Seven disciplines, one shared data layer

Statistical and machine learning models of biological sequences and structures, used to prioritize which experiments are worth running in the lab.

Analysis pipelines that turn raw sequencer output into annotated, searchable datasets with reproducible provenance.

Species detection from trace genetic material in water and soil samples, currently applied to freshwater biodiversity surveys.

Whole-genome and targeted sequencing workflows for research partners, with a focus on non-model organisms.

Liquid-handling and sample-prep automation that reduces manual error in repetitive wet-lab steps before sequencing.

Molecular and population-level simulations used to generate hypotheses ahead of wet-lab validation.

Shared model infrastructure, sequence classifiers, anomaly detection, and evaluation tooling for research teams.