drkg

Name: drkg
Author: QSong-github

132stars4forks

How to install drkg?

qsong-github/drugclaw/drkg

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

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	# DRKG Query Skill
2
3	Search the Drug Repurposing Knowledge Graph (97 238 entities, 5 874 261
4	triplets, 107 relation types) by any entity. Auto-detects entity type by
5	input pattern and returns all KG neighbours.
6
7	## Entity Format
8
9	Entities in DRKG are typed strings: `Type::ID`.
10
11	\| Entity Type \| Example \| Count \|
12	\|---\|---\|---\|
13	\| Compound \| `Compound::DB00945` \| 24 313 \|
14	\| Gene \| `Gene::1956` \| 39 220 \|
15	\| Disease \| `Disease::DOID:162` \| 5 103 \|
16	\| Anatomy \| `Anatomy::UBERON:0001474` \| 400 \|
17	\| Biological Process \| `Biological Process::GO:0006915` \| 11 381 \|
18	\| Cellular Component \| `Cellular Component::GO:0005634` \| 1 391 \|
19	\| Molecular Function \| `Molecular Function::GO:0005515` \| 2 884 \|
20	\| Pathway \| `Pathway::PC7_8078` \| 1 822 \|
21	\| Pharmacologic Class \| `Pharmacologic Class::N0000175605` \| 345 \|
22	\| Side Effect \| `Side Effect::C0000737` \| 5 701 \|
23	\| Symptom \| `Symptom::D009325` \| 415 \|
24	\| Atc \| `Atc::N02BE01` \| 4 048 \|
25	\| Tax \| `Tax::9606` \| 215 \|
26
27	Relations are typed strings: `Source::RelType::HeadType:TailType`, e.g.
28	`DRUGBANK::target::Compound:Gene`, `Hetionet::CtD::Compound:Disease`.
29
30	## Input Auto-Detection
31
32	\| Input Pattern \| Detected As \| Match Logic \|
33	\|---\|---\|---\|
34	\| `Compound::DB00945` \| full DRKG entity \| exact match \|
35	\| `DB\d{5,}` \| DrugBank ID \| prepend `Compound::` \|
36	\| `DOID:\d+` / `MESH:D\d+` \| Disease ID \| prepend `Disease::` \|
37	\| `GO:\d+` \| GO term \| try BP / MF / CC \|
38	\| pure digits (`1956`) \| Entrez Gene ID \| prepend `Gene::` \|
39	\| anything else \| free text \| case-insensitive substring across all entities \|
40
41	## API
42
43	\| Function \| Input \| Returns \|
44	\|---\|---\|---\|
45	\| `search(query, limit=200)` \| single entity string \| dict with `resolved`, `as_head`, `as_tail` \|
46	\| `search_batch(queries, limit=200)` \| list of entity strings \| dict[query → result] \|
47	\| `get_sources(entity)` \| resolved DRKG entity \| source attribution string \|
48	\| `get_relation_info(relation)` \| relation string \| glossary dict \|
49	\| `entity_types()` \| — \| list of 13 entity type names \|
50	\| `summarize(result)` \| search result dict \| compact LLM-readable text \|
51	\| `to_json(result)` \| search result dict \| JSON-serialisable dict \|
52
53	## Usage
54
55	See `if __name__ == "__main__"` block in `25_DRKG.py` for runnable examples:
56	single-entity search (full ID, bare ID, free text), batch search, relation
57	glossary lookup, and JSON output.
58
59	## Data Sources
60
61	DRKG integrates six databases plus COVID-19 literature:
62
63	\| Source \| Triplets \| Coverage \|
64	\|---\|---\|---\|
65	\| DrugBank \| 1 424 790 \| drug–drug, drug–gene, drug–disease, ATC \|
66	\| Hetionet \| 2 250 197 \| gene–gene, anatomy, pathways, side effects \|
67	\| GNBR \| 335 369 \| gene–gene, compound–gene, disease–gene \|
68	\| STRING \| 1 496 708 \| protein–protein interactions \|
69	\| IntAct \| 256 151 \| protein–protein interactions \|
70	\| DGIdb \| 26 290 \| drug–gene interactions \|
71	\| Bibliography \| 84 756 \| COVID-19 related \|
72
73	## Data Files
74
75	Located at `DATA_DIR` in `25_DRKG.py`:
76
77	\| File \| Description \|
78	\|---\|---\|
79	\| `drkg.tsv` \| 5 874 261 triplets (head, relation, tail) \|
80	\| `relation_glossary.tsv` \| relation type glossary with source info \|
81	\| `entity2src.tsv` \| entity → original data-source mapping \|
82
83	## Citation
84
85	```
86	Ioannidis et al. "DRKG - Drug Repurposing Knowledge Graph for Covid-19", 2020.
87	https://github.com/gnn4dr/DRKG
88	```

