Recursion OS: The Heart of Our Operations

Turning drug discovery into a search problem

Central to our mission is the Recursion Operating System (OS), an integrated, multi-faceted system for generating, analyzing and deriving insight from massive biological and chemical datasets to industrialize drug discovery composed of:

Infrastructure Layer of enabling hardware and software

The Recursion Data Universe, which houses our diverse and expansive datasets

The Recursion Map, a suite of proprietary discovery, design, and development tools

Combined, the Recursion OS enables us to explore foundational biology unconstrained by human bias, navigate to new biological insights, and rapidly accelerate programs. Our People & Culture transcend the entire OS as the fuel that brings it to life.


The foundational layer of the Recursion OS is a highly-synchronized network of enabling hardware and software used to design, execute, aggregate and store >23 petabytes of rapidly growing biological and chemical data. We built the core elements of our infrastructure based on cutting-edge technology created in the last several years and continue to adopt new technological advancements within each component.

The components of our infrastructure layer include:

Biological Tools

To build models of human disease and explore biology at scale, including: CRISPR gene editing, soluble factors, live viruses and more

Chemistry Tools

Including a library of ~1.7 million small molecules and on-going exploration into additional modalities (e.g. antibody, protein and RNA-based therapeutics)

Cell Culture

Including state-of-the-art facilities and equipment to culture, store and utilize massive quantities of diverse human cell types and patient-derived cell lines for discovery and validation experiments

Lab Robotics

Highly-scalable, automated laboratory robotics workflow that enables us to conduct up to 2.2 million experiments each week for up to 50 weeks per year

Data Capture

State-of-the-art hardware to capture high-dimensional, multimodal biological and chemical data from our experiments, including high-throughput microscopes, sequencing systems, and continuous video feeds from cameras embedded in custom animal study cages

Technology Stack

Highly scalable, advanced computational resources enabling us to move, store, process and secure ‘petabyte-scale’ data assets in both public and private cloud environments

Experiment Design

Enabling software tools that empower our scientists to design an increasing number of experiments each week and ensure data relatability across time

Experiment Execution and Quality Control

Enabling software tools to orchestrate the execution of up to 2.2 million experiments each week while simultaneously monitoring quality to maintain a productive flow of data

Our platform is robust, but what matters most is that it delivers for our own team.
Here’s what we’re generating from our platform:

Proprietary Dataset:

Recursion’s massive, proprietary dataset of human cellular images. Our dataset automatically aggregates over time ensuring that new questions and new hypotheses can be tested without having to conduct new experiments, increasing the speed of experimentation while also improving the quality of those hypotheses over time.

Learn more at


Unique mathematical identifiers or “blueprints” for cell states, disease models, and drug compound effects, that can be quantitatively compared and contrasted to other ‘prints to drive drug discovery insights.

Intelligence Reports:

Reports that expose novel insights about drug compounds, including both desired and undesired effects on human cells, and Phenoprint and structural similarities to other drug compounds.


We have discovered novel and repurposed drug compounds on our platform.

See our Pipeline for more.

Data-First Discovery

Data is central to everything we do. At Recursion, we validate the unbiased, data-first discoveries from our platform in gold-standard traditional wet lab settings. That information is then fed back into the platform for a virtuous cycle of continuous learning about both the biology and the platform itself.  

Data Universe

Our proprietary collection of highly relatable, high-dimensional biological and chemical datasets spanning multiple different data modalities. These different data sets are highly complementary as we advance drug discovery and development programs.

Recursion has a multi-omics technology stack


Cellular microscopy images that capture composite changes in cellular morphology


Scaled transcriptomic and proteomic datasets used to validate the activity of compounds and further elucidate the mechanism by which drug candidates may be acting

Bespoke One-Off Assays

Custom assays for program-specific validation

ADMET Assays

Large-format absorption, distribution, metabolism, excretion, and toxicology data that enable us to identify and predict early liabilities


Sensor data and continuous video feeds from cameras embedded in custom animal study cages and used to collect more holistic measurements of animal behavior and create abstract representations of in vivo disease states


A rapidly growing suite of in-house software applications designed to process and translate data from the Recursion Data Universe into actionable insights for our research and development teams to accelerate programs. These tools cover a broad set of uses including:

Data Processing

Tools to manage and monitor the streaming of data to the cloud at scale, transform our images into mathematical representations through our in-house proprietary convolutional neural networks, and perform standard and custom analyses

Biological and Chemical Activity Assessment

Scaled transcriptomic and proteomic datasets used to validate the activity of compounds and further elucidate the mechanism by which drug candidates may be acting

Program Insight

Tools that translate processed data into actionable insights, enabling us to infer trillions of relationships among biological and chemical perturbations

Program Acceleration

Tools that equip our teams with valuable information as they optimize therapeutic starting points into viable drug candidates, including in silico hit expansions based on 3D virtual screens and dense structure activity relationships as well as tools to augment in vivo experimentation

Program Insight in action

Central to this suite of tools is our PhenoMap, with which we can infer billions of relationships in silico among thousands of diverse biological perturbations, including CRISPR gene knockouts, soluble factors, viruses and hundreds of thousands of small molecules that have been screened on our platform. These relationships can be used to inform novel drug targets or early therapeutic compounds to start new discovery programs.

Recursion's Maps of Biology

Program Acceleration in action

Scaffold Shopper can compare candidate compounds identified by our platform to over 12 billion ready-to-synthesize and off-the-shelf molecules based on our 3D chemical functionality and shape-based similarities, within a matter of minutes and at low computational expense.

Recursion's digital chemistry tools

By applying the Recursion OS to drug discovery, Recursion expects to turn drug discovery from sequential trial-and-error into a search problem.