single-cell-rna-qc

Filters low-quality cells from AnnData and 10X Genomics single-cell RNA-seq datasets using MAD-based thresholds.

7|Updated Feb 6, 2026
One-click install
npx skills add https://github.com/Epiphytic/ai-plugin-translator --skill single-cell-rna-qc-epiphytic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: single-cell-rna-qc
Source: https://github.com/Epiphytic/ai-plugin-translator/tree/main/packages/core/test/fixtures/regression-output/knowledge-work-plugins/bio-research/skills/single-cell-rna-qc
Command: npx skills add https://github.com/Epiphytic/ai-plugin-translator --skill single-cell-rna-qc-epiphytic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill streamlines single-cell RNA-seq quality control by identifying low-quality cells, evaluating data quality metrics, and applying consistent filtering practices.

Core Features & Use Cases

  • Automated QC Analysis: Calculates count depth, detected genes, mitochondrial, ribosomal, and hemoglobin metrics for single-cell datasets.
  • MAD-Based Filtering: Applies scverse-inspired quality thresholds and generates before-and-after visualizations for informed filtering decisions.
  • Use Case: Analyze an AnnData or 10X Genomics dataset to remove poor-quality cells and prepare a cleaned dataset for downstream single-cell analysis.

Quick Start

Use the single-cell-rna-qc skill to perform quality control analysis on my single-cell RNA sequencing dataset and generate filtered outputs.

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 perform quality control filtering on single-cell RNA-seq datasets?

Perform single-cell RNA-seq quality control by calculating count depth, detected genes, and mitochondrial metrics, then applying MAD-based thresholds to automatically filter low-quality cells and preserve annotated output datasets.

What is MAD-based filtering for identifying low-quality cells in scanpy?

MAD-based filtering applies scverse-inspired median absolute deviation thresholds to single-cell RNA-seq count depth and mitochondrial metrics, identifying and removing outlier cells to ensure consistent quality filtering for downstream analysis.

Can I use this quality control workflow with 10X Genomics files and AnnData objects?

Yes, the quality control workflow supports both AnnData objects and 10X Genomics files, calculating quality metrics and applying filtering thresholds within scverse and scanpy single-cell analysis environments.

How do I visualize before-and-after single-cell RNA-seq quality metrics?

Visualize before-and-after single-cell RNA-seq quality metrics by generating automated plots that compare pre-filtered and post-filtered datasets, showing the impact of MAD-based cell removal on count depth and gene detection distributions.

What metrics are calculated during single-cell RNA-seq quality control?

Single-cell RNA-seq quality control calculates count depth, detected genes, mitochondrial percentages, ribosomal percentages, and hemoglobin metrics to evaluate data quality and identify low-quality cells for removal.

Why should I automate cell filtering instead of manually setting thresholds for scRNA-seq data?

Automated MAD-based filtering for scRNA-seq data removes subjective manual thresholding, ensuring consistent quality control practices across datasets while objectively identifying low-quality cells based on statistical deviations from population medians.