virtual-screening

name	virtual_screening
description	Virtual Screening Pipeline - Virtual screening: search PubChem by substructure, compute similarity, filter by drug-likeness, and predict binding affinity. Use this skill for drug discovery tasks involving search pubchem by smiles calculate smiles similarity calculate mol drug chemistry boltz binding affinity. Combines 4 tools from 3 SCP server(s).

Virtual Screening Pipeline

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

Description

Virtual screening: search PubChem by substructure, compute similarity, filter by drug-likeness, and predict binding affinity.

Tools Used

• search_pubchem_by_smiles from pubchem-server (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/8/Origene-PubChem
• calculate_smiles_similarity from server-2 (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool
• calculate_mol_drug_chemistry from server-2 (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool
• boltz_binding_affinity from server-3 (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model

Workflow

1. Search similar compounds in PubChem
2. Compute molecular similarity
3. Filter by drug-likeness
4. Predict binding affinity

Test Case

Input

{
    "query_smiles": "c1ccc(-c2ccccc2)cc1",
    "target_protein": "MKTIIALSYIFCLVFA"
}

Expected Steps

1. Search similar compounds in PubChem
2. Compute molecular similarity
3. Filter by drug-likeness
4. Predict binding affinity

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 = {
    "pubchem-server": "https://scp.intern-ai.org.cn/api/v1/mcp/8/Origene-PubChem",
    "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)
    :  (result)

  ():
      AsyncExitStack()  stack:
        
        sessions = {}
        sessions[] =  connect(, stack)
        sessions[] =  connect(, stack)
        sessions[] =  connect(, stack)

        
        
        result_1 =  sessions[].call_tool(, arguments={})
        data_1 = parse(result_1)
        ()

        
        result_2 =  sessions[].call_tool(, arguments={})
        data_2 = parse(result_2)
        ()

        
        result_3 =  sessions[].call_tool(, arguments={})
        data_3 = parse(result_3)
        ()

        
        result_4 =  sessions[].call_tool(, arguments={})
        data_4 = parse(result_4)
        ()

        
        ()

 __name__ == :
    asyncio.run(main())