism	name	in_db	currently_used	description	url	md5	source_website	version	is_locked	created_at	branch_id	space_id	created_by_id	run_id	dataframe_artifact_id
id
33	5JnVODh4	BioSample	all	ncbi	False	True	NCBI BioSample attributes	s3://bionty-assets/df_all__ncbi__2023-09__BioS...	None	https://www.ncbi.nlm.nih.gov/biosample/docs/at...	2023-09	False	2025-11-14 11:41:54.456000+00:00	1	1	1	None	None
32	MJRqduf9	bionty.Ethnicity	human	hancestro	False	True	Human Ancestry Ontology	http://purl.obolibrary.org/obo/hancestro/relea...	None	https://github.com/EBISPOT/hancestro	3.0	False	2025-11-14 11:41:54.456000+00:00	1	1	1	None	None
31	10va5JSt	bionty.DevelopmentalStage	mouse	mmusdv	False	True	Mouse Developmental Stages	https://github.com/obophenotype/developmental-...	None	https://github.com/obophenotype/developmental-...	2024-05-28	False	2025-11-14 11:41:54.456000+00:00	1	1	1	None	None
30	1GbFkOdz	bionty.DevelopmentalStage	human	hsapdv	False	True	Human Developmental Stages	https://github.com/obophenotype/developmental-...	None	https://github.com/obophenotype/developmental-...	2024-05-28	False	2025-11-14 11:41:54.456000+00:00	1	1	1	None	None
29	1atB0WnU	Drug	all	chebi	False	False	Chemical Entities of Biological Interest	s3://bionty-assets/df_all__chebi__2024-07-27__...	None	https://www.ebi.ac.uk/chebi/	2024-07-27	False	2025-11-14 11:41:54.456000+00:00	1	1	1	None	None
28	ugaIoIlj	Drug	all	dron	False	True	Drug Ontology	http://purl.obolibrary.org/obo/dron/releases/2...	None	https://bioportal.bioontology.org/ontologies/DRON	2024-08-05	False	2025-11-14 11:41:54.456000+00:00	1	1	1	None	None
27	3rm9aOzL	BFXPipeline	all	lamin	False	True	Bioinformatics Pipeline	s3://bionty-assets/df_all__lamin__1.0.0__BFXpi...	None	https://lamin.ai	1.0.0	False	2025-11-14 11:41:54.456000+00:00	1	1	1	None	None

Which registries have I already learned about? 🤔

• Artifact: datasets & models stored as files, folders, or arrays

• Transform: transforms of artifacts

• Run: runs of transforms

• User: users

• Storage: local or cloud storage locations

Every registry supports arbitrary relational queries using the class methods get and filter. The syntax for it is Django’s query syntax.

Here are some simple query examples.

Py

# get a single record (here the current notebook)
transform = ln.Transform.get(key="tutorial.ipynb")

# get a set of records by filtering for a directory (LaminDB treats directories like AWS S3, as the prefix of the storage key)
ln.Artifact.filter(key__startswith="my_datasets/").to_dataframe()

# query all artifacts ingested from a transform
artifacts = ln.Artifact.filter(transform=transform).all()

# query all artifacts ingested from a notebook with "tutor" in the description
artifacts = ln.Artifact.filter(
    transform__description__icontains="tutor",
).all()

R

# get a single record (here the current notebook)
transform <- ln$Transform$get(key = "tutorial.Rmd")

# get a set of records by filtering for a directory (LaminDB treats directories like AWS S3, as the prefix of the storage key)
ln$Artifact$filter(key__startswith = "my_datasets/")$df()

# query all artifacts ingested from a transform
artifacts <- ln$Artifact$filter(transform = transform)$all()

# query all artifacts ingested from a notebook with "tutor" in the description
artifacts <- ln$Artifact$filter(
  transform__description__icontains = "tutor",
)$all()

Show code cell content Hide code cell content

# get a single record (here the current notebook)
transform = ln.Transform.get(key="tutorial.ipynb")

# get a set of records by filtering for a directory (LaminDB treats directories like AWS S3, as the prefix of the storage key)
ln.Artifact.filter(key__startswith="my_datasets/").to_dataframe()

# query all artifacts ingested from a transform
artifacts = ln.Artifact.filter(transform=transform).all()

# query all artifacts ingested from a notebook with "tutor" in the description
artifacts = ln.Artifact.filter(
    transform__description__icontains="tutor",
).all()

What does a double underscore mean?

For any field, the double underscore defines a comparator, e.g.,

• name__icontains="Martha": name contains "Martha" when ignoring case

• name__startswith="Martha": name starts with "Martha

• name__in=["Martha", "John"]: name is "John" or "Martha"

For more info, see: Query & search registries.

Can I chain filters and searches?

Yes: ln.Artifact.filter(suffix=".jpg").search("my image")

The class methods search and lookup help with approximate matches.

