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

omicverse-single-cell-differential-abundance

Run differential cell-type abundance analysis on single-cell AnnData between conditions.

13|2|Updated Apr 5, 2026
Search Tags:#single-cell#omicverse#anndata#differential-abundance#sccoda#milo#milopy
One-click install
npx skills add https://github.com/Starlitnightly/omicverse-skills --skill omicverse-single-cell-differential-abundance
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: omicverse-single-cell-differential-abundance
Source: https://github.com/Starlitnightly/omicverse-skills/tree/main/src/omicverse_skills/skills/single-cell-differential-abundance
Command: npx skills add https://github.com/Starlitnightly/omicverse-skills --skill omicverse-single-cell-differential-abundance

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, anndata, scanpy, omicverse, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Turn notebook-style differential cell-type abundance analysis into a reusable, triggerable operation so researchers can reliably compare cell-type compositions between experimental conditions without reworking exploratory code each time.

Core Features & Use Cases

  • Multiple backends: Choose between scCODA posterior sampling or Milo-family neighborhood testing (milopy or milo) depending on inference needs.
  • Input validation: Ensures required AnnData fields, sample identifiers, and embedding keys exist before execution to prevent common runtime errors.
  • Reproducible workflows: Encapsulates constructor, run, and result collection patterns so the same analysis can be rerun, smoke-tested, and integrated into larger pipelines.
  • Use Case: Compare Control versus infected samples to identify cell-type compositional shifts using either Bayesian compositional inference or neighborhood-based testing.

Quick Start

Run a differential abundance test comparing Control and Salmonella on an AnnData with sample_key batch and embedding X_pca.

Frequently Asked Questions about omicverse-single-cell-differential-abundance

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

FAQPage Schema
How do I detect differential cell-type abundance in single-cell data?▼

Run differential abundance analysis on single-cell AnnData using scCODA posterior inference or Milo neighborhood testing to detect compositional changes between condition labels.

What's the difference between scCODA and Milo for single-cell compositional analysis?▼

scCODA uses sample-aware Bayesian posterior inference for compositional shifts, while Milo-family methods apply embedding-driven neighborhood testing to identify local differential abundance without requiring strict sample references.

Do I need a sample identifier column to run differential abundance testing?▼

Yes, sample-aware branches like scCODA require a sample identifier column in AnnData obs to correctly model compositional variance. Milo methods additionally require an embedding key stored in obsm.

How do I compare cell-type composition between control and infected samples?▼

Compare control and infected samples by specifying your condition labels and cell-type obs columns in an AnnData object, then executing differential abundance analysis to quantify compositional shifts.

Why does my Milo differential abundance analysis fail on AnnData?▼

Milo analyses fail when required AnnData fields are missing. Input validation requires a condition column, cell-type column, sample identifier, and a valid embedding key in obsm like X_pca before execution.

Related Skills

Explore More Education & Research Skills→
omicverseomicverse
13

omicverse-single-cell-differential-abundance

Run differential abundance analysis on single-cell AnnData objects with scCODA, milopy, or milo.

Official
Advanced
omicverseomicverse
13

omicverse-microbiome-16s-amplicon-dada2

Builds 16S amplicon analysis from FASTQs to AnnData with taxonomy and diversity.

Official
Advanced
StarlitnightlyStarlitnightly
1.2k

Single-cell CellPhoneDB communication mapping

Quantify ligand–receptor communication between single-cell populations and generate CellChat-style visualizations.

Community
Advanced
ActiveInferenceInstituteActiveInferenceInstitute
13

geo-infer-bayes

Fit Bayesian models to geospatial data with MCMC, HMC, VI, SMC, and ABC.

Community
Advanced