Clarity Research Skill
Search protein folding research data from Clarity Protocol, a community-driven platform for protein mutation analysis using AlphaFold2 via ColabFold.
Quick Start
List all available variants:
CODEBLOCK0
Filter by disease:
CODEBLOCK1
Filter by protein name:
CODEBLOCK2
Output Fields
Each variant result includes:
- -
id: Unique fold identifier - INLINECODE1 : Protein name (e.g., "tau", "APP")
- INLINECODE2 : Mutation notation (e.g., "P301L", "A246E")
- INLINECODE3 : Associated disease
- INLINECODE4 : UniProt database identifier
- INLINECODE5 : AlphaFold confidence score (0-100)
- INLINECODE6 : When the fold was created
Rate Limits
- - Anonymous (no API key): 10 requests/minute
- With API key: 100 requests/minute
To use an API key, set the CLARITY_API_KEY environment variable:
CODEBLOCK3
Get your API key at https://clarityprotocol.io
Error Handling
404 Not Found: The endpoint or resource does not exist.
429 Rate Limit: You've exceeded the rate limit. The script will display how long to wait before retrying.
500 Server Error: The API server encountered an error. Try again later.
Timeout: The request took longer than 30 seconds. The server may be under heavy load.
Pagination
Results are paginated. The API returns a next_cursor field if more results are available. The script automatically handles pagination for typical queries.
Use Cases
- - Explore available protein variants for a specific disease
- Find all folded mutations for a particular protein
- Get an overview of research data available in Clarity Protocol
- Identify fold IDs for detailed analysis with other skills
Clarity研究技能
从Clarity Protocol(一个通过ColabFold使用AlphaFold2进行蛋白质突变分析的社区驱动平台)搜索蛋白质折叠研究数据。
快速开始
列出所有可用变体:
bash
python scripts/query_variants.py
按疾病筛选:
bash
python scripts/query_variants.py --disease Alzheimer
按蛋白质名称筛选:
bash
python scripts/query_variants.py --protein-name MAPT
输出字段
每个变体结果包含:
- - id:唯一折叠标识符
- proteinname:蛋白质名称(例如tau、APP)
- variant:突变符号(例如P301L、A246E)
- disease:相关疾病
- uniprotid:UniProt数据库标识符
- averageconfidence:AlphaFold置信度评分(0-100)
- createdat:折叠创建时间
速率限制
- - 匿名用户(无API密钥):每分钟10次请求
- 使用API密钥:每分钟100次请求
要使用API密钥,请设置CLARITYAPIKEY环境变量:
bash
export CLARITYAPIKEY=yourkeyhere
python scripts/query_variants.py
在https://clarityprotocol.io获取您的API密钥
错误处理
404未找到:端点或资源不存在。
429速率限制:您已超过速率限制。脚本将显示重试前需要等待的时间。
500服务器错误:API服务器遇到错误。请稍后重试。
超时:请求耗时超过30秒。服务器可能负载过高。
分页
结果采用分页方式。如果还有更多结果,API会返回next_cursor字段。脚本会自动处理常规查询的分页。
使用场景
- - 探索特定疾病的可用蛋白质变体
- 查找特定蛋白质的所有已折叠突变
- 获取Clarity Protocol中可用研究数据的概览
- 识别折叠ID以便使用其他技能进行详细分析