ClickCease

Frequently Asked Questions

Recursion Key Information

What is Recursion?

|
|

Recursion Pharmaceuticals is a leading clinical-stage company pioneering AI-enabled drug discovery and development decoding biology to radically improve lives. Recursion is advancing a portfolio of differentiated investigational medicines across its wholly owned and partnered pipeline in oncology, rare disease, neuroscience, immunology, and other therapeutic areas with significant unmet need. Enabling its mission is the Recursion OS, an AI-native, end-to-end drug discovery and development platform integrating biology, chemistry, and clinical development into a unified intelligence system. Powered by proprietary multimodal data, purpose-built AI models, and bilingual teams fluent in both science and AI, the Recursion OS is designed to translate complex science into medicines that matter — faster, better, and at scale — for patients who are waiting. ‍

Read more about our mission

Who is Recursion’s CEO?

|
|

Recursion’s CEO and President is Najat Khan, Ph.D.

Who founded Recursion?

|
|

Recursion was founded by Blake Borgeson, Ph.D., Chris Gibson, Ph.D., and Dean Li, M.D., Ph.D.

When was Recursion founded?

|
|

November 5, 2013

What is Recursion’s mission?

|
|

Recursion’s mission is to decode biology to radically improve lives.

Where is Recursion’s headquarters?

|
|

Salt Lake City, Utah

Recursion Clinical Pipeline and Therapeutic Areas

What are Recursion’s clinical-stage programs?

|
|

Recursion’s clinical stage programs span oncology and rare disease:

  • Oncology: 
    • REC-1245: An RBM39 degrader being developed for the treatment of solid tumors and lymphoma, with multiple biomarkers being explored.
    • REC-617: A CDK7 inhibitor being developed for the treatment of multiple advanced solid tumor indications.
    • REC-4539: A LSD1 inhibitor being developed for the treatment of multiple solid tumor and hematology indications.
    • REC-3565: A MALT1 inhibitor being developed for multiple hematology indications.
    • REC-7735: A PI3Kα H1047R inhibitor being developed for the treatment of multiple solid tumor indications
  • Rare disease:
    • REC-4881: A MEK1/2 inhibitor being developed to treat familial adenomatous polyposis (FAP).

For more detailed information on each program, please visit our pipeline page.

How can patients get involved in Recursion clinical trials?

|
|

Information on ongoing Recursion clinical trials and their locations can be found on our clinical trials page and clinicaltrials.gov

‍

Does Recursion work on rare disease drug discovery?

|
|

Yes - Recursion focuses on diseases where there is a high unmet need, including rare diseases and oncology. For rare diseases, Recursion has a clinical-stage program in familial adenomatous polyposis (FAP) and a preclinical stage program in hypophosphatasia. ‍

See our full pipeline

Does Recursion work on cancer drug discovery?

|
|

Yes - Recursion focuses on diseases where there is a high unmet need, including oncology and rare diseases. Recursion has multiple clinical stage and preclinical stage oncology programs ongoing, across solid tumors and blood cancers. ‍

See our full pipeline

Does Recursion work on any other therapeutic areas and indications in drug discovery, outside of oncology and rare disease?

|
|

Yes - alongside our fully owned portfolio, we partner with leading biopharmaceutical companies to discover and develop potential new medicines in oncology as well as neuroscience, immunology, and other therapeutic areas with high unmet need.

Visit our Partners page

Recursion Partnerships

Who does Recursion partner with?

|
|

Recursion collaborates with leading biopharmaceutical and technology companies to broadly explore diverse disease domains and rapidly identify novel therapeutic candidates via AI. Our partners fit into two main categories:

Therapeutic Partners: 

  • Bayer Pharmaceuticals
  • Roche and Genentech
  • Sanofi
  • Merck KGaA, Darmstadt, Germany
  • The Gates Foundation

Data, Technology, and Capability Partners: 

  • NVIDIA
  • Google Cloud
  • Helix
  • Tempus

Visit our Partners page

Recursion Technologies

What is Recursion’s AI-native product engine?

|
|

Recursion’s AI-native product engine is an end-to-end continuous learning system for drug discovery and development. It seamlessly connects physical experimentation in our automated wet labs with computational analysis powered by supercomputing and foundation models.

By operating as a closed loop, with every lab experiment strengthening our AI models, every model informing the next experiment, and every cycle deepening our understanding of human biology, the engine systematically maps disease biology, precision-designs differentiated molecules, and optimizes clinical development to bring better medicines to patients faster.

