omicverse-single-cell-cnmf-program-discovery
CommunityDiscover consensus gene programs with cNMF
AuthorStarlitnightly
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Turn an ephemeral notebook cNMF workflow into a reproducible, triggerable job that fits consensus non-negative matrix factorizations on single-cell AnnData to discover gene expression programs and produce program usages or hard cluster labels.
Core Features & Use Cases
- Fits consensus NMF across a user-provided grid of component ranks and combines replicate factorizations into consensus programs.
- Provides both direct max-usage labeling and classifier-derived hard labels via an RFC path, with explicit CPU vs GPU and single-worker vs multi-worker branches.
- Includes validation and smoke-testing patterns, writable output persistence, and guidance for selecting K and density thresholds; ideal for converting notebook cNMF sections into reusable pipelines for single-cell program discovery.
Quick Start
Run the skill on a preprocessed AnnData to compute consensus programs, load normalized usages, and optionally write hard or RFC-derived cluster labels.
Dependency Matrix
Required Modules
anndatanumpypandasomicverse
Components
scriptsreferencesassets
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: omicverse-single-cell-cnmf-program-discovery Download link: https://github.com/Starlitnightly/omicverse-skills/archive/main.zip#omicverse-single-cell-cnmf-program-discovery Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.