agentsclimarketplace

Drkg

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

A curated collection of AI agent skills for biomedical research, covering genomics, proteomics, single-cell analysis, clinical AI, and protein design.

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

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.

What its author says it does

Copied from the file, not written here

Query the DRKG (Drug Repurposing Knowledge Graph). Use whenever the user asks about drug–gene, drug–disease, gene–disease, or other biomedical entity relationships in a knowledge-graph context, drug repurposing candidates, COVID-19 drug repurposing, or wants to explore neighbours of any biomedical entity (compound, gene, disease, pathway, side effect, etc.) in DRKG.

SKILL.md

3.6 KB, as published. Nobody here has run it

DRKG Query Skill

Search the Drug Repurposing Knowledge Graph (97 238 entities, 5 874 261 triplets, 107 relation types) by any entity. Auto-detects entity type by input pattern and returns all KG neighbours.

Entity Format

Entities in DRKG are typed strings: Type::ID.

Entity TypeExampleCount
CompoundCompound::DB0094524 313
GeneGene::195639 220
DiseaseDisease::DOID:1625 103
AnatomyAnatomy::UBERON:0001474400
Biological ProcessBiological Process::GO:000691511 381
Cellular ComponentCellular Component::GO:00056341 391
Molecular FunctionMolecular Function::GO:00055152 884
PathwayPathway::PC7_80781 822
Pharmacologic ClassPharmacologic Class::N0000175605345
Side EffectSide Effect::C00007375 701
SymptomSymptom::D009325415
AtcAtc::N02BE014 048
TaxTax::9606215

Relations are typed strings: Source::RelType::HeadType:TailType, e.g. DRUGBANK::target::Compound:Gene, Hetionet::CtD::Compound:Disease.

Input Auto-Detection

Input PatternDetected AsMatch Logic
Compound::DB00945full DRKG entityexact match
DB\d{5,}DrugBank IDprepend Compound::
DOID:\d+ / MESH:D\d+Disease IDprepend Disease::
GO:\d+GO termtry BP / MF / CC
pure digits (1956)Entrez Gene IDprepend Gene::
anything elsefree textcase-insensitive substring across all entities

API

FunctionInputReturns
search(query, limit=200)single entity stringdict with resolved, as_head, as_tail
search_batch(queries, limit=200)list of entity stringsdict[query → result]
get_sources(entity)resolved DRKG entitysource attribution string
get_relation_info(relation)relation stringglossary dict
entity_types()list of 13 entity type names
summarize(result)search result dictcompact LLM-readable text
to_json(result)search result dictJSON-serialisable dict

Usage

See if __name__ == "__main__" block in 25_DRKG.py for runnable examples: single-entity search (full ID, bare ID, free text), batch search, relation glossary lookup, and JSON output.

Data Sources

DRKG integrates six databases plus COVID-19 literature:

SourceTripletsCoverage
DrugBank1 424 790drug–drug, drug–gene, drug–disease, ATC
Hetionet2 250 197gene–gene, anatomy, pathways, side effects
GNBR335 369gene–gene, compound–gene, disease–gene
STRING1 496 708protein–protein interactions
IntAct256 151protein–protein interactions
DGIdb26 290drug–gene interactions
Bibliography84 756COVID-19 related

Data Files

Located at DATA_DIR in 25_DRKG.py:

FileDescription
drkg.tsv5 874 261 triplets (head, relation, tail)
relation_glossary.tsvrelation type glossary with source info
entity2src.tsventity → original data-source mapping

Citation

Ioannidis et al. "DRKG - Drug Repurposing Knowledge Graph for Covid-19", 2020.
https://github.com/gnn4dr/DRKG

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.