Gdkd

Skill BioTender-max/awesome-bio-agent-skills/skills/drugclaw/gdkd

Query the Gene-Drug Knowledge Database (GDKD) for variant-specific gene–drug associations in oncology. Use when the user asks about cancer genomic biomarkers, drug sensitivity/resistance by gene or variant, targetable mutations, or clinical evidence for cancer therapeutics.From its SKILL.md

Install

npx -y skills add BioTender-max/awesome-bio-agent-skills --skill gdkd

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

SKILL.md

1.4 KB, 332 tokens by cl100k_base, as published. Nobody here has run it

GDKD Query Skill

Search canonical GDKD rows by drug or gene entity. Auto-detects input type by pattern:

Input Pattern	Detected As	Match Logic
`ABL1`, `EGFR`	Gene symbol	substring on `gene`
`imatinib`, `erlotinib`	Drug name	substring on `drug`
anything else	Free text	substring on `drug` OR `gene`

API

Function	Input	Returns
`load_gdkd(path)`	CSV path	`list[dict]`
`search(rows, entity)`	single entity string	`list[dict]`
`search_batch(rows, entities)`	list of entity strings	`dict[str, list[dict]]`
`summarize(hits, entity)`	rows + label	compact text
`to_json(hits)`	rows	`list[dict]`

Usage

See if __name__ == "__main__" block in example.py for runnable examples.

Data

Source: GDKD normalized full-package output
Paper: Dienstmann et al., Cancer Discovery 2015;5(2):118-123
Format: CSV
Columns: drug, gene, score, source
Path: resources_metadata/dti/GDKD/gdkd.csv (default DATA_PATH in example.py)

What ships with it: 5 files

7.4 KB alongside SKILL.md, 4 of them executable

example.pyruns2.1 KB
gdkd_skill.pyruns3.3 KB
__init__.pyruns122 B
README.md1.2 KB
retrieve.pyruns802 B