mecddi

Name: mecddi
Author: QSong-github

132stars4forks

How to install mecddi?

qsong-github/drugclaw/mecddi

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

Installs into the current project.

Summary

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 key

Files · 1

View on GitHub

SKILL.md

1	# MecDDI Query Skill
2
3	Search MecDDI drug-drug interaction records by drug name or drug ID. Auto-detects input type:
4
5	\| Input Pattern \| Detected As \| Match Logic \|
6	\|---\|---\|---\|
7	\| `D0123` \| MecDDI Drug ID \| exact on `A_Drug_ID` / `B_Drug_ID` \|
8	\| anything else \| free text \| substring on `A_Drug_Name` / `B_Drug_Name` \|
9
10	## Mechanism Categories (7 files)
11
12	\| Category \| Type \|
13	\|---\|---\|
14	\| Affected Gastrointestinal Absorption \| PK \|
15	\| Affected Cellular Transport \| PK \|
16	\| Affected Organization Distribution \| PK \|
17	\| Affected Intra/Extra-Hepatic Metabolism \| PK \|
18	\| Affected Excretion Pathways \| PK \|
19	\| Pharmacodynamic Additive Effects \| PD \|
20	\| Pharmacodynamic Antagonistic Effects \| PD \|
21
22	## API
23
24	\| Function \| Input \| Returns \|
25	\|---\|---\|---\|
26	\| `load_mecddi(data_dir)` \| directory path \| list[dict] (all records) \|
27	\| `search(records, entity)` \| single entity string \| list[dict] \|
28	\| `search_batch(records, entities)` \| list of strings \| dict[str, list[dict]] \|
29	\| `summarize(hits, entity)` \| hits + label \| compact text for LLM \|
30	\| `to_json(hits)` \| list[dict] \| JSON string \|
31
32	## Data
33
34	- Source: 7 TSV files downloaded from <https://mecddi.idrblab.net/download>
35	- Path: `DATA_DIR` variable in `19_MecDDI.py` (default: `resources_metadata/ddi/MecDDI`)
36	- Columns: `A_Drug_ID`, `A_Drug_Name`, `B_Drug_ID`, `B_Drug_Name`, `Mechanism_Category`
37
38	## Usage
39
40	See `if __name__ == "__main__"` block in `19_MecDDI.py` for runnable examples covering:
41
42	1. Single drug name → `search(data, "Atropine")`
43	2. Single drug ID → `search(data, "D0123")`
44	3. Batch query → `search_batch(data, ["Meclizine", "Isocarboxazid", "D0853"])`
45	4. JSON output → `to_json(hits)`
46	5. LLM-friendly summary → `summarize(hits, entity)`

People who liked this also viewed

6 picks

Type

mecddi

132stars4forks

View on GitHub

How to install mecddi?

qsong-github/drugclaw/mecddi

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# MecDDI Query Skill
2
3	Search MecDDI drug-drug interaction records by drug name or drug ID. Auto-detects input type:
4
5	\| Input Pattern \| Detected As \| Match Logic \|
6	\|---\|---\|---\|
7	\| `D0123` \| MecDDI Drug ID \| exact on `A_Drug_ID` / `B_Drug_ID` \|
8	\| anything else \| free text \| substring on `A_Drug_Name` / `B_Drug_Name` \|
9
10	## Mechanism Categories (7 files)
11
12	\| Category \| Type \|
13	\|---\|---\|
14	\| Affected Gastrointestinal Absorption \| PK \|
15	\| Affected Cellular Transport \| PK \|
16	\| Affected Organization Distribution \| PK \|
17	\| Affected Intra/Extra-Hepatic Metabolism \| PK \|
18	\| Affected Excretion Pathways \| PK \|
19	\| Pharmacodynamic Additive Effects \| PD \|
20	\| Pharmacodynamic Antagonistic Effects \| PD \|
21
22	## API
23
24	\| Function \| Input \| Returns \|
25	\|---\|---\|---\|
26	\| `load_mecddi(data_dir)` \| directory path \| list[dict] (all records) \|
27	\| `search(records, entity)` \| single entity string \| list[dict] \|
28	\| `search_batch(records, entities)` \| list of strings \| dict[str, list[dict]] \|
29	\| `summarize(hits, entity)` \| hits + label \| compact text for LLM \|
30	\| `to_json(hits)` \| list[dict] \| JSON string \|
31
32	## Data
33
34	- Source: 7 TSV files downloaded from <https://mecddi.idrblab.net/download>
35	- Path: `DATA_DIR` variable in `19_MecDDI.py` (default: `resources_metadata/ddi/MecDDI`)
36	- Columns: `A_Drug_ID`, `A_Drug_Name`, `B_Drug_ID`, `B_Drug_Name`, `Mechanism_Category`
37
38	## Usage
39
40	See `if __name__ == "__main__"` block in `19_MecDDI.py` for runnable examples covering:
41
42	1. Single drug name → `search(data, "Atropine")`
43	2. Single drug ID → `search(data, "D0123")`
44	3. Batch query → `search_batch(data, ["Meclizine", "Isocarboxazid", "D0853"])`
45	4. JSON output → `to_json(hits)`
46	5. LLM-friendly summary → `summarize(hits, entity)`

People who liked this also viewed

6 picks

Type