skills.rest
Starlitnightly
StarlitnightlyCOMMUNITY
Explore all skills by this author →
GitHub

omicverse-single-cell-preprocessing

Convert raw AnnData objects into preprocessed, clustered single-cell RNA-seq data.

13|2|Updated Apr 5, 2026
Search Tags:#preprocessing#single-cell#clustering#pca#umap#annadata#marker-discovery
One-click install
npx skills add https://github.com/Starlitnightly/omicverse-skills --skill omicverse-single-cell-preprocessing
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: omicverse-single-cell-preprocessing
Source: https://github.com/Starlitnightly/omicverse-skills/tree/main/src/omicverse_skills/skills/single-cell-preprocessing
Command: npx skills add https://github.com/Starlitnightly/omicverse-skills --skill omicverse-single-cell-preprocessing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

Convert raw or partially processed single-cell AnnData into a validated, analysis-ready object by automating QC, normalization, HVG selection, scaling, dimensionality reduction, neighbor graph construction, clustering, and marker discovery so users avoid repetitive notebook rewrites and fragile ad-hoc steps.

Core Features & Use Cases

  • End-to-end preprocessing spine covering QC, multiple preprocessing modes, HVG selection, scaling, PCA, neighbor graph construction, and alternative embeddings (UMAP, t-SNE, MDE).
  • Clustering and marker discovery with Leiden clustering and marker extraction branches (cosg for raw counts, wilcoxon and other statistical tests for log-normalized data), plus marker plotting helpers.
  • Validation and reproducibility checks for required obs/var/obsm/uns keys, preservation of raw counts when needed, explicit mode and method selection, and smoke-testable acceptance criteria for CI.
  • Use Case: Run a small synthetic smoke test to verify CPU preprocessing, then run the full pipeline on experiment data to obtain clusters and top markers for annotation.

Quick Start

Run the OmicVerse preprocessing pipeline on an AnnData object to produce normalized counts, PCA and UMAP embeddings, a neighbor graph, Leiden cluster labels, and optional marker tables.

Frequently Asked Questions about omicverse-single-cell-preprocessing

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

FAQPage Schema
How do I preprocess raw single-cell RNA-seq AnnData for clustering and marker discovery?▼

Single-cell RNA-seq preprocessing automates QC, normalization, HVG selection, scaling, PCA, neighbor graph construction, and Leiden clustering. This transforms raw AnnData into a dimension-reduced, cluster-ready object with extracted top markers for downstream annotation.

What is the best way to normalize raw counts in an AnnData object before running UMAP?▼

The best way to normalize raw counts in an AnnData object before UMAP is using shiftlog or pearson preprocessing modes. This pipeline applies normalization, selects highly variable genes, and scales the data before computing PCA and UMAP embeddings while preserving raw counts when needed.

Does single-cell preprocessing work with both cosg and wilcoxon methods for marker discovery?▼

Yes, single-cell preprocessing supports both cosg and wilcoxon method branches for marker discovery. The cosg method operates on raw counts while wilcoxon applies statistical tests to log-normalized data, enabling flexible cluster marker extraction.

Can I validate obs, var, obsm, and uns keys in my AnnData object before clustering?▼

Yes, you can validate obs, var, obsm, and uns keys in your AnnData object before clustering. The preprocessing pipeline includes validation and reproducibility checks for required AnnData keys to ensure the object is properly structured for dimensionality reduction and Leiden clustering.

How do I run Leiden clustering and generate UMAP embeddings from single-cell data?▼

To run Leiden clustering and generate UMAP embeddings from single-cell data, apply QC, normalization, HVG selection, scaling, and PCA first. The pipeline then constructs a neighbor graph and computes UMAP, t-SNE, or MDE embeddings alongside Leiden cluster labels automatically.

Why does my single-cell preprocessing pipeline fail when switching between normalization modes?▼

Single-cell preprocessing pipelines can fail when switching between normalization modes if required obs, var, obsm, or uns keys are missing or if raw counts are not preserved. The pipeline validates these keys and supports explicit shiftlog or pearson mode selection to prevent mismatched data states.

Related Skills

Explore More Education & Research Skills→
qinyan-aiqinyan-ai
48

anndata

Create, read, and analyze AnnData objects for single-cell experiments.

Community
Advanced
ovachieverovachiever
52

scanpy

Analyze scRNA-seq data with Scanpy workflows for QC through trajectory inference.

Community
Advanced
TianGzlabTianGzlab
155

sc-cell-annotation

Automate cell type annotation for single-cell omics data using marker genes, CellTypist, SingleR, or scmap.

Official
Intermediate
ya-wayya-way

bio-single-cell-data-io

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

Community
Intermediate