# Gene Expression Atlas

> Gene Expression Atlas - Build gene expression atlas: TCGA cancer expression, NCBI gene info, Ensembl gene details, and literature search. Use this skill for transcriptomics tasks involving get gene expression across cancers get gene metadata by gene name get lookup symbol search literature. Combines 4 tools from 4 SCP server(s).

- Skill: `internscience/gene-expression-atlas` (Agent Skill)
- Install (CLI): `npx skillmds@latest add internscience/gene-expression-atlas`
- Raw SKILL.md: https://api.skillmd.com/api/skills/internscience/gene-expression-atlas/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: internscience (https://skillmd.com/u/internscience)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/internscience/gene-expression-atlas

---


# Gene Expression Atlas

**Discipline**: Transcriptomics | **Tools Used**: 4 | **Servers**: 4

## Description

Build gene expression atlas: TCGA cancer expression, NCBI gene info, Ensembl gene details, and literature search.

## Tools Used

- **`get_gene_expression_across_cancers`** from `tcga-server` (streamable-http) - `https://scp.intern-ai.org.cn/api/v1/mcp/11/Origene-TCGA`
- **`get_gene_metadata_by_gene_name`** from `ncbi-server` (streamable-http) - `https://scp.intern-ai.org.cn/api/v1/mcp/9/Origene-NCBI`
- **`get_lookup_symbol`** from `ensembl-server` (streamable-http) - `https://scp.intern-ai.org.cn/api/v1/mcp/12/Origene-Ensembl`
- **`search_literature`** from `server-1` (sse) - `https://scp.intern-ai.org.cn/api/v1/mcp/1/VenusFactory`

## Workflow

1. Get TCGA expression profile
2. Get NCBI gene metadata
3. Get Ensembl gene info
4. Search recent literature

## Test Case

### Input
```json
{
    "gene": "EGFR",
    "species": "human"
}
```

### Expected Steps
1. Get TCGA expression profile
2. Get NCBI gene metadata
3. Get Ensembl gene info
4. Search recent literature

## 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 = {
    "tcga-server": "https://scp.intern-ai.org.cn/api/v1/mcp/11/Origene-TCGA",
    "ncbi-server": "https://scp.intern-ai.org.cn/api/v1/mcp/9/Origene-NCBI",
    "ensembl-server": "https://scp.intern-ai.org.cn/api/v1/mcp/12/Origene-Ensembl",
    "server-1": "https://scp.intern-ai.org.cn/api/v1/mcp/1/VenusFactory"
}

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["tcga-server"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/11/Origene-TCGA", "streamable-http")
    sessions["ncbi-server"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/9/Origene-NCBI", "streamable-http")
    sessions["ensembl-server"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/12/Origene-Ensembl", "streamable-http")
    sessions["server-1"], _, _ = await connect("https://scp.intern-ai.org.cn/api/v1/mcp/1/VenusFactory", "sse")

    # Execute workflow steps
    # Step 1: Get TCGA expression profile
    result_1 = await sessions["tcga-server"].call_tool("get_gene_expression_across_cancers", arguments={})
    data_1 = parse(result_1)
    print(f"Step 1 result: {json.dumps(data_1, indent=2, ensure_ascii=False)[:500]}")

    # Step 2: Get NCBI gene metadata
    result_2 = await sessions["ncbi-server"].call_tool("get_gene_metadata_by_gene_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 Ensembl gene info
    result_3 = await sessions["ensembl-server"].call_tool("get_lookup_symbol", arguments={})
    data_3 = parse(result_3)
    print(f"Step 3 result: {json.dumps(data_3, indent=2, ensure_ascii=False)[:500]}")

    # Step 4: Search recent literature
    result_4 = await sessions["server-1"].call_tool("search_literature", 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())
```