https://github.com/recess-eu-project/drug-repurposing-datasets
Drug Repurposing Datasets for Collaborative Filtering Methods. Notebooks and code to generate datasets for collaborative filtering-based drug repurposing.
https://github.com/recess-eu-project/drug-repurposing-datasets
collaborative-filtering dataset drug-repurposing science-reproducibility
Last synced: 5 months ago
JSON representation
Drug Repurposing Datasets for Collaborative Filtering Methods. Notebooks and code to generate datasets for collaborative filtering-based drug repurposing.
- Host: GitHub
- URL: https://github.com/recess-eu-project/drug-repurposing-datasets
- Owner: RECeSS-EU-Project
- License: mit
- Created: 2023-05-30T10:50:16.000Z (about 3 years ago)
- Default Branch: master
- Last Pushed: 2024-01-04T11:32:22.000Z (over 2 years ago)
- Last Synced: 2025-09-05T04:41:00.867Z (9 months ago)
- Topics: collaborative-filtering, dataset, drug-repurposing, science-reproducibility
- Language: Jupyter Notebook
- Homepage: https://recess-eu-project.github.io
- Size: 190 KB
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Citation: CITATION.cff
- Codemeta: codemeta.json
- Zenodo: .zenodo.json
Awesome Lists containing this project
README
# Drug Repurposing Datasets for Collaborative Filtering Methods
[](https://doi.org/10.5281/zenodo.8014775)
This repository is a part of the EU-funded [RECeSS project](https://recess-eu-project.github.io) (#101102016), and hosts the notebooks and code files which helped to build the following novel drug repurposing datasets:
- TRANSCRIPT dataset [](https://doi.org/10.5281/zenodo.7982969)
- PREDICT dataset [](https://doi.org/10.5281/zenodo.7982964)
The latest versions (v2.0.0 and v2.0.1 of May 29th, 2023) of those datasets correspond to the current notebooks in folder *notebooks/*. The notebooks corresponding to the v1.0.0 and v1.0.1 (December 28th, 2022) are hosted in folder *notebooks/v1.0.0/*. To get more details about the datasets themselves, please refer to the corresponding Zenodo pages.
## Running the notebooks
### Global variables
Update to your liking the following file *paths_global.py*. The corresponding files and how to obtain them are detailed in *notebooks/FEATURELESS_dataset.ipynb*.
### Environment
In order to run the notebooks:
```
conda create -n drug_repurposing python=3.8.5 -y
conda activate drug_repurposing
python3 -m pip install -r requirements.txt
python3 -m pip install notebook>=6.5.4 markupsafe==2.0.1 ## packages for Jupyter notebook
conda deactivate
conda activate drug_repurposing
cd notebooks/ && jupyter notebook
```
## Licence
These datasets and code are under an [OSI-approved](https://opensource.org/licenses/) [MIT license](https://raw.githubusercontent.com/RECeSS-EU-Project/drug-repurposing-datasets/main/LICENSE). Note that the final matrices for PREDICT are not available, due to the usage rules of the DrugBank dataset. However, one can run the corresponding notebook *PREDICT_dataset.ipynb* in order to get the final matrices. A partial dataset is downloadable on Zenodo.
## Citation
```
Clémence Réda. (2023).
Jupyter Notebooks for building drug repurposing datasets in collaborative filtering (v2.0.0).
Zenodo. https://doi.org/10.5281/zenodo.8014774
```
## Community guidelines with respect to contributions, issue reporting, and support
[Pull requests](https://github.com/RECeSS-EU-Project/drug-repurposing-datasets/pulls) and [issue flagging](https://github.com/RECeSS-EU-Project/drug-repurposing-datasets/issues) are welcome, and can be made through the GitHub interface. Support can be provided by reaching out to ``recess-project[at]proton.me``.