Recursion

Join us live at 8:30am ET today to hear updates on interim Phase 1 clinical data for our REC-617 monotherapy trial and a recap of our #AACR presentation from Najat Khan, PhD and Dave H.. Submit questions: https://bit.ly/3ZsQ71x #techbio #drugdiscovery #data

Special delivery from NeurIPS! We just released our latest certified dataset, RxRx3-core, which includes labeled images of 735 genetic knockouts and 1,674 small-molecule perturbations. The related benchmark evaluates the zero-shot prediction of compound-gene activity. Learn more 👇

Live from NeurIPS: faster and more accurate generation of molecular properties with ET-Flow. Majdi Hassan from Valence Labs powered by Recursion explains ET-Flow - Equivariant Transformer Flow-Matching for Molecular Conformer Generation – which uses a generative technique called flow matching to quickly generate lots of molecular poses, or conformations, in order to more accurately represent molecules. ▪️ The ET-Flow method is parameter efficient, generating conformations in as little as five steps, Majdi explains, making it great for high throughput applications. And the molecules are really physically possible, based on a number of metrics. ▪️ Being able to generate numerous molecular conformations is important for drug discovery – helping researchers to understand a molecule’s properties – to determine, for instance, if a large molecule is flexible and can fold, allowing it to permeate a membrane. ▪️ And the tool can help researchers find where certain features match up between a bioactive molecule and a database of molecules in order to discover new hits. 👉 Read the ET-Flow paper here: https://lnkd.in/e4ygG6Fm #neurips #neurips2024 #chemistry #techbio #drugdiscovery

Today, we’re kicking off an exciting two days in London with 250 incredible new colleagues from Exscientia and more than 50 longstanding Recursion leaders and ‘trail guides’ as we come together to chart the next chapter of TechBio. This is more than just a meeting—it’s the start of a shared journey to redefine how technology and biology converge to transform lives. Over the next two days, we’ll dive deep into what unites us and where we’re headed. Here’s a glimpse of what’s ahead: 🔹 Reflecting on the power of shared culture and exploring how our combined strengths will drive innovation. 🔹 Thought-provoking sessions on the evolution of our operating system, patient impact, and multi-dimensional biology—key pillars of the future of TechBio. 🔹 Hands-on breakout sessions like “My Why,” where we’ll connect on a personal level to discover the passion that fuels each of us. 🔹 Collaborative discussions with HR and IT to ensure we build the infrastructure to innovate at scale. 🔹 Fun and creative activities to celebrate this unique milestone—because building the future of TechBio and working this hard should also be fun! TechBio is not just about combining biology and technology; it’s about leveraging data, systems, and innovation to tackle the hardest problems in healthcare, from drug discovery to patient outcomes. As we unite our teams and visions, we’re poised to accelerate this revolution and set the standard for what’s possible in this field. I’m excited about the conversations we’ll have, the ideas we’ll generate, and the bonds we’ll form over these two days. Together, we are laying the foundation for an extraordinary 2025 and beyond. Let’s make this moment count. #TechBio #Innovation #Collaboration #FutureOfHealthcare

Follow us to our spotlight paper on MolPhenix at NeurIPS - the foundation model that can predict the effect of any given molecule and concentration pair on phenotypic cell assays and cell morphology. ▪️ Presented by researchers at Valence Labs, MolPhenix leverages a pre-trained phenomics model to demonstrate significant performance gains across perturbation concentrations, molecular scaffolds, and activity thresholds. ▪️ It offers an 8.1x improvement in zero shot molecular retrieval of active molecules over the previous state-of-the-art, reaching 77.33% in top-1% accuracy. ▪️ These results open the door for machine learning to be applied in virtual phenomics screening, which can significantly benefit drug discovery applications. 📎 Read the paper here: https://lnkd.in/epDf7Md3 #ml #AI #neurips #neurips2024 #techbio #drugdiscovery