Watch our Video to Learn More About Recursion’s AI-Native Product Engine

How is Recursion different from competitors?

|
|

Recursion’s core competitive advantage lies in our end-to-end, AI-native continuous learning system. Unlike competitors that rely on single-point tools or traditional hypothesis-driven research, our integrated platform connects automated data generation, supercomputing, generative chemistry, and clinical development into one closed loop. This closed-loop system turns drug discovery and development into a repeatable, data-driven process, allowing us to consistently translate complex science into clinical-stage investigational medicines at a fraction of traditional timelines.

Watch Recursion’s CEO Najat Khan discuss her vision for AI translation and platform progress.

How does Recursion’s approach differ from traditional pharmaceutical R&D?

|
|

Recursion employs an AI-native strategy, replacing slow, manual, hypothesis-driven research. We use our integrated, end-to-end engine—which connects automated AI-native data factories and supercompute-powered AI/machine learning foundation models—to rapidly and in an unbiased manner discover potential new medicines at an unprecedented scale, achieving speeds up to 3X faster than traditional industry averages.

How does Recursion use AI, and what data powers it?

|
|

Recursion applies AI/ML across the entire drug discovery and development workflow through three core interconnected pillars:

  • Biology: Generates high-resolution Maps of Biology by combining high-dimensional experimental data (such as genome-wide phenomics and single-cell transcriptomics) with causal AI models to uncover novel disease mechanisms and identify true causal targets.
  • Precision Design: Combines generative AI with physics-based modeling in a synthesis-aware design-make-test-learn (DMTL) loop to iteratively create and test novel molecules, rapidly advancing candidates while synthesizing significantly fewer physical compounds.
  • ClinTech: Translates laboratory insights into clinical success by applying predictive models (like Cardinal) to pair drug responders with real-world patient data, and leveraging AI tools (like Site Finder) to optimize trial design, site selection, and enrollment.

This capabilities stack is powered by three core pillars of infrastructure:

  • Massive, Fit-for-Purpose Data: A hybrid data model pairing high-throughput proprietary data from automated wet labs with real-world clinical and multi-omic data from partners like Tempus, Helix, and HealthVerity.
  • Powerful Compute: Our BioHive-2 supercomputer, one of the most powerful supercomputers in the biopharmaceutical industry, trains state-of-the-art foundation models and iterates on our predictive biological and chemical models.
  • World-Class Talent: A "bilingual" team of life scientists and technologists integrating data, compute, and disease biology across every step of the platform.

What is a map of biology?

|
|

Maps of Biology are comprehensive, searchable digital representations of human biological systems created by our AI-native Data Factories.

Instead of relying on single, narrow hypotheses, Recursion builds these high-dimensional maps at an unprecedented scale:

  • Generating Cell Models at Scale: We grow and differentiate disease-relevant human cells using specialized proprietary protocols, overcoming batch-to-batch variability to produce scale equivalent to billions of functional cells.
  • Systematic Manipulation & Measurement: We systematically generate and integrate large-scale experimental data—including gene knockouts, compound perturbations, and multi-omic measurements (such as high-dimensional imaging and cellular sequencing)—manipulating cells up to 2 million times per week using acoustic liquid handling to capture thousands of data points from every experiment.
  • AI Embeddings on BioHive-2: These massive datasets are processed by state-of-the-art foundation models trained on our BioHive-2 supercomputer to create unique biological "fingerprints" for every cellular state and genetic perturbation.

How does Recursion use maps of biology for novel target discovery?

|
|

By comparing the fingerprints of disease-causing mutations against millions of other genetic manipulations on our maps, our AI models identify non-obvious genetic perturbations that mimic or rescue disease states. This uncovers novel, causal biological targets and pathways beyond traditional research—which are then sent directly back to our labs for experimental validation.

Because this high-dimensional data is so rich, our maps of biology are reusable, allowing us to re-mine the same datasets to generate multiple hypotheses across programs over time.

How does Recursion use AI and automation for precision design?

|
|

Recursion transforms chemical design from a slow, trial-and-error process into an automated, closed-loop engineering discipline. By unifying computational molecular design with automated wet-lab synthesis and testing into an integrated Design-Make-Test-Learn (DMTL) cycle, we eliminate the traditional disconnect between prediction and physical chemistry.

Through our design engine, we evaluate complex multi-parameter profiles simultaneously—balancing potency, ADME properties, 3D binding structures, toxicity, and synthesis feasibility using predictive machine learning models. Our computational algorithms prioritize structures that are synthetically accessible before sending them to the lab, ensuring chemistry resources focus only on molecules with high likelihoods of success. These designs flow directly into automated synthesis platforms and testing assays with digital tracking across every reaction step. Because every physical test result immediately feeds back into our computational models, the underlying predictive system continuously sharpens its calculations for subsequent iterations.