Py

# search artifacts
ln.Artifact.search("iris").to_dataframe().head()

# search transforms
ln.Transform.search("tutor").to_dataframe()

# look up records with auto-complete
records = ln.Record.lookup()

R

# search artifacts
ln$Artifact$search("iris")$df()

# search transforms
ln$Transform$search("tutor")$df()

# look up records with auto-complete
records <- ln$Record$lookup()

Show me a screenshot

For more info, see: Query & search registries.

Manage files & folders

Let’s look at a folder in the cloud that contains 3 sub-folders storing images & metadata of Iris flowers, generated in 3 subsequent studies.

Py

# we use anon=True here in case no aws credentials are configured
ln.UPath("s3://lamindata/iris_studies", anon=True).view_tree()

R

# we use anon=True here in case no aws credentials are configured
ln$UPath("s3://lamindata/iris_studies", anon = TRUE)$view_tree()

Show code cell content Hide code cell content

# we use anon=True here in case no aws credentials are configured
ln.UPath("s3://lamindata/iris_studies", anon=True).view_tree()

3 sub-directories & 151 files with suffixes '.jpg', '.csv'
s3://lamindata/iris_studies
├── study0_raw_images/
│   ├── iris-0337d20a3b7273aa0ddaa7d6afb57a37a759b060e4401871db3cefaa6adc068d.jpg
│   ├── iris-0797945218a97d6e5251b4758a2ba1b418cbd52ce4ef46a3239e4b939bd9807b.jpg
│   ├── iris-0f133861ea3fe1b68f9f1b59ebd9116ff963ee7104a0c4200218a33903f82444.jpg
│   ├── iris-0fec175448a23db03c1987527f7e9bb74c18cffa76ef003f962c62603b1cbb87.jpg
│   ├── iris-125b6645e086cd60131764a6bed12650e0f7f2091c8bbb72555c103196c01881.jpg
│   ├── iris-13dfaff08727abea3da8cfd8d097fe1404e76417fefe27ff71900a89954e145a.jpg
│   ├── iris-1566f7f5421eaf423a82b3c1cd1328f2a685c5ef87d8d8e710f098635d86d3d0.jpg
│   ├── iris-1804702f49c2c385f8b30913569aebc6dce3da52ec02c2c638a2b0806f16014e.jpg
│   ├── iris-318d451a8c95551aecfde6b55520f302966db0a26a84770427300780b35aa05a.jpg
│   ├── iris-3dec97fe46d33e194520ca70740e4c2e11b0ffbffbd0aec0d06afdc167ddf775.jpg
│   ├── iris-3eed72bc2511f619190ce79d24a0436fef7fcf424e25523cb849642d14ac7bcf.jpg
│   ├── iris-430fa45aad0edfeb5b7138ff208fdeaa801b9830a9eb68f378242465b727289a.jpg
│   ├── iris-4cc15cd54152928861ecbdc8df34895ed463403efb1571dac78e3223b70ef569.jpg
│   ├── iris-4febb88ef811b5ca6077d17ef8ae5dbc598d3f869c52af7c14891def774d73fa.jpg
│   ├── iris-590e7f5b8f4de94e4b82760919abd9684ec909d9f65691bed8e8f850010ac775.jpg
│   ├── iris-5a313749aa61e9927389affdf88dccdf21d97d8a5f6aa2bd246ca4bc926903ba.jpg
│   ├── iris-5b3106db389d61f4277f43de4953e660ff858d8ab58a048b3d8bf8d10f556389.jpg
│   ├── iris-5f4e8fffde2404cc30be275999fddeec64f8a711ab73f7fa4eb7667c8475c57b.jpg
│   ├── iris-68d83ad09262afb25337ccc1d0f3a6d36f118910f36451ce8a6600c77a8aa5bd.jpg
│   ├── iris-70069edd7ab0b829b84bb6d4465b2ca4038e129bb19d0d3f2ba671adc03398cc.jpg
│   ├── iris-7038aef1137814473a91f19a63ac7a55a709c6497e30efc79ca57cfaa688f705.jpg
│   ├── iris-74d1acf18cfacd0a728c180ec8e1c7b4f43aff72584b05ac6b7c59f5572bd4d4.jpg
│   ├── iris-7c3b5c5518313fc6ff2c27fcbc1527065cbb42004d75d656671601fa485e5838.jpg
│   ├── iris-7cf1ebf02b2cc31539ed09ab89530fec6f31144a0d5248a50e7c14f64d24fe6e.jpg
│   ├── iris-7dcc69fa294fe04767706c6f455ea6b31d33db647b08aab44b3cd9022e2f2249.jpg
│   ├── iris-801b7efb867255e85137bc1e1b06fd6cbab70d20cab5b5046733392ecb5b3150.jpg
│   ├── iris-8305dd2a080e7fe941ea36f3b3ec0aa1a195ad5d957831cf4088edccea9465e2.jpg
