Learn more

Created to accelerate research and
discovery with explainable insights

With traditional AI, you get black-box predictions.
With Abzu's QLattice®, you get trustworthy explanations.


Understand the basis of disease and identify novel points of intervention, even with small and complex data sets, overcoming today’s most considerable challenges in R+D.Determine the cause or causes of heterogeneous diseases with transparent models that reveal the contributions of genetic and environmental factors and hidden biological pathways.

Samuel Demharter sharing disease mechanism causes at Abzu

Identifying multi-omics biomarkersWe identified two gene expressions as primary mortality indicators in breast cancer on a wide data set of only 705 women.



Elevate your understanding of underlying biological mechanisms with our high-precision and explainable models, increasing the identification of potential targets for new drug development.Explore all available evidence and discover non-trivial relationships in your data to design optimized, multi-pronged genomic medicines, small molecules, and more.

Designing drugs with explainable AIWe collaborated with an undisclosed nucleic acid therapeutics company to develop drugs for rare and complex diseases.


Improve the hit rate for effective treatments with simple models that predict the activity of small molecules and therapeutics and explain what drives desirable and undesirable drug properties.Accelerate preclinical drug discovery by enhancing basic research of disease components and druggable targets with intelligent and explainable predictions.

Lykke Pedersen sharing her knowledge on drug development at Abzu

Accelerating R+D and reducing riskWe helped an undisclosed top 10 pharma company understand the key components to safe and efficacious compounds.


Enhance biomarker candidate discovery and qualification by finding consistent associations between markers and diseases and explain treatment responses with predictive power and clarity.Untangle the complexity between molecular and clinical causal drivers and plainly explain relationships to researchers, clinicians, and patients.

Martin Mathiasen solving biomarker discovery problems at Abzu

Understanding causes in patient responsesWe are increasing the share of complete responders through data-driven patient stratification with Checkmate Pharma.


Self-organized and self-managed

We don’t have any bosses. Abzoids determine their own salaries and schedules and make decisions about their work priorities. This requires transparency and trust, which is an integral part of our technology and who we are.

Good humans
at work

Ending poverty, protecting the planet, and promoting peace and prosperity. We’re tackling the UN 17 Sustainable Development Goals (SDGs) one ‘P’ at a time.

No poverty


Zero hunger


Good health and well-being


Quality education

Light bulbLight bulbLight bulbLight bulb

Further reading

Abzu blog - An introduction to calibration (part III): Evaluating the calibration of your QLattice models3.05.2022

Evaluating the calibration of your QLattice models

Let's study how well calibrated the QLattice models are, and to what extent calibrators can improve them.

Read more
The EU flag4.04.2022

The European approach: Towards trustworthy AI

Something is brewing in Europe. Is it an ecosystem of excellence?

Read more
Casper presenting at Tech BBQ 20211.02.2022

Techtopia podcast: Danish AI against breast cancer

Just because you can predict what's going to happen does not mean you have an explanation for the phenomenon.

Read more

Where are we next?

June10:20 - 11:00
Abzu at Oxford Global Discovery Europe

Discovery Europe

Using explainable AI to generate highly predictive and interpretable biomarker signatures from clinical data with Marco Salvatore

September10:00 - 10:30
Abzu at Intelligent Health AI

Intelligent Health

The rise of simple models in health and life science: Interpretable AI for biomarker and target discovery with Samuel Demharter