Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Bulk RNA-seq Orchestrator

An end-to-end router that takes bulk RNA-seq from raw FASTQ through QC, quantification, a counts matrix, DESeq2, pathway enrichment, and publication figures.

Data & AnalyticsAdvanced★ 41,485⑂ 3,824AI score 9/10Last updated: Aug 31, 2026

What it does

  • Drives the full bulk RNA-seq workflow: FastQC/trimming → STAR and/or Salmon quantification → gene-level counts matrix → PyDESeq2 differential expression → GSEA/ORA enrichment → figures.
  • Routes between Path A (nf-core/rnaseq via Nextflow, most reproducible) and Path B (standalone bioconda tools for small or constrained setups) and tells you which to pick.
  • Owns the awkward gap — quant output to a DESeq2-ready matrix — via scripts/build_counts_matrix.py (Salmon through pytximport length_scaled_tpm, STAR strandedness column selection, featureCounts parsing).
  • Enforces design and QC gates: ≥3 biological replicates, batch/confounding checks, strandedness verification, PCA and sample-distance heatmaps, pinned pipeline/tool/genome versions.

Who it's for

  • Wet-lab researchers and grad students who need to go from FASTQ files to DE genes and enriched pathways.
  • Bioinformaticians configuring nf-core/rnaseq or bridging STAR/Salmon/featureCounts output into DESeq2/PyDESeq2.
  • Anyone wanting an experimental design sanity check (replicates, batch, library strandedness) before burning compute.
  • Single-cell data? Use the scanpy skill instead.

Example uses

  1. "Analyze my RNA-seq" → validate the samplesheet → nextflow run nf-core/rnaseq -r 3.26.0 --aligner star_salmon → feed salmon.merged.gene_counts_length_scaled.tsv into DE.
  2. "Build a counts matrix from my Salmon quant folder" → build_counts_matrix.py --from salmon --tx2gene tx2gene.tsv emits counts.csv plus metadata_template.csv.
  3. "3 controls vs 3 treated across two batches — what design formula?" → recommends ~batch + condition, flags confounding, and points to QC thresholds.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/bulk-rnaseq/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/bulk-rnaseq folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/bulk-rnaseq/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/bulk-rnaseq ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Create the skills directory: mkdir -p ~/.claude/skills
  3. Copy this skill in: cp -r scientific-agent-skills/skills/bulk-rnaseq ~/.claude/skills/
  4. Also copy the companion skills it hands off to: cp -r scientific-agent-skills/skills/{pydeseq2,pathway-enrichment,nextflow,scientific-visualization} ~/.claude/skills/
  5. Install the glue dependencies: uv pip install pytximport pandas (or pip install pytximport pandas)
  6. Pick a path — Path A needs Nextflow plus Docker/Singularity; Path B: conda create -n rnaseq -c bioconda -c conda-forge fastqc fastp trim-galore star=2.7.11b salmon=1.10.3 subread multiqc
  7. Restart Claude Code and try a prompt like "take my FASTQ files to differentially expressed genes and enriched pathways".
View source on GitHub ↗License: MIT