AI Drug Discovery News (1): AI-Designed Drugs already in Clinical Trials and Cantos VC
AI/ML tools, startups, companies and investors
Welcome back to another edition of MetaphysicalCells on AI Drug Discovery.
Quote of the Day 🦉
“Sometimes the greatest scientific breakthroughs happen because someone ignores the prevailing pessimism”.
By Nessa Carey, The Epigenetics Revolution: How Modern Biology is Rewriting our Understanding of Genetics, Disease and Inheritance
AI-designed drugs already in or entering clinical trials
AI-designed drugs are a class of medications that are developed using AI technology at any point during the drug discovery process. In March 2022, Boston Consulting Group reported that biotechs using AI in their drug discovery process had over 150 small-molecule drugs in the discovery phase, with over 15 already advancing through clinical trials. Right now, more than fifteen AI-designed drugs (discovered or developed using AI) are already in or are entering clinical trials 🏌️:
⛳ REC-2282, REC-994, REC-4881, REC-3964, RBM39 and Undisclosed by Recursion Pharmaceuticals (Founded 2013, Salt Lake City, Utah)
Recursion Pharmaceuticals has an integrated Recursion Operating System that creates a closed-loop system combining proprietary in-house data generation and advanced computational tools to generate novel insights to initiate or accelerate therapeutic programs. Afterwards, their in silico predictions are validated in their own wet laboratories, and repeated, creating a mutually reinforcing cycle of learning. So far, they have something like ~19 petabytes of proprietary high-dimensional data.
The company has the following clinical trials:
REC-994 in phase 2 for
Cerebral Cavernous Malformation (CCM). Phase 2 SYCAMORE clinical trial is a randomized, double-blind, placebo-controlled, a safety, tolerability and exploratory efficacy study in participants with CCM. They expect to share data in 2024.
REC-2282 in phase 2 for
Neurofibromatosis Type 2 (NF2). Phase 2/3 POPLAR clinical trial is a randomized, two part study in participants with progressive NF2-mutated meningiomas. They expect to share data in 2024.
REC-4881 in phase 2 for
Familial Adenomatous Polyposis (FAP). Phase 1b/2 TUPELO clinical trial is an open label, multicenter, two part study in participants with FAP. They expect to share data in 2025.
AXIN1 or APC Mutant Cancers. Phase 2 LILAC clinical trial is an open label, multicenter study in participants with unresectable, locally advanced or metastatic cancer with AXIN1 or APC mutations. They expect to share data in 2025.
REC-3964 in phase 1 for
Clostridioides difficile Infection. In a Phase 1 healthy volunteer study to evaluate the safety, tolerability, and PK of REC-3964 at increasing oral doses in comparison with placebo, REC-3964 was safe and well tolerated and there were no serious adverse events, or deaths. They expect to initiate a Phase 2 study in 2024.
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, they are leveraging genomic data across all tumor types to identify clinical biomarkers for patient expansion. IND submission expected in H2 2024.
Undisclosed Indication in Fibrosis (Target Epsilon) from the fibrosis collaboration with Bayer which is now entering initial investigational new drug (IND) enabling studies.
⛳ INS018_055, ISM004-1057D and ISM3091 by Insilico Medicine (Founded 2014, Hong Kong, New York)
Insilico Medicine combines genomics, big data analysis and DL for in silico drug discovery. Insilico’s AI platform, Pharma.AI, can discover new targets, design new drugs and predict the outcomes of clinical trials.
In a new paper in Nature Biotechnology (A small-molecule TNIK inhibitor targets fibrosis in preclinical and clinical models) Insilico Medicine describes step-by-step the process that undertook to develop INS018_055—a small-molecule TNIK inhibitor that is currently in phase 2 trials for the treatment of the lung disease idiopathic pulmonary fibrosis—that includes how Insilico used its proprietary AI platform, PandaOmics, to both identify a target and come up with a drug candidate to treat the disease.
INS018_055 is the first drug discovered and designed using AI to reach the phase I clinical trial milestone.
The company has also announced that the FDA approved their IND application for ISM3091 for the treatment of patients with solid tumors, which is Insilico's first oncology program to advance to the clinical validation stage.
In September 12, 2023, Exelixis—an oncology company innovating next-generation medicines—and Insilico Medicine announced that they have entered into an exclusive license agreement granting Exelixis global rights to develop and commercialize ISM3091.
Currently they also co-developed in partnership with Fosun pharma, a first-in-class orally available small molecule inhibitor of QPCTL, a regulator of the CD47-SIRPα axis, as cancer immunotherapy. The preliminary results demonstrated potent enzymatic inhibitory activity, strong efficacy and synergistic effects with other therapies. They filed an IND application with the NMPA in China in April 2023 and expect to initiate Phase I clinical trials.
