gtars

Genomic interval overlap detection on large BED-like datasets is handled using an IGD-based approach backed by Rust. Python bindings expose this functionality to compute overlaps efficiently within bioinformatics research workflows.

Genomic tokenization for machine learning converts genomic intervals into tokens suitable for ML models. This toolkit processes BED-like data through its Rust core to generate tokenized representations, streamlining the preparation of genomic data for deep learning applications.

Yes, you can generate coverage tracks from BED files using the uniwig coverage functionality. This toolkit exposes Python bindings backed by a Rust core to produce WIG and BigWig tracks efficiently from genomic interval datasets.

Yes, reference sequence management is supported through a refget-style approach. This toolkit handles and retrieves reference sequences within genomics workflows, integrating reference data management directly with interval analysis operations.

Processing single-cell fragment data for genomic intervals is supported through dedicated fragment processing features. The Rust core handles single-cell data structures to manipulate and analyze fragment-level genomic information efficiently.

No, you do not need to install or configure Rust separately. The Python bindings encapsulate the compiled Rust core, allowing you to perform high-performance genomic interval analysis directly from Python without managing the underlying environment.