chebi

Name: chebi
Author: QSong-github

132stars4forks

How to install chebi?

qsong-github/drugclaw/chebi

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

Installs into the current project.

Summary

Query the ChEBI (Chemical Entities of Biological Interest) database. Use whenever the user asks about small molecule identifiers, chemical ontology roles, molecular formulae, SMILES, InChI, synonyms, or cross-references for biologically relevant chemical compounds via ChEBI.

Files · 1

View on GitHub

SKILL.md

1	# ChEBI Query Skill
2
3	Search the ChEBI 2.0 REST API by any entity. Auto-detects input type:
4
5	\| Input Pattern \| Detected As \| Action \|
6	\|---\|---\|---\|
7	\| `CHEBI:15422` / `chebi:15422` \| ChEBI ID (prefixed) \| full entity lookup via `/compound/{id}/` \|
8	\| `27732` (pure digits ≤7) \| ChEBI ID (numeric) \| full entity lookup via `/compound/{id}/` \|
9	\| anything else \| free text \| Elasticsearch search via `/es_search/?term=...` \|
10
11	## API
12
13	\| Function \| Input \| Returns \|
14	\|---\|---\|---\|
15	\| `search(query, max_results=25)` \| single entity string \| `list[dict]` \|
16	\| `search_batch(queries, max_results=25)` \| list of entity strings \| `dict[str, list[dict]]` \|
17	\| `summarize(results, label)` \| result list + label \| compact one-line-per-hit text \|
18	\| `to_json(results)` \| result list \| `list[dict]` (JSON-serialisable) \|
19
20	Lower-level helpers (called internally):
21
22	\| Function \| Purpose \|
23	\|---\|---\|
24	\| `search_chebi(query, max_results)` \| keyword search via `GET /es_search/?term=...&size=N` \|
25	\| `get_entity(chebi_id)` \| full entity via `GET /compound/CHEBI:{id}/` \|
26	\| `get_entities_batch(chebi_ids)` \| batch lookup via `GET /compounds/?chebi_ids=id1,id2,...` \|
27
28	`search_batch()` automatically uses the efficient batch endpoint when all
29	queries are ChEBI IDs; otherwise it iterates with a 0.3 s delay.
30
31	## Usage
32
33	See `if __name__ == "__main__"` block in `64_ChEBI.py` for runnable examples
34	covering: single ID lookup, name search, formula search, batch ID search,
35	mixed batch search, and JSON output.
36
37	## Key Fields Returned
38
39	Top-level: `chebi_accession`, `name`, `ascii_name`, `definition`, `stars`
40	(curation quality; 3 = fully curated), `secondary_ids`, `is_released`.
41
42	chemical_data (nested dict): `formula`, `charge`, `mass`,
43	`monoisotopic_mass`.
44
45	default_structure (nested dict): `smiles`, `standard_inchi`,
46	`standard_inchi_key`, `wurcs`.
47
48	names (nested dict by type): keys like `IUPAC NAME`, `SYNONYM`,
49	`BRAND NAME`, `UNIPROT NAME`; each value is a list of name objects.
50
51	ontology_relations: `incoming_relations` and `outgoing_relations`, each a
52	list of `{init_id, init_name, relation_type, final_id, final_name}`.
53
54	database_accessions (nested dict by type): `CAS`, `MANUAL_X_REF`,
55	`REGISTRY_NUMBER`, `CITATION`; cross-refs to DrugBank, KEGG, HMDB, PubChem,
56	PDBeChem, Wikipedia, etc.
57
58	roles_classification: list of role dicts with `chebi_accession`, `name`,
59	`definition`, `biological_role` (bool), `application` (bool),
60	`chemical_role` (bool).
61
62	## Data Source
63
64	- Database: ChEBI 2.0 (EMBL-EBI), >195,000 molecular entities
65	- API base: `https://www.ebi.ac.uk/chebi/backend/api/public/`
66	- Docs: <https://www.ebi.ac.uk/chebi/backend/api/docs/>
67	- License: CC BY 4.0
68	- Citation: Bento et al. Nucleic Acids Res. 2025, 54(D1), D1768–D1774.

