drugmechdb

Name: drugmechdb
Author: QSong-github

132stars4forks

How to install drugmechdb?

qsong-github/drugclaw/drugmechdb

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

Installs into the current project.

Summary

Query the DrugMechDB drug mechanism-of-action database. Use whenever the user asks about drug mechanisms, drug-to-disease paths, biological targets of a drug, or wants to look up any biomedical entity (drug name, protein, disease, DrugBank ID, MESH ID, UniProt ID, GO term, etc.)

Files · 1

View on GitHub

SKILL.md

1	# DrugMechDB Query Skill
2
3	Search drug mechanism-of-action paths by entity name or ID. Each path is a directed graph: Drug → (intermediates) → Disease, with typed nodes and labeled edges.
4
5	## Data
6
7	- Source: `indication_paths.json`
8	- Path: `resources_metadata/drug_mechanism/DRUGMECHDB/indication_paths.json`
9	- Records: ~4846 mechanism paths, ~32k relationships
10
11	## Entity auto-detection
12
13	\| Input pattern \| Detected as \| Example \|
14	\|---\|---\|---\|
15	\| `DB:DB00619` \| DrugBank ID \| exact on node/graph IDs \|
16	\| `MESH:D015464` \| MESH ID \| exact on node/graph IDs \|
17	\| `UniProt:P00519` \| UniProt protein \| exact on node IDs \|
18	\| `GO:0006915` \| GO term \| exact on node IDs \|
19	\| `CHEBI:`, `HP:`, `UBERON:`, `CL:`, `reactome:`, `InterPro:`, `PR:`, `taxonomy:` \| respective types \| exact on node IDs \|
20	\| anything else \| free text \| substring match on drug/disease/node names \|
21
22	## API
23
24	\| Function \| Signature \| Returns \|
25	\|---\|---\|---\|
26	\| `load(path)` \| path to JSON \| `list[dict]` — full database \|
27	\| `build_index(db)` \| loaded db \| `(by_id, by_name, by_drug, by_disease)` dicts for O(1) lookup \|
28	\| `search(db, entity, index=None)` \| single query string \| `list[dict]` — matching paths \|
29	\| `search_batch(db, entities, index=None)` \| list of query strings \| `dict[str, list[dict]]` \|
30	\| `summarize(paths, entity)` \| search results \| compact multi-line text \|
31	\| `to_json(paths)` \| search results \| list of flat dicts (id, drug, disease, nodes, links) \|
32
33	## Node types (14)
34
35	BiologicalProcess, Cell, CellularComponent, ChemicalSubstance, Disease, Drug, GeneFamily, GrossAnatomicalStructure, MacromolecularComplex, MolecularActivity, OrganismTaxon, Pathway, PhenotypicFeature, Protein
36
37	## Quick usage
38
39	```python
40	import drugmechdb_query as dq
41
42	db = dq.load() # uses default DATA_PATH
43	idx = dq.build_index(db) # optional, recommended for repeated queries
44
45	# Single query — by name or ID
46	paths = dq.search(db, "imatinib", idx)
47	paths = dq.search(db, "UniProt:P00519", idx)
48	paths = dq.search(db, "MESH:D003920", idx)
49	print(dq.summarize(paths, "imatinib"))
50
51	# Batch query
52	results = dq.search_batch(db, ["metformin", "MESH:D003920", "asthma"], idx)
53	for entity, paths in results.items():
54	print(dq.summarize(paths, entity))
55
56	# JSON export
57	print(dq.to_json(paths))
58	```
59
60	## Output structure per path
61
62	```
63	graph: { _id, drug, disease, drugbank, drug_mesh, disease_mesh }
64	nodes: [{ id, label, name }, ...]
65	links: [{ source, target, key }, ...]
66	```
67
68	`key` examples: `decreases activity of`, `causes`, `positively regulates`, `treats`, `increases expression of`, etc. (66 relation types total).

People who liked this also viewed

6 picks

Type

drugmechdb

132stars4forks

View on GitHub

How to install drugmechdb?

qsong-github/drugclaw/drugmechdb

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# DrugMechDB Query Skill
2
3	Search drug mechanism-of-action paths by entity name or ID. Each path is a directed graph: Drug → (intermediates) → Disease, with typed nodes and labeled edges.
4
5	## Data
6
7	- Source: `indication_paths.json`
8	- Path: `resources_metadata/drug_mechanism/DRUGMECHDB/indication_paths.json`
9	- Records: ~4846 mechanism paths, ~32k relationships
10
11	## Entity auto-detection
12
13	\| Input pattern \| Detected as \| Example \|
14	\|---\|---\|---\|
15	\| `DB:DB00619` \| DrugBank ID \| exact on node/graph IDs \|
16	\| `MESH:D015464` \| MESH ID \| exact on node/graph IDs \|
17	\| `UniProt:P00519` \| UniProt protein \| exact on node IDs \|
18	\| `GO:0006915` \| GO term \| exact on node IDs \|
19	\| `CHEBI:`, `HP:`, `UBERON:`, `CL:`, `reactome:`, `InterPro:`, `PR:`, `taxonomy:` \| respective types \| exact on node IDs \|
20	\| anything else \| free text \| substring match on drug/disease/node names \|
21
22	## API
23
24	\| Function \| Signature \| Returns \|
25	\|---\|---\|---\|
26	\| `load(path)` \| path to JSON \| `list[dict]` — full database \|
27	\| `build_index(db)` \| loaded db \| `(by_id, by_name, by_drug, by_disease)` dicts for O(1) lookup \|
28	\| `search(db, entity, index=None)` \| single query string \| `list[dict]` — matching paths \|
29	\| `search_batch(db, entities, index=None)` \| list of query strings \| `dict[str, list[dict]]` \|
30	\| `summarize(paths, entity)` \| search results \| compact multi-line text \|
31	\| `to_json(paths)` \| search results \| list of flat dicts (id, drug, disease, nodes, links) \|
32
33	## Node types (14)
34
35	BiologicalProcess, Cell, CellularComponent, ChemicalSubstance, Disease, Drug, GeneFamily, GrossAnatomicalStructure, MacromolecularComplex, MolecularActivity, OrganismTaxon, Pathway, PhenotypicFeature, Protein
36
37	## Quick usage
38
39	```python
40	import drugmechdb_query as dq
41
42	db = dq.load() # uses default DATA_PATH
43	idx = dq.build_index(db) # optional, recommended for repeated queries
44
45	# Single query — by name or ID
46	paths = dq.search(db, "imatinib", idx)
47	paths = dq.search(db, "UniProt:P00519", idx)
48	paths = dq.search(db, "MESH:D003920", idx)
49	print(dq.summarize(paths, "imatinib"))
50
51	# Batch query
52	results = dq.search_batch(db, ["metformin", "MESH:D003920", "asthma"], idx)
53	for entity, paths in results.items():
54	print(dq.summarize(paths, entity))
55
56	# JSON export
57	print(dq.to_json(paths))
58	```
59
60	## Output structure per path
61
62	```
63	graph: { _id, drug, disease, drugbank, drug_mesh, disease_mesh }
64	nodes: [{ id, label, name }, ...]
65	links: [{ source, target, key }, ...]
66	```
67
68	`key` examples: `decreases activity of`, `causes`, `positively regulates`, `treats`, `increases expression of`, etc. (66 relation types total).

People who liked this also viewed

6 picks

Type