TechBio Latest Summer 🍇 News & Updates
Recursion, Exscientia, Isomorphic Labs, Phare Bio, Nanome and Darween Bioscience
“We are the cosmos made conscious and life is the means by which the universe understands itself.”
By Brian Cox
Latest News ⛱️
🍉 Lantern Pharma | Second Quarter 2024 Operating & Financial Results Conference Call
🍒 Recursion and Exscientia Enter Definitive Agreement to Create a Global Technology-Enabled Drug Discovery Leader with End-to-End Capabilities
🍍 The NVIDIA Healthcare team just made two foundation models available as NVDA inference microservices (NIMs). Diffdock, a predictive model for how drug candidates bind with target proteins and MolMIM for controlled generation of small molecules. Both have wide adapality in drug discovery for applications like virtual screening and lead optimization.
🍉 Absci and MSK Collaborate on Generative AI Drug Discovery
🍒 MIT’s SPARROW Redefines Drug Discovery With Smart Synthesis
🍍 PLAIO secures €4.3M to expand AI pharma planning platform
🍉 Insilico Medicine's pan-TEAD inhibitor ISM6331 receives FDA IND clearance for mesothelioma treatment
🍒 Quantiphi Invests in Transcell to Advance AI-Driven Drug Discovery
🍍 QuEra and Quantum Intelligence Partner to Accelerate Drug Discovery with Quantum Computing
🏄 Recursion Pharmaceuticals Inc (NASDAQ: RXRX)
Just this week (August 08, 2024), Recursion Pharmaceutical and Exscientia plc announced that the two companies have entered into a definitive agreement, combining Recursion with Exscientia in an approximately $850M (in cash and cash equivalents between the two companies as of the end of Q2 2024) merger.
The TechBio merger will bring together Recursion OS and Exscientia’s generative AI drug design and chemistry automation capabilities to industrialize drug discovery & deliver high quality medicines at lower prices of a diverse portfolio of clinical and near-clinical programs.
Recursion (2013, Utah US) has built the world’s most advanced ultra-high throughput wet-lab and ML platform (target-agnostic drug-discovery engine), and generates proprietary, high-dimensional, multi-modal and relatable datasets of human cellular biology at massive scale, applying advanced ML approaches to reveal novel biological relationships. In particular, Recursion Pharmaceutical has at its headquarters clusters of robots that treat millions of cells per week with drugs, stain them with six dyes and then take pictures to capture and quantify as many morphological features as they can. By pushing these data through a ML pipeline, they hope to find relationships that are invisible to the human and to tease out clusters of effects that can guide their drug discovery.
Recursion Pharmaceuticals Inc (RXRX), that went public in April 2021, had so far the following transformational partnerships with leading large pharma companies:
⏺ In 2020, a strategic collaboration was announced that to leverage Recursion’s purpose-built AI-guided drug discovery platform and Bayer’s (OTCMKTS: BAYRY) small molecule compound library and deep scientific expertise to discover and develop new treatments for fibrotic diseases of the lung, kidney, heart and more.
On November 10, 2023, Bayer and Recursion expanded their oncology research partnership and may launch up to seven oncology programmes.
Recursion is entitled to receive development and commercial milestone payments of $1.5bn, along with royalty payments on future net product sales.
Bayer will be the first beta-user of their 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.
LOWE is an LLM agent, that represents the next evolution of the Recursion OS (Recursion Operating System, OS), that supports drug discovery programs by orchestrating complex workflows that chain together a variety of steps and tools, from finding significant relationships within Recursion’s Maps of Biology and Chemistry to generating novel compounds and scheduling them for synthesis and experimentation.
Additional updates pertaining to the Bayer partnership include:
Their first joint oncology project is now expected to advance rapidly towards Lead Series nomination; and
They are on track to complete 25 unique multi-modal data packages that they expect to deliver in the third quarter of 2024.
