Lamindb Data Management

pip install lamindb
# With extras for specific data types
pip install 'lamindb[bionty,zarr,fcs]'

lamin login
lamin init --storage ./my-data --name my-project
# Or with cloud storage:
# lamin init --storage s3://my-bucket --name my-project --db postgresql://...

import lamindb as ln

ln.track()  # Start lineage tracking

# Save an artifact
import pandas as pd
df = pd.DataFrame({"gene": ["TP53", "BRCA1"], "score": [0.95, 0.87]})
artifact = ln.Artifact.from_df(df, key="results/gene_scores.parquet", description="Gene importance scores")
artifact.save()
print(f"Saved: {artifact.uid}, size: {artifact.size}")

# Query artifacts
results = ln.Artifact.filter(key__startswith="results/").df()
print(f"Found {len(results)} artifacts")

ln.finish()

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

ln.track()

# From DataFrame
df = pd.DataFrame({"sample": ["A", "B"], "value": [1.5, 2.3]})
artifact = ln.Artifact.from_df(df, key="experiments/batch1.parquet").save()
print(f"ID: {artifact.uid}, Version: {artifact.version}")

# From AnnData
adata = ad.read_h5ad("counts.h5ad")
artifact = ln.Artifact.from_anndata(adata, key="scrna/batch1.h5ad", description="scRNA-seq batch 1").save()

# From file path
artifact = ln.Artifact("results/figure.png", key="figures/fig1.png").save()

# Load back
df_loaded = artifact.load()  # Returns DataFrame/AnnData/etc.
path = artifact.cache()       # Returns local file path

# Versioning
artifact_v2 = ln.Artifact.from_df(df_updated, key="experiments/batch1.parquet", revises=artifact).save()
print(f"v1: {artifact.uid}, v2: {artifact_v2.uid}")
print(f"Latest version: {artifact_v2.is_latest}")

# Delete (archive first, then permanent)
artifact.delete(permanent=False)  # Archive
# artifact.delete(permanent=True)  # Permanent deletion

import lamindb as ln

# Start tracking — captures notebook/script, environment, user
ln.track(params={"method": "PCA", "n_components": 50})

# All artifacts created within this block are linked to this run
input_data = ln.Artifact.get(key="raw/counts.h5ad")
adata = input_data.load()

# ... analysis code ...

output = ln.Artifact.from_anndata(adata, key="processed/pca.h5ad").save()

# View lineage graph
output.view_lineage()

ln.finish()  # Finalize tracking

import lamindb as ln

# Basic filtering
artifacts = ln.Artifact.filter(key__startswith="scrna/").df()
print(f"Found {len(artifacts)} scRNA-seq artifacts")

# Filter by metadata
recent = ln.Artifact.filter(
    created_at__gte="2026-01-01",
    size__gt=1000000
).df()

# Filter by annotated features
immune = ln.Artifact.filter(
    cell_types__name="T cell",
    tissues__name="PBMC"
).df()

# Single record retrieval
artifact = ln.Artifact.get(key="results/final.parquet")  # Exact match, raises if not found
artifact = ln.Artifact.filter(key="results/final.parquet").one_or_none()  # Returns None if missing

# Full-text search
results = ln.Artifact.search("gene expression PBMC")

# Streaming large files (without full load into memory)
artifact = ln.Artifact.get(key="large_dataset.h5ad")
backed = artifact.open()  # AnnData-backed mode
subset = backed[backed.obs["cell_type"] == "B cell"]

import lamindb as ln
import bionty as bt

# Annotate artifacts with features
artifact = ln.Artifact.get(key="scrna/batch1.h5ad")
artifact.features.add_values({
    "tissue": "PBMC",
    "condition": "treated",
    "organism": "human",
    "batch": 1
})

# Validate with schema
curator = ln.curators.AnnDataCurator(adata, schema)
try:
    curator.validate()
    artifact = curator.save_artifact(key="validated/batch1.h5ad")
    print("Validation passed")
except ln.errors.ValidationError as e:
    print(f"Validation failed: {e}")

# Standardize cell type names using ontology
adata.obs["cell_type"] = bt.CellType.standardize(adata.obs["cell_type"])

import bionty as bt

# Available ontologies
# bt.Gene (Ensembl), bt.Protein (UniProt), bt.CellType (CL),
# bt.Tissue (Uberon), bt.Disease (Mondo), bt.Pathway (GO),
# bt.CellLine (CLO), bt.Phenotype (HPO), bt.Organism (NCBItaxon)

