As a species, we so far only understand a tiny fraction of all there is to learn on the subject, despite millions of incredible scientists having dedicated their lives to uncovering its truths. Unraveling the complexity of biology is a path to better medicines.
The emergence of radical technological innovations has created the opportunity to envision new approaches to discovering therapeutics more efficiently and at scale. We are pioneering the integration of these technological innovations across biology, chemistry, automation, data science, and engineering to modernize drug discovery and development.
Our integrated Recursion Operating System creates a closed-loop system combining proprietary in-house data generation and advanced computational tools to generate novel insights to initiate or accelerate therapeutic programs. We iterate on this approach to create a virtuous cycle of learning within our system and progress programs at each stage of discovery and pre-clinical development.
In silico predictions are validated in our own wet laboratories, and repeated, creating a mutually reinforcing cycle of learning. Predictions that validate experimentally are advanced rapidly and reinforce our learning. Predictions that do not validate experimentally generate valuable data that test our understanding and can be used to retrain or reweight the algorithms to improve future predictions. This iterative process of prediction and validation is a key element of successful machine learning over complex datasets.
Human bias is often a major threat to the drug discovery process. As humans, we are limited in the size and scale of data we can interpret and are prone to seeing the data that suits us and justifies our hypothesis. Our machine learning tools are designed to extract insights from foundational biological datasets that are too complex for human interpretation, minimizing human bias and identifying relationships that traditional drug discovery approaches may miss.
Since 2017, we have approximately doubled the capacity of our phenomics platform each year and scaled the total number of executed phenomic experiments to approximately 95 million, the size of its proprietary data universe to over 11 petabytes.
Our goal is to leverage technology to reshape the typical drug discovery funnel by:
Broadening the funnel of potential therapeutic starting points beyond hypothesized and human-biased targets
Rapidly narrowing the funnel by identifying failures earlier in the research cycle when they are relatively inexpensive
Accelerating the development of high potential drug candidates