⏺ On December 7, 2021, Recursion announced a transformational collaboration with Roche (SWX: RO) and Genentech, in order for Recursion to work with both Roche and Genentech's R&D units to leverage technology-enabled drug discovery through the Recursion OS. Under the terms of the agreement, Recursion will receive an upfront payment of $150M while Roche and Genentech (combined) may initiate up to 40 programs, each of which, if successfully developed and commercialized, could yield more than $300M in development, commercialization and net sales milestones for Recursion, as well as tiered royalties on net sales.
On October 2, 2023, just over one and a half years into the exciting collaboration with Roche and Genentech, Recursion announced that they have reached the first milestone: after building fit-for-purpose oncology maps for their partner spanning whole-genome arrayed CRISPR knockouts and hundreds of thousands of small molecules, they have identified and validated the first hit series for this particular disease, and Roche has exercised the Small Molecule Validation Program Option.
⏺ On June 12, 2023, Recursion acquired the two emerging Canadian AI drug-discovery firms: Cyclica and Valence. Subsequently, Recursion announced a collaboration and a $50M investment from NVIDIA. Then Recursion launched Valence Labs, formerly Valence Discovery, a company with roots at Mila and mentorship from Yoshua Bengio (a Canadian computer scientist, most noted for his work on AI networks and DL), dedicated to advancing DL in drug discovery, delivering impactful research and transformative technology and embracing open-source and open-science knowledge sharing with the ML community.
⏺ On January 8, 2024, Nvidia Corp. (NVDA) doubled down on AI powered drug discovery and development, announcing an expanded partnership with Amgen Inc (AMGN) and Recursion Pharmaceuticals Inc (Nvidia dives deeper into AI drug development with Amgen, Recursion partnerships). Amgen’s subsidiary deCODE Genetics is building out a supercomputer to create genomics “foundation models”—models trained on massive datasets to tackle a variety of jobs—to fuel drug discovery. deCode will power its new genomics foundation models with Nvidia’s supercomputer and BioNeMo generative AI platform. Recursion is also joining the party and will be the first third-party addition to the BioNeMo platform, adding its Phenom-Beta program for wider use.
⏺ On May 12, 2024, it was announced that NVIDIA bought $70M of shares in RXRX 0.00%↑. Recursion Pharmaceuticals collaborates with NVIDIA to accelerate drug discovery using AI technology. Their newest supercomputer, BioHive-2, powered by 504 NVIDIA H100 Tensor Core GPUs, delivers 2 exaflops of AI performance—nearly 5x faster than their previous system (Recursion Pharmaceuticals is at the forefront of AI-driven drug discovery!).
Recursion’s BioHive-2 is the largest system in the pharmaceutical industry, located at Recursion’s headquarters in Salt Lake City, and ranks No. 35 on the latest TOP500 list of the world’s fastest supercomputers.
⏺ On June 24, 2024, Helix announced is providing Recursion Pharmaceuticals access to its vast clinico-genomic data to drive drug discovery innovation (Helix and Recursion to Leverage Clinico-Genomics for Drug Discovery). Helix transforms health organizations to leverage the power of genomics across their enterprise, creating strategic value and fueling future growth.
So far at Recursion, they have something like ~20 petabytes of proprietary high-dimensional data and the company has the following clinical trials:
REC-994 (an orally bioavailable small molecule superoxide scavenger) in Phase 2 for Cerebral Cavernous Malformation (CCM). The Symptomatic Cerebral Cavernous Malformation Trial of REC-994 (SYCAMORE).
Topline Phase 2 data readout in September 2024.
REC-2282 (a pan-histone deacetylase inhibitor) in Phase 2 for Neurofibromatosis Type 2 (NF2). Efficacy and Safety of REC-2282 in Patients With Progressive Neurofibromatosis Type 2 (NF2) Mutated Meningiomas (POPLAR-NF2).
Preliminary Phase 2 data readout in the fourth quarter of 2024.
