Loading use case index…
Loading use case index…
AI use case
Recursion operates BioHive-2, one of pharma's most powerful supercomputers built with NVIDIA, ingesting more than 50 petabytes of high-quality multimodal phenomics, transcriptom…
Core facts from this catalog record. Primary narrative lives in the hero above; full raw fields follow in the next section.
Every column from the source row, in stable order. URLs open in a new tab.
Title
Recursion BioHive-2 Supercomputer: 50+ PB Biological Data for AI Drug Discovery at Scale
Content
Recursion Pharmaceuticals is a Salt Lake City-based TechBio company that uses AI and industrial-scale wet-lab automation to discover new medicines. The company frames the problem with a stark statistic: "In traditional drug discovery, 90% of drugs fail in clinical trials, after more than a decade in development and ~$2 billion in costs. We're changing the paradigm - leading with data, AI, and an industrialized approach to dramatically improve the cost, timeline, and probability of success of developing new medicines." Recursion's competitive advantage rests on three integrated assets. First, the company has generated and aggregated more than 50 petabytes of high-quality, multimodal data across phenomics, transcriptomics, proteomics, ADME (absorption, distribution, metabolism, excretion), and de-identified patient data. The scale and quality of this dataset is intended to give AI models a foundation that goes far beyond what is publicly available in biology. Second, the company operates BioHive-2, which Recursion describes as "one of the most powerful supercomputers in pharma," built in partnership with NVIDIA. BioHive-2 supports the training and inference of the large multimodal models that Recursion uses to predict how biological systems respond to chemical perturbations. The supercomputer is positioned at the intersection of Recursion's wet-lab data and its machine-learning stack, enabling high-throughput model experimentation. Third, the company operates automated wet-lab facilities that close the loop between AI prediction and physical experimentation. Robots run high-throughput biology experiments that produce the phenomics data feeding the AI, and the AI in turn proposes the next experiments to run. Recursion's pipeline focuses on oncology and rare diseases, with both preclinical and clinical-stage AI-enabled first-in-class and best-in-class assets. The company partners with major pharmaceutical companies on its platform, and operates in a competitive TechBio landscape that includes Insitro, Exscientia, Isomorphic Labs, and Schrödinger, plus pharmaceutical giants building internal AI capabilities. Looking ahead, Recursion plans to expand BioHive-2 capacity, deepen integrations with pharmaceutical partners, and advance its clinical pipeline candidates toward regulatory milestones as the company navigates the shift from AI-curiosity investor demand to clinical proof-of-concept requirements.
Continue exploring AI deployments in the catalog.
Back to use casesCity
Salt Lake City
Company/Organization
Recursion Pharmaceuticals
Continent
North America
Country
United States
Category
Biotechnology
Type
Deployment
Id
d355f8fb-9214-4d36-bda4-8aa874bd8d89
Created At
2026-06-30T11:11:41.302514+00:00