DeepSeek Harness 蛋白质组学分析即插即用插件
A plug-and-play proteomics analysis plugin for DeepSeek Harness
安装
dsh plugin --profile web add github:YukunR/dsh-ezprot-pluginGitHub 源码安装:首次需按提示配置 allowBuilds 构建授权后重试
安装与环境配置指引、插件开发教程见 DSH 中文社区文档 ↗
安装即在你的机器上以你的权限运行第三方代码——它可读写文件、使用凭据、访问网络,DSH 的工具审批不会为插件代码加沙箱。「检测到 manifest」仅代表发现 dsh.bundle / dsh.plugin 清单,不构成兼容性或安全审查;安装前请审阅源码,不熟悉的插件先在不含密钥的环境试用。
README
A plug-and-play proteomics analysis plugin for DeepSeek Harness. It wraps a full protein-expression analysis workflow — normalization → PCA → batch correction → differential analysis → GO/KEGG enrichment → GSEA — behind a conversation: give the agent your data file, answer a few questions (which columns are what, which groups to compare), and the plugin prepares everything automatically and walks through every step with visible summaries and figures, ending with an interpretation report.
No R or terminal knowledge required: the plugin detects or silently installs its own R 4.4.0 runtime and package library on first use (one-time, ~10–20 min).
Install
Prerequisites: Node.js (bundles npx) and pnpm — npm install -g pnpm.
Requires the dsh CLI (Windows / macOS / Linux), one command:
npx @deepseek-ai/dsh plugin --profile web add dsh-ezprot-plugin@0.1.1
If dsh is already installed globally, drop the npx @deepseek-ai/ prefix:
dsh plugin --profile web add dsh-ezprot-plugin@0.1.1
Then restart dsh web. Every session's agent gains the proteomics_* tools.
Usage
Just talk to the agent. For example:
My proteomics data is at
D:\my-experiment\origin_data.txtwith sample groups inD:\my-experiment\sample_info.txt, mouse samples. Compare HC and HD against NC.
The agent will inspect and QC your data, confirm the comparisons with you, run the analysis step by step, and write an interpretation report (top proteins, enriched pathways, candidate targets). Detailed instructions: biologist's guide (中文).
Development
See CONTRIBUTING.md.
原始 README: https://github.com/YukunR/dsh-ezprot-plugin/blob/main/README.md ↗
同类插件
查看全部 →
dsh-anchored-standard
两阶段 DeepSeek Harness 预设:先 Minimal 对齐的 bootstrap,再切完整 Standard 工具(Project2 98/99)

PicGo-Core
极致的图片上传引擎,CLI 与 API 双支持

awesome-deepseek-harness
DeepSeek Harness(DSH)及其优秀社区插件的精选指南。

awesome-deepseek-harness
DeepSeek Harness (DSH)生态系统:来自dsh-external/hub和公共dsh-plugin主题的精选插件、工具和基础设施。

AI-Novel-Writer
本地优先 AI 小说创作工作台,提供 Windows/macOS 桌面版与 DeepSeek Harness 插件开发预览,支持角色、大纲、章节蓝图、审稿修稿和本地模型。

mcp-for-stata
MCP-for-Stata:把 Stata 集成进你的 agent