│   ├── iris-83f433381b755101b9fc9fbc9743e35fbb8a1a10911c48f53b11e965a1cbf101.jpg
│   ├── iris-874121a450fa8a420bdc79cc7808fd28c5ea98758a4b50337a12a009fa556139.jpg
│   ├── iris-8c216e1acff39be76d6133e1f549d138bf63359fa0da01417e681842210ea262.jpg
│   ├── iris-92c4268516ace906ad1ac44592016e36d47a8c72a51cacca8597ba9e18a8278b.jpg
│   ├── iris-95d7ec04b8158f0873fa4aab7b0a5ec616553f3f9ddd6623c110e3bc8298248f.jpg
│   ├── iris-9ce2d8c4f1eae5911fcbd2883137ba5542c87cc2fe85b0a3fbec2c45293c903e.jpg
│   ├── iris-9ee27633bb041ef1b677e03e7a86df708f63f0595512972403dcf5188a3f48f5.jpg
│   ├── iris-9fb8d691550315506ae08233406e8f1a4afed411ea0b0ac37e4b9cdb9c42e1ec.jpg
│   ├── iris-9ffe51c2abd973d25a299647fa9ccaf6aa9c8eecf37840d7486a061438cf5771.jpg
│   ├── iris-a2be5db78e5b603a5297d9a7eec4e7f14ef2cba0c9d072dc0a59a4db3ab5bb13.jpg
│   ├── iris-ad7da5f15e2848ca269f28cd1dc094f6f685de2275ceaebb8e79d2199b98f584.jpg
│   ├── iris-bc515e63b5a4af49db8c802c58c83db69075debf28c792990d55a10e881944d9.jpg
│   ├── iris-bd8d83096126eaa10c44d48dbad4b36aeb9f605f1a0f6ca929d3d0d492dafeb6.jpg
│   ├── iris-bdae8314e4385d8e2322abd8e63a82758a9063c77514f49fc252e651cbd79f82.jpg
│   ├── iris-c175cd02ac392ecead95d17049f5af1dcbe37851c3e42d73e6bb813d588ea70b.jpg
│   ├── iris-c31e6056c94b5cb618436fbaac9eaff73403fa1b87a72db2c363d172a4db1820.jpg
│   ├── iris-ca40bc5839ee2f9f5dcac621235a1db2f533f40f96a35e1282f907b40afa457d.jpg
│   ├── iris-ddb685c56cfb9c8496bcba0d57710e1526fff7d499536b3942d0ab375fa1c4a6.jpg
│   ├── iris-e437a7c7ad2bbac87fef3666b40c4de1251b9c5f595183eda90a8d9b1ef5b188.jpg
│   ├── iris-e7e0774289e2153cc733ff62768c40f34ac9b7b42e23c1abc2739f275e71a754.jpg
│   ├── iris-e9da6dd69b7b07f80f6a813e2222eae8c8f7c3aeaa6bcc02b25ea7d763bcf022.jpg
│   ├── iris-eb01666d4591b2e03abecef5a7ded79c6d4ecb6d1922382c990ad95210d55795.jpg
│   ├── iris-f6e4890dee087bd52e2c58ea4c6c2652da81809603ea3af561f11f8c2775c5f3.jpg
│   └── meta.csv
├── study1_raw_images/
│   ├── iris-0879d3f5b337fe512da1c7bf1d2bfd7616d744d3eef7fa532455a879d5cc4ba0.jpg
│   ├── iris-0b486eebacd93e114a6ec24264e035684cebe7d2074eb71eb1a71dd70bf61e8f.jpg
│   ├── iris-0ff5ba898a0ec179a25ca217af45374fdd06d606bb85fc29294291facad1776a.jpg
│   ├── iris-1175239c07a943d89a6335fb4b99a9fb5aabb2137c4d96102f10b25260ae523f.jpg
│   ├── iris-1289c57b571e8e98e4feb3e18a890130adc145b971b7e208a6ce5bad945b4a5a.jpg
│   ├── iris-12adb3a8516399e27ff1a9d20d28dca4674836ed00c7c0ae268afce2c30c4451.jpg
│   ├── iris-17ac8f7b5734443090f35bdc531bfe05b0235b5d164afb5c95f9d35f13655cf3.jpg
│   ├── iris-2118d3f235a574afd48a1f345bc2937dad6e7660648516c8029f4e76993ea74d.jpg
│   ├── iris-213cd179db580f8e633087dcda0969fd175d18d4f325cb5b4c5f394bbba0c1e0.jpg
│   ├── iris-21a1255e058722de1abe928e5bbe1c77bda31824c406c53f19530a3ca40be218.jpg
│   ├── iris-249370d38cc29bc2a4038e528f9c484c186fe46a126e4b6c76607860679c0453.jpg
│   ├── iris-2ac575a689662b7045c25e2554df5f985a3c6c0fd5236fabef8de9c78815330c.jpg
│   ├── iris-2c5b373c2a5fd214092eb578c75eb5dc84334e5f11a02f4fa23d5d316b18f770.jpg
│   ├── iris-2ecaad6dfe3d9b84a756bc2303a975a732718b954a6f54eae85f681ea3189b13.jpg
│   ├── iris-32827aec52e0f3fa131fa85f2092fc6fa02b1b80642740b59d029cef920c26b3.jpg
│   ├── iris-336fc3472b6465826f7cd87d5cef8f78d43cf2772ebe058ce71e1c5bad74c0e1.jpg
│   ├── iris-432026d8501abcd495bd98937a82213da97fca410af1c46889eabbcf2fd1b589.jpg
