skills.rest
pwwang
pwwangCOMMUNITY
Explore all skills by this author →
GitHub

seuratmap2ref

Maps query scRNA-seq datasets onto curated brain and tissue references, returning validated predictions and UMAP coordinates for each dataset.

22|4|Updated May 18, 2021
Search Tags:#single-cell#scRNA-seq#umap#reference-mapping#seurat#transfer-learning#label-transfer
One-click install
npx skills add https://github.com/pwwang/immunopipe --skill seuratmap2ref
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: seuratmap2ref
Source: https://github.com/pwwang/immunopipe/tree/main/skills/seuratmap2ref
Command: npx skills add https://github.com/pwwang/immunopipe --skill seuratmap2ref

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This workflow maps query single-cell RNA datasets to high-quality reference atlases using Seurat's reference mapping framework. It enables label transfer, UMAP projection, and integration with reference annotations without modifying the original query data, supporting transferable analyses across tissues and atlas platforms.

Core Features & Use Cases

  • Reference-based annotation: Transfer cell type labels and metadata from curated references (e.g., Azimuth PBMC) to the query.
  • UMAP projection: Visualize query cells in the reference UMAP space for consistent interpretation.
  • Non-destructive mapping: Preserve the query's expression data while augmenting it with reference-derived annotations.
  • Transfer learning workflows: Use established atlases to annotate novel tissues or cell states with confidence.

Quick Start

Load your Seurat query object and a validated reference, configure the mapping parameters, and run the reference-mapping workflow to obtain transferred annotations.

Frequently Asked Questions about seuratmap2ref

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

FAQPage Schema
How do I map my scRNA-seq query data to a reference atlas for label transfer?▼

To map scRNA-seq query data, load a Seurat object and a validated reference, then configure normalization, anchor finding, and mapping parameters to transfer cell type labels and project onto the reference UMAP.

Can I use Azimuth PBMC as a reference to annotate my single-cell dataset?▼

Yes, you can use curated atlases like Azimuth PBMC as validated references to transfer cell type labels and metadata to your scRNA-seq query data without altering the original expression matrix.

Does single-cell reference mapping modify the original query dataset?▼

No, reference mapping is non-destructive; it preserves the query's expression data while augmenting it with reference-derived annotations and UMAP projections for consistent interpretation.

What input formats are required for Seurat reference mapping?▼

Seurat reference mapping requires a query Seurat object and a validated reference object loaded from an RDS or h5seurat file to execute the transfer learning workflow.

How does UMAP projection work when integrating with a tissue-specific reference?▼

UMAP projection visualizes query cells within the reference UMAP space, enabling consistent interpretation and integration of novel tissues or cell states across atlas platforms.

What are the limitations of using transfer learning for scRNA-seq annotation?▼

Transfer learning for scRNA-seq annotation is limited by the quality of the curated reference and the accuracy of anchor finding, making it less reliable for novel cell states absent from the reference atlas.

Related Skills

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

bio-single-cell-data-io

Convert single-cell data objects between Seurat and Scanpy formats.

Community
Intermediate
KetomihineKetomihine
1

scarches

Map single-cell datasets into reference atlases using scArches.

Community
Advanced
pwwangpwwang
22

metabolicexpimputation

Impute dropout values in scRNA-seq expression matrices using ALRA, scImpute, or MAGIC.

Community
Advanced
crazymsncrazymsn
22

scvi-tools

Model single-cell omics data with variational autoencoders for batch correction.

Community
Advanced