skills.rest
wsxwj123
wsxwj123COMMUNITY
Explore all skills by this author →
GitHub

geniml

Learn genomic interval embeddings from BED files using Region2Vec, BEDspace, scEmbed, and Universe.

7|Updated Jan 27, 2026
Search Tags:#embeddings#genomics#tokenization#universe#scembed#region2vec#bed
One-click install
npx skills add https://github.com/wsxwj123/opencode-skills-backup --skill geniml-wsxwj123
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: geniml
Source: https://github.com/wsxwj123/opencode-skills-backup/tree/main/geniml
Command: npx skills add https://github.com/wsxwj123/opencode-skills-backup --skill geniml-wsxwj123

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Geniml enables end-to-end machine learning workflows on genomic interval data by learning embeddings from BED files for downstream analyses such as region similarity, clustering, and search across experiments.

Core Features & Use Cases

  • Region2Vec embeddings for genomic regions and sets
  • BEDspace joint embeddings for regions and metadata labels
  • scEmbed for single-cell ATAC-seq data
  • Universe building for consensus peaks
  • Tokenization, evaluation, and utilities for scalable workflows

Quick Start

Train region embeddings from a BED file collection with Region2Vec or BEDspace to begin downstream analyses.

Frequently Asked Questions about geniml

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

FAQPage Schema
How do I learn embeddings from BED files for genomic interval machine learning?▼

You can learn embeddings from BED files using Region2Vec or BEDspace to generate vector representations of genomic regions for downstream tasks like similarity search and clustering.

What is the best way to run machine learning on single-cell ATAC-seq data?▼

For single-cell ATAC-seq data, you can use the scEmbed tool to train embeddings that capture region-level features and apply them to downstream machine learning workflows.

How do I build a consensus peak universe across multiple BED datasets?▼

You can build a cross-dataset universe of consensus peaks using the Universe tool, which enables consistent tokenization and comparison of genomic intervals across multiple experiments.

Can I apply joint embeddings to genomic regions and metadata labels together?▼

Yes, BEDspace generates joint embeddings for genomic regions and their associated metadata labels, allowing you to integrate biological context directly into region similarity analyses.

Do I need a Python environment to run genomic interval tokenization workflows?▼

Yes, this requires a Python-based toolkit with YAML frontmatter metadata and modular components to handle region tokenization, model training, and evaluation for genomic interval data.

Related Skills

Explore More Data & Analytics Skills→
JosephWoodallJosephWoodall
1

geniml

Build unsupervised genomic interval embeddings from BED files with Region2Vec, BEDspace, scEmbed, and universe-building workflows.

Community
Advanced
LeonChaoXLeonChaoX
783

geniml

Build machine learning embeddings from genomic interval BED files.

Community
Advanced
Hung-3008Hung-3008
1

geniml

Converts genomic interval data from BED files into trainable embeddings for machine learning.

Community
Advanced
LogauaEngstromLogauaEngstrom
18

geniml

Learn unsupervised embeddings from genomic interval data for region-level similarity and clustering.

Community
Advanced