科研 Skill
gget 生信检索助手
gget
跨生信数据库检索基因蛋白信息
官方收录发布者 aipoch-medical-research-skills安全审核通过v0.1.0更新于 2026-08-28
Skill 说明
统一命令行/Python 接口,跨 20+ 生物信息数据库按基因、蛋白 ID 或关键词快速检索基因组、蛋白组、结构与表达数据。 | 适用:按 gene/protein ID 或关键词快速查基础生物信息。
SKILL.md
When to Use
- You need to search genes/proteins by keyword and species across common databases (e.g., Ensembl/UniProt/NCBI).
- You want to fetch detailed metadata for one or many Ensembl/UniProt/NCBI identifiers.
- You need to retrieve nucleotide/protein sequences for downstream analysis or pipelines.
- You want to obtain or predict protein structures (PDB download or AlphaFold prediction) from a sequence.
- You need to query expression resources (e.g., ARCHS4, CELLxGENE, Bgee) or run enrichment analysis (Enrichr).
Key Features
- Unified wrapper (
scripts/wrapper.py) exposing multipleggetsubcommands through a consistent interface. - Gene/protein search and identifier resolution across multiple databases.
- Rich gene/protein information retrieval (annotations and metadata).
- Sequence retrieval for provided IDs.
- Structure workflows: PDB retrieval and AlphaFold-based prediction (optional plotting).
- Expression querying across popular expression atlases.
- Enrichment analysis via Enrichr.
- Backed by the upstream
ggetPython library.
Dependencies
- Python 3.9+ (recommended)
gget(latest compatible version)pandas(latest compatible version)
Install:
uv pip install gget pandas
Example Usage
The skill is accessed via the unified wrapper script:
1) Search for genes by keyword
python scripts/wrapper.py search --keywords "insulin" --species "human"
2) Retrieve gene information by Ensembl ID
python scripts/wrapper.py info --ids "ENSG00000034713"
3) Fetch sequences by Ensembl ID
python scripts/wrapper.py seq --ids "ENSG00000034713"
4) Predict protein structure with AlphaFold (optional plotting)
python scripts/wrapper.py alphafold --sequence "MKWMFK..." --plot
Implementation Details
- Wrapper entrypoint:
scripts/wrapper.pyacts as a dispatcher that maps subcommands (e.g.,search,info,seq,alphafold) to the correspondingggetlibrary functions, normalizing CLI arguments and output behavior. - Supported modules/functions:
- ref: Download reference genomes/annotations.
- search: Keyword-based gene/protein lookup (Ensembl/UniProt/NCBI).
- info: Detailed gene/protein metadata retrieval for one or multiple IDs.
- seq: Nucleotide/protein sequence retrieval for provided IDs.
- structure: Structure retrieval (PDB) and AlphaFold prediction.
- expression: Expression queries (ARCHS4, CELLxGENE, Bgee).
- enrichment: Enrichr-based enrichment analysis.
- Notes on AlphaFold: The
alphafoldsubcommand requires additional setup depending on the environment (e.g., model/data availability). Use--plotto request visualization output when supported. - Further reference: See
references/module_reference.mdfor detailed module-level documentation and parameters.
相关科研 Skill
中药材分子鉴定用ITS2等DNA条形码鉴定药材基原物种,处理多基原与降解样品局限。适用于药材真伪鉴别研究,不替代法定检验。
中药网络药理学用TCMSP等数据库构建成分-靶点-通路网络并做富集分析,批判性讨论方法学局限。适用于中药机制假设生成与论文方法复核。
中医术语标准与知识图谱建立中医药术语与WHO/ICD-11标准的映射,设计本体并用Neo4j构建知识图谱。适用于数据整合与科研检索,不作临床决策系统。
方剂配伍规律挖掘对方剂做药名规范化、关联规则与网络聚类分析,发现候选核心药组。适用于用药规律挖掘,结果仅为待验证假设,不作处方依据。
证候与症状数据分析对症状量表数据做术语规范、潜在类别与因子分析,探索统计学证候模式。适用于证候分型研究,结果不用于个体辨证诊断。
泵用混合物热力学计算Calculates thermodynamic properties and mixture phase behavior for pump applications using the thermo Python library’s DIPPR/NIST correlations. Use for VLE or mixture property calculations.
常见问题
gget 生信检索助手能做什么?
统一命令行/Python 接口,跨 20+ 生物信息数据库按基因、蛋白 ID 或关键词快速检索基因组、蛋白组、结构与表达数据。 | 适用:按 gene/protein ID 或关键词快速查基础生物信息。
如何安装gget 生信检索助手?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「gget 生信检索助手」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。
gget 生信检索助手需要哪些权限?
该科研 Skill声明需要:本地文件。安装前会再次列出,由你确认后才会生效。
gget 生信检索助手经过官方审核吗?
是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。