We are the only company with a massive dataset of biological images generated entirely in-house on our platform and fit for the purpose of machine learning. A robust and relatable dataset built for machine learning is critical to our ability to derive new algorithms and generate new discoveries. Today we’ve imaged more than 27 billion human cells and generated more than 4 petabytes of biological data… making it the world’s largest dataset of its kind.
Elegant, efficient, and effective design is at the heart of everything we do. Our experimental biologists sit side-by-side with data scientists to design massively parallel screening protocols. Then we carefully choose each experimental parameter to unlock the maximum data from our cellular image datasets, elucidate new biology in an unbiased fashion, and continue to build the world’s largest exquisitely curated repository of biological images.
Armed with state-of-the-art experimental protocols, our high-throughput screening (HTS) team generates hundreds of thousands of cellular images every week, transferring each one to the cloud in real-time. Our proprietary software leverages the power of computer vision and classic machine learning alongside neural networks to analyze terabytes of this data every week. At the same time, our custom software and utilization of cloud-computing power enable the scalable management and analysis of our image sets.
Our entirely automated approach to experiment execution and data analysis enables us to achieve the industrialization of discovery biology—screening thousands of compounds against hundreds of disease models at a fraction of the cost and in a fraction of the time of other discovery approaches.
We collect massive amounts of data alongside rigorously defined control and test variations to yield rich biological discoveries each week. Our platform performs large-scale analytics and artificial intelligence model training on the characteristics of hundreds of cellular phenotypes across biology to develop computational “fingerprints,” or Phenoprints™, of a wide variety of biological perturbations. We analyze images from over 10 million cells per week, and add these to our database of more than 2.5 petabytes of biological images.
We’ve used these massive datasets to construct an industry-leading portfolio of high-value cellular models that provide insight into hundreds of monogenic loss-of-function diseases, fibrosis, inflammatory and immunological diseases, efficacy and toxicity scoring, dose-response characteristics, and target discovery and prediction. Our design rigor and scalable platform generate large numbers of high-quality lead candidates from our internal drug library and our partners’ libraries, as well as biological insights that contribute to quickly de-risk discovery programs.
We're already making clinical-stage progress
Recursion offers several partnership opportunities
The Vision Revealed Over Time
The true power of our platform continues to be revealed over time. Every experiment we conduct each week adds to our discovery dataset in a way that’s highly consistent and relatable. By continually expanding this dataset, we’re building a comprehensive database mapping the effects of tens of millions of genetic, chemical, and other biological perturbations on many cell types relevant to human disease. This will enable us to model more complex biological processes, integrate different modalities, and begin to predict fruitful areas of scientific research with minimal de novo experimentation.
As we keep leveraging technology to dramatically decrease the cost and increase the efficiency of biological research, these advances will enable us to realize our ultimate vision of building a map of human cellular biology.