drugsda-data-valid
Check if the input protein sequence or molecule SMILES string is valid.
- License 许可
- MIT
- 最近更新
- 2026-03-20
- Stars
- ★ 172
- Forks
- 10
01 前言 Front Matter
- i18n
- { "zh": { "description": "检查蛋白质序列或SMILES有。" } }
- name
- drugsda-data-valid
- license
- MIT license
- metadata
- { "skill-author": "PJLab" }
- description
- Check if the input protein sequence or molecule SMILES string is valid.
02 资源文件 47
- 其他.DS_Store6.0 KB
- 参考文档csharp/claude-api.md14.1 KB
- 参考文档curl/examples.md6.3 KB
- 参考文档curl/managed-agents.md7.2 KB
- 参考文档go/claude-api.md13.5 KB
- 参考文档go/managed-agents/README.md18.0 KB
- 参考文档java/claude-api.md14.7 KB
- 参考文档java/managed-agents/README.md16.2 KB
- 许可证LICENSE.txt11.1 KB
- 参考文档php/claude-api.md10.9 KB
- 参考文档php/managed-agents/README.md12.9 KB
- 其他python/.DS_Store6.0 KB
- 参考文档python/claude-api/batches.md5.0 KB
- 参考文档python/claude-api/files-api.md3.9 KB
- 参考文档python/claude-api/README.md11.9 KB
- 参考文档python/claude-api/streaming.md5.1 KB
- 参考文档python/claude-api/tool-use.md16.5 KB
- 参考文档python/managed-agents/README.md9.6 KB
- 参考文档ruby/claude-api.md2.9 KB
- 参考文档ruby/managed-agents/README.md9.9 KB
- 参考文档shared/agent-design.md8.1 KB
- 参考文档shared/error-codes.md7.5 KB
- 参考文档shared/live-sources.md16.7 KB
- 参考文档shared/managed-agents-api-reference.md24.3 KB
- 参考文档shared/managed-agents-client-patterns.md9.2 KB
- 参考文档shared/managed-agents-core.md13.6 KB
- 参考文档shared/managed-agents-environments.md11.0 KB
- 参考文档shared/managed-agents-events.md9.4 KB
- 参考文档shared/managed-agents-memory.md9.4 KB
- 参考文档shared/managed-agents-multiagent.md6.4 KB
- 参考文档shared/managed-agents-onboarding.md8.1 KB
- 参考文档shared/managed-agents-outcomes.md6.0 KB
- 参考文档shared/managed-agents-overview.md9.6 KB
- 参考文档shared/managed-agents-self-hosted-sandboxes.md9.7 KB
- 参考文档shared/managed-agents-tools.md14.2 KB
- 参考文档shared/managed-agents-webhooks.md4.9 KB
- 参考文档shared/model-migration.md79.1 KB
- 参考文档shared/models.md8.0 KB
- 参考文档shared/prompt-caching.md9.6 KB
- 参考文档shared/tool-use-concepts.md16.6 KB
- 其他typescript/.DS_Store6.0 KB
- 参考文档typescript/claude-api/batches.md2.5 KB
- 参考文档typescript/claude-api/files-api.md2.2 KB
- 参考文档typescript/claude-api/README.md9.7 KB
- 参考文档typescript/claude-api/streaming.md5.5 KB
- 参考文档typescript/claude-api/tool-use.md15.0 KB
- 参考文档typescript/managed-agents/README.md9.2 KB
03 SKILL.md 正文
Protein or Molecule Data Check
Usage
1. MCP Server Definition
import json
from mcp.client.streamable_http import streamablehttp_client
from mcp import ClientSession
class DrugSDAClient:
def __init__(self, server_url: str):
self.server_url = server_url
self.session = None
async def connect(self):
print(f"server url: {self.server_url}")
try:
self.transport = streamablehttp_client(
url=self.server_url,
headers={"SCP-HUB-API-KEY": "sk-a0033dde-b3cd-413b-adbe-980bc78d6126"}
)
self.read, self.write, self.get_session_id = await self.transport.__aenter__()
self.session_ctx = ClientSession(self.read, self.write)
self.session = await self.session_ctx.__aenter__()
await self.session.initialize()
session_id = self.get_session_id()
print(f"✓ connect success")
return True
except Exception as e:
print(f"✗ connect failure: {e}")
import traceback
traceback.print_exc()
return False
async def disconnect(self):
try:
if self.session:
await self.session_ctx.__aexit__(None, None, None)
if hasattr(self, 'transport'):
await self.transport.__aexit__(None, None, None)
print("✓ already disconnect")
except Exception as e:
print(f"✗ disconnect error: {e}")
def parse_result(self, result):
try:
if hasattr(result, 'content') and result.content:
content = result.content[0]
if hasattr(content, 'text'):
return json.loads(content.text)
return str(result)
except Exception as e:
return {"error": f"parse error: {e}", "raw": str(result)}
2. Protein Sequence Valid Check
The description of tool is_valid_protein_sequence.
Check if the input protein sequence string is valid.
Args:
sequences (List[str]): List of input protein sequences
Return:
status (str): success/partial_success/error
msg (str): message
valid_res (List[dict]): List of dict, each containing the keys 'sequence' and 'is_valid'.
--sequence (str): A protein sequence of the input sequences list
--is_valid (bool): Is the protein sequence valid or not
How to use tool is_valid_protein_sequence :
client = DrugSDAClient("https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool")
if not await client.connect():
print("connection failed")
return
response = await client.session.call_tool(
"is_valid_protein_sequence",
arguments={
"sequences": sequence_list
}
)
result = client.parse_result(response)
valid_res = result["valid_res"]
await client.disconnect()
3. Molecule SMILCES Valid Check
The description of tool is_valid_smiles.
Check if the input SMILES string is valid
Args:
smiles_list (List[str]): List of input SMILES strings, (e.g., ["N[C@@H](Cc1ccc(O)cc1)C(=O)O", "CC(C)C1=CC=CC=C1"])
Return:
status (str): success/partial_success/error
msg (str): message
valid_res (List[dict]): List of dict, each containing the keys 'smiles' and 'is_valid'.
--smiles (str): A SMILES string of smiles_list
--is_valid (bool): Is the SMILES valid or not
How to use tool is_valid_smiles :
client = DrugSDAClient("https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool")
if not await client.connect():
print("connection failed")
return
response = await client.session.call_tool(
"is_valid_smiles",
arguments={
"smiles_list": smiles_list
}
)
result = client.parse_result(response)
valid_res = result["valid_res"]
await client.disconnect()
04 同仓库更多 Skills
scientific-critical-thinking
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.
scientific-brainstorming
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
scientific-literature-search
Search scientific literature and research papers using FlowSearch to find relevant academic articles and publications.
pubmed-article-search
Search PubMed database for scientific articles and publications to retrieve biomedical literature.
biomedical-web-search
Search biomedical literature and web content using Tavily search engine for research and clinical information.
uniprot-protein-retrieval
Retrieve protein sequences and functional information from UniProt database by protein name, enabling protein analysis and bioinformatics workflows.