Recursion

“This is a once-in-a-lifetime opportunity.” In a Fireside Chat with Recursion co-founder and CEO Chris Gibson at Download Day, NVIDIA founder and CEO Jensen Huang shared his vision for the future of healthcare, and how the companies are working together on a data-driven approach to drug discovery that has the potential to radically transform medicine.  ◾ Why he’s excited about this collaboration: “If you look at the foundation of Recursion, three things are in play – the invention of a new algorithm, a new family of algorithms that we call deep learning; supercomputing capabilities that you’ve used here and that we’ve partnered with you to create; and the know-how of processing and extracting the meaning of biology that’s embedded within life, within that data.” ◾ With accelerated computing and generative AI, we are changing “the type of problems we can solve,” he added. ◾ NVIDIA has been an incredible partner as we push to develop the next generation of medicines for patients in need -- including their support in building BioHive-2, the largest supercomputer in the pharma industry, which allows us to run more experiments, build more data, and develop even more powerful foundation models. Watch the full Fireside Chat here: https://lnkd.in/evqAm3QB The full day of presentations and slides from Download Day, featuring experts from across the Recursion ecosystem sharing the latest developments on our platform, pipeline and partnerships, is available here: https://lnkd.in/e9bRKvqf  #techbio #future #ai #health #medicine #pharma #tech

“Looking beyond the lampposts, looking beyond the known biology, is what Recursion’s platform promises to unlock.” ◾ The Bayer-Recursion collaboration brings together Recursion’s technology-forward and AI-leading emphasis and Bayer’s legacy of drug development. The $1.5B deal announced last October in precision oncology already has one joint project now rapidly advancing to Lead Series nomination. ◾ We are on track to complete 25 unique multimodal data packages in Q3. ◾ The Recursion operating system allows Bayer to scale up data generation, explore a large number of oncology targets simultaneously, and “do unbiased discovery.” ◾ Announced at Download Day, Bayer will be the first beta-user of our LOWE LLM-orchestrated workflow software, which will be integrated across the collaboration and offer a more exploratory and intuitive research environment for scientists on both sides. #techbio #ai #platform #partnership #pharma #cancer #oncology #downloadday

The Recursion difference.  As Chris Gibson welcomed investors, analysts, and Recursionauts to Download Day, he provided a vision for the future of the Company and how it is poised to drive a new era of drug discovery. In short: it’s all about the data. ◾ “Everyone is using public datasets and making the same conclusions,” he said. “Data is our biggest differentiator.” ◾ Over the past decade Recursion has built massive, interconnected datasets, gained supercomputing capabilities, and developed ever-more-sophisticated foundational models. ◾ Experts both inside and outside the company shared how we are stitching these data layers together to unlock the vast unknown biological space – discovering novel targets for disease and designing new medicines for patients – with 7 of these clinical programs expected to have readouts in the next 18 months.    ◾ As Laura Schaevitz said: “We’ve already identified thousands of program ideas, validated hundreds through industrialized experiments, resulting in dozens of exciting program opportunities, many with strong chemical matter at the start.” ◾ We heard from our partners at Bayer – who we announced will be the first beta users of our LLM tool LOWE – as well as John Marioni at Genentech who talked about the transformational moment we face and how important it is to build a Bilingual Culture – with computational and basic scientists who speak the same language and are fully engaged across disciplines. ◾ And of course, we were thrilled to welcome Jensen Huang in a closing Fireside Chat. NVIDIA has been a critical partner as we build the TechBio company of the future with the computing power to truly transform the industry. Watch the Download Day presentations and check out the slides here: https://lnkd.in/e9bRKvqf Thank you to everyone who joined us and made the day such a success! Lina Nilsson Imran Haque David Mauro Najat Khan, PhD Michael Secora PhD Matthew Kinn Deepak Nijhawan Ryan Kelly Berton Earnshaw Daniel Cohen Hayley Donnella #techbio #downloadday #partners #future #healthcare #tech #pharma

Looking forward to continued partnership with CTF!

Why is this an inflection point? Appearing on CNBC’s Closing Bell Overtime during Recursion’s recent Download Day, Chris Gibson shared the Company’s major pipeline, platform and partnership updates. ◾ On the pipeline: 7 readouts in the next 18 months in our clinical programs – including 5 efficacy readouts. ◾ On partnerships: Bayer, one of our close partners, is going to be using one of our LLM software tools called LOWE as part of our partnership. “I think this really represents one of the first times a large pharmaceutical company is going to be adopting these AI tools in the way they discover and develop medicines together with us." ◾ On the platform: We are now operating the fastest supercomputer in all of pharma, built with NVIDIA. ◾ On the value proposition: “We’ve been able to demonstrate that using these tools, we can roughly 3x the speed of developing and discovering medicines toward the clinic and dramatically reduce the cost.” The most important measure? “Improving the probability of success.” The message to investors was clear: “Machine learning and AI are the right tools when you bring the right data and the right compute to bear to help us make sense and really decode biology.” Watch the full interview: https://lnkd.in/e_CthC37 #techbio #ai #pharma #biopharma #biotech #llm #downloadday

Today – Monday, June 24 – is Download Day – when Recursion provides investors, partners, patient advocacy groups, equity research analysts and other stakeholders with the latest platform and pipeline updates. We’ll be sharing: ◾ Pipeline Updates: 7 clinical programs, including 5 Phase II programs, with REC-994 for Cerebral Cavernous Malformation expected to have a data readout in September 2024 as well as dozens of internal & partner programs in early stages with our first LLM & causal model-driven programs entering the Recursion pipeline. ◾ Partnership Updates: We’re announcing that Bayer will be the first beta-user of LOWE – our LLM-Orchestrated Workflow Engine. We’ve initiated our first joint project which will now be advancing rapidly towards Lead Series nomination, and we’re on track to complete 25 unique multi-modal data packages in Q3. Learn more: https://lnkd.in/ePJeeE5s #techbio #downloadday #ai #drugdiscovery #pharma #investors #biotech

Last week our Deputy Mayor for Business and Chair of London & Partners along with our North American team was honoured to attend the opening of Recursion’s new office in #London at Pancras Square, King’s Cross 👏. The site will provide Recursion and Valence Labs, the company’s AI research engine, access to world-class talent across Europe’s rapidly growing TechBio sector, and embed Recursion in a thriving innovation ecosystem of leading technology and life science companies 🧬. "London stood out as an ideal location given its brilliant and interdisciplinary talent across the fields of technology, biology and chemistry. It’s also the epicenter for the rapidly growing TechBio sector in Europe, where leading technology and life science companies like Google and Merck both sit within walking distance of our new Recursion site. I look forward to expanding our operations in Europe and hiring many new Recursionauts who will help us advance our mission of decoding biology to radically improve lives.” Co-Founder and CEO Chris Gibson shared. The event started with a ribbon cutting by Chris, followed by welcome remarks 🎀. Howard Dawber introduced the panel discussing the future of AI with Nathan Benaich, Founder and General Partner of Air Street Capital, Professor Michael Bronstein of the University of Oxford, and Valence Labs, President, Daniel Cohen. We look forward to seeing what’s next for Recursion and welcome them to the London ecosystem 👐!

The “search engine for drug discovery” comes to London. A story from Katie Prescott and Helen Cahill in The Times looks at Recursion’s new London AI hub – a 6,700 square-foot office in King’s Cross near Google and Meta.  ◾ In London “there is a density of talent and people who are trained in both biology and computer science and data science” says co-founder and CEO Chris Gibson. “It’s becoming even more prevalent now than when we started this company in 2013.”  ◾ The story notes that Michael Bronstein, DeepMind professor of AI at the University of Oxford, has been appointed Recursion's scientific advisor.  ◾ There’s been an immediate response from interested applicants. “Within the first 24 hours of advertising job openings at the new site, the business had received more than 300 applications. It is currently seeking to fill eight open roles, including software engineers and computational biologists.” #techbio #ai #london #tech #techjobs

