scvelo

Identify cellular trajectories from scRNA-seq data using scVelo dynamical models.

22|4|Updated May 25, 2026
One-click install
npx skills add https://github.com/crazymsn/academic-skills --skill scvelo-crazymsn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scvelo
Source: https://github.com/crazymsn/academic-skills/tree/main/academic-skills/scvelo
Command: npx skills add https://github.com/crazymsn/academic-skills --skill scvelo-crazymsn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires scvelo, scanpy, numpy, matplotlib, and includes scripts (resource) and references (resource) components.

What problem does it solve?

RNA velocity analysis enables reconstruction of developmental trajectories and cell fate decisions from snapshot scRNA-seq data by modeling splicing dynamics.

Core Features & Use Cases

  • Dynamical and stochastic velocity models to infer gene regulation directionality
  • Latent time estimation and velocity graphs for lineage tracing
  • Driver gene identification and integration with Scanpy workflows for downstream analyses
  • Visualization on UMAP embeddings and velocity embeddings for publication-ready figures

Quick Start

Run the velocity workflow on an AnnData object containing spliced and unspliced layers to compute velocities and latent time.

Frequently Asked Questions about scvelo

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I infer cellular trajectories from single-cell RNA velocity data?

To infer cellular trajectories from single-cell RNA velocity data, you apply dynamical or stochastic models to spliced and unspliced counts in a prepared AnnData object to compute velocity fields, latent times, and driver genes for lineage tracing.

What is RNA velocity and when do I need spliced and unspliced counts for trajectory inference?

RNA velocity reconstructs developmental trajectories and cell fate decisions from scRNA-seq data by modeling splicing dynamics. You need spliced and unspliced count layers in your AnnData object to compute the directionality of gene regulation.

Can I use Scanpy workflows and UMAP embeddings for velocity visualizations?

Yes, you can integrate velocity visualizations directly into Scanpy workflows. The tool projects velocity fields and latent time estimates onto existing UMAP embeddings to generate publication-ready figures for downstream analysis.

Do I need a neighbors graph and HVG selection before running dynamical velocity models?

Yes, running dynamical or stochastic velocity models requires a properly prepared AnnData object that already includes a computed neighbors graph and highly variable gene (HVG) selection to ensure accurate latent time estimation.

What's the best way to identify driver genes from scRNA-seq lineage tracing?

The best way to identify driver genes from scRNA-seq lineage tracing is to apply dynamical velocity models to your spliced and unspliced counts, which isolates genes directing cell fate decisions for downstream analyses.