Data-Driven Target Selection

Enabling a data-driven, actionable approach to target discovery, indication expansion and target assessment



Maximise preclinical confidence in target efficacy and safety

With over 70% of failures in the clinical stage attributed to the choice of drug target, preclinical target selection is the most impactful step in drug development. We collaborate with biopharma companies to address this issue by establishing a data-driven, actionable target selection process that maximizes preclinical confidence in target efficacy and safety.

Novel data-driven target insights
Customized data integration
Tailored to your evaluation criteria
Structured and repeatable target assessment process
Enabling data-driven target selection for world leading pharma and biotech companies
Janssen and Janssen Pharmaceutical Companies
Leiden Academic Centre for Drug Research
Astra Zeneca
Boehringer Ingelheim
Tufts University
Biological Knowledge Graph

Harmonized data, available across the target selection process

The basis for data-driven target selection is to make data available across the target selection process with full traceability to sources.We provide biological knowledge graphs that semantically harmonize public and proprietary data, literature and patents. We customize these to create client-specific knowledge graphs with domain specific and/or proprietary data.

H._Lundbeck_A_S_Logo"We worked with Euretos to leverage their AI capabilities with the aim of finding new targets in two different indications. It was a real pleasure to work with them and the whole process was characterized by transparency, their willingness to listen to our needs and suggestions, and swift responses and data delivery. In addition, we found their platform very useful for getting an overview of the different targets and for general queries."


Tau Benned-Jensen, Senior Research Scientist, H. Lundbeck A/S

Computational Disease Models

Novel target biology insights that drive discovery & assessment

Euretos' predictive computational disease models predict novel targets and provide insights in the underlying disease biology. Our machine learning models are driven by multi-omics data minimizing publication bias. We integrate predictions from different types of multi-omics networks to provide biological insight. We retrain our models on custom data to give unique client-specific predictions
Collaborative Target Assessment

A structured and repeatable target assessment process

Our interdisciplinary science team collaborates closely to determine and implement client-specific target assessment criteria. When required, domain specific and/or proprietary data will be added to the knowledge graph. The data can then be queried directly and results are visualized and fine-tuned to empower biological researchers to effectively evaluate targets. This enables our clients to embed target assessment as a repeatable, structured process driven by their evaluation criteria.


This ebook covers the following:

-How computational disease models predict novel gene-disease associations.
-A case study: Target Discovery for Rheumatoid Arthritis
-The benefits of using an AI-integrated knowledge graph for target assessment

SCIENTISTcomlogo     We support purchasing via and science exchange!     Science_Exchange_logo


Enabling data-driven target selection for world leading pharma and biotech companies
Logo Daiichi Sankyo
Logo EMC-1
Logo Sanofi-1
Logo LUMC-1

Data-driven disease insights

Contact Us