omicverse-single-cell-scenic

Run SCENIC regulon inference on single-cell AnnData objects.

13|2|Updated Apr 5, 2026
One-click install
npx skills add https://github.com/Starlitnightly/omicverse-skills --skill omicverse-single-cell-scenic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: omicverse-single-cell-scenic
Source: https://github.com/Starlitnightly/omicverse-skills/tree/main/src/omicverse_skills/skills/single-cell-scenic
Command: npx skills add https://github.com/Starlitnightly/omicverse-skills --skill omicverse-single-cell-scenic

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anndata, numpy, scipy, omicverse, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates reproducible SCENIC regulon inference and downstream regulon-level interpretation on single-cell AnnData objects, removing manual branch selection, resource checks, and brittle notebook steps.

Core Features & Use Cases

  • GRN inference with branch selection: choose regdiffusion, grnboost2, or genie3 and run SCENIC.cal_grn with validated layer handling.
  • Regulon construction and scoring: build modules_from_adjacencies, prune with cisTarget resources, compute AUCell matrices, and return a regulon AnnData handoff.
  • Downstream interpretation: compute regulon specificity scores, binarize activities, rank regulon markers, and optionally visualize TF-target networks for targeted exploration.
  • Use case: convert an OmicVerse SCENIC tutorial into a reusable pipeline that accepts an AnnData with raw counts and external cisTarget databases to produce AUCell, regulon binary calls, and RSS tables for downstream analysis.

Quick Start

Run SCENIC on my AnnData using regdiffusion with the counts layer and my local cisTarget databases to produce regulons, AUCell scores, and binarized activity calls.

Frequently Asked Questions about omicverse-single-cell-scenic

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

FAQPage Schema
How do I run SCENIC regulon analysis on single-cell AnnData?

SCENIC regulon analysis on single-cell AnnData is performed by inferring gene regulatory networks, pruning adjacencies with cisTarget, and computing AUCell scores to generate regulon activity matrices.

What GRN inference methods can I use for single-cell regulon construction?

Gene regulatory network inference for single-cell regulon construction supports regdiffusion, grnboost2, and genie3 methods, allowing branch selection based on available computational resources and dataset characteristics.

Do I need raw counts and cisTarget databases to infer regulons with SCENIC?

Yes, regulon inference with SCENIC requires a single-cell AnnData object containing a validated raw-count layer, along with external cisTarget ranking databases and motif annotation tables for pruning.

How do I calculate regulon specificity scores and binarize AUCell activity?

Regulon specificity scores are calculated from the AUCell matrix to identify cell-type specific regulons, followed by binarization of activity scores to generate binary regulon calls for downstream interpretation.

What is the best way to automate SCENIC regulon inference from an AnnData object?

Automating SCENIC regulon inference involves passing an AnnData object with raw counts and local cisTarget databases to a pipeline that executes GRN inference, motif pruning, and AUCell scoring sequentially.

Can I visualize TF-target networks after computing AUCell scores in single-cell data?

Yes, after computing AUCell scores and constructing regulons, you can visualize transcription factor-centered target networks to explore specific regulon activities within your single-cell dataset.