Bioinformatics

Run analyses directly in your warehouse. No downloads, no pipelines to manage.

Bioinformatics should produce structured data, not loose files

Our warehouse speaks the language of bioinformatics. Every pipeline result lands as machine-readable, validated data you can query, join, and trace. This results in higher performance, better reliability, and lower cost.

.fastq.bam.bed.vcf.tsvreadsreferencevariantschrposrefaltchr110234AGchr115402CTCchr231087GTchr544210TCgenotypes

Germline variant calling

Competitive performance on short-read germline calling, benchmarked against DeepVariant, DRAGEN, and GATK.

Variant Caller Comparison

Taxa classification

More reads classified at the correct species. Fewer misclassifications at every level of the taxonomic tree.

HoX vs Kraken2 by Taxonomic Distance

A growing library of pipelines

We are building the world's most expansive collection of high-performance bioinformatics pipelines, all integrated into the warehouse.

01
Alignment
Short-read and long-read alignment
02
Germline variant calling
SNVs and indels from short reads
03
Expression quantification
Gene and transcript-level RNA quantification
04
Long-read scRNA
Cell typing, V(D)J clonotyping, and isoform resolution from single-cell long reads
05
Taxa classification
Metagenomic species identification

Build workflows visually

Drag, connect, and run pipelines in the browser. No scripting required, no infrastructure to manage.

Composer

Automate from the terminal

Run any pipeline from the CLI. Script analyses, integrate with existing tools, or batch process across datasets. Same tools, same data.

Remote CLI Access

Making biology computable.

Bringing science out of the lab and into the world.

© 2026 HoX Inc. All rights reserved.