│   ├── iris-49a9158e46e788a39eeaefe82b19504d58dde167f540df6bc9492c3916d5f7ca.jpg
│   ├── iris-4b47f927405d90caa15cbf17b0442390fc71a2ca6fb8d07138e8de17d739e9a4.jpg
│   ├── iris-5691cad06fe37f743025c097fa9c4cec85e20ca3b0efff29175e60434e212421.jpg
│   ├── iris-5c38dba6f6c27064eb3920a5758e8f86c26fec662cc1ac4b5208d5f30d1e3ead.jpg
│   ├── iris-5da184e8620ebf0feef4d5ffe4346e6c44b2fb60cecc0320bd7726a1844b14cd.jpg
│   ├── iris-66eee9ff0bfa521905f733b2a0c6c5acad7b8f1a30d280ed4a17f54fe1822a7e.jpg
│   ├── iris-6815050b6117cf2e1fd60b1c33bfbb94837b8e173ff869f625757da4a04965c9.jpg
│   ├── iris-793fe85ddd6a97e9c9f184ed20d1d216e48bf85aa71633eff6d27073e0825d54.jpg
│   ├── iris-850229e6293a741277eb5efaa64d03c812f007c5d0f470992a8d4cfdb902230c.jpg
│   ├── iris-86d782d20ef7a60e905e367050b0413ca566acc672bc92add0bb0304faa54cfc.jpg
│   ├── iris-875a96790adc5672e044cf9da9d2edb397627884dfe91c488ab3fb65f65c80ff.jpg
│   ├── iris-96f06136df7a415550b90e443771d0b5b0cd990b503b64cc4987f5cb6797fa9b.jpg
│   ├── iris-9a889c96a37e8927f20773783a084f31897f075353d34a304c85e53be480e72a.jpg
│   ├── iris-9e3208f4f9fedc9598ddf26f77925a1e8df9d7865a4d6e5b4f74075d558d6a5e.jpg
│   ├── iris-a7e13b6f2d7f796768d898f5f66dceefdbd566dd4406eea9f266fc16dd68a6f2.jpg
│   ├── iris-b026efb61a9e3876749536afe183d2ace078e5e29615b07ac8792ab55ba90ebc.jpg
│   ├── iris-b3c086333cb5ccb7bb66a163cf4bf449dc0f28df27d6580a35832f32fd67bfc9.jpg
│   ├── iris-b795e034b6ea08d3cd9acaa434c67aca9d17016991e8dd7d6fd19ae8f6120b77.jpg
│   ├── iris-bb4a7ad4c844987bc9dc9dfad2b363698811efe3615512997a13cd191c23febc.jpg
│   ├── iris-bd60a6ed0369df4bea1934ef52277c32757838123456a595c0f2484959553a36.jpg
│   ├── iris-c15d6019ebe17d7446ced589ef5ef7a70474d35a8b072e0edfcec850b0a106db.jpg
│   ├── iris-c45295e76c6289504921412293d5ddbe4610bb6e3b593ea9ec90958e74b73ed2.jpg
│   ├── iris-c50d481f9fa3666c2c3808806c7c2945623f9d9a6a1d93a17133c4cb1560c41c.jpg
│   ├── iris-df4206653f1ec9909434323c05bb15ded18e72587e335f8905536c34a4be3d45.jpg
│   ├── iris-e45d869cb9d443b39d59e35c2f47870f5a2a335fce53f0c8a5bc615b9c53c429.jpg
│   ├── iris-e76fa5406e02a312c102f16eb5d27c7e0de37b35f801e1ed4c28bd4caf133e7a.jpg
│   ├── iris-e8d3fd862aae1c005bcc80a73fd34b9e683634933563e7538b520f26fd315478.jpg
│   ├── iris-ea578f650069a67e5e660bb22b46c23e0a182cbfb59cdf5448cf20ce858131b6.jpg
│   ├── iris-eba0c546e9b7b3d92f0b7eb98b2914810912990789479838807993d13787a2d9.jpg
│   ├── iris-f22d4b9605e62db13072246ff6925b9cf0240461f9dfc948d154b983db4243b9.jpg
│   ├── iris-fac5f8c23d8c50658db0f4e4a074c2f7771917eb52cbdf6eda50c12889510cf4.jpg
│   └── meta.csv
└── study2_raw_images/
    ├── iris-01cdd55ca6402713465841abddcce79a2e906e12edf95afb77c16bde4b4907dc.jpg
    ├── iris-02868b71ddd9b33ab795ac41609ea7b20a6e94f2543fad5d7fa11241d61feacf.jpg
    ├── iris-0415d2f3295db04bebc93249b685f7d7af7873faa911cd270ecd8363bd322ed5.jpg
    ├── iris-0c826b6f4648edf507e0cafdab53712bb6fd1f04dab453cee8db774a728dd640.jpg
    ├── iris-10fb9f154ead3c56ba0ab2c1ab609521c963f2326a648f82c9d7cabd178fc425.jpg
    ├── iris-14cbed88b0d2a929477bdf1299724f22d782e90f29ce55531f4a3d8608f7d926.jpg
    ├── iris-186fe29e32ee1405ddbdd36236dd7691a3c45ba78cc4c0bf11489fa09fbb1b65.jpg
    ├── iris-1b0b5aabd59e4c6ed1ceb54e57534d76f2f3f97e0a81800ff7ed901c35a424ab.jpg
    ├── iris-1d35672eb95f5b1cf14c2977eb025c246f83cdacd056115fdc93e946b56b610c.jpg
