Geniml: Genomic Interval Machine Learning

Overview

Geniml is a Python package for building machine learning models on genomic interval data from BED files. It provides unsupervised methods for learning embeddings of genomic regions, single cells, and metadata labels, enabling similarity searches, clustering, and downstream ML tasks.

Installation

Verified against geniml 0.8.4. Install with uv (prefer uv run --with for one-off runs so nothing leaks into the project env):

uv pip install 'geniml[ml]'        # [ml] pulls torch/gensim; needed for region2vec/scembed

scEmbed and scATAC-seq examples also need scanpy: uv pip install scanpy. Universe building (build-universe) and hard tokenization shell out to external binaries — uniwig (coverage tracks) and bedtools — so install those separately.

Development version: uv pip install git+https://github.com/databio/geniml.git

Import paths (IMPORTANT — verified gotcha)