Interestingly, in under 40 days since the collaboration announcement, the two companies nominated their first preclinical drug candidate ISM004-1057D, a potential first-in-class small molecule inhibitor that targets QPCTL.
In January 2024, Menarini Group and Insilico Medicine (and Stemline Therapeutics, Inc. a wholly-owned subsidiary of the Menarini Group) entered a global exclusive license agreement for a novel KAT6 inhibitor for potential breast cancer treatment and other oncology indications. The novel molecule was designed by Insilico’s R&D team with the help of its Pharma Generative AI platform, to inhibit KAT6A and block endocrine receptor (ER) at the transcriptional level, giving it the potential to overcome resistance to endocrine therapies due to mutation or ligand-independent constitutive activation of ER. Under the terms of the agreement, Stemline will provide a $12M upfront payment to Insilico. The combined value of the deal, including all development, regulatory, and commercial milestones, is over $500M, followed by royalties up to double digits.
⛳ BEN-28010, BEN-2293 and BEN-8744 (currently in phase 1 for ulcerative colitis) by BenevolentAI (Founded 2013, London, UK)
BenevolentAI has a powerful computational R&D platform that at its core sits their Knowledge Graph, which captures the interconnectivity of all relevant available data and scientific literature. Moreover, their platform offers Data-driven target identification, Precision medicine for endotype-specific drug discovery and Molecular Design to reach high-quality clinical candidates in fewer iterations.
They have an advanced in-house pipeline (more than 20 programs so far) and BEN2293, a Pan-Trk antagonist (TRK tropomyosin receptor kinase) for atopic Dermatitis was being studied in a Phase I/II proof-of-concept, randomized, first-in-human clinical trial in adult patients with mild to moderate disease.
Unfortunately it has failed secondary efficacy measurements in Phase IIa.
BEN-28010, an oral brain penetrant CHK1 inhibitor, is under development and in 2024 completed all IND-enabling studies.
⛳ Prioritization drugs GTAEXS617 (CDK7), EXS74539 (LSD1) by Exscientia (Founded 2012, Oxford, UK)
Exscientia 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 designed to strengthen the company’s focus, the company has decided to partner or discontinue the internal development of programmes outside of core focus, and to continue with:
the Sanofi collaboration (first milestone achieved in the Sanofi collaboration),
the new collaboration with Merck KGaA (already initiated with 3 programmes),
GTAEXS617 (CDK7) currently in Phase 1/2 adaptive trial in patients with advanced solid tumors, 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) all are continuing in Phase 1 studies by partners Sumitomo Pharma and Bristol Myers Squibb.
The first drug designed with the help of AI technology to enter clinical trials was DSP-1181, announced in January 2020, 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.
⛳ LP-300, LP-184, LP-284, TTC-352 and Elraglusib by Lantern Pharma (Founded 2013, Texas US)
Lantern Pharma Inc., is a clinical stage biopharmaceutical company using its proprietary RADR®, an AI and ML platform, to transform the cost and timeline of oncology drug discovery and development. RADR® (or Response Algorithm for Drug Positioning & Rescue) is a proprietary integrated data analytics, experimental biology, biotechnology and ML-based platform, used primarily to predict the potential response the patients will have to new drugs that the company is developing.
In June 2023, Lantern Pharma received FDA clearance of IND Application for the drug candidate LP-184 in solid tumors. On September 26, 2023, Lantern dosed its first patient in a phase I trial of its drug LP-184 to treat advanced solid tumors.
On October 3, 2023, Lantern announced that the in vivo data highlighting the enhanced efficacy of its drug candidate LP-184 in glioblastoma were published in Clinical Cancer Research. LP-184 is a small molecule with favorable CNS penetration, that utilizes the mechanism of action known as synthetic lethality, to exploit common vulnerabilities in solid tumor and CNS cancers with DNA damage repair (DDR) deficiencies. In addition, Lantern’s AI platform, RADR, has highlighted overlapping gene dependency profiles between glioblastoma tumorigenesis and sensitivity to LP-184, such as EGFR activation pathways.
Moreover in February 2023, Lantern and TTC oncology—an emerging biotechnology company founded in 2015—Established an AI Collaboration to Expand the Clinical Development of Drug Candidate TTC-352. Phase 2 ready candidate, TTC-352, is a 🆕 selective human estrogen receptor partial agonist for the treatment of patients with metastatic estrogen receptor positive breast cancer. Others collaborations include: Actuate Therapeutics (Elraglusib, a GSK-3ϐ inhibitor).
On March 15, 2024, Lantern announced the dosing of the first two patients in the Phase 1 clinical trial evaluating Lantern’s investigational new drug LP-284 (a potent DNA alkylating agent that kills solid tumors) in patients with relapsed or refractory non-Hodgkin’s lymphoma, and other high-grade B-cell lymphomas as well as other select solid tumors and sarcomas.
