https://github.com/astrazeneca/skywalkr-graph-features
Example notebooks that illustrate how to generate knowledge-based features. Features can be used in a variety of ML models, including recommender systems.
Science Score: 49.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 1 DOI reference(s) in README -
✓Academic publication links
Links to: biorxiv.org, zenodo.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (9.1%) to scientific vocabulary
Keywords
Repository
Example notebooks that illustrate how to generate knowledge-based features. Features can be used in a variety of ML models, including recommender systems.
Basic Info
Statistics
- Stars: 10
- Watchers: 3
- Forks: 5
- Open Issues: 0
- Releases: 1
Topics
Metadata Files
README.md
skywalkR-graph-features
This repository contains example notebooks illustrating how to generate knowledge-graph based features. The same types of graph-derived features were used in Gogleva et al, 2021 manuscript and skywalkR app
The repository contains two Jypyter notebooks:
- graph_features_Toy.ipynb - generate features based on a toy graph.
- graph_features_Hetionet.ipynb - here we used Hetionet graph as a representative example of reasonably complex biomedical graph;
Set-up and installation instructions
If not already installed on your setup, install Conda (eg. https://docs.conda.io/en/latest/miniconda.html ).
Run the following command to install RAPIDS-21.08 and the necessary package to run the notebook in a new Conda environment named graphfeaturesnotebook:
conda env create -f rapids-notebook-req.yml
Activate this environment with:
conda activate graphfeaturesnotebook
You can then package this environment in a Jupyter kernel:
python -m ipykernel install --user --name=graphfeaturesnotebook
The Jupyter kernel necessary to run this notebook should now be available in your favorite Jupyter instance.
Owner
- Name: AstraZeneca
- Login: AstraZeneca
- Kind: organization
- Location: Global
- Website: https://www.astrazeneca.com/
- Repositories: 33
- Profile: https://github.com/AstraZeneca
Data and AI: Unlocking new science insights
GitHub Events
Total
- Watch event: 1
Last Year
- Watch event: 1