MecDDI Query Skill

SkillDatabases & data

Query the MecDDI mechanism-based drug-drug interaction database. Use whenever the user asks about drug-drug interactions, DDI mechanisms (PK/PD), enzyme or transporter-mediated interactions, or wants to look up interacting drug pairs by drug name or MecDDI drug ID. Trigger on keywords like DDI, drug interaction, MecDDI, mechanism-based interaction, pharmacokinetic interaction, pharmacodynamic interaction, or any query involving two drugs that may interact.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the MecDDI Query Skill skill

What this skill tells your AI

The instructions your AI receives, as published by qsong-github/drugclaw in skills/ddi/mecddi/SKILL.md and read by ahel’s review.

Search MecDDI drug-drug interaction records by drug name or drug ID. Auto-detects input type:

Input Pattern	Detected As	Match Logic
`D0123`	MecDDI Drug ID	exact on `A_Drug_ID` / `B_Drug_ID`
anything else	free text	substring on `A_Drug_Name` / `B_Drug_Name`

Mechanism Categories (7 files)

Category	Type
Affected Gastrointestinal Absorption	PK
Affected Cellular Transport	PK
Affected Organization Distribution	PK
Affected Intra/Extra-Hepatic Metabolism	PK
Affected Excretion Pathways	PK
Pharmacodynamic Additive Effects	PD
Pharmacodynamic Antagonistic Effects	PD

API

Function	Input	Returns
`load_mecddi(data_dir)`	directory path	list[dict] (all records)
`search(records, entity)`	single entity string	list[dict]
`search_batch(records, entities)`	list of strings	dict[str, list[dict]]
`summarize(hits, entity)`	hits + label	compact text for LLM
`to_json(hits)`	list[dict]	JSON string

Data

Source: 7 TSV files downloaded from https://mecddi.idrblab.net/download
Path: DATA_DIR variable in 19_MecDDI.py (default: resources_metadata/ddi/MecDDI)
Columns: A_Drug_ID, A_Drug_Name, B_Drug_ID, B_Drug_Name, Mechanism_Category

Usage

See if __name__ == "__main__" block in 19_MecDDI.py for runnable examples covering:

Single drug name → search(data, "Atropine")
Single drug ID → search(data, "D0123")
Batch query → search_batch(data, ["Meclizine", "Isocarboxazid", "D0853"])
JSON output → to_json(hits)
LLM-friendly summary → summarize(hits, entity)

Signals

GitHub stars: 116
Forks: 3
Last commit: Aug 2026

Advanced

Item type: skill
Key: mecddi-query
Source: github.com/qsong-github/drugclaw

github.com/qsong-github/drugclaw