Decoding biology demands a bold approach

AI Enabled Drug Discovery and Development, at scale

explore our pipeline

AI Enabled Drug Discovery and Development, at scale

explore our pipeline

Recursion's TechBio approach: The future of AI drug discovery

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 — because patients are waiting.

Recursion’s competitive advantage

A robust pipeline of AI-enabled first-in-class & best-in-class assets

Our advanced preclinical and clinical-stage programs are focused on areas of high unmet need across oncology and rare diseases.

View our pipeline

65 petabytes of proprietary, fit-for-purpose data

We’ve amassed one of the world’s largest relatable biological and chemical datasets across phenomics, transcriptomics, proteomics, InVivomics, ADME, and de-identified patient data.

Our unique approach

BioHive-2, the most powerful supercomputer in pharma

Built in partnership with NVIDIA, BioHive-2 ranks as the 54th most powerful supercomputer by the Top 500 list in 2024.

Our platform

Leading industry partners

We are leveraging partnerships with Big Pharmas and leading tech companies to expand our therapeutic reach, scale and improve our AI platform, and drive new discoveries.

How we collaborate

Data is the differentiator… and scale matters

Unlike traditional drug discovery, which begins with a specific target or hypothesis, we leverage the Recursion OS — our platform of interconnected technical and scientific tools spanning physical experimentation to in silico analysis. This platform, along with 65 petabytes of fit-for-purpose data, allows us to train machine learning models that can help us identify promising new targets and design highly optimized molecules that will become potential first-in-class and best-in-class medicines. Combined with hundreds of thousands of de-identified patient records from our partners Tempus and Helix, all of these data layers are connected in the Recursion OS, which is continuously learning and improving in a “virtuous cycle” feedback loop.

Learn how we generate data

Faster discovery, better medicines

Instead of evaluating a few programs over years to find a “hit,” our system allows us to evaluate hundreds of potential programs, and quickly funnel those into the most promising opportunities. We then use our precision chemistry platform to design the best chemical compounds for synthesis in our automated lab. With this system, we’re able to identify hit candidates in weeks, instead of years, and for thousands of dollars as opposed to millions.

Explore our pipeline
© 2025 Recursion. All rights reserved.