🧠 “To build this genome-wide map, we had to create over 1 trillion neurons, roughly the equivalent of 12 human brains. There was no blueprint for this.” To truly study a disease, you have to work with cells that actually resemble it. In Part 1 of our new series breaking down our end-to-end platform, CEO Najat Khan shares the unprecedented engineering required to map biology at an industrial scale. Starting in 2021, we set out to grow human neurons at scale – executing systematic genome-wide perturbations, and capturing high-dimensional imaging. Using specialized proprietary protocols developed in partnership with Roche and Genentech, we kept these iPSC-derived neurons alive, consistent, and biologically representative. We are already seeing the impact of this work, with Genentech having optioned the first neuroscience target from the collaboration into a joint early discovery program. This is the foundation of high-dimensional target discovery. 🚀 Make sure to follow along over the coming weeks as we continue this series, covering how Recursion maps biology, optimizes precision drug design, and closes the gap between patient and discovery.

clinical medicine may be the largest biological experiment ever conducted, yet we still learn far too little from it. i explored this idea, and much more, with my close friend Najat Khan, PhD, CEO @RecursionPharma

In our newest episode of TechBio Talks, we explore how AI and clinical data are converging to reshape the future of medicine. CEO of Recursion, Najat Khan, PhD talks with Dr. Morgan Cheatham, Partner and Head of Healthcare and Life Sciences at Breyer Capital. As a physician, medical geneticist, and investor, Morgan brings a unique perspective, having spent nearly a decade backing category-defining companies spanning diagnostics, therapeutics, and care delivery. We unpack: 🚀How AI is reshaping the fundamentals of biotech value creation 💊Why “modality market fit” is crucial for matching treatments to patient tolerance 🔬Closing the loop between the wet lab, dry lab, and the clinic 🧬Recasting medicine as an information science to close the gap between discovery and care Listen and follow on: YouTube: piped.video/LmVszrLN0cg?si=5ZF_… Spotify: open.spotify.com/episode/6BE…

📣 Presenting updated Phase 1b/2 data on REC-4881 for familial adenomatous polyposis (FAP). Lisa Boardman, MD, a gastroenterologist at the @MayoClinic, will give a Presidential Plenary at the The Collaborative Group of the Americas on Inherited Gastrointestinal Cancer (@CGAIGC) Annual Meeting in Denver. On Nov. 2, 2:30pm, Dr. Boardman will present “Updated Safety And Efficacy Data Of REC-4881 Monotherapy In Familial Adenomatous Polyposis: Phase 1b/2 Trial Results Contextualized With Real-World Registry Data.” 👉 Learn more: cgaigcmeeting.org/wp-content…

🎙️Where AI is genuinely changing drug discovery and development — and where it isn't. Recursion CSO Dave Hallett joined Patrick Short, CEO of @SanoGenetics and host of The Genetics Podcast for a conversation on the real gains and remaining hurdles for AI drug discovery and development. Drawing on his nearly 30 year experience, beginning at Merck in the mid-1990s, Dave shared how AI has fundamentally changed what’s possible  – from research capabilities, to molecule design, to clinical trial planning – but noted that it still can’t change the laws of physics. 🔹Highlights include: ▪️How AI has allowed for true multi-parameter optimization Dave said the shift from single-parameter to true multi-parameter optimization is the biggest change he's seen at the bench. A person can hold roughly six or seven variables in their head at once, a computational system can track far more, without recency bias, across active learning loops. The result: "AI has massively compressed the time and the cost that's required to get from an idea to a candidate." Recursion has seen that show up as roughly 80% reductions in compounds made and 50-70% cuts to time-to-candidate on affected programs. ▪️Simulating trials before running them Rather than copying existing clinical trial protocols, Dave shared how Recursion pressure tests inclusion and exclusion criteria through simulation before a study launches — asking which criteria are actually still fit for purpose. Applied to REC-7735, evaluated in the ZINNIA trial, that process expanded the pool of patients the trial could reach by approximately 20%. ▪️Looking forward with pragmatism and optimism Dave was candid about AI’s limitations, too, noting that the industry is "still a long way" from modeling emergent human pathophysiology at the organism scale. He also discussed Recursion's partnership work on the breakthrough neuro map, and offered advice to early-career scientists: build deep domain expertise while remaining "bilingual" across biology, chemistry, and computation. 👉 Check out the full conversation: piped.video/watch?v=BD34s2h6…

🚀 From data factory to better drugs: inside Recursion's AI-native product engine In our new video, we take you behind the scenes of Recursion’s AI-native data factory and product engine – the first, and one of the largest, of its kind. 💠Capturing Cells AI Can Decipher It starts with perturbing cells via CRISPR and other compounds — dozens of methods at nano scale, generating up to 2 million experiments a week. Recursion’s labs are built to randomize experiments so models learn what's real biology versus noise. Cells are imaged and sequenced at scale, yielding thousands of measurements per experiment — high-dimensional data that trains our foundation models and can be mined again and again. 💠Creating Maps of Biology Our foundation models turn every perturbation — imaging, genetic, and patient data — into a unique fingerprint. Mapping these fingerprints lets us compare genetic manipulations, spot ones with similar effects, and generate new hypotheses for what drives or rescues a disease state. 💠De-Risking Discoveries & Designing New Drugs We validate hypotheses at the bench against the same high bar pharma partners hold themselves to. Each target becomes a chemistry problem, solved in Centaur — our integrated design environment running hundreds of ML and physics-based models. Starting from target properties, we generatively design novel molecules, improving with each cycle. A chemist can run a full design cycle in about a day, using tools like Nesso-1 and in-house AI agents to explore novel chemical space and plan design synthesis. Hundreds of models — ADME, potency, simulations — narrow millions of molecules to a short, makeable list. We’ve produced 10+ development candidates, and each held to that same high bar. 💠Synthesizing Compounds Compounds move directly into automated testing. Scientists describe an experiment in plain language and the platform generates the protocol, cutting pharmacology costs roughly in half compared to industry. Every result feeds back into the models, letting us reach a development candidate with about 90% fewer molecules synthesized than industry average — one closed loop, built to make fewer molecules, not more. 💠Carrying Insights Into the Clinic Clinical candidates enter our ClinTech platform. Our AI compares lab response data to real patient tumors to predict who benefits before enrollment even starts. Our Site Finder tool mines hundreds of millions of patient records to find high-quality trial sites in hours, improving enrollment 30–60% and slashing feasibility and startup timelines. Once running, a biometrics engine turns dose-escalation decisions that used to take 7–10 days into 24–48 hours. This is an end-to-end AI-native product engine that has already put multiple programs in the clinic and is changing the way medicines are made. 👉 Watch the full video: piped.video/watch?v=0T8MlHDr…

As AI in biopharma moves from theory to reality, what’s next? Recursion CEO Najat Khan will be a featured speaker at @Endpts AI Day on Oct. 14 in NYC and online, joining Senior Biopharma Correspondent and AI Day host @AndrewE_Dunn for “Endpoints Takes,” modeled after the internet talk show “Subway Takes” where biopharma leaders offer their most compelling takes on the industry. The theme of this year’s event is “AI in biopharma: no longer theoretical.” Join Najat and other leaders across biopharma, academia, frontier labs, and venture capital – including @nc_frey, Head of Drug Discovery and Development research at #Anthropic and Nobel Prize-winning professor David Baker – for engaging conversations about the future of the industry. 👉 Learn more and register: events.endpoints.news/aiday2…

🎉We won! Proud to announce that Recursion has won a @FiercePharma AI Innovation Award for AI Innovation in Drug Discovery. 💠 The award recognizes the impact of the Recursion OS which connects biology, design, and clinical development into a single AI product engine. They note that this engine is more than a collection of point solutions. “Instead of stitching together fragmented public datasets, Recursion generates its own proprietary data at industrial scale and feeds it directly back into the system.” As CEO Najat Khan says: “It enables our scientists to generate and test hypotheses at a scale and resolution that simply wasn’t possible before, uncovering novel biology and designing more precise medicines faster for patients who are waiting. And it has delivered tangible proof points – including multiple drugs advancing in our internal clinical and pre-clinical pipeline, and ongoing milestones for pharma partners.” Those proof points include REC-4881 for FAP (familial adenomatous polyposis). “REC-4881 marks the first potential treatment for the condition and the first clinical validation of the Recursion OS, backed by encouraging Phase 2 data,” they write. “The same platform also uncovered a novel mechanism for treating FAP – MEK 1/2 inhibition – and used real-world data to broaden patient eligibility for the trial.”  We’ll be presenting additional Phase 2 data from the TUPELO trial at the Collaborative Group of the Americas on Inherited Gastrointestinal Cancer (CGA-IGC) Annual Meeting in November. 🚀 We’re thrilled to have won this recognition from Fierce and look forward to continuing to demonstrate proof points from both partnerships and clinical programs. 👉 Read more: fiercepharma.com/ai-and-mach… #FierceAIInnovationAwards

Recursion CEO Najat Khan, PhD is speaking at the World Medical Innovation Forum in Boston on Sept. 23 as part of the panel “Riding the AI Tsunami: How Organizations Are Driving Cultural Change.” The Forum is presented by @MassGenBrigham and @BankofAmerica, and brings together global leaders across healthcare, life sciences, and investment to assess what’s advancing and what it takes to move innovation at speed and scale. 👉 Learn more and register here: 2026.worldmedicalinnovation.…

🎯Working on difficult-to-drug targets can feel like walking a tight rope through chemical space. At Recursion, we’re using AI agents to work alongside our scientists, and help us navigate that tight rope with precise steps. We’re making 97 billion predictions across 5.5 billion compound records traceable to the design runs that made them and the problem the designer was trying to solve. That gives future agents a playbook to follow. With automation and our BioHive-2 supercomputer, we run calculations proactively for each project compound. That ensures that our design agents have a rich context for interpreting experimental data. And agents don’t just give us predictions – but explanations. When a chemist asks how to improve potency, the agents identify an insight from a compound the team had set aside due to solubility issues. Then it explains why. The agent pulls in precomputed physics-based calculations to show that this gain isn't a new interaction. It's a conformational strain. that tells the team exactly how to redesign. Using AI agents in the chemical space, we’re moving faster. And as this drug design lab-in-the-loop cycle continues, we’re building up an immense catalog of design knowledge that agents are helping to unlock.

📣 In a new story in @GENbio, @AlexWestchester spoke with Recursion VP of Neuroscience Chris Winrow about the delivery of the first neuroscience target from our partnership with Genentech, which has now been validated and is advancing in a joint early-discovery program. Neuroscience is one of the toughest areas in drug development. More than 3 billion people live with neurological conditions, yet only 1 in 40 neuroscience drugs that reach the clinic are ever approved. To find new biology, the team built the first whole-genome CRISPR knockout map from over a trillion neurons derived from induced pluripotent stem cells — roughly 12 brains' worth of cells. “The cell context is important. We’re starting with human iPSCs and driving these into a very clearly homogenous population of neurons that we can test—and we do this at scale,” Winrow said. The screen spanned 17,000+ genes and thousands of small molecules, generating 46 million+ cellular images analyzed across hundreds of features (mitochondrial shape, nuclear morphology, and more) using AI foundation models and Recursion's BioHive-2 supercomputer. “You look for what we would call gene-compound interactions, to uncover some of those insights, at the same time as looking at the gene-gene interactions.” He added: “We’re looking at whole genome-wide knockout, not just a handful of areas or pathways of interest. That’s really a big game changer, in that we have this broad view.” he added. This and other maps developed in the partnership (including a whole-genome microglia map) will continue to be mined for additional programs. 👉 Read the full story: genengnews.com/topics/artifi…

A new generation of AI companies believes it can reduce the number of failed drug trials, by discovering entirely new biology. bloomberg.com/news/newslette…

🚀 How we unlocked the first neuroscience target for the Recursion and Genentech collaboration. The collaboration began with a mission to unlock new targets in one of medicine's most challenging therapeutic areas: neuroscience. Today, that work has reached an important milestone, with the first previously unexplored neuroscience target advancing into a joint early discovery program. In a new story from @fabiennekatrin in @business – and our latest blog – we share how the team developed new manufacturing processes to produce more than 1 trillion hiPSC-derived neuronal cells, systematically perturbed 17,000+ genes, captured 30 million+ cellular images, and built a foundation model to create an AI-enabled Map of Biology capable of surfacing unexplored biology in neuroscience. 🔹 What made this approach unique and what were the outcomes? ▪️We built disease-relevant human models with high-dimensional data, generating disease-relevant biology at unprecedented scale ▪️We explored the human genome at scale, identifying unexplored biology from our maps, reviewed and prioritized by scientists ▪️We navigated from known to unknown biology, developing a ranked list of potentially novel, biologically connected targets ▪️We validated experiments with Genentech, resulting in their decision to advance a target into an early discovery program 🎁 Read the Bloomberg story with this gift link: bloomberg.com/news/articles/… 👉 Check out the blog: recursion.com/news/unlocking…

Join us on Wednesday, August 5 at 8am ET / 6am MT / 1pm BST for our Q2 2026 Earnings Call where we'll provide business updates and report our second quarter 2026 financial results. nitter.net/i/broadcasts/1XxyggqLb… Questions may be submitted at: forms.gle/UGRGWTckLVJAq1sC6

Recursion will host its second quarter financial results and business updates in an Earnings Call on August 5, 2026 at 8:00 am ET / 6:00 am MT / 1:00 pm BST. Join the call on: ▪️LinkedIn: linkedin.com/company/recursi… ▪️YouTube: piped.video/@RecursionPharma ▪️X: nitter.net/RecursionPharma Analysts, investors, and the public have the opportunity to ask questions by submitting questions here: forms.gle/tcYtfHRL8KagYZQw9 👉More: ir.recursion.com/news-releas…

