All datasets / tim-shu

tim-shu/drug-affinity-multisource

125 downloads in 30 days0 likesLast modified 26 Oct 2026View on Hugging Face

Permissive or share-alike

The declared licence (cc-by-sa-4.0) is classified as share-alike.

Declared licence: cc-by-sa-4.0, from the tagEvidence: README.md at de24e30
Licence files: LICENSES.md, detected as cc-by-sa-3.0Evidence: LICENSES.md at de24e30
Declared sources: None listed in the card metadata
Access gated on Hugging Face: No

Each cell links to what was checked: a file, a file list or a Hub record.

Tasks

tabular-regression

Citation text from the card

The transformed integrated collection is distributed under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/). Unchanged original reference files in `reference/chembl/` retain CC BY-SA 3.0. Original source notices remain applicable; see [LICENSES.md](LICENSES.md). Changes include filtering, structure standardisation, sequence checks, label transformation/aggregation, source reconciliation and fixed splits.

Code and executed EDA: [annual project repository](https://github.com/TimothyShumilov/Year_project_2026-2027_drug_repurposing/tree/codex/checkpoint-2-eda-rf). SHA-256 file checksums and retrieval records accompany this release.

For exact local reproduction of the RF runs, download this repository and copy `prepared/*.parquet` to the project's `data/multisource_v3/`, `features/fingerprints.npz` to that same directory, and `reference/chembl/*` to `data/processed/`. Run `scripts/run_multisource.py --stage train` and compare its metrics with the supplied metadata.

All datasets marked Permissive or share-alike | JSON

The same facts for your agent

A free MCP server at mcp.datalicense.uk/mcp. Connect it from an MCP client such as Claude or Cursor.

dataset_licence({ "id": "tim-shu/drug-affinity-multisource" })
signal: "permissive"
stated_licence: "cc-by-sa-4.0"
sources: 0