    ├── iris-1f941001f508ff1bd492457a90da64e52c461bfd64587a3cf7c6bf1bcb35adab.jpg
    ├── iris-2a09038b87009ecee5e5b4cd4cef068653809cc1e08984f193fad00f1c0df972.jpg
    ├── iris-308389e34b6d9a61828b339916aed7af295fdb1c7577c23fb37252937619e7e4.jpg
    ├── iris-30e4e56b1f170ff4863b178a0a43ea7a64fdd06c1f89a775ec4dbf5fec71e15c.jpg
    ├── iris-332953f4d6a355ca189e2508164b24360fc69f83304e7384ca2203ddcb7c73b5.jpg
    ├── iris-338fc323ed045a908fb1e8ff991255e1b8e01c967e36b054cb65edddf97b3bb0.jpg
    ├── iris-34a7cc16d26ba0883574e7a1c913ad50cf630e56ec08ee1113bf3584f4e40230.jpg
    ├── iris-360196ba36654c0d9070f95265a8a90bc224311eb34d1ab0cf851d8407d7c28e.jpg
    ├── iris-36132c6df6b47bda180b1daaafc7ac8a32fd7f9af83a92569da41429da49ea5b.jpg
    ├── iris-36f2b9282342292b67f38a55a62b0c66fa4e5bb58587f7fec90d1e93ea8c407a.jpg
    ├── iris-37ad07fd7b39bc377fa6e9cafdb6e0c57fb77df2c264fe631705a8436c0c2513.jpg
    ├── iris-3ba1625bb78e4b69b114bdafcdab64104b211d8ebadca89409e9e7ead6a0557c.jpg
    ├── iris-4c5d9a33327db025d9c391aeb182cbe20cfab4d4eb4ac951cc5cd15e132145d8.jpg
    ├── iris-522f3eb1807d015f99e66e73b19775800712890f2c7f5b777409a451fa47d532.jpg
    ├── iris-589fa96b9a3c2654cf08d05d3bebf4ab7bc23592d7d5a95218f9ff87612992fa.jpg
    ├── iris-61b71f1de04a03ce719094b65179b06e3cd80afa01622b30cda8c3e41de6bfaa.jpg
    ├── iris-62ef719cd70780088a4c140afae2a96c6ca9c22b72b078e3b9d25678d00b88a5.jpg
    ├── iris-819130af42335d4bb75bebb0d2ee2e353a89a3d518a1d2ce69842859c5668c5a.jpg
    ├── iris-8669e4937a2003054408afd228d99cb737e9db5088f42d292267c43a3889001a.jpg
    ├── iris-86c76e0f331bc62192c392cf7c3ea710d2272a8cc9928d2566a5fc4559e5dce4.jpg
    ├── iris-8a8bc54332a42bb35ee131d7b64e9375b4ac890632eb09e193835b838172d797.jpg
    ├── iris-8e9439ec7231fa3b9bc9f62a67af4e180466b32a72316600431b1ec93e63b296.jpg
    ├── iris-90b7d491b9a39bb5c8bb7649cce90ab7f483c2759fb55fda2d9067ac9eec7e39.jpg
    ├── iris-9dededf184993455c411a0ed81d6c3c55af7c610ccb55c6ae34dfac2f8bde978.jpg
    ├── iris-9e6ce91679c9aaceb3e9c930f11e788aacbfa8341a2a5737583c14a4d6666f3d.jpg
    ├── iris-a0e65269f7dc7801ac1ad8bd0c5aa547a70c7655447e921d1d4d153a9d23815e.jpg
    ├── iris-a445b0720254984275097c83afbdb1fe896cb010b5c662a6532ed0601ea24d7c.jpg
    ├── iris-a6b85bf1f3d18bbb6470440592834c2c7f081b490836392cf5f01636ee7cf658.jpg
    ├── iris-b005c82b844de575f0b972b9a1797b2b1fbe98c067c484a51006afc4f549ada4.jpg
    ├── iris-bfcf79b3b527eb64b78f9a068a1000042336e532f0f44e68f818dd13ab492a76.jpg
    ├── iris-c156236fb6e888764485e796f1f972bbc7ad960fe6330a7ce9182922046439c4.jpg
    ├── iris-d99d5fd2de5be1419cbd569570dbb6c9a6c8ec4f0a1ff5b55dc2607f6ecdca8f.jpg
    ├── iris-d9aae37a8fa6afdef2af170c266a597925eea935f4d070e979d565713ea62642.jpg
    ├── iris-dbc87fcecade2c070baaf99caf03f4f0f6e3aa977e34972383cb94d0efe8a95d.jpg
    ├── iris-e3d1a560d25cf573d2cbbf2fe6cd231819e998109a5cf1788d59fbb9859b3be2.jpg
    ├── iris-ec288bdad71388f907457db2476f12a5cb43c28cfa28d2a2077398a42b948a35.jpg
    ├── iris-ed5b4e072d43bc53a00a4a7f4d0f5d7c0cbd6a006e9c2d463128cedc956cb3de.jpg
    ├── iris-f3018a9440d17c265062d1c61475127f9952b6fe951d38fd7700402d706c0b01.jpg
    ├── iris-f47c5963cdbaa3238ba2d446848e8449c6af83e663f0a9216cf0baba8429b36f.jpg
    ├── iris-fa4b6d7e3617216104b1405cda21bf234840cd84a2c1966034caa63def2f64f0.jpg
    ├── iris-fc4b0cc65387ff78471659d14a78f0309a76f4c3ec641b871e40b40424255097.jpg
    └── meta.csv

