Analyze RNA velocity data from single-cell transcriptomic matrices with scVelo.
npx skills add https://github.com/dralkh/seerai --skill scvelo-dralkh
Please help me install this Agent Skill. Skill: scvelo Source: https://github.com/dralkh/seerai/tree/main/skills/scvelo Command: npx skills add https://github.com/dralkh/seerai --skill scvelo-dralkh
This Skill helps you turn single-cell RNA-seq count data into directional biological insight by estimating how cells transition between states. It removes the guesswork from trajectory interpretation by using unspliced and spliced mRNA dynamics to reveal where cells are headed.
Ask the Skill to run an scVelo RNA velocity analysis on your single-cell dataset and summarize the inferred trajectories, latent time, and top driver genes.
High-intent search queries and answers about installing and using this skill.
To infer cell trajectories from RNA velocity, you can use scVelo to estimate cell-state transitions from spliced and unspliced mRNA counts. This workflow requires an AnnData object with spliced and unspliced layers, followed by Scanpy preprocessing to generate neighbor graphs for velocity modeling.
Latent time ordering in scRNA-seq is the process of arranging cells along a biologically informed timeline based on transcriptional dynamics. scVelo calculates this by applying velocity models to spliced and unspliced count matrices, mapping cellular transitions to a continuous pseudotime scale.
Yes, spliced and unspliced count matrices are required to run trajectory inference using scVelo. These layers must be present in your AnnData object, as the velocity models rely on the dynamic relationship between unspliced and spliced mRNA to estimate directional cell-state transitions.
You can identify driver genes by analyzing single-cell transcriptomic matrices with scVelo to find genes whose kinetic behavior explains observed state changes. The workflow evaluates spliced and unspliced dynamics to highlight top driver genes that push trajectory transitions.
Yes, you can use Scanpy preprocessing with scVelo velocity models. Scanpy is a required dependency for preparing the AnnData object, computing neighbor graphs, and performing initial dimensionality reduction before applying scVelo to estimate RNA velocity and downstream confidence metrics.
Limitations of RNA velocity for trajectory analysis include its strict dependence on high-quality spliced and unspliced count matrices and accurate Scanpy neighbor graphs. Additionally, velocity models require robust downstream confidence metrics to validate inferred cell-state transitions and avoid misleading trajectory interpretations.
OwnLabAICompute RNA velocity and latent time from scRNA-seq data.
KetomihineGuide scVelo RNA velocity workflows from data loading to visualization.
K-Dense-AIAnalyze single-cell RNA-seq splicing dynamics to infer cell state transitions.
Estrella-231Infer RNA velocity and cell fate trajectories from single-cell RNA-seq AnnData.
