Skip to content

Add plugin microbe - #23

Open
Presisitence wants to merge 1 commit into
hetaoBackend:mainfrom
Presisitence:add-microbe
Open

Add plugin microbe#23
Presisitence wants to merge 1 commit into
hetaoBackend:mainfrom
Presisitence:add-microbe

Conversation

@Presisitence

Copy link
Copy Markdown

What changes

New Plugin Presisitence/microbe — 16S/ITS downstream microbiome analysis via local Rscript (alpha/beta diversity, composition, differential abundance, co-occurrence, random forest, taxonomy tree).

Path: plugins/Presisitence/microbe. Standalone source: https://github.com/Presisitence/microbe-mcp

User value

Given a feature table, taxonomy, and metadata, MiniMax Code can run vegan/DESeq2-style downstream plots and write png+pdf without starting from raw reads.

Example prompt:

I have feature_table.csv, taxonomy.csv, and metadata.csv (groups DP vs DSP). Draw alpha and beta
diversity, a genus stacked bar, DESeq2 differential abundance, and a co-occurrence network.

Expected result: microbe_env then microbe_alpha, microbe_beta, microbe_composition, microbe_diff, microbe_network; png+pdf paths and key stats returned. Does not run DADA2/QIIME2.

Plugin submission checklist

  • Plugin lives at plugins/<github-owner>/<plugin-name>.
  • plugin.json name matches the Plugin directory.
  • README.md includes a real example prompt and expected result.
  • LICENSE and plugin.json declare an open-source license.
  • Required executables, accounts, paid services, and supported platforms are disclosed.
  • Network destinations and data handled by the plugin are disclosed.
  • No credentials, private endpoints, hidden telemetry, installers, symlinks, or native binaries are included.
  • Every scaffold TODO has been replaced.
  • npm run check validator accepts this Plugin (validateHostedPluginDirectory).

Dependencies and platforms

  • Python 3.10+ and uv on PATH.
  • R with Rscript on PATH, or MICROBE_RSCRIPT.
  • R packages such as vegan, ggplot2, igraph; DESeq2/edgeR optional (tools degrade with install hints).
  • Windows, macOS, Linux.

Network and data behavior

Analyses are local on user CSVs. No telemetry. No credentials. tests/prep_test.py writes synthetic OTU-like tables only.

Evidence

validateHostedPluginDirectory plugins/Presisitence/microbe
OK Presisitence/microbe skills=microbe mcp=microbe

Manual: stdio MCP uses bare uv + ${PLUGIN_ROOT}; MIT LICENSE; no private 16S data shipped.

16S/ITS downstream microbiome analysis via local Rscript (alpha/beta diversity, composition, differential abundance, co-occurrence).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant