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

Single-cell preprocessing with omicverse

Automate single-cell RNA-seq preprocessing with omicverse notebooks for QC, HVG detection, and embeddings.

1.2k|145|Updated Mar 22, 2021
Search Tags:#quality control#bioinformatics#normalization#GPU#single-cell preprocessing#UMAP#PCA#omicverse#HVG
One-click install
npx skills add https://github.com/Starlitnightly/omicverse --skill single-cell-preprocessing-with-omicverse
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Single-cell preprocessing with omicverse
Source: https://github.com/Starlitnightly/omicverse/tree/main/.claude/skills/single-preprocessing
Command: npx skills add https://github.com/Starlitnightly/omicverse --skill single-cell-preprocessing-with-omicverse

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires omicverse, scanpy, scvelo, numpy, matplotlib, rapids-singlecell, scrublet, and includes references (resource) components.

What problem does it solves? Preparing raw single-cell RNA-seq data for analysis involves numerous critical steps like quality control, normalization, and dimensionality reduction, which are often computationally intensive and require careful parameter tuning. This Skill automates and accelerates these processes.

Core Features & Use Cases

  • Comprehensive Quality Control: Perform QC filtering, including doublet detection (Scrublet), to ensure high-quality data.
  • Normalization & HVG Detection: Normalize counts, log-transform, and identify highly variable genes (HVGs) for feature selection.
  • Dimensionality Reduction & Embedding: Compute PCA, build neighborhood graphs, and generate UMAP/MDE embeddings for visualization.
  • GPU Acceleration: Support for CPU, CPU-GPU mixed, and pure GPU (RAPIDS) processing for faster workflows.
  • Use Case: Take raw 10x Genomics PBMC3k data, apply QC filters, normalize and select HVGs, then generate a UMAP embedding, leveraging GPU acceleration for faster processing.

Quick Start

Preprocess my PBMC3k single-cell data, including QC with Scrublet, normalize with shiftlog|pearson, and generate a UMAP embedding.

Frequently Asked Questions about Single-cell preprocessing with omicverse

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

FAQPage Schema
How do I preprocess single-cell RNA-seq data with quality control and normalization?▼

Single-cell preprocessing automates QC filtering, normalization, and feature selection on raw RNA-seq data. This Skill applies Scrublet for doublet detection, normalizes counts, identifies highly variable genes, and generates dimensionality-reduced embeddings (PCA, UMAP) across CPU and GPU backends using omicverse workflows.

Can I accelerate single-cell preprocessing with GPU computing?▼

Yes. This Skill supports CPU, CPU-GPU mixed, and pure GPU (RAPIDS) processing stacks. GPU acceleration speeds up normalization, HVG detection, neighborhood graph construction, and UMAP embedding generation on large single-cell datasets.

What's the best way to detect and remove doublets from single-cell data?▼

Doublet detection using Scrublet identifies and filters artifactual cell doublets before downstream analysis. This Skill integrates Scrublet as part of comprehensive QC, removing low-quality observations and ensuring data integrity for normalization and clustering.

How do I select highly variable genes for single-cell analysis?▼

Highly variable gene (HVG) detection identifies genes with the most biological signal for dimensionality reduction. This Skill automates HVG selection with tunable parameters, enabling focused PCA and UMAP embedding while reducing noise and computational cost.

Does this preprocessing work with 10x Genomics PBMC data?▼

Yes. This Skill is designed for 10x Genomics PBMC3k data and produces standard AnnData objects compatible with downstream analysis tools. It handles the full pipeline from raw counts through QC, normalization, and embedding generation.

What parameters should I tune for normalization and dimensionality reduction?▼

This Skill specifies normalization mode (shiftlog, pearson), HVG thresholds, PCA components, and UMAP parameters. Metadata defines layer management and backend integration, allowing reproducible preprocessing tuned to your data characteristics and computational environment.

Related Skills

Explore More Education & Research Skills→
CHENyiru3CHENyiru3

anndata

Organize annotated single-cell data matrices using the AnnData structure.

Community
Advanced
ovachieverovachiever
52

scanpy

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

Community
Advanced
anthropicsanthropics
568

single-cell-rna-qc

Filter low-quality cells from single-cell RNA-seq data using MAD-based QC.

Official
Intermediate
ya-wayya-way

bio-single-cell-preprocessing

Automate QC, filtering, and normalization for single-cell RNA-seq data with Seurat and Scanpy.

Community
Intermediate