Protein Property Comparison

---
name: protein_property_comparison
description: "Cross-Species Protein Comparison - Compare proteins across species: get orthologs from NCBI, compute properties for each, and compare similarity. Use this skill for comparative biology tasks involving get gene orthologs calculate protein sequence properties calculate smiles similarity get homology id. Combines 4 tools from 3 SCP server(s)."
---

# Cross-Species Protein Comparison

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

## Description

Compare proteins across species: get orthologs from NCBI, compute properties for each, and compare similarity.

## Tools Used

- **`get_gene_orthologs`** from `ncbi-server` (streamable-http) - `https://scp.intern-ai.org.cn/api/v1/mcp/9/Origene-NCBI`
- **`calculate_protein_sequence_properties`** from `server-2` (streamable-http) - `https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool`
- **`calculate_smiles_similarity`** from `server-2` (streamable-http) - `https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool`
- **`get_homology_id`** from `ensembl-server` (streamable-http) - `https://scp.intern-ai.org.cn/api/v1/mcp/12/Origene-Ensembl`

## Workflow

1. Get orthologs from NCBI
2. Calculate properties for human protein
3. Calculate properties for mouse ortholog
4. Get Ensembl homology data

## Test Case

### Input
```json
{
    "gene_id": 7157
}
```

### Expected Steps
1. Get orthologs from NCBI
2. Calculate properties for human protein
3. Calculate properties for mouse ortholog
4. Get Ensembl homology data

## Usage Example

> **Note:** Replace `sk-[REDACTED]` 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 contextlib import AsyncExitStack
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
from mcp.client.sse import sse_client

SERVERS = {
    "ncbi-server": "https://scp.intern-ai.org.cn/api/v1/mcp/9/Origene-NCBI",
    "server-2": "https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool",
    "ensembl-server": "https://scp.intern-ai.org.cn/api/v1/mcp/12/Origene-Ensembl"
}

async def connect(url, stack):
    transport = streamablehttp_client(url=url, headers={"SCP-HUB-API-KEY": "sk-[REDACTED]"})
    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["ncbi-server"] = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/9/Origene-NCBI", stack)
        sessions["server-2"] = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool", stack)
        sessions["ensembl-server"] = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/12/Origene-Ensembl", stack)

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

        # Step 2: Calculate properties for human protein
        result_2 = await sessions["server-2"].call_tool("calculate_protein_sequence_properties", arguments={})
        data_2 = parse(result_2)
        print(f"Step 2 result: {json.dumps(data_2, indent=2, ensure_ascii=False)[:500]}")

        # Step 3: Calculate properties for mouse ortholog
        result_3 = await sessions["server-2"].call_tool("calculate_smiles_similarity", arguments={})
        data_3 = parse(result_3)
        print(f"Step 3 result: {json.dumps(data_3, indent=2, ensure_ascii=False)[:500]}")

        # Step 4: Get Ensembl homology data
        result_4 = await sessions["ensembl-server"].call_tool("get_homology_id", 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())
```