Build unsupervised embeddings and tokenization workflows for genomic interval data.
npx skills add https://github.com/swaruplab/operon --skill geniml-swaruplab
Please help me install this Agent Skill. Skill: geniml Source: https://github.com/swaruplab/operon/tree/main/src-tauri/protocols/geniml Command: npx skills add https://github.com/swaruplab/operon --skill geniml-swaruplab
Geniml provides a focused, scalable framework for modeling genomic interval data by producing region embeddings and tokenization workflows that enable fast similarity searches and integrative analyses.
Tokenize BED files with the universe and train Region2Vec to generate embeddings for downstream analysis
High-intent search queries and answers about installing and using this skill.
You can build unsupervised embeddings for genomic interval data using Region2Vec and scEmbed, which produce vector representations for BED files and scATAC-seq data to enable clustering, retrieval, and downstream ML pipelines.
Tokenizing BED files requires building a consensus universe of peaks to standardize intervals. This Skill provides tokenization and evaluation utilities to prepare genomic regions for training Region2Vec models.
Yes, scEmbed specifically generates single-cell chromatin accessibility embeddings for scATAC-seq analyses, enabling fast similarity searches and integrative downstream evaluations.
BEDspace creates joint region and metadata embeddings that support metadata-aware queries, allowing you to integrate genomic intervals with experimental metadata for cross-modal retrieval.
No external dependencies are required. The framework provides a Python API and CLI workflows for tokenization, training, and evaluation that integrate directly into existing genomic analysis pipelines.
Universe building generates consensus peaks across samples to standardize genomic intervals before tokenization. It is needed when preparing multiple BED files for consistent Region2Vec embedding training.
jasrajtulsiBuild embeddings and search workflows for genomic interval data from BED files and scATAC-seq datasets.
OpenCovenGenerate sentence embeddings for semantic similarity, clustering, and retrieval tasks.
CHENyiru3Integrate multi-modal single-cell RNA and protein data with Seurat v5 WNN.
Lord1EgyptTrain machine learning models on genomic interval data from BED files.
