Generate unsupervised embeddings from genomic interval BED files for ML analyses.
npx skills add https://github.com/rubensliv/k-dense-ai --skill geniml-rubensliv
Please help me install this Agent Skill. Skill: geniml Source: https://github.com/rubensliv/k-dense-ai/tree/main/scientific-skills/geniml Command: npx skills add https://github.com/rubensliv/k-dense-ai --skill geniml-rubensliv
Geniml enables researchers to transform genomic interval data from BED files into rich, ML-ready embeddings for similarity search, clustering, and cross-modal analyses.
Train Region2Vec with your BED files by first tokenizing against a universe and then training the region2vec model.
High-intent search queries and answers about installing and using this skill.
To generate embeddings from BED files, you tokenize genomic intervals against a reference universe and train a Region2Vec model to produce ML-ready vectors for clustering and similarity search.
Region2Vec is an unsupervised learning technique that transforms genomic interval data from BED files into rich embeddings, enabling downstream tasks like similarity search and cross-modal analyses.
Yes, scEmbed is specifically designed to generate cell-level embeddings for scATAC-seq workflows, allowing you to process single-cell genomic interval data within the same pipeline.
Yes, universe-building standardizes reference vocabularies before tokenization, which is a required step to ensure consistent region mapping when training models on bulk BED collections.
Yes, BEDspace supports joint region and metadata embeddings, enabling bidirectional queries where you can map region to label and label to region for cross-referencing genomic data.
Unsupervised genomic interval tokenization relies entirely on a predefined universe for vocabulary standardization, meaning model quality depends heavily on the chosen reference intervals and data coverage.
shushuznBuild machine learning embeddings from genomic interval BED files.
Estrella-231Generate machine learning embeddings for genomic intervals from BED files.
SciMate-AITrain genomic-interval embeddings from BED data for region similarity and clustering.
jackspaceGenerate unsupervised embeddings for genomic intervals from BED files.