The TechBio trinity: scale of proprietary data, scale of compute, and scale of impact. In a recent Fireside Chat at the Goldman Sachs 45th Annual Global Healthcare Conference, Recursion CFO Michael Secora PhD framed the above idea and shared insights into Recursion’s operating system, upcoming clinical and preclinical readouts, recent partnerships, and business development deals. Below, 3 key takeaways from the discussion.  1️⃣ How is Recursion different from other TechBio companies? Recursion’s operating system begins with an automated wet lab that has now done over a quarter billion experiments. We do up to 2 million experiments per week across many different biological and chemical contexts and it serves a primary purpose – data generation. In that data generation we are either mapping biological and chemical patient-centric insights or we are using that same OS to validate a given insight. To complement that wet lab is our computational dry lab, supercomputer, and all the different software tools that we have developed that allow us to analyze and map that data. 2️⃣ What can you tell us about Recursion’s pipeline? We are going to have 7 readouts in the span of about 18 months – 5 Phase II, and 2 Phase I – beginning next quarter with a Phase II readout in Cerebral Cavernous Malformation, a rare disease with no approved therapy that affects approximately 360,000 patients in the US and EU5. In Q4 of this year, we have a Phase II readout in Neurofibromatosis Type 2 which affects approximately 33,000 patients in the US and EU5, and in the first half of next year we have data coming for Familial Adenomatous Polyposis as well as AXIN1 or APC Mutant Cancers which affects approximately 50,000 and over 100,000 patients in the US and EU5, respectively. 3️⃣ What is Recursion’s advantage and how do you intend to maintain it in a rapidly evolving field? There are 3 things Recursion continues to do: integrate, scale and automate technology along the entirety of the drug discovery and development value chain. Over the last year, we have scaled our proprietary dataset to over 50 petabytes. We’ve sequenced over one million transcriptomes, complementing our phenomics dataset. We struck partnerships with Tempus AI and Helix around accessing multimodal patient-centered data which gets into not just clinical records but DNA and RNA sequencing. On the computational side, we acquired Cyclica (acquired by Recursion, Nasdaq: RXRX) and Valence Labs which helped boost our digital chemistry tools and generative AI capabilities. We have also constructed a vast chemoproteomic data layer using Cyclica’s software. With help from our partner NVIDIA, we designed and built our next-generation supercomputer BioHive-2 which is now a top 50 supercomputer across any industry. Listen to the full conversation here: https://lnkd.in/es6ZCgEe #techbio #data #pipeline #pharma #cancer #ai #biology #chemistry #supercomputer

Using microscopy data to create powerful foundation models of cellular biology. ◾ In a new paper, researchers from Recursion and Valence Labs reveal the next level of scaling microscopy images for use in biological research – offering a significant improvement over weakly supervised learning (WSL). They are presenting their findings in a keynote and poster presentation at the IEEE/CVF Conference on Computer Vision and Pattern Recognition June 18 & 19. ◾ While images have been a powerful means to explore chemical and genetic changes that happen in cells, and while we now have massive datasets at our disposal like RxRx3 – a publicly available database of 2.2 million images that represents less than 1% of Recursion’s total dataset – developing robust and feature extraction pipelines using open source software packages has been challenging. ◾ One approach has been to use weakly supervised learning (WSL) to train models that predict the perturbations used to treat cells in an image – but these models are limited with larger datasets, including forgetting known biological relationships. In part, this is because perturbations are noisy labels with clusters of similar effects – and many have no significant effect. ◾ In the preprint, researchers demonstrate a new framework for learning representations of high content screening datasets based on self-supervised learning. They hypothesized that if they had more compute, more data, and more parameters, they would get improved performance (a.k.a., the "scaling hypothesis"). ◾ Using the BioHive supercomputer (more compute), Recursion’s public and private datasets (more data) and vision transformer (ViT) masked autoencoders (more parameters) the team found that they could scale microscopy-based representation of cellular biology that could accurately infer known biological relationships without losing recall – achieving as much as a 11.5% relative improvement when recalling known biological relationships curated from public databases. ◾ What’s more, they developed a new channel-agnostic masked autoencoder architecture (CA-MAE) that allows for inputting images of different numbers and orders of channels. Learn more: https://lnkd.in/einj4_5N Oren Kraus Kian Kenyon-Dean Berton Earnshaw Saber Saberian Maryam Fallah Peter McLean Jess Leung Vasudev Sharma Ayla Khan Safiye C. Dominique Beaini Maciej Sypetkowski Maureen Makes Kristen Morse Ben Mabey #ai #ml #tech #techbio #wsl #vit #mae #data  #cvpr