sc-multiome

Name: sc-multiome
Availability: InStock
Author: TianGzlab

Integrate single-cell RNA, protein, and ATAC data with WNN and MOFA+ workflows.

155|26|Updated Mar 14, 2026

Search Tags:#MOFA #multi-modal #multiome #singlecell #CITE-seq #WNN

Ready to run

npx skills add https://github.com/TianGzlab/OmicsClaw --skill sc-multiome

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sc-multiome
Source: https://github.com/TianGzlab/OmicsClaw/tree/main/skills/singlecell/sc-multiome
Command: npx skills add https://github.com/TianGzlab/OmicsClaw --skill sc-multiome

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the complex process of integrating and analyzing multiple types of single-cell omics data, such as RNA and protein or RNA and ATAC, enabling a more comprehensive understanding of cellular states.

Core Features & Use Cases

Multi-modal Integration: Supports technologies like CITE-seq, 10X Multiome, and SHARE-seq.
Analysis Workflows: Implements Weighted Nearest Neighbor (WNN) analysis, MOFA+, and muon/MuData workflows.
Visualization: Generates joint UMAPs and plots modality weights.
Use Case: Analyze a CITE-seq dataset to simultaneously explore gene expression and surface protein levels, identifying distinct cell populations based on both modalities.

Quick Start

Run the sc-multiome skill on your processed multi-omics data file.

Frequently Asked Questions about sc-multiome

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

FAQPage Schema

How do I integrate CITE-seq RNA and protein data for single-cell analysis?▼

Multi-omics integration combines RNA, protein (ADT), and ATAC modalities to provide a comprehensive understanding of cellular states. This Skill implements WNN analysis, MOFA+, and Muon workflows to jointly analyze multiple data types from technologies like CITE-seq and 10X Multiome.

Can I use scanpy for multi-modal single-cell integration with ATAC data?▼

Yes, this Skill performs multi-modal integration using scanpy and numpy, supporting RNA, protein (ADT), and ATAC modalities. It utilizes Weighted Nearest Neighbor (WNN) analysis, MOFA+, and Muon workflows to jointly analyze and visualize your single-cell data.

What is the best way to visualize joint UMAPs for 10X Multiome datasets?▼

The best way to visualize joint UMAPs for 10X Multiome datasets is by using this Skill's Muon and MuData workflows. It generates joint UMAP plots and visualizes modality weights to help you explore integrated cellular states across multiple omics layers.

Does MOFA+ work with WNN analysis for single-cell multiome integration?▼

Yes, MOFA+ works alongside Weighted Nearest Neighbor (WNN) analysis for single-cell multiome integration. This Skill implements both methods to process multi-modal data, allowing you to simultaneously explore gene expression and surface protein levels.

What Python packages do I need for multi-omics single-cell integration?▼

You need scanpy and numpy as required Python packages for multi-omics single-cell integration. Optionally, you can install muon, Seurat, Signac, or ArchR to access advanced functionalities for analyzing RNA, protein, and ATAC modalities.