Skip to content


The Neurobagel ecosystem comprises four primary tools:

  • The annotation tool (
    • to create harmonized annotations of phenotypic variables
    • intended for use by researchers and domain experts
    • static site, deployed on GitHub Pages
  • The command-line interface
    • to extract subject-specific metadata from annotated phenotypic and BIDS data
    • intended for data managers to create graph-ready harmonized data
  • The knowledge graph store and Neurobagel API (e.g.,
    • to store and query extracted metadata using RDF and the SPARQL query language
    • intended for research/data platform owners and for isolated deployments
  • The query tool (
    • to search across datasets and obtain metadata for subjects based on harmonized subject-level attributes
    • intended to help researchers and scientific data users find cohorts
    • static site, deployed on GitHub Pages

You can also find official Docker images for our containerized tools on the Neurobagel Docker Hub profile.


Add Neurobagel figure for overview.

Getting started

Want to annotate an exiting dataset using Neurobagel? See Annotating a dataset.

Want to deploy the Neurobagel software stack at your local research institute? See Setting up a graph.

Want to search for participants in the Neurobagel graph? See Running cohort queries.