Recursion is making a bold bet on supercomputing in drug discovery. In 2023, the company announced a strategic partnership with NVIDIA, that included a $50 million investment to support the development of novel foundation models for AI-enabled drug discovery.
NVIDIA CEO Jensen Huang was recently highlighted at Recursion's Download Day event, where he urged Recursion and other similarly digitally savvy companies to embrace risk and a "once-in-a-lifetime opportunity."
While a certain amount of risk is a given, companies must have the courage to venture into the unknown. As Huang put it, "You have to be willing to take that leap."
Thanks to Olivia Bass for sharing the news.
“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
It’s all about the patients.
◾ By the time Connie Lee’s daughter Julia was 4 years old, she’d had 4 major hemorrhages and brain surgeries as a result of an aggressive form of a rare disease known as cerebral cavernous malformation (CCM).
◾ CCM causes abnormal blood vessels in the capillary bed that can hemorrhage and lead to stroke, seizures, and neurological deficits.
◾ There are some 350,000 symptomatic patients in the U.S. and EU (and many more who have the disorder but don’t know it), and no approved treatments.
◾ In 2002, Connie founded a CCM patient advocacy organization, Alliance to Cure Cavernous Malformation, to bring patients together, and support research to find treatments.
◾ By 2005, the organization had launched the International CCM Scientific Meeting, happening this week in Toronto.
◾ It was at one of these meetings, in 2011, that Connie first met Chris Gibson, then a grad student at University of Utah, where he presented on how CCM2 regulates superoxide and nitric oxide.
◾ He’d made new discoveries into CCM mechanisms – and a new way to treat it – using a method of image-based profiling assay developed in Anne Carpenter’s lab at Massachusetts Institute of Technology.
◾ In 2013, Recursion was established, with REC-994 -- the first ever therapeutic designed to treat CCM -- as the company’s lead program (and Dr. Carpenter became a scientific advisor).
◾ In 2015, REC-994 received Orphan Drug Status from the FDA and Recursion worked with Alliance to Cure and the FDA on developing CCM-specific clinical trial endpoints.
◾ Connie and her organization have partnered with Recursion on every step of this journey – connecting us with PIs, hosting webinars, and providing outreach to patients.
◾ Soon, we’ll have the first Phase II readouts of this lead program. Connie presented at a recent All Hands meeting reminding us of the patients who have invested over 2 years to participate in this trial who are proud to be a part of it.
◾ Patients are the driving force behind everything we do and they inspire us to work harder every day. 💪
For more information about Alliance to Cure visit their website at https://lnkd.in/gbMYMKdt.
*Pictures are from this summer's Alliance to Cure Family Weekend in Silver Lake, NY.
National Organization for Rare Disorders#ccm#raredisease#patients#patientadvocacy#clinicaltrials#pharma#drugdiscovery#techbio
Live from the International Conference on Machine Learning in Vienna!
◾ At ICML, Semih Cantürk presents our poster on the Graph Positional and Structural Encoder (GPSE) - the first-ever graph encoder designed to replace hand-crafted positional and structural encodings (PSE) by learned PSE in any graph neural network (GNN).
◾ Across a wide range of benchmarks, GPSE-enhanced models significantly outperformed those that employ hand-crafted PSEs, paving the way for the development of foundational pre-trained graph encoders for extracting positional and structural information, and highlighting their potential as a powerful, efficient alternative to explicitly computed PSEs.
📎 https://lnkd.in/efhBCiXH
🚀 And join us tonight at ICML -- July 25, 6pm -- for the Polaris Launch Party!
Polaris - Benchmarks for methods that matter is a new platform for ML in drug discovery that aims to provide standardized, domain-appropriate datasets, guidelines, and tools for method evaluation and comparison.
Register here: https://lu.ma/wj1agv8o#icml#icml2024#science#tech#ai#ml#techbio#drugdiscoveryValence Labs
From protein structure prediction to modeling protein-DNA interaction:
How evolving AI capabilities are revealing new insights into the cellular drivers of disease.
◾ A new story by Sachin Rawat in SynBioBeta looks at how AI, data, and modeling are rapidly improving our understanding of protein-DNA interactions that regulate cell processes and are critical to understanding many diseases that arise from dysfunctional cellular processes. “Mapping protein-DNA interactions,” he writes “has substantial therapeutic implications.”
◾ Deep learning lets us predict protein structures even with limited information, and he notes that the third iteration of AlphaFold, for instance, even shows how these structures interact with DNA, ligands and ions.
◾ Connecting multiple ML approaches provides even better modeling outcomes. “The next generation solutions are not going to come from just individual models that solve individual problems, but from suites of solutions that are based on these virtual cycles of improvement between data sets and models,” said Lina Nilsson, our SVP of Emerging Technologies.
