3 key ingredients: data, models, and compute

Over the last decade, we have built one of the largest fit-for-purpose proprietary biological and chemical datasets in the world — 65 petabytes spanning phenomics, transcriptomics, InVivomics, proteomics, ADME, and de-identified patient data. Our automated wet lab utilizes robotics and computer vision to capture millions of cell experiments per week — enabling us to quickly make and test novel discoveries. All of our results feed back into our drug discovery and drug development platform – the Recursion Operating System – in a continuously improving feedback loop.

Our data and the Recursion OS enable us to train intelligent machine learning models for AI drug discovery and development, which help us rapidly identify new targets and design highly optimized molecules that fuel our pipeline of potential first-in-class and best-in-class medicines.

To process all this data, we worked with NVIDIA to build biopharma’s most powerful supercomputer: BioHive-2.