AI drug positioning

Matching the right drug and patient for better responses

We explore new drug uses by combining existing knowledge and multimodal patient data

Question

How do we match the right patient to the right drug?

By better understanding the drug mechanism of action in patient subpopulations through more complete knowledge of the tumor microenvironment and of clinical heterogeneity.

Owkin’s solution

Drug positioning engine

For a given drug, our engine identifies novel disease indications and subgroups for development, by aggregating causal evidence from prior knowledge and multimodal patient data.
Input: multimodal data plus known target of candidate drug
Clinical data
Histology
Omics
First-in-class clinical candidate
Failed asset
Marketed drug

Methodology

Click
Next
Step 1
1
Build knowledge graphs
to screen all diseases impacted by the target(s) in question.
Down
Outputs
Knowledge graph of target.
Step 1
Build knowledge graphs
To screen all diseases
Click
Next
Step 2
2
Apply advanced interpretable AI
to analyze knowledge graphs to select a short list of diseases impacted by the relevant mechanistic pathway of interest.
Down
Outputs
Ranked list of top disease indications impacted by the target(s) in question.
Step 2
Apply interpretable AI
To select impacted diseases
Click
Next
Step 3
3
Deep dive into indications
(Optional - indication specific)
To understand biological traits that impact the treatment response.
Down
Outputs
Key +/- regulators of treatment response, subgroups and/or potential combos.
Step 3
Deep dive into indications
To understand biological drivers

AI drug positioning

Why work with Owkin?

Experts at combining multiple data modalities

Expert team of biologists, medical experts and data scientists combine multiple data modalities to build quality knowledge graphs and disease maps.

Interpretable AI

Owkin knowledge graphs and specific disease maps are fully interpretable to identify key regulators and high/low responder subgroups.

Access to multimodal patient data and samples

Patient data helps to capture disease heterogeneity and the tumor microenvironment for a multiscale understanding of inter-patient response variability.

Get in touch

Subgroup discovery

Multimodal AI-powered biomarkers

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

Find out more

TargetMATCH

A new approach to target discovery

A suite of end-to-end tools that uses multimodal patient data as the input, and outputs the top candidate targets and paired patient subgroups that would most benefit from therapeutic intervention on these targets.

Find out more