◾ The field is moving from identifying DNA-binding sites on a protein to “charting the complete landscape of protein-DNA interactions in an organism,” he writes. Bringing together proteomics with data from transcriptomics, phenomics, cell morphology, and transcriptomics, among other modalities, and analyzing it with machine learning, “We take a broad, unbiased view into biology,” Lina says.
Read more: https://lnkd.in/ef5HbaBjRory Kelleher#ai#ml#machinelearning#tech#techbio#dna#science#biology#cells
From V to T: Transforming the drug discovery funnel.
At Download Day, Laura Schaevitz, SVP and head of research, shared how we are transforming the traditional “V-shaped” drug discovery funnel – in which a small number of ideas advance steadily from early discovery to costly development – to a “T-shaped” discovery approach – using massive connected datasets to rapidly surface thousands of novel opportunities, validating them through hundreds of industrialized experiments, in order to pursue dozens of promising new programs.
Instead of years and millions of dollars to identify candidate programs and generate the data to support our predictions, she says, “we can confirm insights for tens of thousands of dollars each and in just weeks.”
How it works:
◾ Our standardized, automated workflows generate new programs in an extremely efficient and repeatable way. Data from dozens of programs show that if our in silico predictions suggest a relationship will fail, 90% of the time that is the outcome we see. This is the first step in rapidly narrowing the funnel, relying on our predictions to increase the probability that we are working only on high potential programs.
◾ We run the same high content assays in highly standardized ways to answer many core questions in drug discovery. By creating consistency we are able to have just a handful of people, who work both to continuously refine the process and drive our portfolio of dozens of programs in hit to lead. In contrast, in traditional pharma, separate teams drive individual drug discovery programs through a series of specialized assays that take significantly more time and money to establish.
◾ With Matchmaker, an additional data layer which predicts protein target ligand interactions, we can learn about the binding potential of these hit compounds. This data gives us additional confidence that these hit compounds have promise as new drug candidates.
In short: We are dramatically reshaping the drug discovery funnel, morphing it from a V to a T in order to drive down the cost and timeline and increase later-stage success rates, ultimately leading to more impactful medicines.
#ai#techbio#drugdiscovery#ml#science#tech#data
How we use phenomics and computational modeling for chemical design.
At the upcoming Gordon Research Conference (GRC) on Computational Chemistry (July 21-26 in Portland, Maine), a premier, international scientific conference focused on advancing the frontiers of science through the presentation of cutting-edge and unpublished research, Senior Scientist Ivan Franzoni will share insights into how we use our operating system to find new therapeutic targets and quickly produce and test new drug candidates.
◾ It starts with building a purpose-built dataset using high-content microscopy, arrayed CRISPR genome editing methods, and machine learning – amassing phenotypes from millions of perturbations in multiple cell types.
◾ This leads to promising new biological insights and novel therapeutic targets with unique mechanisms of action.
◾ We then introduce a broad but targeted method for expanding the chemical space of interest, identifying compounds related to the desired phenotypic profile.
◾ Using computational techniques, we then search chemical libraries and use compound scoring to deliver crucial insights and employ rapid GPU-enabled shape screening in our internal chemical library to discover novel chemical structures.
Learn more about the GRC on Computational Chemistry here: https://lnkd.in/e2FxZEBZ#ai#ml#techbio#platform#chemistry#biology#drugdiscovery#crispr#grc#grc2024Gordon Research Conferences
From data to drugs.
Great insights from our investor Kinnevik on the "seismic shift" happening in drug discovery thanks to 3 key elements:
▪ The industrialisation of data collection and curation
▪ An explosion of compute power
▪ Advancements in AI algorithms
This shift involves the true convergence of technology and biology and includes tech powerhouses like NVIDIA partnering with biotech companies.
Ala Alenazi writes:
"Recursion has become synonymous with TechBio. Through its industrialisation of research, Recursion’s robotised labs can carry out 2.2 million experiments each week for up to 50 weeks per year. Today, they boast 50 petabytes of high-dimensional data.
In a strong sign of faith, NVIDIA has both invested in Recursion and partnered with them to build BioHive-2, the largest system in the industry and the 35th fastest globally according to the TOP500 list. BioHive-2 will allow Recursion to double the insights generated from wet-lab work, with that ratio improving over time according to CTO Ben Mabey."
Read more: https://lnkd.in/eWn4vNyX#ai#partner#techbio#biotech#drugdiscovery#tech#venture#investment
Congrats to Berton Earnshaw, AI Founding Fellow and Director of Valence Labs at Recursion who has been named College of Science Senior Fellow at the University of Utah College of Science.
“I first met Berton in the math department during his PhD studies,” said Dean Peter Trapa. “It’s great to see him come full circle with the U as a Senior Fellow in the College of Science. Currently, he’s at the top of his game in machine learning as it relates to drug development and will add appreciably as an executive advisor to the College and its research priorities.”
#ai#ml#research#drugdevelopment
Enterprise PR Specialist at NVIDIA
3wGreat summary of the conversation, Brian!