Gtars

If you're doing computational genomics work with interval data, this gives you fast Rust-based tools for the bread-and-butter operations: overlap detection, coverage track generation, and genomic tokenization for ML models. It handles BED files, generates BigWig tracks, and includes specialized features like fragment splitting for single-cell ATAC-seq. The Python bindings are clean and there's a CLI for quick analyses. Honestly most useful if you're already working with the geniml ecosystem or need the performance gains from Rust over pure Python genomics libraries. The tokenization module is aimed squarely at training transformer models on genomic sequences.

skills.sh installs: 2K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill gtars --agent claude-code

Installs into .claude/skills of the current project.

Files

Gtars

Gtars provides native Rust implementations, Python bindings, and a feature-gated gtars binary for genomic interval and reference-sequence work. Start with the bundled local inspectors; call upstream code only after the data contract, provenance, resource bounds, and side effects are explicit.