Recursion

💡 New computational tools are lowering the barrier to entry for drug discovery – but data is still the differentiator. A new story from David Wild in In Vivo looks at how computational tools are making drug discovery accessible to a much broader population – and even high school students are designing promising new molecules. Interviewed for the piece, Recursion CTO @BMabey noted that powerful structure-prediction models are now widely accessible. “Some of these models would have been groundbreaking ten years ago. Now anyone can download them.” At the same time, he underscores that the hardest problems still depend on proprietary, large-scale datasets — especially in phenotypic screening, where Recursion’s high-content imaging and foundation models like OpenPhenom require massive, purpose-built data to uncover novel biology. Ben draws a sharp distinction between open models and closed data: “You’re seeing less of the data being made available, because that’s where a lot of the value is. Companies are far more protective of the data, because that’s where the therapeutic insights are going to be found.” At Recursion, we’re excited about how democratized tools will bring more ideas and talent into drug discovery — and we remain focused on generating the rich experimental datasets needed to turn those ideas into transformational medicines. 👉 Read the article: insights.citeline.com/in-vivo/innova… @Citeline

🚀 Reshaping drug discovery – and the future of medicine – with AI. Recursion CFO Ben Taylor joined the Opto Sessions podcast from @CMC_Aureon to share how Recursion uses AI, lab automation, biological data, and machine learning to improve the way new medicines are discovered and developed. 💠 They discuss: ▪️How pairing AI with lab automation across biology, chemistry, and clinical technology allows us to move beyond the ~10–12% of the genome currently addressed by approved or in-trial medicines and explore the vast realm of untapped biology. ▪️How Recursion is advancing REC-4881 for patients with familial adenomatous polyposis (FAP) — a progressive condition with no approved medical therapies — after achieving Phase 2 proof-of-concept and demonstrating meaningful reductions in polyp burden. ▪️How Recursion is compressing timelines and improving efficiency with high-quality, ML-ready data to design better molecules with ~90% fewer experimental chemistries and to run smarter, faster clinical trials. 👉 Check out the full conversation: youtube.com/watch?v=XF__xw…

Our bodies’ molecules aren’t static so why do many AI models treat them that way? Without considering the physical movement of molecules, many AI tools fail to robustly capture what makes drug candidates promising. AquaGen is a generative AI framework built to close that gap: an all-atom, explicit-solvent model that runs an order of magnitude faster than traditional MD methods. We’re excited about the implications of this work on early-stage drug discovery. Technical report and blog below.

📈 Toward safer, faster, first-in-human studies. Recursion’s clinical development and biometrics teams are rethinking how early-phase trials run in practice — starting with how quickly dose-escalation decisions get made. A case study from @posit_pbc highlights Recursion’s ClinTech advances – including turning around dose-escalation reviews in just 24-48 hours compared to previous rates of 7-10 business days — a 7x faster data-to-decision cycle. Instead of PDF snapshots, investigators and medical monitors now have governed self-service access to live trial data: cohort-level overviews, patient-level safety signals, and targeted visualizations designed around the questions they most need to answer. This is bringing new efficiency to how we run clinical trials and laying the foundation for the next phase: AI-enabled clinical workflows that can support the FDA’s vision for real-time clinical trials. 👉 Read more: posit.co/about/customer…

🤖 Automated labs will be a driving force in the AI drug discovery era. A new story from @patrickcsisson for @sciam looks at how automated labs are adding new speed and efficiency to drug discovery and development. Recursion, he notes, is bringing “industrial scale” to lab automation, running up to 2.2 million experiments a week and processing “more than 50 petabytes of proprietary data through BioHive-2, its in-house supercomputer” using that data “to map biological processes and search for unexpected drug targets.” The story cites Recursion VP of Neuroscience, Christopher Winrow, who shares how Recursion has used automated labs to develop both an in-house clinical-stage pipeline and “large-scale cellular maps, using models of neurons and microglia” with pharma partners. The story notes: “The rest of the pharmaceutical industry is moving in the same direction” in its effort to bring down costs and improve success rates of new therapeutics. 👉 Read more: scientificamerican.com/article/autono…

For FAP Awareness Week, we want to highlight one of the strongest advocates in the space. Living with the rare disease familial adenomatous polyposis (FAP) means a lifetime of uncertainty, surgeries, and complications. Jenny Jones, founder of Life's a Polyp Foundation, along with her dad, Timothy Jones, shared what that journey has looked like for their family – where not only Jenny, but her mother and grandfather, struggled with the disease which results in hundreds to thousands of polyps developing in the GI tract that have 100% likelihood of turning cancerous if not removed. Once she was diagnosed at age 8, Jenny says, FAP became a part of her daily life. By age 10, she’d had multiple surgeries, including the removal of her colon. Her dad called it a miracle that she survived. The major surgeries continued throughout her life – and have led to numerous challenges, including nutrient deficiencies, dehydration, limitations in what she can eat, painful bowel movements, and medical PTSD. “It’s something that’s always on the mind,” she says. Jenny has now dedicated her life to serving as a resource and building a trusted network for the FAP community via her foundation, and supports research into new treatment options for FAP patients who currently have no non-surgical options available. Recursion is working toward solutions for patients with FAP. 👉 Learn more at: recursion.com

Recursion is advancing the first potential drug for rare disease FAP, discovered with AI. For FAP Awareness Week, we’re resharing our video featuring CEO and President Najat Khan, announcing the first clinical validation of Recursion’s AI-enabled drug discovery platform – positive Phase 1b/2 data for AI-identified drug REC-4881 in Familial Adenomatous Polyposis (FAP). This progressive rare disease – which often begins in the teens and results in hundreds or thousands of polyps developing in the GI tract which have a 100% likelihood of becoming cancerous if not removed, requires a lifetime of invasive surveillance and life-altering surgeries. There are currently no FDA-approved treatments. Recursion used AI not only to deliver the first potential treatment for this disease but also to quantify – for the first time at scale – the true natural progression of polyp burden in the trial-relevant population. This program is the first clinical validation of the Recursion OS, and demonstrates our ability to translate unbiased phenotypic insights into potentially differentiated treatments for diseases with high unmet need. We’re working hard to advance new solutions for FAP patients, this week and every week.

🎉 We’re on the Shatter List! Recursion has been named to the 2026 Women Tech Council’s Shatter List. This is our 9th year making the list, which recognizes workplaces where talented people want to grow, lead, and build meaningful careers. 💠 This year, Recursion has earned recognition in the Community Choice category, which highlights: 🙌 Companies people most want to work for right now 🚀 Strong cultures that attract top talent and enable career growth 🌟 Visionary leadership in a rapidly evolving economy 👉 Learn more: womentechcouncil.com/shatter-list/

“In its quest to transform how medicines are made, engineering, AI-pattern recognition, and cloud computing have proven as necessary as biochemical expertise.” A recent Case Study from @googlecloud highlights how Recursion is accelerating new treatments using the Recursion OS platform which “supports bursts of computational power that weigh in at trillions of calculations per second.” Combining a data-driven understanding of biology and chemistry with the latest in machine learning tools, the study notes that Recursion is advancing a pipeline of clinical stage drugs, including REC-4881, a potential first-in-disease treatment for the rare disease Familial Adenomatous Polyposis (FAP) that is one of the most advanced AI drugs in development today. “Recursion has reached an inflection point — from proving that AI can participate in drug discovery to demonstrating that an AI-native operating system can generate clinical proof and durable value,” notes CEO and President Najat Khan. In addition to five drugs advancing through clinical trials in Recursion’s internal pipeline and with partners like @sanofi and @Roche and @genentech, the study notes that Recursion has developed a suite of state-of-the-art machine learning foundation models, and maps of biology both internally and with partners (including the world's first whole-genome Neuromap and Microglia Map) that are uncovering unknown biology in difficult areas like neurological diseases. Leveraging a hybrid computing approach – training models on Recursion’s supercomputer, BioHive-2, and running inference on Cloud GPUs and TPUs – has allowed Recursion to continue to scale efficiently. "The potential of using Cloud TPU pods to accelerate our research while keeping operational costs and complexity low is a big draw," says CTO @bmabey. 👉 Read more:  cloud.google.com/customers/recu…

