Skip to main content
Ctrl+K
logo

Lamin Docs

Site Navigation

  • Guide
  • API Reference
  • Integrations
  • Changelog

Site Navigation

  • Guide
  • API Reference
  • Integrations
  • Changelog

Overview

  • Introduction
  • Tutorial

How to

  • Install & setup
  • Query & search
    • Query tables in storage
    • Query arrays in storage
  • Track notebooks, scripts & workflows
  • Organize datasets
    • Curate datasets
  • Manage changes
  • Access & manage ontologies
    • Manage biological ontologies
    • Access public ontologies
      • Gene
      • Protein
      • Organism
      • CellLine
      • CellType
      • CellMarker
      • Tissue
      • Disease
      • Phenotype
      • Pathway
      • ExperimentalFactor
      • DevelopmentalStage
      • Ethnicity
  • Transfer & sync across databases

Use cases

  • Agentic analyses
    • Target prioritization
    • Copy-number variation
    • Perturbation modeling
    • Scanpy analysis
  • Query & build atlases
    • 1000 Genomes
    • Arc Virtual Cell Atlas
    • CELLxGENE
      • Curate AnnData based on the CELLxGENE schema
    • EWAS Data Hub
    • Hubmap
    • RxRx
  • Manage data types
    • scRNA-seq
      • Standardize and append a dataset
      • Query artifacts
      • Analyze a collection in memory
      • Train a machine learning model on a collection
      • Concatenate datasets to a single array store
      • Preprocessing and clustering 3k PBMCs
    • Bulk RNA-seq
    • Methylation
    • Genomic variants
    • Flow cytometry
      • Append a new dataset
      • Query & integrate data
      • Analyze the collection and save a result
    • Spatial RNA-seq
      • Interactive visualization using Vitessce
      • Curate and ingest spatial data
      • Train a spatial ML model
    • Single-cell imaging
      • Generate single-cell images
      • Featurize single-cell images
      • Identify autophagy-positive cells
    • Multi-modal
    • EHR
  • Leverage ontologies
    • CellTypist
    • Gene Ontology (GO)
    • Cell type annotation and pathway analysis
    • RDF export & SPARQL queries
  • Manage computational pipelines
    • Nextflow
    • Redun
    • Snakemake
  • Manage MLOps
    • Lightning
    • Curate MNIST
    • Weights & Biases
    • MLFlow
    • ClearML
    • Croissant
  • Manage visualization dashboards
    • Vitessce: AnnData
    • Vitessce: SpatialData

The Hub

  • Manage records
  • Launch computational pipelines
  • Manage access permissions
  • Audit log
  • Security

Other topics

  • System design
    • Will data & metadata stay in sync?
    • Will data get duplicated upon re-running code?
  • FAQ
    • Pydantic, Pandera, and LaminDB
    • Can I disable tracking run inputs?
    • How do I validate & annotate arbitrary data structures?
    • Keep artifacts local in a cloud instance
    • Why should I not index datasets with gene symbols?
    • How does search work?
  • Influences
  • Glossary

FAQ .md¶

  • Pydantic, Pandera, and LaminDB
  • Can I disable tracking run inputs?
  • How do I validate & annotate arbitrary data structures?
  • Keep artifacts local in a cloud instance
  • Why should I not index datasets with gene symbols?
  • How does search work?

previous

Will data get duplicated upon re-running code?

next

Pydantic, Pandera, and LaminDB

© 2026 Lamin Labs · Hub · Docs · Security · Blog · Contact · About · Legal · Imprint · LinkedIn · X · GitHub