scvelo

Model RNA velocity from spliced and unspliced counts in AnnData.

1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/SciMate-AI/scicli --skill scvelo-scimate-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scvelo
Source: https://github.com/SciMate-AI/scicli/tree/main/internal/skills/bundled/claude-scientific-skills/skills/scvelo
Command: npx skills add https://github.com/SciMate-AI/scicli --skill scvelo-scimate-ai

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 with scVelo enables inference of dynamic cell states from static single-cell RNA-seq data by modeling spliced and unspliced mRNA dynamics to reveal directionality of cell-state transitions.

Core Features & Use Cases

  • Estimate RNA velocity from spliced and unspliced counts to infer lineage direction
  • Compute latent time and identify driver genes to highlight regulatory dynamics
  • Complement existing workflows in Scanpy/scVI-tools for trajectory inference across developmental or differentiation studies

Quick Start

Load an AnnData object with spliced and unspliced layers, then run the scvelo velocity workflow to estimate RNA velocity 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 calculate RNA velocity from scRNA-seq data?

RNA velocity is calculated by modeling spliced and unspliced mRNA dynamics from single-cell RNA sequencing data to infer the directionality of cell-state transitions. This requires an AnnData object containing distinct 'spliced' and 'unspliced' count layers.

What's the best way to estimate latent time and identify driver genes in single-cell data?

Estimating latent time and identifying driver genes involves fitting stochastic or dynamical RNA velocity models to spliced and unspliced counts. This approach highlights regulatory dynamics across developmental or differentiation trajectories.

Does scVelo work with Scanpy for trajectory inference?

Yes, scVelo integrates seamlessly with Scanpy. You must preprocess your single-cell RNA-seq data using Scanpy to prepare the AnnData object before fitting the velocity models to infer dynamic cell states.

Why does RNA velocity analysis require spliced and unspliced counts?

RNA velocity analysis requires spliced and unspliced counts because the mechanism models the transcriptional dynamics between these two mRNA states. By measuring the ratio of unspliced to spliced mRNA, the model infers whether a gene is being induced or repressed.

Can I use scVelo for dynamical modeling across differentiation studies?

Yes, scVelo supports dynamical modeling for trajectory inference across developmental or differentiation studies. It fits a dynamical model to spliced and unspliced counts to estimate latent time and recover regulatory dynamics.

When should I not use RNA velocity for trajectory inference?

RNA velocity for trajectory inference is not suitable when your single-cell dataset lacks spliced and unspliced mRNA count layers. Without these specific layers in your AnnData object, the underlying stochastic or dynamical models cannot be fitted.