Does this skill generate visual reports?

Yes, it produces several PNG visualizations including QC distribution plots, threshold overlays, and post-filtering comparisons.

What is the benefit of MAD-based filtering over hard thresholds?

Median Absolute Deviation (MAD) provides a data-driven approach to outlier detection that adapts to the specific distribution of each dataset, preventing the loss of biological signal common with arbitrary hard cutoffs.

Which file formats are supported for single-cell QC?

The skill natively supports .h5ad (AnnData format) and .h5 files (10X Genomics Cell Ranger output).

How do I use this within a custom Python script?

The skill includes modular building blocks in scripts/qc_core.py that can be imported into your custom Python workflows for granular control.

Can I customize the mitochondrial gene detection pattern?

Yes, you can specify custom patterns via parameters like --mt-pattern to accommodate different species conventions, such as 'MT-' for humans or 'mt-' for mice.

Single-Cell RNA Quality Control

Name: Single-Cell RNA Quality Control
Author: anthropics

byanthropics

•

147

Data Science & ML

Automates quality control workflows for single-cell RNA-seq data using scverse best practices and MAD-based outlier detection.

About

This skill provides a robust, automated pipeline for processing single-cell RNA-sequencing data in AnnData (.h5ad) or 10X Genomics (.h5) formats. It implements industry-standard scverse and scanpy best practices, utilizing Median Absolute Deviation (MAD) for outlier detection to ensure data-driven, permissive filtering. Users can instantly generate pre- and post-filtering visualizations, calculate critical metrics like mitochondrial and ribosomal gene content, and export analysis-ready datasets, making it an essential tool for bioinformaticians and life science researchers looking to standardize their preprocessing workflows.

Key Features

Comprehensive pre- and post-filtering visualization suite
Automated calculation of mitochondrial, ribosomal, and hemoglobin metrics
147 GitHub stars
Automated QC pipeline for .h5ad and 10X Genomics .h5 file formats
Robust outlier detection using Median Absolute Deviation (MAD) thresholds
Modular Python utility functions for custom filtering and thresholding logic

Use Cases

Cleaning raw single-cell datasets by removing low-quality cells and empty droplets
Standardizing preprocessing across multiple scRNA-seq samples following scverse best practices
Generating publication-ready QC distribution plots and filtering threshold visualizations

About

Key Features

Comprehensive pre- and post-filtering visualization suite
Automated calculation of mitochondrial, ribosomal, and hemoglobin metrics
147 GitHub stars
Automated QC pipeline for .h5ad and 10X Genomics .h5 file formats
Robust outlier detection using Median Absolute Deviation (MAD) thresholds
Modular Python utility functions for custom filtering and thresholding logic

Use Cases

Cleaning raw single-cell datasets by removing low-quality cells and empty droplets
Standardizing preprocessing across multiple scRNA-seq samples following scverse best practices
Generating publication-ready QC distribution plots and filtering threshold visualizations