Train Region2Vec embeddings on genomic interval BED files.
npx skills add https://github.com/yf8578/clawomics --skill geniml-yf8578
Please help me install this Agent Skill. Skill: geniml Source: https://github.com/yf8578/clawomics/tree/main/skills/geniml Command: npx skills add https://github.com/yf8578/clawomics --skill geniml-yf8578
This Skill streamlines complex machine learning tasks on genomic interval data, such as BED files, by providing specialized tools for embedding generation, consensus peak calling, and single-cell analysis.
Use the geniml skill to train Region2Vec embeddings on the provided BED files.
High-intent search queries and answers about installing and using this skill.
To run machine learning on BED files, you can train Region2Vec or BEDspace models to learn unsupervised embeddings of genomic regions and associated metadata for downstream bioinformatics analysis.
Analyzing scATAC-seq data is best done using scEmbed to generate cell-level embeddings, which can then be used for downstream clustering with scanpy to identify distinct cell populations.
Generating consensus peaks involves building robust reference peak sets, known as universes, by applying various statistical methods to your genomic interval data to create a unified reference set.
Yes, you need PyTorch and scanpy in your Python environment to use geniml. These dependencies are required for training genomic embeddings and performing single-cell ATAC-seq analysis.
Yes, BED files can be used for unsupervised learning of region embeddings. The geniml skill provides specialized Python packages to train models like Region2Vec directly on genomic interval data.
Building reference peak sets requires careful selection of statistical methods for consensus generation. Limitations depend on the quality of input BED files and the robustness of the chosen statistical universe generation approach.
sanand0Train Region2Vec embeddings on genomic interval BED files.
tony-zhelonkinAnalyze scATAC-seq data to generate batch-correct latent embeddings and differential accessibility.
felixboehmTrain Region2Vec embeddings on genomic interval BED files.
galeepGenerate unsupervised embeddings for genomic regions from interval data.
