geniml — genomic interval machine learning on BED files (Region2Vec, BEDspace, scEmbed, consensus peaks)
Python package for ML on genomic interval data — Region2Vec region embeddings, BEDspace joint region-metadata embeddings, scEmbed single-cell ATAC-seq embeddings, consensus-peak universe building, and utilities (BBClient, BEDshift, tokenization, evaluation)
- What
- Python package for ML on genomic interval data — Region2Vec region embeddings, BEDspace joint region-metadata embeddings, scEmbed single-cell ATAC-seq embeddings, consensus-peak universe building, and utilities (BBClient, BEDshift, tokenization, evaluation)
- Cost
- Free
- Needs
- genomic interval data (BED files) and Python with uv — the skill is a workflow guide for the geniml package, not the software itself
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @davila7's geniml skill: a working guide to the geniml Python package (databio) for machine learning on genomic interval data from BED files. Five capabilities: Region2Vec — unsupervised word2vec-style embeddings of genomic regions for similarity analysis and downstream ML; BEDspace — StarSpace joint embeddings of region sets and metadata labels for cross-modal region↔label queries; scEmbed — single-cell ATAC-seq cell embeddings integrating with scanpy workflows; consensus-peak universe building — reference peak sets via CC, CCF, ML, or HMM statistical methods; and utilities — BBClient BED caching, BEDshift randomization, embedding evaluation metrics, tokenization helpers, and Text2BedNN neural search. Includes full pipelines (basic region-embedding pipeline, scATAC-seq analysis, universe build/evaluate), a CLI reference, tool-selection guidance, best practices (universe quality, tokenization coverage, reproducibility), performance considerations, and troubleshooting. Honest caveats: a niche scientific-computing skill — expects BED files, reference universes, and sometimes heavy compute (PyTorch, StarSpace); installation snippets use uv; part of the BEDbase ecosystem (pairs with the gtars skill). MIT per the discovery manifest (the skill frontmatter states no license — the manifest makes faith). Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: genomic interval data (BED files) and Python with uv — the skill is a workflow guide for the geniml package, not the software itself Install "geniml — genomic interval machine learning on BED files" for me. It gives my agent @davila7's geniml workflow: train Region2Vec region embeddings, build BEDspace joint region-metadata embeddings, run scEmbed single-cell ATAC-seq analysis with scanpy, construct consensus-peak universes (CC, CCF, ML, HMM), and use utilities (BBClient caching, BEDshift, tokenization, evaluation) — with full pipelines, CLI reference, tool-selection guidance, best practices, and troubleshooting. MIT-licensed (per the discovery manifest; the skill frontmatter states no license). Repository: https://github.com/davila7/claude-code-templates/blob/main/cli-tool/components/skills/scientific/geniml/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "geniml". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install geniml via uv myself, provide my BED files and a reference universe; nothing else — it's a methodology). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.