A data-driven approach to your Indication Selection process

Finding new indications for an existing therapeutic target is a common approach in drug development. Although seen as a risk-mitigating strategy, selecting the most appropriate indication to pursue raises many difficult challenges, including:

• With thousands of indications to consider; how do you compare them all and select the best ones?
  
• How to avoid literature bias and find indications with strong underlying biology but few or no literature references?
  
• How can you enable domain experts to evaluate indications in unknown therapeutic areas?

Euretos has collaborated with many leading pharma and biotech companies to address these challenges in indication selection. We have developed a unique, data-driven approach for discovering and assessing new indications that:

• Uses AI-driven computational disease models to discover novel indications with low literature bias.
  
• Provides an AI-integrated knowledge base to assess indications against biomolecular data bases, literature and patents.
  
• Empowers our client’s domain experts to undertake this assessment through access to the Euretos AI Platform.

This approach of finding novel indications using computational disease models that can subsequently be evaluated by the client’s domain experts in the Euretos AI Platform, significantly accelerates and de-risks the process of indication discovery and assessment.

Euretos uses AI-powered computational disease models that have been tried and tested in multiple projects with pharma and biotech companies. These models systematically evaluate gene-disease associations across the whole indication landscape by:

• Incorporating all indications for which genetic associations with the target of interest have been reported - for complex and monogenic diseases.
  
• Constructing the biological network of the target, based on co-expression, protein-protein interactions and pathway annotations.
  
• Leveraging this network to predict novel associations with indications for which there is no direct genetic association with the target of interest.

Having proven computational disease models and the target assessment environment already in place, we can significantly accelerate and de-risk the indication discovery and assessment process.

Find out how we help our clients in accelerating and de-risking their indication selection process: