Drug Target Structure

Drug-Target Structural Biology

Discipline: Structural Pharmacology | Tools Used: 4 | Servers: 3

Description

Integrate drug and target structure: get drug from ChEMBL, target structure from PDB, dock them, and predict ADMET.

Tools Used

• get_drug_by_name from chembl-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/4/Origene-ChEMBL
• retrieve_protein_data_by_pdbcode from server-2 (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool
• quick_molecule_docking from server-3 (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model
• pred_molecule_admet from server-3 (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model

Workflow

1. Get drug data from ChEMBL
2. Download target structure
3. Perform molecular docking
4. Predict ADMET for drug

Test Case

Input

{
    "drug": "imatinib",
    "pdb_code": "1IEP"
}

Expected Steps

1. Get drug data from ChEMBL
2. Download target structure
3. Perform molecular docking
4. Predict ADMET for drug

Usage Example

Note: Replace sk-b04409a1-b32b-4511-9aeb-22980abdc05c with your own SCP Hub API Key. You can obtain one from the SCP Platform.

import asyncio
import json
from contextlib import AsyncExitStack
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
from mcp.client.sse import sse_client

SERVERS = {
    "chembl-server": "https://scp.intern-ai.org.cn/api/v1/mcp/4/Origene-ChEMBL",
    "server-2": "https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool",
    "server-3": "https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model"
}

async def connect(url, stack):
    transport = streamablehttp_client(url=url, headers={"SCP-HUB-API-KEY": "sk-b04409a1-b32b-4511-9aeb-22980abdc05c"})
    read, write, _ = await stack.enter_async_context(transport)
    ctx = ClientSession(read, write)
    session = await stack.enter_async_context(ctx)
    await session.initialize()
    return session

def parse(result):
    try:
        if hasattr(result, 'content') and result.content:
            c = result.content[0]
            if hasattr(c, 'text'):
                try: return json.loads(c.text)
                except: return c.text
        return str(result)
    except: return str(result)

async def main():
    async with AsyncExitStack() as stack:
        # Connect to required servers
        sessions = {}
        sessions["chembl-server"] = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/4/Origene-ChEMBL", stack)
        sessions["server-2"] = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool", stack)
        sessions["server-3"] = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model", stack)

        # Execute workflow steps
        # Step 1: Get drug data from ChEMBL
        result_1 = await sessions["chembl-server"].call_tool("get_drug_by_name", arguments={})
        data_1 = parse(result_1)
        print(f"Step 1 result: {json.dumps(data_1, indent=2, ensure_ascii=False)[:500]}")

        # Step 2: Download target structure
        result_2 = await sessions["server-2"].call_tool("retrieve_protein_data_by_pdbcode", arguments={})
        data_2 = parse(result_2)
        print(f"Step 2 result: {json.dumps(data_2, indent=2, ensure_ascii=False)[:500]}")

        # Step 3: Perform molecular docking
        result_3 = await sessions["server-3"].call_tool("quick_molecule_docking", arguments={})
        data_3 = parse(result_3)
        print(f"Step 3 result: {json.dumps(data_3, indent=2, ensure_ascii=False)[:500]}")

        # Step 4: Predict ADMET for drug
        result_4 = await sessions["server-3"].call_tool("pred_molecule_admet", arguments={})
        data_4 = parse(result_4)
        print(f"Step 4 result: {json.dumps(data_4, indent=2, ensure_ascii=False)[:500]}")

        # Cleanup
        print("Workflow complete!")

if __name__ == "__main__":
    asyncio.run(main())