Trains unsupervised embeddings for genomic intervals and metadata from BED files.
npx skills add https://github.com/fuzzy-dynamics/strings --skill geniml-fuzzy-dynamics
Please help me install this Agent Skill. Skill: geniml Source: https://github.com/fuzzy-dynamics/strings/tree/main/packages/skills/geniml Command: npx skills add https://github.com/fuzzy-dynamics/strings --skill geniml-fuzzy-dynamics
Geniml enables unsupervised learning of embeddings for genomic intervals and associated metadata from BED files, enabling similarity search, clustering, and downstream ML tasks.
Prepare BED files and a universe file, then run the region2vec pipeline to train embeddings.
High-intent search queries and answers about installing and using this skill.
To generate embeddings for genomic intervals from BED files, you can use the region2vec pipeline to train unsupervised embeddings that enable dimensionality reduction and similarity analysis across your genomic regions.
Yes, you can embed single-cell ATAC-seq data using the scEmbed workflow, which generates cell-level embeddings specifically designed to support clustering and cell type annotation tasks.
A universe reference is a standardized set of consensus peaks required to tokenize genomic intervals from BED files. You must provide a universe file to standardize tokenization and enable cross-dataset comparisons.
To jointly query genomic regions and metadata labels, use the BEDspace workflow to jointly embed regions and labels, enabling cross-modal queries like region-to-label and label-to-region searches.
After learning genomic interval embeddings, you can perform similarity search, clustering, and downstream ML tasks using the trained embeddings alongside provided utilities for evaluation, caching, and search.
Yes, geniml supports scATAC workflows across both bulk and single-cell data, allowing you to generate region and cell-level embeddings from BED files using a standardized universe reference for tokenization.
LeonChaoXBuild machine learning embeddings from genomic interval BED files.
AlterLab-IEUBuild unsupervised embeddings from genomic interval data with Geniml.
SciMate-AITrain genomic-interval embeddings from BED data for region similarity and clustering.
hxk622Train genomic region embeddings and analyze single-cell ATAC-seq data with Python.
