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

omicverse-single-cell-clustering-backends

Compare Leiden, Louvain, GMM, and scICE clustering backends on AnnData embeddings.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converts a clustering notebook into a reusable, triggerable workflow that runs and compares multiple backends on a prepared AnnData embedding.

Core Features & Use Cases

  • Run Leiden, Louvain, GMM, or scICE on a ready embedding to obtain comparable cluster assignments.
  • Produce consistent output columns (e.g., gmm_cluster, mclust) for downstream validation and reporting.
  • Smoke-testable via a minimal Python script that exercises the backend options and reports success.

Quick Start

Provide an AnnData with a PCA or other embedding and call the clustering wrapper to compare backends across a fixed set of parameters.

Frequently Asked Questions about omicverse-single-cell-clustering-backends

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

FAQPage Schema
How do I compare single-cell clustering methods like Leiden and Louvain on an AnnData object?▼

Comparing single-cell clustering methods requires running Leiden, Louvain, GMM, and scICE backends on a prepared AnnData embedding to produce consistent output columns like gmm_cluster and mclust for validation.

What is the best way to run GMM clustering on a single-cell embedding?▼

Running GMM clustering on a single-cell embedding involves applying a clustering backend to an AnnData object with a usable embedding, generating observable outputs such as gmm_cluster for downstream analysis.

Do I need a precomputed graph to run Leiden clustering on an AnnData object?▼

A precomputed graph is required for graph-based clustering paths like Leiden on an AnnData object, while a usable embedding satisfies the core input contract for other backends.

Can I use scICE for clustering validation on ready AnnData embeddings?▼

You can use scICE for clustering validation on ready AnnData embeddings by running it alongside Leiden, Louvain, and GMM to enable back-to-back comparisons and produce consistent output columns for downstream reporting.

Why does my single-cell clustering workflow need a usable embedding?▼

A single-cell clustering workflow needs a usable embedding because the input contract requires an AnnData object with an existing PCA or other embedding to identify and run the best clustering backend for the dataset.

What are the limitations of comparing clustering backends on an AnnData object?▼

Comparing clustering backends on an AnnData object requires an existing graph for graph-based paths and assumes the input embedding is already prepared, limiting execution to ready datasets.

Related Skills

Explore More Data & Analytics Skills→
omicverseomicverse
13

omicverse-single-cell-clustering-backends

Run Leiden, Louvain, GMM, or scICE clustering on a prepared AnnData object.

Official
Intermediate
vtran5290vtran5290
3

Schema Guardian

Validate weekly report payloads against a fixed JSON schema.

Community
Intermediate
omicverseomicverse
13

omicverse-single-cell-annotation

Annotate clustered AnnData objects with OmicVerse cell-type labels.

Official
Advanced
omicverseomicverse
32

single-cell-clustering-and-batch-correction-with-omicverse

Performs end-to-end cell clustering and batch correction on AnnData using OmiVerse utilities.

Official
Advanced