qsong-github/drugclaw/ttd

Claude Code and agent skill by qsong-github/drugclaw

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Query the Therapeutic Target Database (TTD) for drug-target-disease interaction data. Use this skill when the user asks about therapeutic targets, drugs, diseases, or their relationships — including target-drug mappings, clinical status of drugs, disease indications, UniProt/gene associations, and pathway annotations. Triggers on queries like "what drugs target EGFR", "which diseases is Imatinib used for", "find targets for lung cancer", or any lookup involving TTD IDs, gene symbols, drug names, or disease names.

Install

npx vskill@latest install qsong-github/drugclaw/ttd

SKILL.md

TTD — Therapeutic Target Database

Source: https://ttd.idrblab.cn/ Paper: https://academic.oup.com/nar/article/52/D1/D1465/7275004 Data dir: resources_metadata/dti/TTD

Data files (4 required)

FileContent
P1-01-TTD_target_download.txtTarget info: name, UniProt, gene, type, function, disease indication, pathway
P2-01-TTD_target_drug.txtTarget ↔ Drug links with clinical status (Approved / Phase I–III / Experimental)
P1-06-Target_disease.txtTarget ↔ Disease associations
P1-07-Drug_disease.txtDrug ↔ Disease associations

File formats:

  • P1-01, P2-01 — block format: blank-line separated records, each line <ID>\t<KEY>\t<VALUE>
  • P1-06, P1-07 — TSV with header row

Query API

query(entities, entity_type="auto", data_dir=DATA_DIR)

Returns a list of dicts, one per queried entity.

ParameterTypeDescription
entitiesstr or list[str]One or more entity names / IDs
entity_type"auto" / "target" / "drug" / "disease"Restrict search; "auto" tries target → drug → disease
data_dirstrPath to TTD data directory
query_json(entities, ...) → str

Same as query() but returns a JSON string. Use for LLM consumption.

Input formats accepted

InputExamples
Gene / protein name"EGFR", "TP53", "BCR-ABL"
Drug name"Imatinib", "Gefitinib", "Osimertinib"
Disease name"Lung cancer", "Diabetes mellitus" (partial match supported)
TTD Target ID"TTDTARGET00001"
TTD Drug ID"D0Y4GH"

Matching is case-insensitive; disease names support partial matching.

Output structure

Target result
json
{
  "query": "EGFR",
  "entity_type": "target",
  "ttd_id": "TTDTARGET00001",
  "name": "Epidermal growth factor receptor",
  "uniprot": "P00533",
  "gene": "EGFR",
  "target_type": "Successful target",
  "function": "Receptor tyrosine kinase...",
  "disease": "Non-small-cell lung cancer [ICD-11: 2C25]",
  "pathway": "EGFR signaling pathway",
  "drugs": [
    {"drug_id": "D0Y4GH", "drug_name": "Gefitinib", "clinical_status": "Approved"},
    {"drug_id": "D08VGC", "drug_name": "Erlotinib", "clinical_status": "Approved"}
  ]
}
Drug result
json
{
  "query": "Imatinib",
  "entity_type": "drug",
  "drug_id": "D0IQX1",
  "drug_name": "Imatinib",
  "targets": [
    {"ttd_target_id": "TTDTARGET00002", "target_name": "BCR-ABL",
     "clinical_status": "Approved", "drug_id": "D0IQX1"}
  ],
  "diseases": ["Chronic myelogenous leukemia", "Gastrointestinal stromal tumor"]
}
Disease result
json
{
  "query": "Lung cancer",
  "entity_type": "disease",
  "disease_name": "non-small-cell lung cancer",
  "targets": [
    {"ttd_target_id": "TTDTARGET00001", "target_name": "EGFR"}
  ],
  "drugs": ["Gefitinib", "Osimertinib", "Erlotinib"]
}
Not found
json
{"query": "XYZ123", "entity_type": "not_found", "message": "No match found in TTD."}

Usage examples

python
from 17_TTD import query, query_json
# Single entity
results = query("EGFR")
# Multiple entities (mixed types — auto-detected)
results = query(["EGFR", "Imatinib", "Lung cancer"])
# Restrict to drug search only
results = query(["Gefitinib", "Osimertinib"], entity_type="drug")
# JSON string output (for LLM)
print(query_json("TP53"))

CLI (demo runs with EGFR / Imatinib / Lung cancer if no args):

bash
python 17_TTD.py EGFR Imatinib "Lung cancer"
python 17_TTD.py TTDTARGET00001

Notes

  • `entity_type="auto"` stops at the first match type per entity (target → drug → disease). Use explicit type to resolve ambiguity.
  • `drugs` in target results lists all TTD-linked drugs; filter clinical_status == "Approved" for marketed drugs.
  • Disease partial matching — "lung cancer" will match "non-small-cell lung cancer". The first candidate is returned; use entity_type="disease" with a more specific name if needed.
  • Multi-value fields (e.g. multiple pathways for one target) are returned as lists.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
116
Repository forks
3
7-day trend score
24

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/qsong-github/drugclaw/ttd/badge)](https://verified-skill.com/skills/qsong-github/drugclaw/ttd)

Something wrong with this skill or its page? Tell us.