Let’s create an artifact for the first sub-folder.

Py

artifact = ln.Artifact("s3://lamindata/iris_studies/study0_raw_images").save()
artifact

R

artifact <- ln$Artifact("s3://lamindata/iris_studies/study0_raw_images")$save()
artifact

Show code cell content Hide code cell content

artifact = ln.Artifact("s3://lamindata/iris_studies/study0_raw_images").save()
artifact

→ referenced read-only storage location at s3://lamindata, is managed by instance with uid 4XIuR0tvaiXM

Artifact(uid='7NipNDk2vSatBwWm0000', version=None, is_latest=True, key='iris_studies/study0_raw_images', description=None, suffix='', kind=None, otype=None, size=658465, hash='IVKGMfNwi8zKvnpaD_gG7w', n_files=51, n_observations=None, branch_id=1, space_id=1, storage_id=2, run_id=1, schema_id=None, created_by_id=1, created_at=2025-11-14 11:42:08 UTC, is_locked=False)

As you see from path, the folder was merely registered in its present storage location without copying it.

Py

artifact.path

R

artifact$path

Show code cell content Hide code cell content

artifact.path

S3QueryPath('s3://lamindata/iris_studies/study0_raw_images')

LaminDB keeps track of all your storage locations.

Py

ln.Storage.to_dataframe()

R

ln$Storage$df()

Show code cell content Hide code cell content

ln.Storage.to_dataframe()

	uid	root	description	type	region	instance_uid	is_locked	created_at	branch_id	space_id	created_by_id	run_id
id
2	YmV3ZoHvAAAA	s3://lamindata	None	s3	us-east-1	4XIuR0tvaiXM	False	2025-11-14 11:42:07.761000+00:00	1	1	1	1.0
1	IpIww7jFzPYA	/home/runner/work/lamin-docs/lamin-docs/docs/l...	None	local	None	5WCoFhciyw3n	False	2025-11-14 11:41:54.413000+00:00	1	1	1	NaN

How do I update or delete an artifact?

artifact.description = "My new description"  # change description
artifact.save()  # save the change to the database
artifact.delete()  # move to trash
artifact.delete(permanent=True)  # permanently delete

How do I create an artifact for a local file or folder?

Source path is local:

ln.Artifact("./my_data.fcs", key="my_data.fcs")
ln.Artifact("./my_images/", key="my_images")

Upon artifact.save(), the source path will be copied or uploaded into your instance’s current storage, visible & changeable via ln.settings.storage.

If the source path is remote or already in a registered storage location (one that’s registered in ln.Storage), artifact.save() will not trigger a copy or upload but register the existing path.

ln.Artifact("s3://my-bucket/my_data.fcs")  # key is auto-populated from S3, you can optionally pass a description
ln.Artifact("s3://my-bucket/my_images/")  # key is auto-populated from S3, you can optionally pass a description

You can use any storage location supported by `fsspec`.

Which fields are populated when creating an artifact record?

Basic fields:

• uid: universal ID

• key: a (virtual) relative path of the artifact in storage

• description: an optional string description

• storage: the storage location (the root, say, an S3 bucket or a local directory)

• suffix: an optional file/path suffix

• size: the artifact size in bytes

• hash: a hash useful to check for integrity and collisions (is this artifact already stored?)

