gtars

Genomic interval tokenization converts BED file regions into integer token IDs mapped against a defined universe vocabulary, producing structured numerical representations essential for machine learning preprocessing pipelines.

High-performance interval set arithmetic executes intersection, union, merge, complement, and subtract operations on large BED files using a Rust-backed core, delivering rapid genomic region manipulation for bioinformatics workflows.

Universe building constructs a consensus BED file from multiple sample peak files, generating a unified genomic interval vocabulary that serves as the reference for consistently tokenizing diverse ATAC-seq or ChIP-seq datasets.

Yes, high-performance I/O reads and writes large genomic interval BED files using a Rust-backed Python library, delivering efficient data throughput necessary for large-scale bioinformatics and genomic annotation workflows.

Yes, numpy integrates with genomic interval tokenization operations in bioinformatics pipelines, processing BED file intervals into tokenized representations while leveraging numpy for downstream machine learning data handling.

Rust-backed libraries deliver superior performance for genomic interval arithmetic on large BED files by handling heavy I/O and set operations efficiently, preventing bottlenecks when processing thousands of peak files in machine learning workflows.