skills.rest
SciMate-AI
SciMate-AIOFFICIAL
Explore all skills by this author →
GitHub

geniml

Train genomic-interval embeddings from BED data for region similarity and clustering.

1|Updated Mar 11, 2026
Search Tags:#embeddings#genomics#tokenization#universe#scembed#bedspace#region2vec
One-click install
npx skills add https://github.com/SciMate-AI/scicli --skill geniml-scimate-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: geniml
Source: https://github.com/SciMate-AI/scicli/tree/main/internal/skills/bundled/claude-scientific-skills/skills/geniml
Command: npx skills add https://github.com/SciMate-AI/scicli --skill geniml-scimate-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Geniml provides a modular toolkit to transform genomic interval data into ML-friendly embeddings, enabling scalable analysis of genomic regions, single-cell ATAC-seq data, and cross-dataset comparisons.

Core Features & Use Cases

  • Region2Vec: train unsupervised region embeddings from BED data for similarity search and clustering.
  • BEDspace: joint region and metadata embeddings for metadata-aware queries.
  • scEmbed: cell-level embeddings for single-cell ATAC-seq analysis and integration with scanpy.
  • Universe/Consensus Peaks: build reference universes for tokenization and standardization across datasets.
  • Utilities: tokenization, evaluation, caching, and search infrastructure to support end-to-end workflows.

Quick Start

Run Region2Vec on your BED files using a provided universe and then evaluate the embeddings.

Frequently Asked Questions about geniml

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

FAQPage Schema
How do I convert BED files into genomic embeddings for region similarity analysis?▼

Geniml transforms genomic interval data into ML-friendly embeddings using Region2Vec to train unsupervised models on BED files, enabling region similarity search and clustering across bulk BED collections.

What is the best way to generate cell-level embeddings for single-cell ATAC-seq data?▼

scEmbed generates cell-level embeddings for single-cell ATAC-seq analysis, integrating with scanpy to enable cell clustering and metadata-aware queries on chromatin accessibility data.

Can I build a cross-dataset reference universe for genomic tokenization?▼

Yes, Geniml builds reference universes or consensus peaks for tokenization and standardization across datasets, establishing a shared vocabulary for cross-dataset comparisons and modular tokenization workflows.

Does Geniml support metadata-aware queries on genomic interval data?▼

BEDspace provides joint region and metadata embeddings to enable metadata-aware queries, allowing you to search and analyze genomic intervals while accounting for associated sample or cell metadata.

How do I evaluate genomic interval embeddings after training a model?▼

Geniml includes evaluation utilities to assess trained genomic interval embeddings, allowing you to validate model quality after running Region2Vec or other embedding methods on your BED data.

Related Skills

Explore More Data & Analytics Skills→
shushuznshushuzn
4

geniml

Build machine learning embeddings from genomic interval BED files.

Community
Advanced
jackspacejackspace
16

geniml

Generate unsupervised embeddings for genomic intervals from BED files.

Community
Advanced
LeonChaoXLeonChaoX
783

geniml

Build machine learning embeddings from genomic interval BED files.

Community
Advanced
hxk622hxk622
8

geniml

Train genomic region embeddings and analyze single-cell ATAC-seq data with Python.

Community
Advanced