
AI target discovery
A new approach to target discovery
Owkin uses AI applied to multimodal patient data to find relevant targets and subgroups
Question
Why do current targets not convert to drugs?
- Patient data is underutilized
- Pre-clinical models lack translatability to human biology
- Disease heterogeneity is not captured
Owkin's solution
AI Target Discovery Engine
Owkin’s AI target discovery engine identifies novel candidate targets with associated patient subgroups by applying interpretable AI models to multimodal patient data and aggregating causal evidence from prior knowledge using large language models.
Input: multimodal data
Methodology
Click

1
to cluster patients based on multimodal patient data.
Patient subgroups with
distinct biology.
distinct biology.
Step 1
Data access
Gather, curate and prepare multimodal patient data
Click

2
to analyze inter/intra differential clinical and biological characteristics to define subgroups.
Characterised homogeneous subgroups.
Step 2
Patient characterization
Apply AI to multimodal patient data to characterize patients based on disease biology
Click

3
applied to regions of interest to predict which genes are associated with patient outcome, e.g. prognosis.
Ranked list of molecular markers/biomarkers.
Step 3
Target characterization
Apply AI to prior knowledge to characterize targets based on genetic and molecular features
Click

4
to assess the expression, essentiality, mutation status and target safety of candidate targets.
A ranked list of potential targets for the disease of interest.
Step 4
AI reasoning
Combine AI and human expertise to optimize and prioritize target-subgroup pairings
Testimonial
"I'm excited about the Sanofi and Owkin collaboration and its potential to transform drug discovery. Owkin's data network and AI capabilities combined with Sanofi's expertise, can potentially lead to new treatments and better patient outcomes."
Frank Nestle
Global Head of Research and Chief Scientific Officer, Sanofi
Subgroup discovery
Multimodal AI-powered biomarkers
We combine cutting-edge machine learning and biology to identify biomarkers.
Indication discovery
Matching the right drug and patient for better responses
For a given drug, we identify novel disease indications and subgroups for development, by aggregating causal evidence from prior knowledge and multimodal patient data.