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

scVelo RNA Velocity Analysis

Guides Claude through a full scVelo RNA velocity pipeline — cell state transitions, latent time, and driver genes from spliced/unspliced scRNA-seq counts.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Walks through the complete scVelo workflow with runnable code: data loading (loom / merged AnnData), preprocessing, moments, velocity estimation (stochastic / deterministic / dynamical), latent time, driver-gene ranking, and PAGA velocity graphs.
  • Accounts for the scVelo 0.3 API change where filter_and_normalize() no longer log-transforms or selects HVGs, adding the correct Scanpy steps instead.
  • Includes reference tables for AnnData output fields (layers['velocity'], obs['latent_time'], var['fit_gamma'], ...), model trade-offs, best practices, and a troubleshooting matrix.

Who it's for

  • Single-cell genomics researchers and grad students inferring differentiation trajectories
  • Users who already produced spliced/unspliced matrices via velocyto, STARsolo, kallisto|bustools, or alevin-fry
  • Bioinformaticians who want directional information layered onto an existing Scanpy pipeline

Example uses

  1. "Merge my velocyto loom with the processed h5ad and give me a quick stochastic stream plot" → merge + preprocessing + velocity_embedding_stream code.
  2. "Run the dynamical model for publication and produce a latent-time heatmap" → recover_dynamics → latent_time → top-300 gene heatmap.
  3. "My velocity arrows look random" → suggests tuning n_neighbors, switching models, checking for swapped spliced/unspliced layers.

· · · 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/scvelo/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/scvelo folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/scvelo/.
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/scvelo ~/.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 just this skill: cp -r scientific-agent-skills/skills/scvelo ~/.claude/skills/
  4. Install the Python deps (Python 3.10+): uv pip install scvelo scanpy anndata — for the verified scvelo 0.3.4 you also need pandas<3, and the stochastic estimator needs numpy<2.
  5. Restart Claude Code and ask something like "run an RNA velocity analysis with scvelo on my h5ad".
  6. Before running, confirm your AnnData has layers['spliced'], layers['unspliced'], and obsm['X_umap'].
View source on GitHub ↗License: MIT