skills.rest
omicverse
omicverseOFFICIAL
Explore all skills by this author →
WebsiteGitHub

omicverse-single-cell-cnmf-program-discovery

Discover gene programs in single-cell AnnData datasets with OmicVerse cNMF.

13|2|Updated Apr 5, 2026
Search Tags:#consensus#single-cell#omics#anndata#cnmf#nmf#gene-programs
One-click install
npx skills add https://github.com/omicverse/omicverse-skills --skill omicverse-single-cell-cnmf-program-discovery-omicverse
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: omicverse-single-cell-cnmf-program-discovery
Source: https://github.com/omicverse/omicverse-skills/tree/main/src/omicverse_skills/skills/single-cell-cnmf-program-discovery
Command: npx skills add https://github.com/omicverse/omicverse-skills --skill omicverse-single-cell-cnmf-program-discovery-omicverse

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?

This Skill turns single-cell gene program discovery into a reusable workflow, so you do not have to remember which OmicVerse function to call, how to choose K, or how to interpret the results.

Core Features & Use Cases

  • Classical cNMF Workflow: Run consensus NMF with factorization, combination, consensus building, and result loading for AnnData inputs.
  • Fast Rust-backed NMF: Use the nmf-rs backend for rapid K selection, consensus heatmaps, and program labeling on large datasets.
  • Practical Analysis Scenarios: Fit gene programs on single-cell data, compare candidate ranks, generate normalized usage matrices, and produce direct or RFC-based cluster labels.

Quick Start

Use the OmicVerse cNMF skill to analyze my single-cell AnnData object, choose the appropriate K, run consensus NMF, and return normalized usage, top genes, and labels.

Frequently Asked Questions about omicverse-single-cell-cnmf-program-discovery

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

FAQPage Schema
How do I discover gene programs in single-cell AnnData?▼

You can discover gene programs in single-cell AnnData by running consensus NMF factorization, which decomposes expression matrices into normalized usage matrices and top genes for program identification.

What is consensus NMF for single-cell analysis?▼

Consensus NMF is a factorization technique that identifies stable gene programs by repeatedly factorizing single-cell expression data and combining results into consensus clusters and usage matrices.

How do I select the optimal K value for NMF clustering?▼

Select the optimal K for NMF clustering by comparing candidate ranks using the Rust-backed K selection workflow, which evaluates factorization stability across large single-cell datasets.

Do I need non-negative normalized data for cNMF factorization?▼

Yes, cNMF factorization requires non-negative normalized single-cell input data to correctly decompose gene expression and produce valid factorized programs and usage matrices.

Can I use nmf-rs for fast consensus NMF on large datasets?▼

Yes, the Rust-backed nmf-rs backend supports fast consensus NMF, K selection, consensus heatmaps, and program labeling specifically designed for large single-cell datasets.

How do I label single-cell clusters after NMF factorization?▼

Label single-cell clusters after NMF factorization by assigning cNMF_cluster labels or using Random Forest Classifier (RFC) labels based on the resulting normalized usage matrices.

Related Skills

Explore More Education & Research Skills→
StarlitnightlyStarlitnightly
13

omicverse-single-cell-cnmf-program-discovery

Run consensus non-negative matrix factorization on single-cell AnnData to discover gene programs.

Community
Advanced
pwwangpwwang
22

clustermarkers

Identify differentially expressed gene markers for cell clusters in single-cell RNA-seq data.

Community
Advanced
KetomihineKetomihine
1

scanpy-single-cell-analysis

Analyze single-cell RNA-seq .h5ad data with Scanpy from QC to clustering.

Community
Advanced
omicverseomicverse
13

omicverse-single-cell-cellphonedb-communication

Analyze single-cell ligand-receptor communication from annotated AnnData objects.

Official
Advanced