REC-4881 (an orally bioavailable, non-ATP-competitive allosteric small molecule inhibitor of MEK1 and MEK2) in Phase 2 for Familial Adenomatous Polyposis (FAP). Evaluate REC-4881 in Patients With FAP (TUPELO).
Preliminary Phase 2 data readout in the first half of 2025.
REC-4881 for the potential treatment of advanced AXIN1/APC mutant cancers. A Study of REC-4881 in Participants With Cancers Which Have an AXIN1 or APC Mutation.
Preliminary Phase 2 data readout in the first half of 2025.
REC-3964 in Phase 1 for Clostridioides difficile Infection. REC-3964 represents a novel small molecule approach designed to selectively inhibit the toxin produced by Clostridioides difficile in the gastrointestinal tract. This molecule has the potential, when used as part of a treatment regimen, to prevent recurrent disease and/or other forms of C. diff infection, which is a leading cause of antibiotic-induced diarrhea sometimes leading to significant morbidity and mortality. More than 29,000 patients die in the US every year from C. diff infection.
Phase 2 study initiation in the fourth quarter of 2024 and preliminary data readout by the end of 2025.
REC-1245 (previously identified as Target γ) targets RBM39, a novel CDK12-adjacent target identified by the Recursion OS, for HR-Proficient Ovarian Cancers and Other Solid Tumors. As a result of their collaboration with Tempus (NASDAQ: TEM), they are leveraging genomic data across all tumor types to identify clinical biomarkers for patient expansion (already incorporating causal AI models into the Recursion OS trained using data from Tempus Labs after a data partnership was announced in 2023).
IND submission in the third quarter of 2024, Phase 1/2 initiation in the fourth quarter of 2024 and Phase 1 dose-escalation data readout by the end of 2025.
Undisclosed Indication in Fibrosis (Target Epsilon) from the fibrosis collaboration with Bayer which is now entering initial investigational new drug (IND) enabling studies.
IND submission in early 2025 and Phase 1 healthy volunteer study data readout by the end of 2025.
Dozens of internal and partner programs in early stages with the first LLM and causal model driven programs entering the Recursion pipeline.
Let’s see now what Exscientia plc is offering in this mega TechBio merger.
Exscientia (Founded 2012, Oxford, UK) (NASDAQ: EXAI) is combining genetic data and global literature in ML models and anticipates and confirms disease-target associations, and then records responses in real patient samples. In 2023, after a prioritization strategy, Exscientia decided to strengthen the company’s focus, and to partner or discontinue the internal development of programmes outside of core focus, and to continue with:
the Sanofi (EPA: SAN) collaboration (first milestone achieved in the Sanofi collaboration). For more about Sanofi:
the new collaboration with Merck KGaA (ETR: MRK) (already initiated with 3 programmes). For more about Merck:
GTAEXS617 (CDK7) currently in Phase 1/2 adaptive trial in patients with advanced solid tumors,
On July 18, 2024, Exscientia plc announced it has reached an agreement to acquire GT Apeiron’s share of its oral CDK7 inhibitor programme, gaining full control of GTAEXS617 (‘617) and all related intellectual property (Exscientia Acquires Full Rights to Potential Best-in-Class CDK7 Inhibitor Ahead of Phase 1 Dose Escalation Data Readout). And
EXS74539 (LSD1), IND submission expected in the first quarter of 2024.
In 2021, Exscientia announced the first AI-designed molecule for immuno-oncology to enter human clinical trials. The A2a receptor antagonist EXS-21546 (blocks adenosine at the adenosine A2A receptor and notable adenosine A2A receptor antagonists include caffeine, theophylline and istradefylline) was co-invented and developed through a Joint Venture between Exscientia and Evotec.
In October 2023, the A2A candidate EXS21546 was discontinued after data from an unnamed peer clouded the candidate’s future.
In 2021, it was announced that their second molecule developed in collaboration between Exscientia and Japanese firm Sumitomo Dainippon Pharma, DSP-0038 (a selective serotonin 5-HT2A receptor antagonist and a serotonin 5-HT1A receptor agonist), was also about to enter Phase I trials in the US for the treatment of Alzheimer’s disease psychosis.
