geniml

Train unsupervised genomic region embeddings from BED files with geniml.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/Yezez9/Research-Agent --skill geniml-yezez9
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geniml
Source: https://github.com/Yezez9/Research-Agent/tree/main/scientific-skills/geniml
Command: npx skills add https://github.com/Yezez9/Research-Agent --skill geniml-yezez9

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies complex machine learning tasks on genomic interval data (BED files), enabling advanced analysis of chromatin accessibility, gene regulation, and more.

Core Features & Use Cases

  • Genomic Embeddings: Train unsupervised embeddings (Region2Vec, BEDspace) for genomic regions and cells.
  • Single-Cell Analysis: Perform scATAC-seq analysis and cell clustering with scEmbed.
  • Consensus Peaks: Build standardized reference peak sets from multiple datasets.
  • Use Case: Analyze single-cell ATAC-seq data to identify distinct cell populations by training embeddings that capture chromatin accessibility patterns.

Quick Start

Use the geniml skill to train Region2Vec embeddings on BED files located in the 'bed_files/' directory.

Frequently Asked Questions about geniml

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

FAQPage Schema
How do I train unsupervised embeddings for genomic regions from BED files?

You can train unsupervised embeddings for genomic regions from BED files using Region2Vec or BEDspace algorithms. This generates numerical vector representations capturing genomic interval similarities for downstream machine learning tasks.

Can I perform scATAC-seq cell clustering using chromatin accessibility data?

Yes, scATAC-seq cell clustering is supported using the scEmbed method. It trains embeddings on single-cell chromatin accessibility datasets to identify distinct cell populations based on their accessibility patterns.

What is the best way to build a consensus peak set from multiple scATAC-seq datasets?

Building a consensus peak set from multiple datasets creates a standardized reference peak set. This constructs a unified genomic interval coordinate system for consistent cross-dataset chromatin accessibility comparisons.

Does this machine learning approach work directly with raw BED file intervals?

Yes, this approach works directly with genomic interval data formatted as BED files. It processes these raw genomic coordinates to learn region similarities and single-cell feature representations without requiring pre-converted formats.

What are the limitations of learning embeddings for single-cell chromatin accessibility?

Learning embeddings for single-cell chromatin accessibility requires sufficient genomic interval coverage in BED files. Unsupervised feature learning on sparse scATAC-seq datasets may produce noisy cell clustering if peak overlap is minimal.