We’re improving clinical trials with AI before the first patient enrolls. A new article from Brian Buntz in @RandDWorld highlights the current roadblocks in clinical trials and how Recursion is improving the process with a data- and AI-driven approach. Today, protocols are on the rise, meaning more endpoints, procedures and eligibility rules. “The share of Phase 1 through 4 protocols requiring at least one amendment hit 76%, up from 57% in 2015,” the story notes. Through an expanded partnership with Norstella's @Citeline, Recursion is stress-testing protocols against real-world patient data before committing resources: mapping how each eligibility criterion changes who actually qualifies, catching when a protocol is "so scientifically perfect" it can't be operationalized, and simulating enrollment scenarios in real time. Since Recursion was built as an AI-first company, “you get to try different approaches,” says Sid Jain, SVP of Clinical Development. “What makes it really hard to deploy AI and technology is exactly that 20 or 30 years of legacy technology silos, which we frankly don’t have to deal with. We can design these systems for a very modern architecture and take advantage of the latest and greatest technology.” This ClinTech approach is delivering results in Recursion’s pipeline, including expanded eligibility criteria in our REC-4881 program, and beating historical enrollment projections by 30-60% in most clinical studies by identifying the right sites and countries from day one. We're not just discovering drugs differently. We're running trials differently — and it's translating into faster, smarter execution across our clinical pipeline. 👉 Read more: rdworldonline.com/recursion-…

📣 Presenting a new method for recognizing which tumors are most likely to benefit from dsRNA therapies. At @AACR Drug Discovery and Development (AACR D3), July 21-24 in Boston, Recursion will present the poster “Identifying actionable dsRNA biomarkers from sense-antisense transcript pairs,” a new computational approach for identifying which patients are more likely to benefit from dsRNA-inducing therapies or immunotherapy combinations. Some new cancer therapies work by increasing double-stranded RNA (dsRNA) inside tumor cells, a molecular pattern the body usually associates with viral infection. When dsRNA builds up, it can switch on antiviral immune pathways, drive cancer cell death, and strengthen anti-tumor immunity. The problem is measurement: dsRNA is hard to quantify with conventional approaches, where the signal is often noisy and the dynamic range is low, so drug-driven changes can be easy to miss. Recursion’s poster describes a computational pipeline that recovers this dsRNA signal from standard RNA sequencing (RNA-seq) data. The pipeline looks for sense-antisense transcript pairs, where two RNAs transcribed from overlapping regions on opposite DNA strands bind to each other to form dsRNA. To confirm which pairs genuinely form duplexes, researchers combined this with an experiment that sequences only dsRNA, isolating the pairs that truly bind together. With this filtering, targeting enzymes that regulate dsRNA produces rapid, dose-dependent increases in dsRNA that look flat in standard analyses. Across cell lines and models, there is repeated evidence of a conserved set of dsRNA-forming pairs. Scoring these pairs in patient tumor datasets highlights cohorts with elevated baseline dsRNA that may be more likely to benefit from dsRNA-inducing therapies or immunotherapy combinations. ▪️Abstract: Identifying actionable dsRNA biomarkers from sense-antisense transcript pairs ▪️Session: Poster Session A ▪️Session Date and Time: Wednesday, July 22, 6:15-8:45pm ET 👉 Learn more: aacr.org/meeting/aacr-d3-202…

🚀 A better, faster co-folding-based binding affinity model. Predicting how tightly a drug candidate binds to its target is critical in drug discovery. It also requires massive computational resources. State-of-the-art models can take 20 seconds to a minute per prediction, impractical for the demands of large scale early-stage programs . 💠 Today, Recursion’s @Valence_ai is releasing Nesso-1: the fastest open-source co-folding-based binding affinity model available. At 1 second per prediction, it’s roughly 20x faster than our previous collaboration on Boltz-2 while matching or surpassing its accuracy across public and internal benchmarks. By leveraging @NVIDIAHealth cuEquivariance, we’ve been able to further accelerate both training and inference by an additional 2-3x. We look forward to continuing to improve Nesso-1 in collaboration with @NVIDIA. Weights and code are fully open-sourced. The core architectural ideas behind Nesso-1 build on the insight that coarse-grained co-folding representations can match full-atom models for affinity prediction at a fraction of the cost. Nesso-1 is the first open implementation of this approach with no proprietary dependencies, trained entirely on public data, built to be reproducible and extensible. We’re already using Nesso-1 internally in active drug discovery programs. Fast, reliable affinity prediction at scale is foundational to the kind of autonomous design loops that define our vision for Autonomous Precision Design and Nesso-1 is a meaningful step toward that. 👉 Report: valencelabs.com/wp-content/u… 👉 Github: github.com/recursionpharma/n… 👉 HF: huggingface.co/recursionphar…