geniml

Train Region2Vec embeddings on genomic interval data from BED files.

1|Updated Jan 14, 2026
One-click install
npx skills add https://github.com/Sologa/codex-pipeline --skill geniml-sologa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geniml
Source: https://github.com/Sologa/codex-pipeline/tree/main/.codex/skills/geniml
Command: npx skills add https://github.com/Sologa/codex-pipeline --skill geniml-sologa

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 (like BED files), enabling advanced analysis of DNA regions and single-cell data without deep ML expertise.

Core Features & Use Cases

  • Genomic Embeddings: Learn vector representations of genomic regions (Region2Vec) or single cells (scEmbed) for similarity analysis and clustering.
  • Metadata Integration: Jointly embed regions and their associated metadata (e.g., cell types) for powerful cross-modal searches (BEDspace).
  • Reference Building: Create standardized "universe" peak sets from multiple experiments for consistent analysis.
  • Use Case: Analyze single-cell ATAC-seq data to identify distinct cell populations by generating cell embeddings and clustering them using scanpy.

Quick Start

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

Frequently Asked Questions about geniml

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

FAQPage Schema
How do I generate vector embeddings for BED files to cluster genomic regions?

You can train Region2Vec embeddings on BED files to learn vector representations of genomic regions, enabling similarity analysis and clustering of DNA intervals without requiring deep machine learning expertise.

Can I perform single-cell embeddings on scATAC-seq data using scanpy?

Yes, the scEmbed feature generates single-cell embeddings from scATAC-seq data, allowing you to identify distinct cell populations by clustering them using scanpy for downstream analysis.

What is the best way to jointly embed genomic intervals and associated metadata like cell types?

BEDspace jointly embeds genomic regions and their associated metadata, such as cell types, to enable powerful cross-modal searches and integrated analysis of interval data with experimental annotations.

How do I build a standardized consensus peak universe from multiple genomic experiments?

You can build standardized consensus peak universes from multiple experiments to establish a consistent reference set of genomic intervals for uniform downstream analysis and evaluation.

Do I need PyTorch and StarSpace installed to train region embeddings on genomic intervals?

Yes, training region embeddings requires Python libraries including PyTorch and StarSpace, along with scanpy, to process BED files and scATAC-seq data for machine learning tasks.

Why use machine learning for genomic interval data instead of standard statistical analysis?

Machine learning on genomic interval data captures complex patterns in DNA regions and single-cell profiles that standard statistical methods miss, transforming raw BED files into quantitative vector representations for deeper analysis.