• hash_type: the type of the hash

• created_at: time of creation

• updated_at: time of last update

Provenance-related fields:

• created_by: the User who created the artifact

• run: the Run of the Transform that created the artifact

For a full reference, see Artifact.

What exactly happens during save?

In the database: An artifact record is inserted into the Artifact registry. If the artifact record exists already, it’s returned.

In storage:

• If the default storage is in the cloud, .save() triggers an upload for a local artifact.

• If the artifact is already in a registered storage location, only the metadata of the record is saved to the artifact registry.

How does LaminDB compare to a AWS S3?

LaminDB provides a database on top of AWS S3 (or GCP storage, file systems, etc.).

Similar to organizing files with paths, you can organize artifacts using the key parameter of Artifact.

However, you’ll see that you can more conveniently query data by entities you care about: people, code, experiments, genes, proteins, cell types, etc.

Are artifacts aware of array-like data?

Yes.

You can make artifacts from paths referencing array-like objects:

ln.Artifact("./my_anndata.h5ad", key="my_anndata.h5ad")
ln.Artifact("./my_zarr_array/", key="my_zarr_array")

Or from in-memory objects:

ln.Artifact.from_dataframe(df, key="my_dataframe.parquet")
ln.Artifact.from_anndata(adata, key="my_anndata.h5ad")

You can open large artifacts for slicing from the cloud or load small artifacts directly into memory via:

artifact.open()

Manage biological registries

Every bionty registry is based on configurable public ontologies (>20 of them) that are automatically leveraged during validation & annotation. Sometimes you want to access the public ontology directly.

import bionty as bt

cell_type_ontology = bt.CellType.public()
cell_type_ontology

Show code cell output Hide code cell output

PublicOntology
Entity: CellType
Organism: all
Source: cl, 2025-04-10
#terms: 3136

The returned object can be searched like you can search a registry.

cell_type_ontology.search("gamma-delta T cell").head(2)

Show code cell output Hide code cell output

	name	definition	synonyms	parents
ontology_id
CL:0000798	gamma-delta T cell	A T Cell That Expresses A Gamma-Delta T Cell R...	gamma-delta T lymphocyte|gamma-delta T-lymphoc...	[CL:0000084]
CL:4033072	cycling gamma-delta T cell	A(N) Gamma-Delta T Cell That Is Cycling.	proliferating gamma-delta T cell	[CL:4033069, CL:0000798]

Because you can’t update an external public ontology, you update the content of the corresponding registry. Here, you create a new cell type.

# create an ontology-coupled cell type record and save it
neuron = bt.CellType.from_source(name="neuron").save()

# create a record to track a new cell state
new_cell_state = bt.CellType(
    name="my neuron cell state", description="explains X"
).save()

# express that it's a neuron state
new_cell_state.parents.add(neuron)

# view ontological hierarchy
new_cell_state.view_parents(distance=2)

Show code cell output Hide code cell output

Manage AnnData objects

LaminDB supports a growing number of data structures: DataFrame, AnnData, MuData, SpatialData, and Tiledbsoma with their corresponding representations in storage.

Let’s go through the example of the quickstart, but store the dataset in an AnnData this time.

# define var schema
var_schema = ln.Schema(itype=bt.Gene.ensembl_gene_id, dtype=int).save()

# define composite schema
anndata_schema = ln.Schema(
    otype="AnnData", slots={"obs": schema, "var.T": var_schema}
).save()

Validate & annotate an AnnData.

import anndata as ad

# store the dataset as an AnnData object to distinguish data from metadata
adata = ad.AnnData(df.iloc[:, :3], obs=df.iloc[:, 3:-1])

# save curated artifact
artifact = ln.Artifact.from_anndata(
    adata, key="my_datasets/my_rnaseq1.h5ad", schema=anndata_schema
).save()
artifact.describe()

Show code cell output Hide code cell output

→ writing the in-memory object into cache

→ loading artifact into memory for validation

→ returning schema with same hash: Schema(uid='0Mg3OQtjlDCLmJGf', name=None, description=None, n=8, is_type=False, itype='Feature', otype=None, dtype=None, hash='1SotJiS28Qs9O7bjf4cWOA', minimal_set=True, ordered_set=False, maximal_set=False, slot=None, branch_id=1, space_id=1, created_by_id=1, run_id=1, type_id=None, validated_by_id=None, composite_id=None, created_at=2025-11-14 11:42:03 UTC, is_locked=False)

