How do I install the 16_DGIdb skill?

Run npx skillmds@latest add gabrielmoreira/16-dgidb in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is 16_DGIdb safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with 16_DGIdb?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is 16_DGIdb free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published 16_DGIdb?

gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.

16_DGIdb by gabrielmoreira — Agent Skill

Name: 16_DGIdb
Rating: 4.2 (5 reviews)
Author: gabrielmoreira

16_DGIdb

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, druggability category) in DGIdb.

gabrielmoreira Updated Sep 9, 2026 17 repo stars

File contents

DGIdb Query Skill

Search DGIdb records by any entity. Auto-detects type by naming convention:

Input Pattern	Detected As	Example
ALL-CAPS ≤15 chars	Gene	`EGFR`, `BRAF`, `TP53`
Known category keyword	Druggability category	`clinically actionable`, `kinase`
Anything else	Drug	`imatinib`, `erlotinib`

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.

API

Function	Input	Returns
`search(entity)`	single entity string	`list[dict]`
`search_batch(entities)`	list of entity strings	`dict[str, list[dict]]`
`summarize(results, entity)`	result list + label	compact text for LLM
`to_json(results)`	result list	`list[dict]` (passthrough)

Key Fields

Gene result: name, long_name, categories, interaction_count, interactions[] (each with drug, drug_concept_id, score, types, directionality, attributes, pmids, sources).

Drug result: name, concept_id, approval_ratings, interaction_count, interactions[] (each with gene, gene_long_name, score, types, directionality, attributes, pmids, sources).

Category result: category, gene_count, genes[] (each with name, long_name).

Usage

See if __name__ == "__main__" block in 16_DGIdb.py for runnable examples covering: single gene, single drug, category, batch (mixed types), and JSON output.

Data Source

Database: DGIdb v5.0 — Drug-Gene Interaction Database
Endpoint: https://dgidb.org/api/graphql (GraphQL, no API key)
Coverage: 40+ source databases, ~100 k drug-gene interactions
Paper: Freshour et al., Nucleic Acids Res. 2024; 52(D1):D1227-D1235. DOI: 10.1093/nar/gkac1046

---name: 16-dgidbdescription: 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, druggability category) in DGIdb.--- # DGIdb Query Skill Search DGIdb records by any entity. Auto-detects type by naming convention: | Input Pattern | Detected As | Example | |---|---|---| | ALL-CAPS ≤15 chars | Gene | `EGFR`, `BRAF`, `TP53` | | Known category keyword | Druggability category | `clinically actionable`, `kinase` | | Anything else | Drug | `imatinib`, `erlotinib` | 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`. ## API | Function | Input | Returns | |---|---|---| | `search(entity)` | single entity string | `list[dict]` | | `search_batch(entities)` | list of entity strings | `dict[str, list[dict]]` | | `summarize(results, entity)` | result list + label | compact text for LLM | | `to_json(results)` | result list | `list[dict]` (passthrough) | ## Key Fields **Gene result**: `name`, `long_name`, `categories`, `interaction_count`, `interactions[]` (each with `drug`, `drug_concept_id`, `score`, `types`, `directionality`, `attributes`, `pmids`, `sources`). **Drug result**: `name`, `concept_id`, `approval_ratings`, `interaction_count`, `interactions[]` (each with `gene`, `gene_long_name`, `score`, `types`, `directionality`, `attributes`, `pmids`, `sources`). **Category result**: `category`, `gene_count`, `genes[]` (each with `name`, `long_name`). ## Usage See `if __name__ == "__main__"` block in `16_DGIdb.py` for runnable examples covering: single gene, single drug, category, batch (mixed types), and JSON output. ## Data Source - **Database**: DGIdb v5.0 — Drug-Gene Interaction Database - **Endpoint**: `https://dgidb.org/api/graphql` (GraphQL, no API key) - **Coverage**: 40+ source databases, ~100 k drug-gene interactions - **Paper**: Freshour et al., *Nucleic Acids Res.* 2024; 52(D1):D1227-D1235. DOI: [10.1093/nar/gkac1046](https://doi.org/10.1093/nar/gkac1046)

Frequently asked questions