Binding Site Characterization

---
name: binding_site_characterization
description: 'Binding Site Characterization - Characterize binding sites: predict
  pockets with fpocket and P2Rank, get binding site info from ChEMBL, and visualize.
  Use this skill for structural biology tasks involving run fpocket pred pocket prank
  get binding site by id visualize protein. Combines 4 tools from 3 SCP server(s).'
i18n:
  zh:
    description: 结合位点表征与可视化。
---

# Binding Site Characterization

**Discipline**: Structural Biology | **Tools Used**: 4 | **Servers**: 3

## Description

Characterize binding sites: predict pockets with fpocket and P2Rank, get binding site info from ChEMBL, and visualize.

## Tools Used

- **`run_fpocket`** from `server-3` (streamable-http) - `https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model`
- **`pred_pocket_prank`** from `server-3` (streamable-http) - `https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model`
- **`get_binding_site_by_id`** from `chembl-server` (streamable-http) - `https://scp.intern-ai.org.cn/api/v1/mcp/4/Origene-ChEMBL`
- **`visualize_protein`** from `server-2` (streamable-http) - `https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool`

## Workflow

1. Predict pockets with fpocket
2. Predict pockets with P2Rank
3. Get ChEMBL binding site data
4. Visualize protein structure

## Test Case

### Input
```json
{
    "pdb_code": "1AKE"
}
```

### Expected Steps
1. Predict pockets with fpocket
2. Predict pockets with P2Rank
3. Get ChEMBL binding site data
4. Visualize protein structure

## Usage Example

> **Note:** Replace `<YOUR_SCP_HUB_API_KEY>` with your own SCP Hub API Key. You can obtain one from the [SCP Platform](https://scphub.intern-ai.org.cn).

```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-3": "https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model",
    "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"
}

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-3"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/3/DrugSDA-Model", "streamable-http")
    sessions["chembl-server"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/4/Origene-ChEMBL", "streamable-http")
    sessions["server-2"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool", "streamable-http")

    # Execute workflow steps
    # Step 1: Predict pockets with fpocket
    result_1 = await sessions["server-3"].call_tool("run_fpocket", arguments={})
    data_1 = parse(result_1)
    print(f"Step 1 result: {json.dumps(data_1, indent=2, ensure_ascii=False)[:500]}")

    # Step 2: Predict pockets with P2Rank
    result_2 = await sessions["server-3"].call_tool("pred_pocket_prank", 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 binding site data
    result_3 = await sessions["chembl-server"].call_tool("get_binding_site_by_id", arguments={})
    data_3 = parse(result_3)
    print(f"Step 3 result: {json.dumps(data_3, indent=2, ensure_ascii=False)[:500]}")

    # Step 4: Visualize protein structure
    result_4 = await sessions["server-2"].call_tool("visualize_protein", 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())
```