# Import and search ontology
bt.CellType.import_source()
results = bt.CellType.search("T helper")
print(results.head())

# Get specific term
t_cell = bt.CellType.get(name="T cell")
print(f"Ontology ID: {t_cell.ontology_id}")

# Explore hierarchy
children = t_cell.children.all()
parents = t_cell.parents.all()
print(f"Children: {[c.name for c in children]}")

# Validate a list of terms
validated = bt.CellType.validate(["T cell", "B cell", "Unknown_type"])
# Returns boolean array: [True, True, False]

import lamindb as ln

# Create a collection
artifacts = ln.Artifact.filter(key__startswith="scrna/batch_").all()
collection = ln.Collection(artifacts, name="scRNA-seq batches Q1 2026").save()
print(f"Collection: {collection.name}, {collection.n_objects} artifacts")

# Query collection
for artifact in collection.artifacts.all():
    print(f"  {artifact.key}: {artifact.size} bytes")

# Organize with hierarchical keys
# Convention: project/experiment/datatype/file
# e.g., "immunology/exp42/scrna/counts.h5ad"

ln.track(params={"key": "value"})   # Start: captures code, environment, user
# ... analysis ...
ln.finish()                          # End: finalizes lineage links

import lamindb as ln
import anndata as ad

ln.track()

# Register multiple experiments
data_files = ["batch1.h5ad", "batch2.h5ad", "batch3.h5ad"]
tissues = ["PBMC", "bone_marrow", "PBMC"]
conditions = ["control", "treated", "treated"]

for i, (file, tissue, condition) in enumerate(zip(data_files, tissues, conditions)):
    adata = ad.read_h5ad(file)
    artifact = ln.Artifact.from_anndata(
        adata, key=f"scrna/batch_{i}.h5ad", description=f"scRNA-seq batch {i}"
    ).save()
    artifact.features.add_values({
        "tissue": tissue, "condition": condition, "batch": i
    })
    print(f"Registered batch {i}: {artifact.uid}")

# Query across all experiments
treated_pbmc = ln.Artifact.filter(
    key__startswith="scrna/",
    features__tissue="PBMC",
    features__condition="treated"
).all()
print(f"Found {len(treated_pbmc)} matching datasets")

# Load and concatenate
import anndata as ad
adatas = [a.load() for a in treated_pbmc]
combined = ad.concat(adatas)
print(f"Combined: {combined.shape}")

ln.finish()

import lamindb as ln
import bionty as bt
import anndata as ad

ln.track()

# 1. Import ontologies
bt.CellType.import_source()
bt.Gene.import_source(organism="human")

# 2. Load raw data
adata = ad.read_h5ad("raw_counts.h5ad")
print(f"Raw: {adata.shape}")

# 3. Validate and standardize cell types
validated = bt.CellType.validate(adata.obs["cell_type"].unique())
if not all(validated):
    adata.obs["cell_type"] = bt.CellType.standardize(adata.obs["cell_type"])

# 4. Validate gene names
gene_validated = bt.Gene.validate(adata.var_names)
print(f"Valid genes: {sum(gene_validated)}/{len(gene_validated)}")

# 5. Curate and save
curator = ln.curators.AnnDataCurator(adata, schema)
curator.validate()
artifact = curator.save_artifact(key="curated/validated_counts.h5ad")
print(f"Saved curated artifact: {artifact.uid}")

ln.finish()

import lamindb as ln
from pathlib import Path

ln.track()

data_dir = Path("raw_data/")
for fcs_file in data_dir.glob("*.fcs"):
    artifact = ln.Artifact(str(fcs_file), key=f"flow_cytometry/{fcs_file.name}").save()
    artifact.features.add_values({"assay": "flow_cytometry", "source": "batch_import"})
    print(f"Registered: {fcs_file.name} -> {artifact.uid}")

ln.finish()

import lamindb as ln

artifact = ln.Artifact.get(key="results/final_analysis.h5ad")

# View lineage graph (opens in browser or notebook)
artifact.view_lineage()

# Programmatic lineage access
run = artifact.run
print(f"Created by: {run.transform.name}")
print(f"User: {run.created_by.name}")
print(f"Date: {run.created_at}")
print(f"Input artifacts: {[a.key for a in run.input_artifacts.all()]}")

import bionty as bt

bt.CellType.import_source()
t_cell = bt.CellType.get(name="T cell")

# Explore hierarchy
print(f"Parents: {[p.name for p in t_cell.parents.all()]}")
print(f"Children: {[c.name for c in t_cell.children.all()]}")

# Find all descendants
descendants = t_cell.children.all()
for child in descendants:
    grandchildren = child.children.all()
    print(f"  {child.name}: {[gc.name for gc in grandchildren]}")