People who liked this also viewed

6 picks

Type

chebi

132stars4forks

View on GitHub

How to install chebi?

qsong-github/drugclaw/chebi

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# ChEBI Query Skill
2
3	Search the ChEBI 2.0 REST API by any entity. Auto-detects input type:
4
5	\| Input Pattern \| Detected As \| Action \|
6	\|---\|---\|---\|
7	\| `CHEBI:15422` / `chebi:15422` \| ChEBI ID (prefixed) \| full entity lookup via `/compound/{id}/` \|
8	\| `27732` (pure digits ≤7) \| ChEBI ID (numeric) \| full entity lookup via `/compound/{id}/` \|
9	\| anything else \| free text \| Elasticsearch search via `/es_search/?term=...` \|
10
11	## API
12
13	\| Function \| Input \| Returns \|
14	\|---\|---\|---\|
15	\| `search(query, max_results=25)` \| single entity string \| `list[dict]` \|
16	\| `search_batch(queries, max_results=25)` \| list of entity strings \| `dict[str, list[dict]]` \|
17	\| `summarize(results, label)` \| result list + label \| compact one-line-per-hit text \|
18	\| `to_json(results)` \| result list \| `list[dict]` (JSON-serialisable) \|
19
20	Lower-level helpers (called internally):
21
22	\| Function \| Purpose \|
23	\|---\|---\|
24	\| `search_chebi(query, max_results)` \| keyword search via `GET /es_search/?term=...&size=N` \|
25	\| `get_entity(chebi_id)` \| full entity via `GET /compound/CHEBI:{id}/` \|
26	\| `get_entities_batch(chebi_ids)` \| batch lookup via `GET /compounds/?chebi_ids=id1,id2,...` \|
27
28	`search_batch()` automatically uses the efficient batch endpoint when all
29	queries are ChEBI IDs; otherwise it iterates with a 0.3 s delay.
30
31	## Usage
32
33	See `if __name__ == "__main__"` block in `64_ChEBI.py` for runnable examples
34	covering: single ID lookup, name search, formula search, batch ID search,
35	mixed batch search, and JSON output.
36
37	## Key Fields Returned
38
39	Top-level: `chebi_accession`, `name`, `ascii_name`, `definition`, `stars`
40	(curation quality; 3 = fully curated), `secondary_ids`, `is_released`.
41
42	chemical_data (nested dict): `formula`, `charge`, `mass`,
43	`monoisotopic_mass`.
44
45	default_structure (nested dict): `smiles`, `standard_inchi`,
46	`standard_inchi_key`, `wurcs`.
47
48	names (nested dict by type): keys like `IUPAC NAME`, `SYNONYM`,
49	`BRAND NAME`, `UNIPROT NAME`; each value is a list of name objects.
50
51	ontology_relations: `incoming_relations` and `outgoing_relations`, each a
52	list of `{init_id, init_name, relation_type, final_id, final_name}`.
53
54	database_accessions (nested dict by type): `CAS`, `MANUAL_X_REF`,
55	`REGISTRY_NUMBER`, `CITATION`; cross-refs to DrugBank, KEGG, HMDB, PubChem,
56	PDBeChem, Wikipedia, etc.
57
58	roles_classification: list of role dicts with `chebi_accession`, `name`,
59	`definition`, `biological_role` (bool), `application` (bool),
60	`chemical_role` (bool).
61
62	## Data Source
63
64	- Database: ChEBI 2.0 (EMBL-EBI), >195,000 molecular entities
65	- API base: `https://www.ebi.ac.uk/chebi/backend/api/public/`
66	- Docs: <https://www.ebi.ac.uk/chebi/backend/api/docs/>
67	- License: CC BY 4.0
68	- Citation: Bento et al. Nucleic Acids Res. 2025, 54(D1), D1768–D1774.

People who liked this also viewed

6 picks

Type