skills.rest
robotlearning123
robotlearning123COMMUNITY
Explore all skills by this author →
𝕏@wan73184085GitHub

geniml

Generate machine learning embeddings for genomic interval data from BED files.

Updated Dec 17, 2025
Search Tags:#machine learning#genomics#single-cell analysis#genomic data#machine learning embeddings
One-click install
npx skills add https://github.com/robotlearning123/claude-scientific-skills --skill geniml-robotlearning123
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: geniml
Source: https://github.com/robotlearning123/claude-scientific-skills/tree/main/scientific-skills/geniml
Command: npx skills add https://github.com/robotlearning123/claude-scientific-skills --skill geniml-robotlearning123

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, scipy, scikit-learn, gensim, torch, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill addresses the challenge of working with genomic interval data by providing machine learning embeddings, enabling complex genomic analyses like single-cell ATAC-seq analysis, peak calling, and metadata-aware searches.

Core Features & Use Cases

  • Region2Vec: Generates embeddings for genomic regions for similarity analysis and downstream ML tasks.
  • BEDspace: Trains embeddings for regions and metadata labels, enabling joint analysis and searches.
  • scEmbed: Embeds single-cell ATAC-seq data for clustering, cell-type annotation, and integration with scanpy.
  • Consensus Peaks: Builds reference peak sets (universes) for standardized genomic region analysis.
  • Utilities: Offers tools for caching, randomization, evaluation, and search.
  • Use Case: Imagine you have scATAC-seq data and want to perform cell-type annotation. Use scEmbed to generate cell embeddings and integrate with scanpy for clustering and visualization.

Quick Start

Use the geniml skill to train a Region2Vec model on your genomic regions and metadata.

Frequently Asked Questions about geniml

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

FAQPage Schema
How do I generate machine learning embeddings for genomic interval data?▼

To generate machine learning embeddings for genomic interval data, use the Region2Vec feature to train models on genomic regions, producing embeddings for similarity analysis and downstream ML tasks. Input data should be provided in BED file format.

Can I use this skill for single-cell ATAC-seq analysis and cell-type annotation?▼

Yes, you can perform single-cell ATAC-seq analysis using the scEmbed feature. It embeds single-cell ATAC-seq data for clustering, cell-type annotation, and integrates with scanpy for visualization and downstream analysis workflows.

What file format do I need for genomic data to train region and metadata embeddings?▼

You need genomic data in BED file format to train region and metadata embeddings. The BEDspace feature trains embeddings for genomic regions and metadata labels, enabling joint analysis and metadata-aware searches.

Do I need PyTorch and scikit-learn to run single-cell ATAC-seq embedding workflows?▼

Yes, you need PyTorch and scikit-learn, along with numpy, scipy, and gensim, to run single-cell ATAC-seq embedding workflows. These dependencies support the underlying machine learning embeddings and genomic data processing.

What is the best way to build a standardized reference peak set for genomic region analysis?▼

The best way to build a standardized reference peak set for genomic region analysis is using the Consensus Peaks feature. It builds reference peak sets, or universes, to standardize genomic region analysis across different datasets.

Related Skills

tassiovaletassiovale
13

geniml

Train machine learning models on genomic interval BED files with geniml.

Community
Advanced
StarlitnightlyStarlitnightly
1.2k

Single-cell preprocessing with omicverse

Automate single-cell RNA-seq preprocessing with omicverse notebooks for QC, HVG detection, and embeddings.

Community
Advanced
LeonChaoXLeonChaoX
783

geniml

Build machine learning embeddings from genomic interval BED files.

Community
Advanced
galeepgaleep

geniml

Generate unsupervised embeddings for genomic regions from interval data.

Community
Advanced