Basecamp Research built a genomic data pipeline on Azure to train its EDEN foundation models.
Basecamp had to process 9.7 trillion nucleotides from 1 million newly sequenced species, with unpredictable data flows from field teams and infrastructure scaling about 10X a year. It built a pipeline on Azure Kubernetes Service, Container Registry, Blob Storage, Files and Azure Machine Learning Studio. The page reports EDEN-designed recombinases covering 100% of disease-relevant target sites, 97% lab-confirmed success for antimicrobial peptides, and 9,000 generated bacterial species at 99% biological accuracy.
Basecamp Research is a London and Boston biology AI company that trains EDEN foundation models on proprietary evolutionary genomic data for therapeutic and enzyme design.
This sits in the Build stage of the AI use-case lifecycle: Named examples from the foundation-model labs and platforms pharma teams use to actually construct, train and generate the model or application.
Published by Basecamp Research on its own site — read the original case study on microsoft.com ↗
Note: Page is Microsoft's customer story, not Basecamp's own site.
Related use cases
- 01Basecamp Research raised $140M and set out an EDEN-designed therapeutic pipeline.
- 02Basecamp Research and P&G partnered to design cold-water laundry enzymes with AI.
- 03OpenAI's dedicated healthcare vertical page/launch post.
- 04Frontier reasoning model built for biology, drug discovery and translational medicine; named qualified customers include Amgen, Moderna, Allen Institute, and Thermo Fisher Scientific.
- 05follow-up update to the life-sciences model.
- 06"How Amgen uses GPT-5": Amgen applies GPT-5/frontier models to help accelerate delivery of potential new therapies; found GPT-5 met scientific-accuracy standards.