AI subgroup discovery

Multimodal AI-powered biomarkers

We combine cutting-edge machine learning and biology to identify biomarkers


Patient subgroups are key to precision medicine

By using AI to analyze multimodal patient data, we categorize patients into distinct subtypes based on their biology.

This allows us to identify biomarkers that drive our AI engines for target discovery, clinical trial optimization, and diagnostic development.

Find out more:

How does Owkin identify biomarkers from multimodal data?  [02:55]

Owkin’s solution

Our AI powered
orthogonal approach

Our orthogonal approach combines data from multiple modalities to fully understand the tumor microenvironment to define phenotypic subtypes.

Our biomarker models are built on high-quality patient data, carefully selected and verified by medical experts from our Federated Research Network.

These models have been designed to be interpretable by researchers and medical experts leading to a multiscale understanding of the disease.

What makes Owkin different?

Owkin’s orthogonal approach leverages multimodal patient data

Expertly validated

Owkin biomarkers are expertly validated by KOLs in our Federated Research Network and our internal medical team for critical medical context. 

Hypothesis free

Our models discover patterns in the data that are correlated with the predicted labels from scratch, without any help from medical experts. This means that the models’ predictions are exempt from any existing biases.


Our models are interpretable by nature so our medical experts can gain insights from the predictions the model has made and our data scientists can bring continuous improvement to the model's performance. 


Our models are multimodal so they capture the full picture of the patient’s disease heterogeneity.

Work with us

Case studies

“Historical approaches with precision medicine have been based on single biomarkers, mostly oncogene activation. Now with Owkin, we are moving to a more comprehensive and multimodal characterization, which is needed in the setting of innovative therapies such as immunotherapies.”
Prof. Nicolas Girard, MD, PhD
Head of Thorax Institute Curie Montsouris