biocypher/biocypher

A unifying framework for biomedical research knowledge graphs

What it solves

BioCypher simplifies the complex process of creating and maintaining knowledge graphs (KGs), particularly for the life sciences. It provides a structured way to integrate diverse biological data sources into a graph format that can be used for data storage, reasoning, and artificial intelligence applications.

How it works

BioCypher acts as a framework for building pipelines that transform raw data from various resources into a semantic graph structure. It utilizes adapters to connect to different data sources and outputs, allowing users to define how data is mapped and integrated into a unified knowledge graph.

Who it’s for

Researchers and data scientists in the life sciences who need to organize complex biological data into knowledge graphs for analysis, exploration, or AI-driven discovery.

Highlights

  • Supports the creation and maintenance of semantic knowledge graphs.
  • Integrates with Neo4j for graph database storage.
  • Provides a project template to help users quickly start their own data pipelines.
  • Peer-reviewed and published in Nature Biotechnology.

Related

  • Project
    InternScience/GraphGen

    A framework for generating knowledge-driven synthetic data using knowledge graphs to fill knowledge gaps in LLMs for improved supervised fine-tuning.

  • Project
    neo4j/graph-data-science

    A graph data science library for Neo4j that provides graph algorithms, transformations, and machine learning pipelines operated via Cypher procedures.

  • Project
    Graphify-Labs/graphify

    A tool that maps codebases, docs, and media into a knowledge graph, allowing developers to query relationships and trace paths between concepts instead of grepping files.

  • Project
    neo4j/neo4j-graphrag-python

    The official Neo4j Python package for building GraphRAG applications, enabling the automated construction of knowledge graphs and hybrid retrieval for LLMs.

  • Project
    xoai/sage-wiki

    A graph-based knowledge base that uses LLMs to compile raw documents into an interlinked wiki and knowledge graph for shared human-AI memory.