bindingdb

Name: bindingdb
Author: QSong-github

132stars4forks

How to install bindingdb?

qsong-github/drugclaw/bindingdb

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

Installs into the current project.

Summary

Query the BindingDB drug-target binding affinity database. Use whenever the user asks about protein-ligand binding data, affinity measurements (Ki, IC50, Kd, EC50), or wants to look up binding partners for a UniProt ID, PDB ID, or compound SMILES string.

Files · 1

View on GitHub

SKILL.md

1	# BindingDB Query Skill
2
3	Search BindingDB binding affinity records by any entity. Auto-detects type by pattern:
4
5	\| Input Pattern \| Detected As \| Example \| API Endpoint \|
6	\|---\|---\|---\|---\|
7	\| `P35355`, `Q9Y233` \| UniProt ID \| `P00533` (EGFR) \| `getLigandsByUniprots` \|
8	\| `1Q0L`, `3ANM` \| PDB ID (4-char, digit-leading) \| `1Q0L` \| `getLigandsByPDBs` \|
9	\| contains `=()#[]@/\` \| SMILES string \| `CC(=O)Oc1ccccc1C(O)=O` \| `getTargetByCompound` \|
10	\| fallback \| treated as UniProt \| — \| `getLigandsByUniprots` \|
11
12	## API
13
14	\| Function \| Input \| Returns \|
15	\|---\|---\|---\|
16	\| `search(entity, cutoff)` \| single entity string \| dict with `entity`, `type`, `hits`, `affinities` \|
17	\| `search_batch(entities, cutoff)` \| list of entity strings \| dict[str, search_result] \|
18	\| `summarize(result)` \| search() output \| compact multi-line text \|
19	\| `to_json(result)` \| search() output \| list[dict] of affinity records \|
20	\| `query_by_uniprot(ids, cutoff)` \| UniProt ID(s), nM cutoff \| list[dict] \|
21	\| `query_by_pdb(ids, cutoff, identity)` \| PDB ID(s), nM cutoff, % identity \| list[dict] \|
22	\| `query_by_smiles(smiles, cutoff)` \| SMILES, similarity 0–1 \| list[dict] \|
23
24	Parameters
25
26	- `cutoff` (int): affinity threshold in nM (default 10 000). Entries with IC50/Ki/Kd ≤ cutoff are returned.
27	- `identity` (int, PDB only): sequence-identity cutoff in percent (default 92).
28	- Results are capped at 50 per query for LLM readability.
29
30	## Usage
31
32	See `if __name__ == "__main__"` block in `26_BindingDB.py` for runnable examples covering: UniProt single query, PDB query, SMILES compound query, batch query, and JSON output.
33
34	## Key Fields in Each Affinity Record
35
36	\| Field \| Description \|
37	\|---\|---\|
38	\| `query` \| Target protein name \|
39	\| `monomerid` \| BindingDB compound ID \|
40	\| `smile` \| SMILES structure of ligand \|
41	\| `affinity_type` \| Ki, IC50, Kd, or EC50 \|
42	\| `affinity` \| Value in nM \|
43	\| `pmid` \| PubMed ID of source \|
44	\| `doi` \| DOI of source publication \|
45
46	## Data Source
47
48	- Database: BindingDB (https://www.bindingdb.org/)
49	- Size: 3.2M data points, 1.4M compounds, 11.4K targets
50	- Access: Public REST API (JSON), no authentication required
51	- Citation: BindingDB in 2024: a FAIR knowledgebase of protein-small molecule binding data. Nucleic Acids Research, 53(D1), D1633 (2025). DOI: 10.1093/nar/gkae1199

People who liked this also viewed

6 picks

Type

bindingdb

132stars4forks

View on GitHub

How to install bindingdb?

qsong-github/drugclaw/bindingdb

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# BindingDB Query Skill
2
3	Search BindingDB binding affinity records by any entity. Auto-detects type by pattern:
4
5	\| Input Pattern \| Detected As \| Example \| API Endpoint \|
6	\|---\|---\|---\|---\|
7	\| `P35355`, `Q9Y233` \| UniProt ID \| `P00533` (EGFR) \| `getLigandsByUniprots` \|
8	\| `1Q0L`, `3ANM` \| PDB ID (4-char, digit-leading) \| `1Q0L` \| `getLigandsByPDBs` \|
9	\| contains `=()#[]@/\` \| SMILES string \| `CC(=O)Oc1ccccc1C(O)=O` \| `getTargetByCompound` \|
10	\| fallback \| treated as UniProt \| — \| `getLigandsByUniprots` \|
11
12	## API
13
14	\| Function \| Input \| Returns \|
15	\|---\|---\|---\|
16	\| `search(entity, cutoff)` \| single entity string \| dict with `entity`, `type`, `hits`, `affinities` \|
17	\| `search_batch(entities, cutoff)` \| list of entity strings \| dict[str, search_result] \|
18	\| `summarize(result)` \| search() output \| compact multi-line text \|
19	\| `to_json(result)` \| search() output \| list[dict] of affinity records \|
20	\| `query_by_uniprot(ids, cutoff)` \| UniProt ID(s), nM cutoff \| list[dict] \|
21	\| `query_by_pdb(ids, cutoff, identity)` \| PDB ID(s), nM cutoff, % identity \| list[dict] \|
22	\| `query_by_smiles(smiles, cutoff)` \| SMILES, similarity 0–1 \| list[dict] \|
23
24	Parameters
25
26	- `cutoff` (int): affinity threshold in nM (default 10 000). Entries with IC50/Ki/Kd ≤ cutoff are returned.
27	- `identity` (int, PDB only): sequence-identity cutoff in percent (default 92).
28	- Results are capped at 50 per query for LLM readability.
29
30	## Usage
31
32	See `if __name__ == "__main__"` block in `26_BindingDB.py` for runnable examples covering: UniProt single query, PDB query, SMILES compound query, batch query, and JSON output.
33
34	## Key Fields in Each Affinity Record
35
36	\| Field \| Description \|
37	\|---\|---\|
38	\| `query` \| Target protein name \|
39	\| `monomerid` \| BindingDB compound ID \|
40	\| `smile` \| SMILES structure of ligand \|
41	\| `affinity_type` \| Ki, IC50, Kd, or EC50 \|
42	\| `affinity` \| Value in nM \|
43	\| `pmid` \| PubMed ID of source \|
44	\| `doi` \| DOI of source publication \|
45
46	## Data Source
47
48	- Database: BindingDB (https://www.bindingdb.org/)
49	- Size: 3.2M data points, 1.4M compounds, 11.4K targets
50	- Access: Public REST API (JSON), no authentication required
51	- Citation: BindingDB in 2024: a FAIR knowledgebase of protein-small molecule binding data. Nucleic Acids Research, 53(D1), D1633 (2025). DOI: 10.1093/nar/gkae1199

People who liked this also viewed

6 picks

Type