A curated collection of resources originally put together for the Open Data Knowledge Graph hackathon. This list includes relevant literature, github repos, technical blogs, videos, tools, and workspace resources that can help you learn more about knowledge graphs for biomedical datasets.
- The Unified Biomedical Knowledge Graph (UBKG) - Silverstein JC, et al. (2023)
- UBKG Context Schema - J. Alan Simmons, Jonathan C. Silverstein, Benjamin J. Stear, Taha Mohseni Ahooyi, Deanne M. Taylor: Ontologies and annotation sources
- NIH CFDE Data Distillery GitHub Repository - Mohseni Ahooyi T, Stear B, Nemarich C, Simmons A, Silverstein J, Taylor DM (2025a)
- Homo sapiens Chromosomal Location Ontology - Mohseni Ahooyi T, et al. (2025b): A framework for genomic data in biomedical knowledge graphs
- Petagraph - Stear, B.J., et al. (2024)
- Petagraph Data Source Descriptions - Stear BJ, Mohseni Ahooyi T, Taylor DM
- Petagraph Project - Stear BJ, Mohseni Ahooyi T, Taylor DM
- BioHackrXiv Preprint - Validating Subtype Specific Oncology Drug Predictions
- OSF Project - Oncomatch- Optimizing Oncology Combination Therapy Prediction
- GSoC 2025 - Generate Gene and Pathway Lists for OncoTree Codes using LLM Prompting
- An Open Source Knowledge Graph Ecosystem for the Life Sciences (Nature Scientific Data, 2024)
- KG-Hub—Building and Exchanging Biological Knowledge Graphs (Bioinformatics, 2023)
- PrimeKG—A Multimodal Knowledge Graph for Precision Medicine Analyses (Nature Scientific Data, 2023)
- Knowledge Graphs for the Life Sciences: Recent Developments and Future Directions (Dagstuhl, TGDK, 2023)
- PubMed Knowledge Graph 2.0 (Nature Scientific Data, 2025)
- Biolink Model: A universal schema for knowledge graphs in clinical, biomedical, and translational science (Clin Transl Sci. 2022)
- Biolink Model
- Open Source Knowledge Graph Ecosystem for Life Sciences - PheKnowLator (Nature Scientific data, 2024)
- Data-centered Knowledge Graphs for Drug/Chemical Development (Computational and Structural Biotechnology Journal, 2022)
- mosGraphGPT: a foundation model for multi-omic signaling graphs using generative AI
- mosGraphGPT
- KG-Microbe - Building Modular and Scalable Knowledge Graphs for Microbiome and Microbial Sciences
- KG-Microbe
- Improving Biomedical Knowledge Graph Quality: A Community Approach
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
- Insights, Techniques, and Evaluation for LLM-Driven Knowledge Graphs
- BaseGraph: Largest Biodiversity Knowledge Graph
- GraphRAG Tutorial with PyG and Graph Databases
- Knowledge Graphs on AWS
- Sample Agents for Healthcare and Life Sciences on AWS
- Example Knowledge Graph using UniProt
- NVIDIA Technical Blog on GraphRAG
- Web-Scale Data Integration in Life Sciences
- Transformer-Based Knowledge Graph Engines for Biomedicine
- Building GraphRAG solutions using Amazon Bedrock knowledge bases and Amazon Neptune analytics
- Open Knowledge Bases in the Age of Generative AI - BOSC2025 Keynote 2 Chris Mungall
- Knowledge-Graph-Hub
- KG-Cookiecutter
- TreeTag
- GraphRAG Toolkit Sample notebooks
- Neptune Graph Notebook example
- Excalidraw
- PyG Container
- New module: Check out the new 25.09 NVIDIA PyG container. This includes the latest GNN+LLM features. See examples/llm/README.md in PyG Github or inside the container itself.
- New module for Graph ML enhanced RAG
torch_geometric.llm - Example for full e2e GNN infused RAG pipeline including KG creation, Retrieval, GNN+LLM Finetuning, and Question Answering Evaluation using an LLM judge
examples/llm/txt2kg_rag.py - Graph Neural Networks & LLMs in PyG