DSP-0038, as well as DSP-2342 (dual 5-HT2A/5-HT7 antagonist), and EXS4318 (PKC-theta) are all continuing in Phase 1 studies by partners Sumitomo Pharma (TYO: 4506) and Bristol Myers Squibb (NYSE: BMY).
For more about Bristol Myers Squibb
For more about Japan and AI:
Moreover, the first ever drug designed with the help of AI technology to enter clinical trials in January 2020 was DSP-1181, by Exscientia and Sumitomo Pharma and used to treat obsessive compulsive disorder. The compound was discovered in silico and managed to reach clinical testing in 12 months, as opposed to the typical 5 years with traditional methods. However, the drug did not progress past Phase I and in July 2022 it was discontinued.
🚨 On May 21, 2024, Exscientia cut a quarter of staff while preserving the AI-generated pipeline. Unfortunately, the company was just sued for Securities Law Violations (Exscientia plc Sued for Securities Law Violations - Contact Levi & Korsinsky Before June 25, 2024 to Discuss Your Rights).
“Every carbon atom in every living thing on the planet was produced in the heart of a dying star.”
By Brian Cox, Wonders of the Universe
🚣 Isomorphic Labs Limited
Isomorphic Labs is a drug discovery company launched in the UK in 2021 and established under Alphabet’s (NASDAQ: GOOGL) DeepMind to build on the success of AlphaFold, DeepMind’s work in protein folding. Isomorphic Labs was launched from Alphabet’s DeepMind to build on the success of AlphaFold2, DeepMind’s work. The founder of Isomorphic Labs Demis Hassabis (also Founder & CEO of DeepMind) believes there may be a common underlying structure between biology and information science, an isomorphism, a structure-preserving mapping between two structures of the same type that can be reversed by an inverse mapping, while he is trying to reimagine the entire drug discovery process from first principles with an AI-first approach.
On January 9, 2023, Isomorphic Lab announced the formation of its Scientific Advisory Board. Among its scientific advisors are Nobel Prize laureates Jennifer Doudna, David MacMillan, Paul Nurse and Venki Ramakrishnan.
On January 7, 2024, Alphabet’s Isomorphic stacked two new deals with Lilly, Novartis worth nearly $3B ahead of JPM. Eli Lilly (NYSE: LLY) is handing over $45M upfront to discover small molecule therapies for undisclosed disease targets with more than $1.7 billion in milestone payments. Also the deal with Novartis is similar including $37.5M in upfront cash with $1.2 billion in biobucks in milestone payments, identifying small molecules against three undisclosed targets. For more about Novartis and Lilly:
On May 8, 2024, Google’s DeepMind and Isomorphic Labs announced AlphaFold 3 AI model. AlphaFold 3 is a new AI model that can accurately predict the structure and interactions of molecules down to the DNA. When compared to AlphaFold 2, the AlphaFold 3 delivers a 50% improvement for the interactions of proteins with other molecule types. In some categories, the AlphaFold 3 delivers double the prediction accuracy. Also, AlphaFold 3 has become the first AI system to surpass physics-based tools for biomolecular structure prediction.
AlphaFold 3 model with a substantially updated diffusion-based architecture is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues.
The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein–ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein–nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody–antigen prediction accuracy compared with AlphaFold-Multimer v.2.3.
Together, these results show that high-accuracy modeling across biomolecular space is possible within a single unified deep-learning framework.
Accurate structure prediction of biomolecular interactions with AlphaFold 3.
Additionally, Google DeepMind also announced the launch of AlphaFold Server, a free tool for predicting how proteins interact with other molecules throughout the cell. Scientists around the world can use this tool for free for non-commercial research. Google DeepMind will be expanding its free AlphaFold education online course with EMBL-EBI and they will equip scientists with the tools they need to accelerate adoption and research.
“In science, there are no universal truths, just views of the world that have yet to be shown to be false.”
