gtars

Process BED regions and fragments for overlap detection, coverage generation, and tokenization.

Updated May 24, 2026
One-click install
npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill gtars-estrella-231
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gtars
Source: https://github.com/Estrella-231/Mathematical_modeling_tongmeng/tree/main/.agents/skills/gtars
Command: npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill gtars-estrella-231

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It solves the problem of slow and error-prone handling of genomic interval files by providing efficient overlap detection, coverage generation, tokenization, and fragment/refget utilities in one toolkit.

Core Features & Use Cases

  • Overlap Detection & IGD Indexing: Quickly find overlaps between BED region sets using an IGD-based index, supporting annotation and set operations; use it for regulatory element comparisons and variant-to-feature overlap queries.
  • Coverage Track Generation (Uniwig): Convert BED/fragment intervals into coverage tracks such as WIG or BigWig for visualization and downstream analyses; use it for ATAC-seq/ChIP-seq coverage profiles.
  • Genomic Tokenization for ML: Transform genomic regions into discrete tokens suitable for machine learning preprocessing, including integration patterns for genomic ML pipelines.
  • Reference Sequence Management (refget): Load/reference FASTA-backed stores, extract subsequences, and compute/verify refget digests (GA4GH refget protocol).
  • Fragment Processing & Scoring: Split fragments by barcodes/clusters and score enrichment against reference datasets for single-cell workflows.

Quick Start

Use the gtars skill to generate a BigWig coverage track from a fragments BED file and write it to coverage.bw.

Frequently Asked Questions about gtars

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate BigWig coverage tracks from BED files for ATAC-seq analysis?

To generate BigWig coverage tracks from BED files, you process genomic fragment intervals using the uniwig engine to output WIG or BigWig formats. This directly supports ATAC-seq and ChIP-seq coverage profile visualization.

What is the best way to detect overlaps between large BED region sets?

Detecting overlaps between large BED region sets uses an IGD-based index for fast and efficient overlap detection. This supports regulatory element comparisons and variant-to-feature overlap queries without slow, error-prone file handling.

How does genomic tokenization work for machine learning preprocessing?

Genomic tokenization transforms genomic regions into discrete tokens suitable for machine learning preprocessing. This process integrates directly into genomic ML pipelines by processing reference sequences and interval data via Rust core operations.

Can I process single-cell fragments and score enrichment against reference datasets?

Yes, you can split single-cell fragments by barcodes or clusters and score enrichment against reference datasets. This fragment processing supports single-cell workflows by utilizing Rust Python bindings for efficient computation.

Does refget reference handling support extracting subsequences from FASTA stores?

Refget reference handling loads FASTA-backed stores to extract subsequences and compute GA4GH refget protocol digests. This ensures proper reference sequence management and verification for downstream genomic interval operations.