Donovan Chin is joining Recursion as Senior Vice President of Drug Design, effective June 22. His career spans small molecules, RNA-targeted therapeutics, novel peptide modalities, and AI-enabled discovery platforms. At Parabilis, Donovan led the computational drug discovery strategy behind Helicons, a novel class of constrained alpha-helical peptides that helped advance a first-in-class β-catenin inhibitor program to FDA Fast Track designation. At Arrakis Therapeutics, he pioneered computational approaches for RNA-targeted drug discovery, helping unlock small-molecule engagement of previously inaccessible RNA structures. Earlier at Novartis, he helped pioneer the application of computational approaches to drug discovery, building capabilities that supported a diverse portfolio across oncology, cardiovascular and metabolic disease, infectious disease, and chemical biology. Throughout his career, he has built high-performing multidisciplinary teams and advanced programs at the intersection of computation, chemistry, and biology – the same intersection where we believe the next generation of medicines will be discovered. Welcome to Recursion, Donovan!

One of the most important applications of AI is in improving clinical trials which encompass up to 70% of R&D costs and where most drugs in development fail. On June 17, 4:20pm at @HLTHEVENT Europe in Amsterdam, Recursion CFO Ben Taylor will present on the panel “Trials & tribulations: Exploring the next frontier in evidence generation,” looking at the rise of new clinical models that are shifting the traditional framework – including in silico models, digital twins, synthetic controls, adaptive frameworks, and hybrid or decentralized trials. He’ll be joined by Mati Gill, CEO of @AionLabs; Peter Donnelly, Co-Founder & CEO of Genomics; and Yajing Zhu, Director, Computational RWE at @novonordisk. Moderated by Adama Ibrahim, President, Digital Transformation at Crest Meridian, the panel will explore how clinical trials have evolved, expected breakthroughs on the horizon, and how pharma can prepare for a world where evidence generation is faster, more diverse, and increasingly augmented by technology. 👉 Learn more: hlth.com/events/europe/…

💡“Just like we simulate molecules and we simulate biology, what if we could simulate our trials before we run them?” In this clip from CEO and President Najat Khan's conversation with Selina Koch for the @BioCentury Show, she talks about where AI is making an impact on clinical trials. 💠Recursion’s approach is focused in three areas, Najat says. 1. Improving patient stratification - “Can you improve the signal to noise to know which patients would better respond?” 2. Smarter protocol design and simulating the protocol. 3. Improving recruitment and enrollment. “80% of trials don’t recruit on time.” 👉 Watch the full conversation here: youtube.com/watch?v=LfGy7F…

Inside the AI drug discovery evolution. A new story from Thomas Macaulay in @RunInfiniteLoop highlights Recursion’s industrial-scale approach to mapping biology and how the AI drug discovery industry is evolving. As Recursion CTO @bmabey said: "AI gives us better insights earlier in the process so we have greater certainty that a program will succeed or fail in patients and to identify which patients will be most likely to benefit." 👉 Read more: infiniteloop.media/p/ai-drug-disc…

🚀 AI drug discovery is in acceleration mode. A new article from @RealEndptsMel in @NatureBiotech highlights how next-generation AI companies like Recursion are transforming biology into an engineering discipline. Commenting on efficiency, Recursion CEO and President Najat Khan said: “On average, we go from project start to advanced candidate in 17 months.” That acceleration signals a fundamental shift. Across the industry, drug discovery is becoming data-driven, iterative, and scalable. The story highlights Recursion’s approach: ▪️ Leveraging machine learning to uncover previously “invisible” biological signals ▪️ Repurposing and advancing compounds with new mechanistic insight ▪️ Building an end-to-end platform that connects discovery, biology, and development It’s a critical point for the industry: Real impact comes from integrating AI across the full R&D lifecycle — from data generation to clinical execution. 👉 Read more: nature.com/articles/s4158…

