Generate genomic interval embeddings from BED files using Region2Vec.
npx skills add https://github.com/crazymsn/academic-skills --skill geniml-crazymsn
Please help me install this Agent Skill. Skill: geniml Source: https://github.com/crazymsn/academic-skills/tree/main/academic-skills/geniml Command: npx skills add https://github.com/crazymsn/academic-skills --skill geniml-crazymsn
Geniml provides an end-to-end toolkit to convert genomic interval data (BED files) into meaningful embeddings and searchable representations, enabling rapid comparison, clustering, and metadata-aware queries.
Train a Region2Vec model on your BED dataset to generate embeddings for downstream analyses.
High-intent search queries and answers about installing and using this skill.
To generate genomic embeddings from BED files, you can use the Region2Vec workflow to train an unsupervised model on your genomic interval data, creating vector representations for downstream similarity searches and clustering.
Region2vec is used to transform genomic interval data into unsupervised region embeddings, enabling rapid similarity searches, metadata-aware cross-modal queries, and clustering across multiple bulk datasets.
Yes, you can compute single-cell chromatin accessibility embeddings from scATAC-seq data using the scEmbed workflow, which generates vector representations specifically designed for cell clustering and cell-type annotation.
Yes, building a universe reference BED is required for tokenization and standardization. It creates consensus peak references across multiple datasets to ensure consistent region tokenization before model training.
Training and searching genomic embeddings requires optional dependencies such as PyTorch and StarSpace, which support the model training and similarity search components of the embedding workflows.
You can create joint embeddings for genomic regions and metadata labels using the BEDspace workflow, which constructs a shared embedding space to support cross-modal queries between intervals and experimental conditions.
Lord1EgyptTrain machine learning models on genomic interval data from BED files.
TianGzlabAutomate cell type annotation for single-cell omics data using marker genes, CellTypist, SingleR, or scmap.
galeepGenerate unsupervised embeddings for genomic regions from interval data.
Yezez9Train unsupervised genomic region embeddings from BED files with geniml.
