DNABERT-S

Creates embeddings from DNA sequences for comparing genomes, identifying functional regions, and other genomic analyses.

Field
Biology & genomics
Method
Foundation model
Data it takes
sequence
License
Apache-2.0

DNABERT-S produces species-aware embeddings of DNA sequences, trained so that fragments from the same organism cluster together.

This suits metagenomic binning: separating a mixed environmental sample into per-organism groups without a reference genome. Most organisms in an environmental sample have no assembled reference.

Upstream project →

Catalog entry last checked 2026-08-17. All models →

Run DNABERT-S on your data

The lab runs this on its own compute, in a container, with the inputs and parameters recorded alongside the result. Initial scoping conversations are free.

Contact the Lab