FranceHealthcare and life sciences2025 – ongoingPhagos
AI selection of bacteriophages for personalized treatments
Phagos needed 50% fewer wet-lab tests after using AI to select bacteriophages
Problem
Matching bacteria with suitable bacteriophages required extensive laboratory screening. Testing every possible combination manually was impractical.
Approach
Phagos trained models on genomic and laboratory data using Amazon SageMaker AI. In production, its scientists sequenced incoming bacterial samples and used model predictions to select phages for laboratory testing.
Results
Takeaway
AI narrowed Phagos's experimental workload before laboratory validation. The company still tested candidate treatments in the wet lab.
Categories
- Size
- Small business
- Industry
- Healthcare and life sciences
- Business function
- IT and R&D
- Innovation type
- Process innovation
- AI technology
- Generative AI
- Adoption
- Built in-house
- Evidence
- Vendor case study
Sources
Source summaries
AWS described Phagos's production use of models to predict phage-bacteria interactions. It reported that these predictions reduced required wet-lab tests by 50%. The page carries no date; the Internet Archive first saved it on December 11, 2025.
Full details are in the original sources.
