gtars

Genomic interval overlap detection across large BED-like datasets is handled by a Rust-based toolkit offering IGD indexing and distance queries with Python bindings for seamless integration into existing bioinformatics workflows.

Coverage track generation and genomic tokenization for ML models is achieved by utilizing a high-performance Rust core with Python bindings to produce machine learning-ready genomic data efficiently.

Python bindings for genomic interval processing fully support seamless integration with NumPy and pandas, enabling users to leverage safe parallel processing and memory efficiency within familiar bioinformatics workflows.

Genomic tokenization for machine learning pipelines includes built-in reference sequence management, allowing users to handle tokenization and sequence references within a single high-performance toolkit.

Automating genomic interval analysis from a BED file starts by installing the toolkit from PyPI and running a minimal RegionSet.from_bed workflow to confirm the setup and process intervals.