Think of it as industrialized drug discovery.
We combine artificial intelligence and machine learning with automation and wet lab validation to conduct experimental biology at unprecedented scale — conducting more than 800,000 experiments every week. Our embrace of high-throughput biology and commitment to a target-agnostic approach are generating novel discoveries. With every experiment, our system gets smarter.
We’re using technology to accelerate every step in drug discovery.
We’ve built the world’s largest dataset of biological images, fit for the purpose of machine learning. We’re training our algorithms on this data to reveal drug candidates, mechanisms of action, novel chemistry, and potential toxicity, to discover new, transformative treatments for patients.
“Deep learning has recently proven capable of driving cars, beating the world champion of the game of Go, translating from one language to another and recognizing faces dramatically better than any previous efforts to date. Recursion is taking this success and applying it to millions of high-resolution cellular images, with a high potential to make biological discoveries with a medical impact and breadth never seen before.”
Recursion Scientific Advisor
Our investors
The latest news
Articles and Press Releases
12.23.19
In good companies
Co-Founder and CEO Chris Gibson, PhD, shares news about our strategy to spin-out our first subsidiary to shepherd our lead clinical-stage asset for Neurofibromatosis Type 2 (NF2).
11.21.19
Recursion Building Onsite Childcare Facility to Support Working Parents
High-tech biopharma company partnering with childcare leader, Bright Horizons, to ensure working parents have the support they need to achieve their family and career ambitions
11.09.19
Gormley’s Take: Biotech and Tech VCs Have Different Views on AI-Based Drug Discovery
Two recent commentaries by biotechnology industry insiders highlighted a divide among venture capitalists: those who see artificial intelligence powering a revolution in drug discovery, and those who don’t.
