InternScience/drug_repurposing_screen

Drug Repurposing Screening

Discipline: Drug Discovery | Tools Used: 4 | Servers: 3

Description

Screen existing drugs for new indications by querying FDA indications, ChEMBL mechanisms, and OpenTargets drug-disease associations.

Tools Used

• get_indications_by_drug_name from fda-drug-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/14/Origene-FDADrug
• get_mechanism_of_action_by_drug_name from fda-drug-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/14/Origene-FDADrug
• get_drug_by_name from chembl-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/4/Origene-ChEMBL
• get_associated_drugs_by_target_name from opentargets-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/15/Origene-OpenTargets

Workflow

1. Get current indications from FDA
2. Get mechanism of action
3. Get ChEMBL drug data
4. Search OpenTargets for new target associations

Test Case

Input

{
    "drug_name": "metformin"
}

Expected Steps

1. Get current indications from FDA
2. Get mechanism of action
3. Get ChEMBL drug data
4. Search OpenTargets for new target associations

Usage Example

Note: Replace <YOUR_SCP_HUB_API_KEY> with your own SCP Hub API Key. You can obtain one from the SCP Platform.

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

SERVERS = {
    "fda-drug-server": "https://scp.intern-ai.org.cn/api/v1/mcp/14/Origene-FDADrug",
    "chembl-server": "https://scp.intern-ai.org.cn/api/v1/mcp/4/Origene-ChEMBL",
    "opentargets-server": "https://scp.intern-ai.org.cn/api/v1/mcp/15/Origene-OpenTargets"
}

async def connect(url, transport_type):
    transport = streamablehttp_client(url=url, headers={"SCP-HUB-API-KEY": "<YOUR_SCP_HUB_API_KEY>"})
    read, write, _ = await transport.__aenter__()
    ctx = ClientSession(read, write)
    session = await ctx.__aenter__()
    await session.initialize()
    return session, ctx, transport

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():
    # Connect to required servers
    sessions = {}
    sessions["fda-drug-server"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/14/Origene-FDADrug", "streamable-http")
    sessions["chembl-server"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/4/Origene-ChEMBL", "streamable-http")
    sessions["opentargets-server"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/15/Origene-OpenTargets", "streamable-http")

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

    # Step 2: Get mechanism of action
    result_2 = await sessions["fda-drug-server"].call_tool("get_mechanism_of_action_by_drug_name", arguments={})
    data_2 = parse(result_2)
    print(f"Step 2 result: {json.dumps(data_2, indent=2, ensure_ascii=False)[:500]}")

    # Step 3: Get ChEMBL drug data
    result_3 = await sessions["chembl-server"].call_tool("get_drug_by_name", arguments={})
    data_3 = parse(result_3)
    print(f"Step 3 result: {json.dumps(data_3, indent=2, ensure_ascii=False)[:500]}")

    # Step 4: Search OpenTargets for new target associations
    result_4 = await sessions["opentargets-server"].call_tool("get_associated_drugs_by_target_name", 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())