"To the extent that you have fit-for-purpose control datasets that you understand really deeply, that sets you up to do powerful things with machine learning." -- Lina Nilsson, SVP of Platform A new story from David Wild at Citeline Commercial looks at how companies are using data, AI, and foundation models, among other approaches, to "fail fast" and optimize for success earlier in the drug discovery pipeline. He notes that in addition to curating fit-for-purpose datasets, "Recursion also assiduously tests its AI/ML models and benchmarks them." “The sooner you come to that insight on whether the drug meets your needs, the less time you’re going to spend making and waiting for new molecules to be made and tested,” Dr. Nilsson said. "Failing fast is nice, but really you want to learn fast." 👉 Read more: https://lnkd.in/eQkft46X #ai #ml #data #drugdiscovery #techbio

REC-617 is a testament to the potential of AI-guided precision chemistry and design to deliver new cancer treatments. Today, Dave H. and Najat Khan, PhD presented the latest interim data for our monotherapy Phase 1 trial for REC-617, a potential best-in-class CDK7 inhibitor, in a live Update Call. ▪️ They shared details about how the design team used our AI-enabled precision oncology platform to design and optimize a molecule that had a modest half life and robust target coverage – with the goal of offering a safer and more effective means to inhibit CDK7 in order to treat aggressive cancers. ▪️ Of particular note were the unexpected preliminary efficacy findings – including a durable partial response of tumor reduction and reduced tumor markers in a 69-year old patient with platinum resistant ovarian cancer who had progressed following 4 lines of prior therapy with metastatic disease to lungs and lymph nodes. In addition, 4 patients with different tumor types – including late stage colorectal and small cell lung cancer – demonstrated durable response of stable disease for up to 6 months. ▪️ “CDK7 is a fantastic target but not properly tested,” said Dr. Hallett. “We delivered proof of that design principle.” ▪️ Our AI-guided precision oncology platform allowed us to design and optimize REC-617 – and progress it into the clinic – much faster and more efficiently than industry average. ▪️ REC-617 was initially developed through a collaboration between Exscientia and GT Apeiron that centered on using Exscientia’s AI chemistry platform to design and prioritize new high-impact oncology therapeutics. Exscientia bought out the program in July 2024 believing it had the potential to overcome the safety and efficacy limitations of approved treatments. REC-617 progressed from hit identification to candidate selection in under 12 months, with only 136 novel compounds synthesized during optimization. In a typical drug development program, companies produce over 2500 compounds to find a lead candidate. ▪️ “200 versus 2500 or more and timing under a year – that speaks to the ability to get to the right answers better and faster using these approaches,” said Dr. Khan on the call. “Leveraging AI and multimodal data to really understand not just the biological signature but the right patient at the right time – this is how we will drive precision medicine.” ▪️ Both Dr. Hallet and Dr. Khan noted that as both the monotherapy and combination therapy (beginning in H1 2025) portions of the ELUCIDATE trial progress, we will leverage expansive oncology patient data through our partnerships, allowing us to create more robust causal models and further stratify our patient population. 👉 See the slide deck from the Update Call here: https://lnkd.in/gVt-95tS #ai #oncology #clinicaltrial #cdk7 #chemistry #techbio

Today we’re reporting interim Phase 1 clinical data for our REC-617 monotherapy trial – with plans to expand into combination studies in advanced solid tumors. At the AACR Special Conference in Cancer Research, Dave H., our Chief Scientific Officer, shared interim monotherapy dose-escalation data from the Phase 1/2 study (ELUCIDATE) of REC-617, a selective CDK7 inhibitor, in advanced solid tumors. 🔹 The interim Phase 1 clinical data for REC-617 included: ▪️ Dose-linear pharmacokinetics (PK) with rapid absorption and robust pharmacodynamic (PD) biomarker modulation, suggesting substantial target engagement; ▪️ Confirmed partial response (PR) during monotherapy dose-escalation in a patient with platinum-resistant ovarian cancer, treated with 4 lines of prior therapy in an advanced setting, with durable response ongoing after more than 6 months of treatment; ▪️ In 4 additional patients, a best response of stable disease (SD) for up to 6 months of treatment. Dr. Hallett noted: “Cell cycle dysregulation and transcriptional 'addiction' are both hallmarks of many aggressive cancers. By inhibiting CDK7, we have the potential to target both mechanisms while fine tuning the therapeutic index.” "These initial findings for REC-617 represent an exciting step forward in the development of CDK7 inhibitors, with a favorable PK/PD profile and a durable confirmed partial response observed in dose escalation in a highly pre-treated patient population," said Najat Khan, PhD, Chief R&D Officer and Chief Commercial Officer. “Designed using our AI-powered OS platform, REC-617 reflects our focus on enhancing the therapeutic index to deliver more effective and safer treatment options for patients. We are eager to continue this momentum in dose escalation and to initiate the next phase of the program next year."  👉 Learn more: https://lnkd.in/eExy4gBz 🔹 Join the Update Call: Tomorrow, Tues., Dec. 10 at 8:30am ET, Dr. Hallett and Dr. Khan will hold a live Update Call webcast to present the preliminary data. ▪️ Submit questions for the Update Call here: https://bit.ly/3ZsQ71x ▪️ Tune in to the Update Call here on LinkedIn or on:  Twitter/X: https://lnkd.in/gn52iH5F  YouTube: https://lnkd.in/gNx66QJK #techbio #clinicaltrial #oncology #data #aacr

