Generate unsupervised embeddings for genomic intervals from BED files.
npx skills add https://github.com/jackspace/ClaudeSkillz --skill geniml
Please help me install this Agent Skill. Skill: geniml Source: https://github.com/jackspace/ClaudeSkillz/tree/main/skills/scientific-pkg-geniml Command: npx skills add https://github.com/jackspace/ClaudeSkillz --skill geniml
Geniml provides tooling for learning embeddings from genomic interval data (BED files), enabling region-level ML, scATAC-seq analyses, and universe-building for tokenization.
High-intent search queries and answers about installing and using this skill.
Genomic region embeddings are learned representations of intervals that enable similarity search and clustering. Geniml trains unsupervised embeddings using Region2Vec or BEDspace on tokenized BED file collections, producing vectors that capture region relationships for downstream ML tasks.
Yes. Geniml includes scEmbed for single-cell ATAC-seq analysis and supports universe-based tokenization workflows to process ATAC-seq peaks as BED intervals, enabling region-level clustering and metadata-driven evaluation.
Create a universe from consensus peaks, tokenize BED files using universe tokens, train region embeddings via Region2Vec or BEDspace, then evaluate embeddings against metadata. Geniml provides CLI utilities for each step including caching and region search.
Yes. BED files must be tokenized using a universe definition before embedding training. Geniml handles universe genesis from peak collections and provides tokenization utilities; no external preprocessing is required.
Both are unsupervised embedding methods for genomic intervals. Region2Vec focuses on region sequence context; BEDspace integrates region features with metadata. Choose based on whether metadata enrichment is needed for your analysis.
Yes. Region embeddings enable region-level similarity search and clustering. Geniml includes utilities for caching embeddings and performing downstream searches across region collections.
shushuznBuild machine learning embeddings from genomic interval BED files.
silversteinProduces Tunring-style songwriting sprints with customizable durations and tempos.
jasrajtulsiBuild embeddings and search workflows for genomic interval data from BED files and scATAC-seq datasets.
tassiovaleTrain machine learning models on genomic interval BED files with geniml.