By Brian Cox, Why Does E=mc²?
🏊 Phare Bio Limited
Phare Bio (2020, US) is a social venture using novel AI and Deep Learning to tackle the world’s most urgent threats, like the aggressive evolution of antibiotic-resistant bacteria and a dwindling antibiotic discovery pipeline that have resulted in an antimicrobial resistance (AMR) crisis. Accordingly, Phare has integrated world-class expertise and decades of experience in AI, bioengineering and pharmaceutical development to rapidly discover and develop novel classes of antibiotics that target urgent threats like Acinetobacter baumannii, Pseudomonas aeruginosa and Klebsiella pneumoniae. This unique and self-sustaining approach will enable them to outpace the emergence and global dissemination of antibiotic resistance.
A White-Box Machine Learning Approach for Revealing Antibiotic Mechanisms of Action.
How Phare Bio is using AI to discover new antibiotics with the potential to save millions of lives.
Phare Bio (a public charity located in Boston, MA) has partnered with the Collins Lab at MIT and the Broad Institute on its AI/deep learning platform for antibiotic discovery work.
“One of the beautiful things about mathematical physics is that equations contain stories.”
By Brian Cox, Human Universe
🚣 Nanome Inc
Nanome (2015, US) is virtual reality software for molecular modeling, collaborative drug design, 3d visualization of molecular structures and many more. Nanome offers a global real-time collaboration using Virtual Reality from general chemistry to pharmaceutical drug discovery, for Medicinal Chemists, Computational Chemists, Structural Biologists, Crystallographers and Protein Engineers.
Last year, as part of the latest generation of LLM-enabled applications, Nanome launched MARA (Molecular Analysis and Reasoning Assistant), an AI Agentic system for Scientific Informatics. This scientific co-pilot sits completely behind your IT firewall and enables your team to easily build tools and workflows that seamlessly integrate internal databases and tasks.
Right now, top R&D labs conduct cutting-edge research and make billion-dollar decisions by utilizing Nanome, a tool that isn’t just for experts but can also be used by students and amateur scientists studying chemistry and biology to build 3D molecules or simulate an entire protein made of hundreds of atoms, all in one collaborative environment.
Download Nanome for free on: Nanome Home, Oculus, SteamVR and Viveport.
Lantern Pharma Second Quarter 2024
CEO and President Panna Sharma and management shared exciting updates of the quarter - with additional focus on preliminary patient data and clinical readouts for Phase 2 LP-300 Harmonic™️ Trial 👇
For more about Lantern Pharma:
🧜 Darween Bioscience Inc
Darween Bioscience (2023, France) is a molecular farming company focused on the production of biosimilar pharmaceuticals using oilseed crops. Their technology is designed to tackle the key challenges associated with biologic drugs, which include their high cost and frequent shortages, since oilseed crops can be used to efficiently produce biosimilar pharmaceuticals making them more affordable and widely available. Their first monoclonal antibody is a biosimilar to Keytruda reference medicine that is currently sold at an annual cost of $190,000. Instead Darween’s biosimilar will be sold 4 times cheaper at $45,000, reaching price-parity with current chemotherapy with X-ray treatment.
Darween Bioscience was founded Cyril Véran, former CEO of a Plant Biotech company acquired by Champerché (Smart Farming System was cultivating high-value active pharmaceutical ingredients, APIs, within plant roots), Leonard Strouk, a Biochemist and former co-founder of the GenAI startup Selas (a Platform as a Service with Plug and Play AI services to leverage State of the Art text-to-anything features for your product) and Bertrand Gakière, VP of the Biology Department at Paris-Saclay University and a researcher at the IPS2 metabolic platform at the Saclay Plant Science Institute.
Currently they are raising and so far they were backed by: SkyDeck Batch 18/Equity Funding, Berkeley SkyDeck/Equity Funding, Conseil Régional Ile de France/€15k Grant, Bpifrance Innovation/€90k Grant and EIT Health/ €1k Grant.