People who liked this also viewed

6 picks

Type

drkg

132stars4forks

View on GitHub

How to install drkg?

qsong-github/drugclaw/drkg

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# DRKG Query Skill
2
3	Search the Drug Repurposing Knowledge Graph (97 238 entities, 5 874 261
4	triplets, 107 relation types) by any entity. Auto-detects entity type by
5	input pattern and returns all KG neighbours.
6
7	## Entity Format
8
9	Entities in DRKG are typed strings: `Type::ID`.
10
11	\| Entity Type \| Example \| Count \|
12	\|---\|---\|---\|
13	\| Compound \| `Compound::DB00945` \| 24 313 \|
14	\| Gene \| `Gene::1956` \| 39 220 \|
15	\| Disease \| `Disease::DOID:162` \| 5 103 \|
16	\| Anatomy \| `Anatomy::UBERON:0001474` \| 400 \|
17	\| Biological Process \| `Biological Process::GO:0006915` \| 11 381 \|
18	\| Cellular Component \| `Cellular Component::GO:0005634` \| 1 391 \|
19	\| Molecular Function \| `Molecular Function::GO:0005515` \| 2 884 \|
20	\| Pathway \| `Pathway::PC7_8078` \| 1 822 \|
21	\| Pharmacologic Class \| `Pharmacologic Class::N0000175605` \| 345 \|
22	\| Side Effect \| `Side Effect::C0000737` \| 5 701 \|
23	\| Symptom \| `Symptom::D009325` \| 415 \|
24	\| Atc \| `Atc::N02BE01` \| 4 048 \|
25	\| Tax \| `Tax::9606` \| 215 \|
26
27	Relations are typed strings: `Source::RelType::HeadType:TailType`, e.g.
28	`DRUGBANK::target::Compound:Gene`, `Hetionet::CtD::Compound:Disease`.
29
30	## Input Auto-Detection
31
32	\| Input Pattern \| Detected As \| Match Logic \|
33	\|---\|---\|---\|
34	\| `Compound::DB00945` \| full DRKG entity \| exact match \|
35	\| `DB\d{5,}` \| DrugBank ID \| prepend `Compound::` \|
36	\| `DOID:\d+` / `MESH:D\d+` \| Disease ID \| prepend `Disease::` \|
37	\| `GO:\d+` \| GO term \| try BP / MF / CC \|
38	\| pure digits (`1956`) \| Entrez Gene ID \| prepend `Gene::` \|
39	\| anything else \| free text \| case-insensitive substring across all entities \|
40
41	## API
42
43	\| Function \| Input \| Returns \|
44	\|---\|---\|---\|
45	\| `search(query, limit=200)` \| single entity string \| dict with `resolved`, `as_head`, `as_tail` \|
46	\| `search_batch(queries, limit=200)` \| list of entity strings \| dict[query → result] \|
47	\| `get_sources(entity)` \| resolved DRKG entity \| source attribution string \|
48	\| `get_relation_info(relation)` \| relation string \| glossary dict \|
49	\| `entity_types()` \| — \| list of 13 entity type names \|
50	\| `summarize(result)` \| search result dict \| compact LLM-readable text \|
51	\| `to_json(result)` \| search result dict \| JSON-serialisable dict \|
52
53	## Usage
54
55	See `if __name__ == "__main__"` block in `25_DRKG.py` for runnable examples:
56	single-entity search (full ID, bare ID, free text), batch search, relation
57	glossary lookup, and JSON output.
58
59	## Data Sources
60
61	DRKG integrates six databases plus COVID-19 literature:
62
63	\| Source \| Triplets \| Coverage \|
64	\|---\|---\|---\|
65	\| DrugBank \| 1 424 790 \| drug–drug, drug–gene, drug–disease, ATC \|
66	\| Hetionet \| 2 250 197 \| gene–gene, anatomy, pathways, side effects \|
67	\| GNBR \| 335 369 \| gene–gene, compound–gene, disease–gene \|
68	\| STRING \| 1 496 708 \| protein–protein interactions \|
69	\| IntAct \| 256 151 \| protein–protein interactions \|
70	\| DGIdb \| 26 290 \| drug–gene interactions \|
71	\| Bibliography \| 84 756 \| COVID-19 related \|
72
73	## Data Files
74
75	Located at `DATA_DIR` in `25_DRKG.py`:
76
77	\| File \| Description \|
78	\|---\|---\|
79	\| `drkg.tsv` \| 5 874 261 triplets (head, relation, tail) \|
80	\| `relation_glossary.tsv` \| relation type glossary with source info \|
81	\| `entity2src.tsv` \| entity → original data-source mapping \|
82
83	## Citation
84
85	```
86	Ioannidis et al. "DRKG - Drug Repurposing Knowledge Graph for Covid-19", 2020.
87	https://github.com/gnn4dr/DRKG
88	```

People who liked this also viewed

6 picks

Type