Arboreto (Claude Skill)

Claude skill that drives Arboreto for gene-regulatory-network (GRN) inference — fitting GRNBoost2 or GENIE3 regression models that identify transcription-factor → target-gene relationships from bulk or single-cell expression data.

   
Type Claude Skill
Supplier K-Dense Inc. (community OSS)
Availability GA — actively maintained 2025–2026
Pricing Free / OSS skill (MIT collection); Arboreto itself is BSD-3
Capabilities Read/Write — Claude executes Arboreto via Python/Bash; Dask handles parallelism

How to install

  • Also packaged in the SciAgent-Skills collection (jaechang-hits (community OSS, CC BY 4.0)): clone jaechang-hits/SciAgent-Skills and run /plugin install sciagent-skills in Claude Code (or copy skills/genomics-bioinformatics/arboreto-grn-inference into ~/.claude/skills/).
  • Claude Code / Claude.ai — Skills CLI (recommended): 
    npx skills add K-Dense-AI/scientific-agent-skills

    Installs the K-Dense collection; enable the arboreto skill when prompted (also works in Cursor/Codex via the Agent Skills spec; requires Node ≥ 18).

  • Claude Code / Claude Desktop — manual clone: 
    git clone https://github.com/K-Dense-AI/scientific-agent-skills
cp -r scientific-agent-skills/skills/arboreto ~/.claude/skills/
pip install arboreto

Project-scoped alternative: copy into .claude/skills/ instead of ~/.claude/skills/.

What it does

SKILL.md with recipes for:

  • GRNBoost2 — gradient-boosting GRN inference with self-tuning early stopping (the recommended default)
  • GENIE3 — classical random-forest GRN inference for reproducing legacy analyses
  • TF-restricted inference using a curated transcription-factor list
  • Single-cell GRN inference (compatible with pySCENIC pre-processing)
  • Distributed execution via Dask — single machine to multi-node clusters
  • Importance-threshold filtering and ranking of TF–target edges

Primary use cases: Transcription-factor regulon discovery, single-cell GRN inference as a step in pySCENIC pipelines, regulator prioritisation for target-discovery and drug-repurposing studies.

Notes

Pairs with the scanpy, pydeseq2, and cellxgene-census skills — Arboreto consumes the (cells × genes) expression matrix produced by upstream QC. The Python script must include the standard if __name__ == "__main__": guard because Dask spawns child processes. Skill is documentation plus Python recipes — Claude calls Arboreto locally via Bash/Python.

Sources

Installed this tool?

Share feedback — install path, OS, errors, workarounds. The form opens with this tool pre-selected and a link back to this page.