BioKG with attributes and decoupled benchmarks
<p>BioKG is a biomedical knowledge graph containing relationships between proteins, molecules, diseases, and others. It was originally proposed by Walsh et al. (2020) in <a href="https://dl.acm.org/doi/10.1145/3340531.3412776">"BioKG: A Knowledge Graph for Relational Learning On Biological Data"</a>.</p> <p>We enrich this dataset with the aim of incorporating multimodal data associated with biomedical entities:</p> <ul> <li>Proteins: Protein embeddings computed with <a href="https://github.com/agemagician/ProtTrans">ProtTrans</a> from aminoacid sequences</li> <li>Molecules: Molecule embeddings computed with <a href="https://github.com/kexinhuang12345/MolTrans">MolTrans</a> from SMILES representations</li> <li>Diseases: Textual descriptions retrieved from <a href="https://www.nlm.nih.gov/mesh/meshhome.html">MeSH</a></li> </ul> <p>Furthermore, we decouple the benchmarks provided by Walsh et al. from the edges in the knowledge graph, which ensures that there is no direct data leakage between the benchmarks and the triples used to train link prediction models.</p>
ShareScore
36/100
Overall dataset sharing score
Score breakdown
These five areas show where the dataset supports — or may limit — practical reuse.
- Stewardship
- 8
- Harmonization
- 4
- Access
- 16
- Reuse readiness
- 8
- Engagement
- 0
Topics
Dataset details
- Repository
- zenodo
- Published
- June 4, 2023
- License
- cc-by-4.0
- DOI
- 10.5281/zenodo.8005710
Scored with release 0.9.0
ScienceDex for faculty
Your academic CV and NIH biosketch
Make your CV in your school's format and your NIH biosketch from it, then download both as Word files.