Sharing our latest breakthroughs at NeurIPS: foundation models and agentic systems for AI drug discovery. ▪️ With our research engine Valence Labs, we’re presenting 12+ papers at NeurIPS this week, the premier machine learning conference taking place in Vancouver Dec. 10-15. ▪️ A major focus of our papers and presentations are foundation models and agentic systems – and the pivotal role they play in advancing the next generation of AI drug discovery. 🔹 Breakthroughs in Foundation Models - Valence has expanded our foundation models from biology to chemistry - and at NeurIPS will present: ▪️ Phenom, which translates all of our phenomics data into a digital representation; ▪️ MolPhenix, which takes phenomics data and integrates it with chemistry data; and ▪️ MolGPS, a property prediction foundation model. All three of these models are currently being transferred to the RecursionOS. Notably, foundation models trained on public data, such as MolGPS, showed significant gains in performance when researchers added even a small subset of our proprietary data. 🔹 Breakthroughs in Agentic Systems - Our LLM-Orchestrated Workflow Engine (LOWE) expedites drug discovery by streamlining complex workflows using a natural language interface. The software allows any scientist to easily query our massive proprietary biological and chemical datasets – 60+ petabytes – to identify new therapeutic targets of interest – and immediately test them and develop new drug candidates. Valence is currently at work on the next generation agentic system. https://neurips.cc/ #neurips #neurips2024 #foundationmodels #llms #techbio

🚀 Demo Day is back for Year 4! Join us for an inspiring day filled with groundbreaking startup stories, exclusive fireside chats, and fresh surprises as Altitude Lab adds its signature twist to an industry staple. Location: Gateway, Salt Lake City, Utah Date: February 19th, 2025 Time: 11:30am - 5:30pm Don’t wait—this event will sell out! Use code EarlyBird20 for 20% off at checkout. Reserve your spot now: https://lu.ma/r7d0iddb Altitude Lab is thrilled to be part of the inaugural BioHive Week, celebrating Utah’s thriving life sciences and healthcare ecosystem. #Biotech #biohiveweek #utahstartups #biotechstartups #medtech #utahlifesciences #techbio #demoday BioHive Utah, Anziva Pharmaceuticals, Simerdeep Singh Gupta, Ph.D., Alexis Weston, Conduit Bio, Jamie Cartland, Freyya Stefan Niederauer, Intactis Bio Corp Daniel Rodriguez-Granrose, PhD, PSM, Light-Hope Diagnostics, Inc., RAUSHAN SINGH, Monere, Mou Nandi, Prism AI Therapeutics, Orly Alter, QUANTiSCOPE®, Kevin Christopher, Sethera Therapeutics, Karsten Eastman, Snow Canyon Therapeutics, David Blackwell, Spect Inc., Michael Leung, MS, SPIRE Therapeutics, Jan Kubanek, SymbioCellTech, LLC, Anna Gooch, PhD, NephroNovus, Kevin Yang, David Chen, Vira Regen Inc., Kapil K. Sharma, MS, MBA, MSF