liveBook · Manning

Hetionet

As explained in Knowledge Graphs and LLMs in Action

Hetionet is a biomedical knowledge graph integrating entities and relationships involving diseases, genes, drugs, and other biological concepts.

Hetionet is a heterogeneous biomedical knowledge graph integrating 29 public resources into a shared schema of compounds, diseases, genes, anatomies, pathways, biological processes, molecular functions, cellular components, perturbations, pharmacologic classes, side effects, and symptoms. section 4.3

A practical Hetionet workflow includes:

  • Import the publicly available Neo4j database rather than assembling the contributing resources manually. section 4.3
  • Inspect node and relationship distributions to evaluate schema coverage and information completeness. section 4.3

Scale and evidence

The imported graph contains 47,031 nodes across 11 types and 2,250,197 relationships across 24 types. A Compound–binds–Gene relationship records its supporting reference as an edge attribute. section 4.3

How Knowledge Graphs and LLMs in Action covers it

How deep it goes
Descends through schema design, Neo4j import, distribution checks, typed paths, and path-based analysis.
Examples
Uses compound–gene binding edges, node-type distributions, relationship distributions, metapaths, PDP, and DWPC.
What you can do after
Operate Hetionet in Neo4j and analyze typed biomedical paths while checking coverage and relationship provenance.
How it connects
Connects knowledge graphs with metapaths, drug–target interactions, drug–disease treatments, and biological processes.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Knowledge Graphs and LLMs in Action. The section links point to the parts of the book it draws on.