🚀Clinical momentum, capital efficiency, and high-quality data. Ben Taylor, Recursion CFO and President of Recursion UK, sat down recently with Alec Stranahan at the @BankofAmerica Global Healthcare Conference, highlighting how Recursion’s data- and AI-led approach is building a more predictive, risk-diversified model to get better medicines to patients faster. 🔹 Here are three key takeaways: 1. It’s all about patient impact. As Ben noted, every part of the Recursion OS is designed to increase the probability of clinical success. "At the heart of it, we're a therapeutics company. And so we really focus on making sure that we're advancing the pipeline.” 2. Data quality is essential. As the industry rushes to train foundation models, Ben stressed that simply having massive amounts of data isn't enough. It’s about quality. "If you're just using public data or even if you're just using data that has been generated outside of the ML context, the fidelity of it is pretty low,” he said. “A much smaller data set of highly annotated data actually creates far more predictive models than a massive data set of poorly annotated data." 3. Driving capital efficiency with technology. Recursion is leveraging technology not only to advance new medicines, but to radically improve the unit economics of drug discovery – applying a strict analytical framework to ensure that capital flows directly to value-driving programs. “We should always be getting more impact for less cost,” Ben said. “Right now, most people don't realize this, about two-thirds of our cost is going directly into pipeline programs and our partnerships." With continued pipeline momentum and catalysts across multiple clinical programs over the next 12-18 months, we are demonstrating clear proof points for our data- and AI-led approach. 👉 Catch the full session here: bofa.veracast.com/webcasts/bofa/…

Join us at the AI Compute Summit in Amsterdam! Maureen Makes, VP of Engineering at Recursion, is speaking May 19 on the panel “People, power and performance" at the 2nd annual AI Compute Summit in Amsterdam from @TheEconomist Enterprise. Along with Marina Antoniou, Global Markets Head of Market Abuse Risk Assessment at @NatWestGroup; Rui Oliveira, Director of the Minho Advanced Computing Centre; and Valeriu Codreanu, Manger of Compute Services at SURF, they’ll discuss how AI infrastructure is expanding faster than the talent to run it, and how organizations can reskill teams and develop leadership for a world defined by GPUs, automation and data governance. The panel will be moderated by Matus Samel, Principal of Energy & Sustainability at Economist Enterprise. 👉 Learn more and register: events.economistenterprise.com/ai-compute/

🧬 Bridging the gap in AI drug discovery. @AlisandraDenton, Staff Machine Learning Scientist at Recursion and one of the authors on our recent paper in @NatureBiotech, explains how the AI model TxPert predicts how a cell will respond to perturbations. Predicting a cell’s RNA activity, or transcriptome, is key to bridging the gap between cellular changes and clinical outcomes and advancing the potential for AI drug discovery. As Ali says, “with hundreds of cell types and so much disease variation, the total possibilities are too vast to measure in a lab.” She describes how TxPert allows us to perform a “Virtual Assay,” taking the mathematical signature of a healthy cell called the Basal State and adding the perturbation’s embedding to deliver a highly accurate prediction of what the cell’s transcriptome will look like after treatment. TxPert uses layered graph-based models that integrate phenomics — or how a cell looks — and transcriptomics — which genes are expressed — along with massive public biological knowledge resources. The model can even predict how a perturbation will work in entirely new cell lines it hasn’t seen before as well as accurately forecast the effects of “double perturbations,” consistently identifying "unknown unknowns" that traditional models — and even massive general-purpose AI — often miss. Ali notes that TxPert is currently predicting genetic perturbations, but more flexible models —  including those predicting drug effects — are in the works. 👉 Check out the full paper in Nature Biotech: nature.com/articles/s4158…