geniml

Train Region2Vec embeddings on genomic interval BED files.

Updated Mar 10, 2026

Search Tags:#embeddings #machine learning #genomics #scATAC-seq #bed files #peak calling

Ready to run

npx skills add https://github.com/felixboehm/biochem-allergy --skill geniml-felixboehm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: geniml
Source: https://github.com/felixboehm/biochem-allergy/tree/main/.claude/skills/geniml
Command: npx skills add https://github.com/felixboehm/biochem-allergy --skill geniml-felixboehm

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines machine learning tasks involving genomic interval data (BED files), simplifying complex analyses like region embeddings and single-cell data processing.

Core Features & Use Cases

Genomic Region Embeddings: Learn unsupervised embeddings of genomic regions using Region2Vec.
Single-Cell Analysis: Process scATAC-seq data with scEmbed for cell clustering and annotation.
Consensus Peak Calling: Build robust reference peak sets from multiple experiments.
Use Case: Analyze a collection of ChIP-seq BED files to identify patterns and generate feature vectors for downstream classification tasks.

Quick Start

Use the geniml skill to train Region2Vec embeddings on BED files 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 generate unsupervised embeddings for genomic regions in BED files?▼

You can generate unsupervised embeddings for genomic regions in BED files using the Region2Vec method. It learns feature vectors from BED file intervals, enabling downstream classification tasks and pattern identification across collections of genomic regions.

What is the best way to process single-cell ATAC-seq data for cell clustering?▼

Processing single-cell ATAC-seq data for cell clustering is handled using the scEmbed method. It generates unsupervised single-cell embeddings from scATAC-seq datasets to facilitate accurate cell clustering and subsequent cellular annotation.

How do I build a consensus peak set from multiple ChIP-seq experiments?▼

Building a consensus peak set from multiple ChIP-seq experiments requires using the built-in consensus peak calling utilities. This constructs a robust reference peak set by aggregating genomic intervals across multiple BED files.

Can I use scanpy for downstream analysis of scATAC-seq embeddings?▼

Yes, scanpy is supported as a required Python package for downstream analysis of scATAC-seq embeddings. The generated single-cell embeddings integrate with scanpy workflows for cell clustering and annotation tasks.

Do I need PyTorch to train machine learning models on genomic interval data?▼

PyTorch is potentially required as a machine learning dependency to train models on genomic interval data. The skill uses it alongside the geniml and scanpy Python packages to support underlying deep learning operations for embedding generation.