biobtree

is a Knowledge Graph.

BioBTree is a unified biomedical knowledge graph that integrates more than 70 primary data sources, including Ensembl, UniProt, PDB, ChEMBL, Reactome, and ClinVar, into a single queryable graph of cross-reference edges spanning genes, proteins, compounds, diseases, pathways, and clinical data. It lets users search, map, and traverse identifiers across databases with a chain-query syntax (for example, mapping a gene in Ensembl to UniProt proteins and on to PDB structures), and exposes the graph through a REST API, a Model Context Protocol (MCP) server, and a question-answering web interface for grounding LLM responses in structured biomedical data.

License

AGPL-3.0

Homepage

biobtree

Repository

GitHub

External IDs

No external IDs available

Product Summary

Contacts

Tamer Gur

Github: tamerh

Products

From this Resource
ID Name URL Category Format Description
biobtree.graph.human-subgraph BioBTree Knowledge Graph - Human Subgraph (KGX) 20816742 Graph kgx Human-scoped, Neo4j-ready subgraph of...
biobtree.api BioBTree REST API api Programming Interface http REST API for searching identifiers an...
biobtree.mcp BioBTree MCP Server mcp Programming Interface http Model Context Protocol (MCP) server e...
biobtree.qa BioBTree Q&A Interface biobtree Graphical Interface http Web-based question-and-answer interfa...
biobtree.docs BioBTree Repository and Documentation biobtree Documentation http Source code, dataset documentation, a...
From other Resources
ID Name URL Category Format Relation Description
sugi-atlas.portal Sugi Atlas Web Site atlas Graphical Interface http was derived from Sugi Atlas web site with search and o...
sugi-atlas.manifest Sugi Atlas Manifest manifest.json (12.2 MB) Product json was derived from JSON manifest of the atlas corpus, ma...

Details

BioBTree

BioBTree is a unified biomedical knowledge graph that integrates more than 70 primary data sources into a single queryable graph of cross-reference edges. It spans genes, proteins, compounds, diseases, pathways, and clinical data from resources such as Ensembl, UniProt, PDB, ChEMBL, Reactome, and ClinVar.

Users can search identifiers and special keywords, map between databases using a chain-query syntax, and traverse connections across resources in a single query. BioBTree is accessible through a REST API, a Model Context Protocol (MCP) server for AI and LLM integration, and a question-answering web interface designed to ground LLM responses in authoritative, identifier-anchored biomedical data.

Is this information incorrect or incomplete? Request an update.

Created: June 15, 2026 | Last modified: June 24, 2026