skills.rest
anthropics
anthropicsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

single-cell-rna-qc

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

568|102|Updated Oct 17, 2025
Search Tags:#quality control#data visualization#data analysis#single-cell RNA-seq#scverse#bioinformatics#filtering
One-click install
npx skills add https://github.com/anthropics/life-sciences --skill single-cell-rna-qc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: single-cell-rna-qc
Source: https://github.com/anthropics/life-sciences/tree/main/single-cell-rna-qc
Command: npx skills add https://github.com/anthropics/life-sciences --skill single-cell-rna-qc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anndata, scanpy, scipy, matplotlib, seaborn, numpy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Analyzing single-cell RNA-seq data requires rigorous quality control to remove low-quality cells and technical artifacts. This process is often complex, time-consuming, and critical for accurate downstream analysis. This Skill automates this essential first step, ensuring your data is clean and ready for biological insights.

Core Features & Use Cases

  • Automated QC Workflow: Automatically performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) following scverse best practices.
  • Intelligent Filtering: Applies robust MAD-based (Median Absolute Deviation) filtering to identify and remove low-quality cells, ensuring your downstream analysis is based on high-quality data.
  • Comprehensive Visualizations: Generates detailed plots (histograms, violin plots, scatter plots) before and after filtering, providing clear insights into data quality and the impact of the QC process.
  • Use Case: A biologist has generated new single-cell RNA-seq data and needs to quickly assess its quality and filter out problematic cells before proceeding with cell type identification. This Skill provides a "just works" solution, saving days of manual scripting and debugging.

Quick Start

For standard QC on an AnnData file:

python3 scripts/qc_analysis.py input.h5ad

For 10X Genomics .h5 files:

python3 scripts/qc_analysis.py raw_feature_bc_matrix.h5

Frequently Asked Questions about single-cell-rna-qc

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

FAQPage Schema
How do I filter low-quality cells from single-cell RNA-seq data?▼

Quality control filtering identifies and removes low-quality cells using MAD-based (Median Absolute Deviation) thresholds. This Skill automates the process on .h5ad and .h5 files, applying robust statistical filtering to ensure downstream analysis uses only high-quality data aligned with scverse best practices.

What's the best way to assess single-cell RNA-seq data quality before analysis?▼

Comprehensive QC assessment generates histograms, violin plots, and scatter plots showing metrics before and after filtering. This Skill visualizes quality indicators across your dataset, revealing data distribution, outliers, and the impact of filtering so you can make informed decisions about cell retention.

Can I run quality control on 10X Genomics .h5 files?▼

Yes, this Skill accepts both .h5ad (AnnData) and .h5 (10X Genomics) formats as input. It performs the same MAD-based filtering and QC analysis on 10X data, following scanpy and scverse conventions for seamless integration into standard bioinformatics workflows.

Do I need to manually set filtering thresholds for quality control?▼

Filtering thresholds are configurable, allowing you to adjust MAD multipliers and species-specific gene patterns to match your dataset. The Skill provides default settings following best practices but supports custom workflows where you define which cells meet your quality criteria.

What happens to my data during the QC process?▼

The Skill calculates QC metrics (read counts, gene detection, mitochondrial content), flags low-quality cells using MAD-based statistics, removes them from your dataset, and generates before/after visualizations. Your filtered data remains in the same AnnData format, ready for downstream cell type identification or clustering.

Related Skills

Explore More Education & Research Skills→
MubasherMohammedMubasherMohammed

scrna-orchestrator

Automate single-cell RNA-seq analysis with Scanpy, including QC, clustering, and reporting.

Community
Advanced
PancrePal-xiaoyibaoPancrePal-xiaoyibao
6

scrna-celltype-annotation

Annotate single-cell RNA-seq clusters with literature-backed evidence and R code.

Official
Advanced
1479089714790897
7

kwp-bio-research-single-cell-rna-qc

Automate quality control and filtering of single-cell RNA-seq datasets in .h5ad or .h5 formats.

Community
Advanced
NigarumOvumNigarumOvum

volatility

Calculate annualized historical volatility, rank percentiles, and generate trading signals.

Community
Advanced