Skill v1.0.0

currentAutomated scan100/100

internscience/scp/protein-drug-interaction

──Details

PublishedJune 16, 2026 at 11:17 PM

Content Hashsha256:095e88bd3168df28...

Git SHAcea539856403

──Files

Files (1 file, 4.5 KB)

SKILL.md4.5 KBactive

SKILL.md · 116 lines · 4.5 KB

version: "1.0.0" name: protein_drug_interaction description: "Protein-Drug Interaction Profiling - Profile protein-drug interactions: protein properties, drug structure, binding affinity prediction, and interaction data. Use this skill for molecular pharmacology tasks involving calculate protein sequence properties ChemicalStructureAnalyzer boltz binding affinity PredictDrugTargetInteraction. Combines 4 tools from 4 SCP server(s)."

Protein-Drug Interaction Profiling

Discipline: Molecular Pharmacology | Tools Used: 4 | Servers: 4

Description

Profile protein-drug interactions: protein properties, drug structure, binding affinity prediction, and interaction data.

Tools Used

`calculate_protein_sequence_properties` from server-2 (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool
`ChemicalStructureAnalyzer` from server-28 (sse) - https://scp.intern-ai.org.cn/api/v1/mcp/28/InternAgent
`boltz_binding_affinity` from server-3 (streamable-http) - https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model
`PredictDrugTargetInteraction` from server-29 (sse) - https://scp.intern-ai.org.cn/api/v1/mcp/29/SciToolAgent-Bio

Workflow

Calculate protein properties
Analyze drug structure
Predict binding affinity
Predict drug-target interaction

Test Case

Input

json

{
    "sequence": "MKTIIALSYIFCLVFA",
    "drug": "caffeine"
}

Expected Steps

Calculate protein properties
Analyze drug structure
Predict binding affinity
Predict drug-target interaction

Usage Example

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

python

import asyncio
import json
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
from mcp.client.sse import sse_client
SERVERS = {
    "server-2": "https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool",
    "server-28": "https://scp.intern-ai.org.cn/api/v1/mcp/28/InternAgent",
    "server-3": "https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model",
    "server-29": "https://scp.intern-ai.org.cn/api/v1/mcp/29/SciToolAgent-Bio"
}
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["server-2"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool", "streamable-http")
    sessions["server-28"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/28/InternAgent", "sse")
    sessions["server-3"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model", "streamable-http")
    sessions["server-29"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/29/SciToolAgent-Bio", "sse")
    # Execute workflow steps
    # Step 1: Calculate protein properties
    result_1 = await sessions["server-2"].call_tool("calculate_protein_sequence_properties", arguments={})
    data_1 = parse(result_1)
    print(f"Step 1 result: {json.dumps(data_1, indent=2, ensure_ascii=False)[:500]}")
    # Step 2: Analyze drug structure
    result_2 = await sessions["server-28"].call_tool("ChemicalStructureAnalyzer", arguments={})
    data_2 = parse(result_2)
    print(f"Step 2 result: {json.dumps(data_2, indent=2, ensure_ascii=False)[:500]}")
    # Step 3: Predict binding affinity
    result_3 = await sessions["server-3"].call_tool("boltz_binding_affinity", arguments={})
    data_3 = parse(result_3)
    print(f"Step 3 result: {json.dumps(data_3, indent=2, ensure_ascii=False)[:500]}")
    # Step 4: Predict drug-target interaction
    result_4 = await sessions["server-29"].call_tool("PredictDrugTargetInteraction", 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())

All versions