Single-cell clustering and batch correction with omicverse

Community

Cluster & correct single-cell batches.

AuthorStarlitnightly
Version1.0.0
Installs0

System Documentation

What problem does it solves? Analyzing single-cell data often involves complex preprocessing, robust clustering, and correcting for technical batch effects. This Skill provides a comprehensive workflow to handle these challenges efficiently, from initial quality control to advanced integration and clustering.

Core Features & Use Cases

  • Quality Control & Preprocessing: Filter low-quality cells, normalize, scale, and reduce dimensionality.
  • Multi-Method Clustering: Apply and evaluate various clustering algorithms (Leiden, scICE, GMM, cNMF, LDA).
  • Batch Correction & Integration: Harmonize datasets using methods like Harmony, ComBat, Scanorama, scVI, and CellANOVA.
  • Use Case: Process a multi-batch single-cell RNA-seq experiment, apply Harmony for batch correction, then cluster the integrated data using scICE, and benchmark the integration performance to ensure robust biological insights.

Quick Start

Preprocess my single-cell data, apply Harmony for batch correction, then cluster using Leiden, and visualize the UMAP embedding.

Dependency Matrix

Required Modules

omicversescanpyscvelonumpypandasmatplotlibstatsmodelsscib-metricsscvi-toolsrpy2

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: Single-cell clustering and batch correction with omicverse
Download link: https://github.com/Starlitnightly/omicverse/archive/main.zip#single-cell-clustering-and-batch-correction-with-omicverse

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository