genenmf-metaprogram-discovery

Identify reproducible transcriptional programs via per-sample NMF and consensus meta-programs.

1|Updated Nov 20, 2025

Search Tags:#consensus #single-cell #seurat #nmf #metaprograms #cross-sample #ucell

Ready to run

npx skills add https://github.com/tony-zhelonkin/SciAgent-toolkit --skill genenmf-metaprogram-discovery

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: genenmf-metaprogram-discovery
Source: https://github.com/tony-zhelonkin/SciAgent-toolkit/tree/main/skills/genenmf-metaprogram-discovery
Command: npx skills add https://github.com/tony-zhelonkin/SciAgent-toolkit --skill genenmf-metaprogram-discovery

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Identify reproducible transcriptional programs across multiple single-cell samples by performing per-sample non-negative matrix factorization and deriving consensus meta-programs.

Core Features & Use Cases

Per-sample NMF to learn gene programs in each donor/sample.
Consensus meta-program discovery across donors, enabling cross-patient signatures without batch correction.
Score cells by meta-program signatures using UCell within Seurat workflows; applicable to tumor heterogeneity and multi-donor studies.

Quick Start

Split your Seurat object by donor, run multiNMF across samples, then extract and score meta-programs.

Frequently Asked Questions about genenmf-metaprogram-discovery

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

FAQPage Schema

How do I discover reproducible gene programs across multiple single-cell samples without joint batch correction?▼

Cross-sample gene programs can be discovered by performing per-sample NMF to learn programs in each donor, then deriving consensus meta-programs. This per-sample factorization followed by consensus scoring enables cross-patient signatures without joint modeling.

What is a consensus meta-program in single-cell RNA-seq analysis?▼

A consensus meta-program is a reproducible transcriptional program identified by performing per-sample non-negative matrix factorization across multiple donors, then deriving shared programs through consensus scoring. It captures cross-sample gene signatures without requiring a joint model.

How do I run per-sample NMF on a multi-donor Seurat object?▼

Split your Seurat object by donor, run multiNMF across samples to learn gene programs in each, then extract and derive consensus meta-programs. This workflow uses GeneNMF to enable cross-sample meta-program discovery.

Does cross-sample NMF work for multi-donor tumor datasets with strong batch effects?▼

Yes, per-sample NMF is specifically suited for multi-donor tumor datasets where batch effects hinder joint modeling. It factorizes each sample independently, then uses consensus scoring to find reproducible meta-programs across donors without batch correction.

How do I score cells by meta-program signatures using UCell in Seurat?▼

After extracting consensus meta-programs from per-sample NMF, use UCell within Seurat workflows to score cells by meta-program signatures. This enables quantification of program activity across donors in tumor heterogeneity studies.

When should I avoid joint modeling and use per-sample NMF for cross-patient studies?▼

Per-sample NMF is preferred when batch effects across patients or donors are too strong for joint modeling. It avoids batch correction by factorizing each sample independently and deriving consensus meta-programs through cross-sample scoring.