Example biomedical knowledge graph for training and benchmarking

[dmccloskey]

Description

As a researcher, I would like an open-source biomedical knowledge graph that can be used for testing and benchmarking. A popular open-source knowledge graph that has been used in various benchmarking tasks is PrimeKG https://github.com/mims-harvard/PrimeKG which has been used in STARK https://github.com/snap-stanford/stark and BioBridge https://github.com/RyanWangZf/BioBridge. In particular, we are most interested in the question and answering tasks (node classification) from STARK and potentially the cross-modality prediction from BioBridge

Checklist

• Scripts for downloading PrimeKG
• Scripts for setting up and running the STARK benchmark
• (Optional) Scripts for setting up and running the BioBridge benchmark

Acceptance criteria

• Docs, Lints, and Unit tests as appropriate to support the scripts for downloading the data assets and running the benchmarks
• Jupyter notebook demonstrating how to download the datasets and run the benchmarks
• Successful PR

Resources

Please see "Downloading datasets and models (Stark example)" from https://virtualpatientengine.github.io/VPEHackathonAIAgentsCO/setup/

[github-actions]

🎉 This issue has been resolved in version 1.5.0 🎉

The release is available on GitHub release

Your semantic-release bot 📦🚀