Artifact: my_datasets/my_rnaseq1.h5ad (0000)
├── uid: mtpBd8pT5XE95jjH0000            run: 0NDdAcE (tutorial.ipynb)
│   kind: dataset                        otype: AnnData               
│   hash: TWUlDi-V-Try1uCxWJ65nQ         size: 29.5 KB                
│   branch: main                         space: all                   
│   created_at: 2025-11-14 11:42:12 UTC  created_by: anonymous        
│   n_observations: 3                                                 
├── storage/path: /home/runner/work/lamin-docs/lamin-docs/docs/lamindb-tutorial/.lamindb/mtpBd8pT5XE95jjH0000.h5ad
├── Dataset features
│   ├── obs (8)                                                                                                    
│   │   assay_oid                       bionty.ExperimentalFactor.ontolo…  EFO:0008913                             
│   │   cell_type_by_expert             bionty.CellType                    B cell, CD8-positive, alpha-beta T cell 
│   │   cell_type_by_model              bionty.CellType                    B cell, T cell                          
│   │   perturbation                    Record                             DMSO, IFNG                              
│   │   donor                           str                                                                        
│   │   sample_note                     str                                                                        
│   │   concentration                   str                                                                        
│   │   treatment_time_h                num                                                                        
│   └── var.T (3 bionty.Gene.ensembl_…                                                                             
│       CD8A                            num                                                                        
│       CD4                             num                                                                        
│       CD14                            num                                                                        
└── Labels
    └── .records                        Record                             DMSO, IFNG                              
        .cell_types                     bionty.CellType                    T cell, B cell, CD8-positive, alpha-bet…
        .experimental_factors           bionty.ExperimentalFactor          single-cell RNA sequencing              

Because AnnData separates the high-dimensional count matrix that’s typically indexed with Ensembl gene ids from the metadata, we’re now working with two types of feature sets (bt.Gene for the counts and ln.Feature for the metadata). These correspond to the obs and the var schema in the anndata_schema.

If you want to find a dataset by whether it measured CD8A, you can do so as as follows.

# query for all feature sets that contain CD8A
feature_sets = ln.Schema.filter(genes__symbol="CD8A").all()

# query for all artifacts linked to these feature sets
ln.Artifact.filter(feature_sets__in=feature_sets).to_dataframe()

Show code cell output Hide code cell output

	uid	key	description	suffix	kind	otype	size	hash	n_files	n_observations	version	is_latest	is_locked	created_at	branch_id	space_id	storage_id	run_id	schema_id	created_by_id
id
4	mtpBd8pT5XE95jjH0000	my_datasets/my_rnaseq1.h5ad	None	.h5ad	dataset	AnnData	30232	TWUlDi-V-Try1uCxWJ65nQ	None	3	None	True	False	2025-11-14 11:42:12.603000+00:00	1	1	1	1	4	1

Scale learning

How do you integrate new datasets with your existing datasets? Leverage Collection.

# a new dataset
df2 = ln.examples.datasets.mini_immuno.get_dataset2(otype="DataFrame")
adata = ad.AnnData(df2.iloc[:, :3], obs=df2.iloc[:, 3:-1])
artifact2 = ln.Artifact.from_anndata(
    adata, key="my_datasets/my_rnaseq2.h5ad", schema=anndata_schema
).save()

Show code cell output Hide code cell output

→ writing the in-memory object into cache

→ loading artifact into memory for validation

Create a collection using Collection.

collection = ln.Collection([artifact, artifact2], key="my-RNA-seq-collection").save()
collection.describe()
collection.view_lineage()

Show code cell output Hide code cell output

Collection: my-RNA-seq-collection (0000)
└── uid: SgXmC2QRIWGNNEXx0000            run: 0NDdAcE (tutorial.ipynb)
    branch: main                         space: all                   
    created_at: 2025-11-14 11:42:14 UTC  created_by: anonymous        

# if it's small enough, you can load the entire collection into memory as if it was one
collection.load()

# typically, it's too big, hence, open it for streaming (if the backend allows it)
# collection.open()

# or iterate over its artifacts
collection.artifacts.all()

# or look at a DataFrame listing the artifacts
collection.artifacts.to_dataframe()

Show code cell output Hide code cell output

	uid	key	description	suffix	kind	otype	size	hash	n_files	n_observations	version	is_latest	is_locked	created_at	branch_id	space_id	storage_id	run_id	schema_id	created_by_id
id
5	hjWUc0ed8T9sWzI40000	my_datasets/my_rnaseq2.h5ad	None	.h5ad	dataset	AnnData	23712	evwa9JaetcfvvMASeqqDVA	None	3	None	True	False	2025-11-14 11:42:14.292000+00:00	1	1	1	1	4	1
4	mtpBd8pT5XE95jjH0000	my_datasets/my_rnaseq1.h5ad	None	.h5ad	dataset	AnnData	30232	TWUlDi-V-Try1uCxWJ65nQ	None	3	None	True	False	2025-11-14 11:42:12.603000+00:00	1	1	1	1	4	1

Directly train models on collections of AnnData.

# to train models, batch iterate through the collection as if it was one array
from torch.utils.data import DataLoader, WeightedRandomSampler
dataset = collection.mapped(obs_keys=["cell_medium"])
sampler = WeightedRandomSampler(
    weights=dataset.get_label_weights("cell_medium"), num_samples=len(dataset)
)
data_loader = DataLoader(dataset, batch_size=2, sampler=sampler)
for batch in data_loader:
    pass

Read this blog post for more on training models on distributed datasets.