skills.rest
CHENyiru3
CHENyiru3COMMUNITY
Explore all skills by this author →
GitHub

seurat-v5

Integrate multi-modal single-cell RNA and protein data with Seurat v5 WNN.

Updated Apr 19, 2026
Search Tags:#integration#multimodal#single-cell#adt#seurat#rna#wnn
One-click install
npx skills add https://github.com/CHENyiru3/AI-Skills-Collections --skill seurat-v5
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: seurat-v5
Source: https://github.com/CHENyiru3/AI-Skills-Collections/tree/main/skills-market/compbio/single-cell/integration/seurat-v5
Command: npx skills add https://github.com/CHENyiru3/AI-Skills-Collections --skill seurat-v5

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables researchers to unify multi-modal single-cell data (RNA and proteins) within a single analytical framework, simplifying cross-modality interpretation and downstream analyses.

Core Features & Use Cases

  • Multi-modal integration using Weighted Nearest Neighbors (WNN) to combine RNA and ADT data for a coherent cellular landscape.
  • Workflow support for loading CITE-seq or multi-omics datasets, performing clustering, and visualizing integrated embeddings (UMAP).
  • Use case: build and annotate cell-type maps from combined RNA and surface protein signals for robust downstream inference.

Quick Start

Install Seurat v5, create a Seurat object with RNA and ADT data, and perform initial multi-modal integration with FindMultiModalNeighbors and clustering.

Frequently Asked Questions about seurat-v5

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

FAQPage Schema
How do I integrate CITE-seq RNA and ADT data for clustering in R?▼

To integrate CITE-seq RNA and ADT data in R, use Seurat v5 to perform weighted-nearest-neighbors integration. This combines RNA and protein measurements into a unified cellular landscape for clustering and visualization.

What is weighted nearest neighbors (WNN) integration for single-cell data?▼

Weighted nearest neighbors (WNN) integration is a method to combine multi-modal single-cell data, such as RNA and ADT assays, into a coherent cellular landscape. It calculates modality weights to enable unified clustering and UMAP visualization.

Does Seurat v5 require separate RNA and ADT assays for multi-modal integration?▼

Yes, Seurat v5 multi-modal integration requires a Seurat object containing both an RNA assay and a protein (ADT) assay. These distinct modalities are necessary to compute WNN and perform unified clustering.

Can I visualize integrated multi-modal single-cell data using UMAP?▼

Yes, you can visualize integrated multi-modal single-cell data using UMAP. After performing WNN integration with FindMultiModalNeighbors and FindClusters, RunUMAP generates integrated embeddings for cross-modality interpretation.

What's the best way to build cell-type maps from combined RNA and surface protein signals?▼

The best way to build cell-type maps from RNA and surface protein signals is using Seurat v5 WNN integration. This multi-modal approach applies FindMultiModalNeighbors to robustly annotate cell types from combined CITE-seq data.

When should I not use WNN integration for single-cell analysis?▼

You should not use WNN integration if your dataset lacks either RNA or protein (ADT) measurements, as this multi-modal approach requires both assays to function. Single-modality datasets do not meet the prerequisite for weighted-nearest-neighbors analysis.

Related Skills

Explore More Data & Analytics Skills→
ya-wayya-way

bio-single-cell-multimodal-integration

Integrate multi-modal single-cell RNA, protein, and ATAC data into unified representations.

Community
Advanced
tassiovaletassiovale
13

scvi-tools

Analyze single-cell RNA-seq data with scvi-tools deep generative models.

Community
Advanced
KetomihineKetomihine
1

seurat-single-cell-analysis

Run Seurat v5 single-cell RNA-seq analysis in R from .rds/.rdata inputs.

Community
Advanced
CHENyiru3CHENyiru3

scribble

Integrate RNA, ATAC, and protein data into joint embeddings for single-cell analyses.

Community
Advanced