Data-driven microbiome medicines for oncology
The outcomes
- Microbiome-based models help predict response to cancer immunotherapy.
- Insights directly inform the development of microbiome medicines to increase treatment efficacy.
The context
A biotechnology company develops and commercializes innovative microbiome medicines for patients with severe oncology diseases. One of its core objectives is to enhance patient response to immunotherapy by modifying the intestinal microbiota, a key driver of immune system performance. Euranova has been supporting this company for over three years across research and product development initiatives, with a shared goal: using data and advanced analytics to create therapies better adapted to targeted diseases.
The logic
Understanding and manipulating the microbiome requires working with high-dimensional biological data, limited patient cohorts, and strict scientific constraints. The biotech company needed robust data science approaches that could extract meaningful signals from sparse datasets—while remaining reliable enough to guide both clinical research and industrial production.
The solution
Euranova supported the biotech innovator across the full lifecycle, connecting microbiome research insights with scalable, production-ready solutions. In the field of research, the biotech company analyses patients’ microbiota using gene sequencing to characterize intestinal ecosystems. Euranova built predictive models leveraging this data to estimate the likelihood of a positive response to immunotherapy. By learning from cohorts of responders and non-responders, the models identify microbiota profiles linked to better outcomes—directly guiding the design of microbiome medicines. When it comes to production, microbiome medicines are complex ecosystems that must remain stable through successive mixing and fermentation steps. Euranova developed models to predict final ecosystem composition from input samples and, conversely, recommend the optimal inputs to reach a desired target state. These models were embedded into web applications used by production teams.
Next steps in applied excellence
Model efficiency is directly correlated with data fidelity. Adding external data sources will further increase predictive accuracy and operational robustness.