skills.rest
qinyan-ai
qinyan-aiCOMMUNITY
Explore all skills by this author →
GitHub

geniml

Transform genomic interval data from BED files into embeddings for ML workflows.

48|6|Updated Mar 9, 2026
Search Tags:#embeddings#bioinformatics#genomics#scembed#region2vec#bed
One-click install
npx skills add https://github.com/qinyan-ai/qinyan-academic-skills --skill geniml-qinyan-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: geniml
Source: https://github.com/qinyan-ai/qinyan-academic-skills/tree/main/skills/05-%E7%94%9F%E7%89%A9%E4%BF%A1%E6%81%AF%E4%B8%8E%E5%9F%BA%E5%9B%A0%E7%BB%84%E5%AD%A6/geniml
Command: npx skills add https://github.com/qinyan-ai/qinyan-academic-skills --skill geniml-qinyan-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Geniml provides a scalable machine-learning workflow to derive embeddings from genomic interval data (BED files), enabling similarity searches, clustering, and downstream predictive analyses across large-scale genomic datasets.

Core Features & Use Cases

  • Region2Vec: Unsupervised embeddings for genomic regions and region sets to enable dimensionality reduction and similarity queries.
  • BEDspace: Joint embeddings of regions and metadata labels for metadata-aware searches and cross-modal queries.
  • scEmbed: Single-cell chromatin accessibility embeddings for scATAC-seq workflows integrated with scanpy.
  • Consensus Peaks (Universe): Tools to build reference universes from multiple BED files for standardized tokenization.
  • Utilities: Supporting tools such as tokenization, caching, evaluation, and randomization for robust workflows.

Quick Start

Install the Geniml package and run a basic Region2Vec workflow using a prepared universe file to tokenize BED files and train embeddings.

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 from BED file genomic interval data?▼

To generate embeddings from BED file genomic interval data, you can use the Region2Vec workflow to tokenize genomic regions against a reference universe and train unsupervised embeddings for similarity queries and clustering tasks.

Can I use scEmbed for single-cell chromatin accessibility embeddings with scATAC-seq data?▼

Yes, you can use scEmbed to generate single-cell chromatin accessibility embeddings for scATAC-seq data, integrating directly with scanpy workflows for downstream dimensionality reduction and predictive analyses.

What is the process for building a consensus peaks reference universe for genomic region tokenization?▼

Building a consensus peaks reference universe involves processing multiple BED files to create a standardized set of genomic intervals, enabling consistent tokenization of BED file collections for downstream machine learning pipelines.

Does this genomic interval embedding workflow support metadata-aware cross-modal searches?▼

Yes, the BEDspace feature generates joint embeddings of genomic regions and metadata labels, enabling metadata-aware searches and cross-modal queries across large-scale genomic datasets.

Do I need standard Python packages to run genomic region machine learning pipelines?▼

Yes, this modular pipeline requires standard Python packages to function, utilizing optional references and scripts assets to expand capabilities for genomic interval feature learning and randomization workflows.

Related Skills

Explore More Education & Research Skills→
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
OwnLabAIOwnLabAI
21

geniml

Generate unsupervised embeddings for genomic intervals from BED files.

Official
Intermediate
hxk622hxk622
8

geniml

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

Community
Advanced