oregano

Name: oregano
Author: QSong-github

132stars4forks

How to install oregano?

qsong-github/drugclaw/oregano

$npx -y skills add QSong-github/DrugClaw --skill oregano

Installs into the current project.

Summary

Query the OREGANO knowledge graph for computational drug repurposing. Use whenever the user asks about drug–target–disease–gene–pathway relationships, compound cross-references, drug repurposing hypotheses, or wants to explore neighbors of any biomedical entity in a knowledge gra

Files · 1

View on GitHub

SKILL.md

1	# OREGANO Query Skill
2
3	Search the OREGANO knowledge graph (88,937 nodes, 824,231 links) by any entity. Auto-resolves input to OREGANO node IDs via cross-reference tables.
4
5	\| Input Pattern \| Detected As \| Match Logic \|
6	\|---\|---\|---\|
7	\| OREGANO internal ID (e.g. `1234`) \| OREGANO node ID \| exact in triplet index \|
8	\| `DB00331` / DrugBank ID \| external xref \| exact in COMPOUND.tsv \|
9	\| UniProt / KEGG / MeSH / UMLS ID \| external xref \| exact across all metadata TSVs \|
10	\| `metformin`, `BRCA1`, free text \| entity name \| substring on name columns \|
11
12	## API
13
14	\| Function \| Input \| Returns \|
15	\|---\|---\|---\|
16	\| `search(query)` \| single entity string \| dict: `{query, resolved_ids, metadata, triplets}` \|
17	\| `search_batch(queries)` \| list of entity strings \| `dict[str, search_result]` \|
18	\| `summarize(result)` \| search result dict \| compact LLM-readable text \|
19	\| `to_json(result)` \| search result dict \| JSON-serializable dict \|
20	\| `get_stats()` \| — \| graph-level counts (triplets, nodes, predicates, entity types) \|
21
22	## Graph Schema
23
24	11 node types: Compound (90,868), Gene (35,794), Target (22,096), Disease (18,333), Phenotype (11,605), Side Effect (6,060), Indication (2,714), Pathway (2,129), Effect (171), Activity (78).
25
26	19 relation types (predicates): e.g. `has_target`, `has_indication`, `has_side_effect`, `interacts_with`, `involved_in_pathway`, `associated_with`, `has_phenotype`, etc. Run `get_stats()` to list all predicates with counts.
27
28	## Usage
29
30	See `if __name__ == "__main__"` block in `21_OREGANO.py` for runnable examples covering: free-text drug name search, DrugBank ID lookup, batch search, JSON pipeline output, and graph statistics.
31
32	## Data
33
34	- Source: Zenodo DOI 10.5281/zenodo.10103842 (CC-BY 4.0)
35	- Version: v2.1 (published 2023-11-10)
36	- Core file: `OREGANO_V2.1.tsv` — tab-delimited triplets (Subject, Predicate, Object)
37	- Metadata files: `COMPOUND.tsv`, `TARGET.tsv`, `GENES.tsv`, `DISEASES.tsv`, `PHENOTYPES.tsv`, `PATHWAYS.tsv`, `INDICATION.tsv`, `SIDE_EFFECT.tsv`, `ACTIVITY.tsv`, `EFFECT.tsv`
38	- Path: `DATA_DIR` variable in `21_OREGANO.py`
39
40	## Citation
41
42	Boudin, M., Diallo, G., Drancé, M. & Mougin, F. The OREGANO knowledge graph for computational drug repurposing. Sci Data 10, 871 (2023). https://doi.org/10.1038/s41597-023-02757-0

People who liked this also viewed

6 picks

Type

oregano

132stars4forks

View on GitHub

How to install oregano?

qsong-github/drugclaw/oregano

$npx -y skills add QSong-github/DrugClaw --skill oregano

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# OREGANO Query Skill
2
3	Search the OREGANO knowledge graph (88,937 nodes, 824,231 links) by any entity. Auto-resolves input to OREGANO node IDs via cross-reference tables.
4
5	\| Input Pattern \| Detected As \| Match Logic \|
6	\|---\|---\|---\|
7	\| OREGANO internal ID (e.g. `1234`) \| OREGANO node ID \| exact in triplet index \|
8	\| `DB00331` / DrugBank ID \| external xref \| exact in COMPOUND.tsv \|
9	\| UniProt / KEGG / MeSH / UMLS ID \| external xref \| exact across all metadata TSVs \|
10	\| `metformin`, `BRCA1`, free text \| entity name \| substring on name columns \|
11
12	## API
13
14	\| Function \| Input \| Returns \|
15	\|---\|---\|---\|
16	\| `search(query)` \| single entity string \| dict: `{query, resolved_ids, metadata, triplets}` \|
17	\| `search_batch(queries)` \| list of entity strings \| `dict[str, search_result]` \|
18	\| `summarize(result)` \| search result dict \| compact LLM-readable text \|
19	\| `to_json(result)` \| search result dict \| JSON-serializable dict \|
20	\| `get_stats()` \| — \| graph-level counts (triplets, nodes, predicates, entity types) \|
21
22	## Graph Schema
23
24	11 node types: Compound (90,868), Gene (35,794), Target (22,096), Disease (18,333), Phenotype (11,605), Side Effect (6,060), Indication (2,714), Pathway (2,129), Effect (171), Activity (78).
25
26	19 relation types (predicates): e.g. `has_target`, `has_indication`, `has_side_effect`, `interacts_with`, `involved_in_pathway`, `associated_with`, `has_phenotype`, etc. Run `get_stats()` to list all predicates with counts.
27
28	## Usage
29
30	See `if __name__ == "__main__"` block in `21_OREGANO.py` for runnable examples covering: free-text drug name search, DrugBank ID lookup, batch search, JSON pipeline output, and graph statistics.
31
32	## Data
33
34	- Source: Zenodo DOI 10.5281/zenodo.10103842 (CC-BY 4.0)
35	- Version: v2.1 (published 2023-11-10)
36	- Core file: `OREGANO_V2.1.tsv` — tab-delimited triplets (Subject, Predicate, Object)
37	- Metadata files: `COMPOUND.tsv`, `TARGET.tsv`, `GENES.tsv`, `DISEASES.tsv`, `PHENOTYPES.tsv`, `PATHWAYS.tsv`, `INDICATION.tsv`, `SIDE_EFFECT.tsv`, `ACTIVITY.tsv`, `EFFECT.tsv`
38	- Path: `DATA_DIR` variable in `21_OREGANO.py`
39
40	## Citation
41
42	Boudin, M., Diallo, G., Drancé, M. & Mougin, F. The OREGANO knowledge graph for computational drug repurposing. Sci Data 10, 871 (2023). https://doi.org/10.1038/s41597-023-02757-0

People who liked this also viewed

6 picks

Type