geniml

Generate unsupervised embeddings for genomic regions from interval data.

Updated May 17, 2026

Search Tags:#machine learning #single-cell analysis #genomic analysis #genomic embeddings #consensus peak building

Ready to run

npx skills add https://github.com/galeep/plugin-place --skill geniml-galeep

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: geniml
Source: https://github.com/galeep/plugin-place/tree/main/plugins/sci-bioinformatics-genomics/skills/geniml
Command: npx skills add https://github.com/galeep/plugin-place --skill geniml-galeep

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires geniml, PyTorch, StarSpace, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Geniml addresses the challenge of working with genomic interval data by providing machine learning embeddings that simplify the analysis of genomic regions.

Core Features & Use Cases

Genomic Region Embeddings: Learn embeddings for genomic regions for similarity searches, clustering, and downstream machine learning tasks.
Single-Cell Analysis: Train embeddings for single-cell ATAC-seq data for clustering and annotation.
Consensus Peak Building: Build consensus peak sets (universes) from multiple experiments for standardized genomic region analysis.
Use Case: For a genomic researcher analyzing scATAC-seq data, Geniml can help in clustering cells and annotating cell types based on chromatin accessibility.

Quick Start

Train embeddings for your genomic data using the geniml skill.

Frequently Asked Questions about geniml

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

FAQPage Schema

How do I generate embeddings for genomic regions using machine learning?▼

To generate embeddings for genomic regions, you can use this skill to train unsupervised representations from your genomic interval data, outputting vectors for similarity searches and downstream clustering tasks.

Can I use machine learning embeddings for single-cell ATAC-seq clustering?▼

Yes, you can train embeddings for single-cell ATAC-seq data to enable cell clustering and cell type annotation based on chromatin accessibility patterns.

What is the best way to build consensus peak sets from multiple genomic experiments?▼

Building consensus peak sets involves generating standardized genomic region universes from multiple experiments, allowing you to perform consistent downstream region similarity analysis across datasets.

Do I need PyTorch and StarSpace to analyze genomic interval data?▼

Yes, analyzing genomic interval data with this skill requires Python along with specific dependencies like PyTorch, StarSpace, and the geniml library to run the unsupervised embedding models.

What downstream machine learning tasks can I perform with genomic region embeddings?▼

Genomic region embeddings can be used for similarity searches, clustering genomic intervals, and training models for downstream machine learning tasks like single-cell annotation.

Does this skill support supervised learning for chromatin accessibility data?▼

No, this skill generates unsupervised embeddings for genomic regions, meaning it learns representations from interval data structures without requiring labeled chromatin accessibility examples.