dgidb

Name: dgidb
Author: QSong-github

132stars4forks

How to install dgidb?

qsong-github/drugclaw/dgidb

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

Installs into the current project.

Summary

Query the DGIdb (Drug-Gene Interaction Database) for drug-gene interactions, gene druggability categories, and drug target information. Use whenever the user asks about drug targets, druggable genes, gene-drug interactions, or wants to look up any entity (gene name, drug name, dr

Files · 1

View on GitHub

SKILL.md

1	# DGIdb Query Skill
2
3	Search DGIdb records by any entity. Auto-detects type by naming convention:
4
5	\| Input Pattern \| Detected As \| Example \|
6	\|---\|---\|---\|
7	\| ALL-CAPS ≤15 chars \| Gene \| `EGFR`, `BRAF`, `TP53` \|
8	\| Known category keyword \| Druggability category \| `clinically actionable`, `kinase` \|
9	\| Anything else \| Drug \| `imatinib`, `erlotinib` \|
10
11	Supported category keywords: `clinically actionable`, `drug resistance`, `druggable genome`, `tumor suppressor`, `transcription factor`, `kinase`, `g protein coupled receptor`, `hormone activity`, `ion channel`, `protease`, `dna repair`.
12
13	## API
14
15	\| Function \| Input \| Returns \|
16	\|---\|---\|---\|
17	\| `search(entity)` \| single entity string \| `list[dict]` \|
18	\| `search_batch(entities)` \| list of entity strings \| `dict[str, list[dict]]` \|
19	\| `summarize(results, entity)` \| result list + label \| compact text for LLM \|
20	\| `to_json(results)` \| result list \| `list[dict]` (passthrough) \|
21
22	## Key Fields
23
24	Gene result: `name`, `long_name`, `categories`, `interaction_count`, `interactions[]` (each with `drug`, `drug_concept_id`, `score`, `types`, `directionality`, `attributes`, `pmids`, `sources`).
25
26	Drug result: `name`, `concept_id`, `approval_ratings`, `interaction_count`, `interactions[]` (each with `gene`, `gene_long_name`, `score`, `types`, `directionality`, `attributes`, `pmids`, `sources`).
27
28	Category result: `category`, `gene_count`, `genes[]` (each with `name`, `long_name`).
29
30	## Usage
31
32	See `if __name__ == "__main__"` block in `16_DGIdb.py` for runnable examples covering: single gene, single drug, category, batch (mixed types), and JSON output.
33
34	## Data Source
35
36	- Database: DGIdb v5.0 — Drug-Gene Interaction Database
37	- Endpoint: `https://dgidb.org/api/graphql` (GraphQL, no API key)
38	- Coverage: 40+ source databases, ~100 k drug-gene interactions
39	- Paper: Freshour et al., Nucleic Acids Res. 2024; 52(D1):D1227-D1235. DOI: [10.1093/nar/gkac1046](https://doi.org/10.1093/nar/gkac1046)

People who liked this also viewed

6 picks

Type

dgidb

132stars4forks

View on GitHub

How to install dgidb?

qsong-github/drugclaw/dgidb

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# DGIdb Query Skill
2
3	Search DGIdb records by any entity. Auto-detects type by naming convention:
4
5	\| Input Pattern \| Detected As \| Example \|
6	\|---\|---\|---\|
7	\| ALL-CAPS ≤15 chars \| Gene \| `EGFR`, `BRAF`, `TP53` \|
8	\| Known category keyword \| Druggability category \| `clinically actionable`, `kinase` \|
9	\| Anything else \| Drug \| `imatinib`, `erlotinib` \|
10
11	Supported category keywords: `clinically actionable`, `drug resistance`, `druggable genome`, `tumor suppressor`, `transcription factor`, `kinase`, `g protein coupled receptor`, `hormone activity`, `ion channel`, `protease`, `dna repair`.
12
13	## API
14
15	\| Function \| Input \| Returns \|
16	\|---\|---\|---\|
17	\| `search(entity)` \| single entity string \| `list[dict]` \|
18	\| `search_batch(entities)` \| list of entity strings \| `dict[str, list[dict]]` \|
19	\| `summarize(results, entity)` \| result list + label \| compact text for LLM \|
20	\| `to_json(results)` \| result list \| `list[dict]` (passthrough) \|
21
22	## Key Fields
23
24	Gene result: `name`, `long_name`, `categories`, `interaction_count`, `interactions[]` (each with `drug`, `drug_concept_id`, `score`, `types`, `directionality`, `attributes`, `pmids`, `sources`).
25
26	Drug result: `name`, `concept_id`, `approval_ratings`, `interaction_count`, `interactions[]` (each with `gene`, `gene_long_name`, `score`, `types`, `directionality`, `attributes`, `pmids`, `sources`).
27
28	Category result: `category`, `gene_count`, `genes[]` (each with `name`, `long_name`).
29
30	## Usage
31
32	See `if __name__ == "__main__"` block in `16_DGIdb.py` for runnable examples covering: single gene, single drug, category, batch (mixed types), and JSON output.
33
34	## Data Source
35
36	- Database: DGIdb v5.0 — Drug-Gene Interaction Database
37	- Endpoint: `https://dgidb.org/api/graphql` (GraphQL, no API key)
38	- Coverage: 40+ source databases, ~100 k drug-gene interactions
39	- Paper: Freshour et al., Nucleic Acids Res. 2024; 52(D1):D1227-D1235. DOI: [10.1093/nar/gkac1046](https://doi.org/10.1093/nar/gkac1046)

People who liked this also viewed

6 picks

Type