This integration accelerates timelines, cutting time to delivering a candidate down from an industry benchmark of roughly 42 months to approximately 17 months. By coupling synthesis-aware computation with data-driven physical testing, Recursion reaches quality clinical-stage candidates after synthesizing only around 300 physical compounds. This represents roughly 90% fewer molecules than the traditional pharmaceutical industry average of ~5,000 compounds per program.

What is ClinTech?

|
|

ClinTech is Recursion's approach to applying AI and technology across clinical research, extending our industrialized platform beyond initial discovery and directly into human trials. The strategy is built on three key pillars:

  • Optimizing Trial Design & Patient Matching: Using predictive AI models like Cardinal to bridge laboratory findings with real patients. Cardinal compares cellular responses observed in the lab against thousands of real patient tumors to identify matching biological profiles, ensuring trials enroll the patient populations most likely to benefit.
  • Streamlining Trial Execution: Leveraging technology like Site Finder—which draws on real-world data from over 300 million patient records and hundreds of thousands of trial sites globally—to evaluate feasibility in hours instead of months and improve enrollment rates by 30% to 60%.
  • Improving Evidence Generation: Applying machine learning to integrate high-dimensional clinical and real-world datasets, accelerating trial startup timelines and generating robust, regulatory-compliant evidence to bring medicines to patients faster.

This overall approach aims to improve the speed and efficiency of bringing new therapies to patients.

Are any of Recursion’s data or models available publicly?

|
|

Yes. Recursion is committed to advancing science through open-sourcing data and models for non-commercial use. Our current public offerings include:

  • Datasets: Six large-scale open-source datasets (Rxrx1, Rxrx2, Rxrx19a, Rxrx19b, Rxrx3, and Rxrx3-core). Note: These represent less than 1% of Recursion’s full, proprietary dataset.
  • OpenPhenom-S/16 model: A foundation model available on Google Cloud’s Model Garden and on HuggingFace.
  • Boltz-2 Model: Developed with MIT, this is an open-source model that combines structure and binding affinity prediction. It approaches the accuracy of physics-based free energy perturbation (FEP) calculations while being over 1,000 times faster and less computationally expensive. We also released a related open-source SynFlowNet-Boltz trainer, enabling researchers to to find diverse, synthesizable, high-affinity binders.

You can explore Recursion’s open source data and models at rxrx.ai

General Scientific/Technological Information

What is TechBio?

|
|

TechBio is an evolution of the life sciences focused on leveraging advanced technologies like artificial intelligence, machine learning, engineering and automation to understand biology at a systems level to discover new medicines. It relies on the creation of large, robust, highly structured biological and chemical datasets to fuel advanced computational models that can reveal subtle patterns that humans alone might miss. TechBio companies have data, compute and AI models at their core, enabling a new era of data-driven and unbiased drug discovery. 

We believe TechBio companies will create step-function shifts in the healthcare industry. Recursion is both leading this new sector, and working hard to help define it.

What is the difference between TechBio and traditional biotech?

|
|

The difference lies in the strategic starting point and technological core. Traditional biotech begins with a therapeutic hypothesis developed around a simplified view of disease biology, relying on serial, human-intensive lab work. TechBio, conversely, starts with massive, scaled data generation and supercomputing power to train AI models and identify patterns humans can’t see. This industrialized approach enables companies like Recursion to move beyond limited hypotheses and understand complex biology at a systems level, leading to data-driven, unbiased drug discovery with vastly accelerated speed and scale.

What is Phenomics?

|
|

Phenomics measures the morphology (shape and structure) of cultured cells grown in laboratory plates. Morphology is a holistic readout that integrates changes from underlying layers of cell biology—such as gene expression and protein modification—into a single, powerful measure of cellular state.

Phenomics forms the backbone of Recursion’s Maps of Biology by enabling the platform to:

  • Identify and analyze biological and chemical relationships.
  • Inform on potential pathway biology (e.g., mechanism of action).
  • Detect off-target liabilities (unintended drug effects).

What is Transcriptomics?

|
|

Transcriptomics is a high-dimensional measure of cellular biology, distinct from phenomics, that assesses gene expression by measuring RNA levels in the cell.

As a crucial complementary data layer, Recursion uses high-throughput transcriptomics platforms to generate massive amounts of data on chemically or genetically perturbed cells. This non-image-based data is combined with other modalities to:

  • Provide confirmation of biological changes detected by the platform.
  • Validate hypotheses derived from the predictive AI models.
© 2026 Recursion. All rights reserved.