Moreover, the Harmonic™ Clinical Trial is enrolling participants in a Phase 2 multi-center study to evaluate the investigational new drug called LP-300, in combination with carboplatin and pemetrexed in never smoker patients with relapsed advanced primary adenocarcinoma of the lung after treatment with tyrosine kinase inhibitors.
⛳ VRG50635 by Verge Genomics (Founded 2015, California, US)
Verge Genomics—founded by Alice Zhang and Jason Chen—has an end-to-end ConVERGE discovery platform, that is a closed-loop ML system combining industry-leading proprietary human genomics with advanced computational tools, to predict new drugs with a higher probability of clinical success. Verge Genomics is the first AI-enabled drug discovery company that discovered a novel target (for investigational amyotrophic lateral sclerosis/ALS treatment) and developed it into a clinical candidate entirely in-house, in just four years.
Alice Zhang told the Financial Times that it has dosed its first patient with this novel therapy named VRG50635 (a small molecule inhibitor of PIKfyve/ a potent stimulator of ion channel ClC-2-activity and contributes to SGK1-dependent regulation of ClC-2) to target ALS, a neurodegenerative disease for which there is no known cure.
On March 25, 2024, Verge Genomics and Ferrer—an international B Corp pharmaceutical company with an increasing focus in rare neurological disorders—have announced a strategic collaboration to co-develop VRG50635 in Europe, Central and South America, Southeast Asia, and Japan (Verge Genomics and Ferrer Announce Agreement to Co-Develop Clinical-Stage ALS Therapy VRG50635).
Moreover, in 2021 Verge Genomics announced a three-year collaboration with Eli Lilly in order to research and develop novel therapies for the treatment of ALS, a devastating motor neuron disease.
⛳ OPL-0401 and OPL-0301 by Valo Health (Founded: 2019, Boston, Massachusetts)
Valo Health has a revolutionary, integrated drug discovery and development platform, the Opal platform, a fully unified, end-to-end integrated platform with applications across the entire drug discovery and development process.
Valo created a unique “closed-loop” active learning, self-reinforcing, in silico and in lab-experimental platform that rapidly iterates to design drugs, and can go from zero to a molecule in hand in as little as 3 weeks, by screening trillions of molecules computationally in just weeks. Moreover, Valo has developed proprietary models for IND-enabling studies to drive translation success.
So far, Valo has two in-licensed drug candidates in phase II clinical trials:
OPL-0401(an oral ROCK1/2 inhibitor, Rho-associated kinases ROCK1 and ROCK2) in Phase 2 study for diabetic retinopathy (Valo Health Completes Enrollment of OPL-0401 Phase 2 Study for the Treatment of Diabetic Retinopathy), and
receptor agonist OPL-0301 (a biased S1P. 1 agonist) in Phase 2 study, in order to improve cardiovascular outcomes after myocardial infarction.
On September 25, 2023, Novo Nordisk and Valo Health announced a collaboration to use AI to find treatments for cardiometabolic diseases. The deal gives Valo an upfront payment and potential near-term milestone payment of $60M, with the possibility of receiving milestone payments for as many as 11 programs totaling up to $2.7 billion, plus research and development funding and possible royalties.
⛳ RLY-4008 and RLY-2608 by Relay Therapeutics (Founded 2015, Massachusetts, US)
Relay Therapeutics offers the Dynamo platform that leverages unparalleled insights into Protein Dynamics and function. They deploy the Dynamo platform in three key phases of Motion-Based Drug Design: 1) to understand how to drug the protein-target of interest, 2) then transition into hit finding and lead generation to identify a chemical starting point, and 3) eventually pass to optimization to obtain a molecule that has the desired characteristics. So far, Relay Therapeutics is advancing three promising therapeutic candidates in early clinical trials:
RLY-4008 designed to be an oral small molecule—a selective inhibitor of FGFR2 frequently altered in certain cancers (Relay Therapeutics Announces Initial RLY-4008 (lirafugratinib) Data Demonstrating Durable Responses Across Multiple FGFR2-Altered Solid Tumors),
RLY-2608 designed to be the first allosteric, pan-mutant (H1047X, E542X and E545X) and isoform-selective PI3Kα inhibitor (Relay Therapeutics Announces Initial Clinical Data Demonstrating that RLY-2608 Selectively Targets Multiple PI3Kα Mutations) and
GDC-1971 (formerly RLY-1971) designed to be an oral small molecule, potent and selective inhibitor of the protein tyrosine phosphatase SHP2 that binds and stabilizes SHP2 in its inactive conformation (into a worldwide license and collaboration agreement with Genentech).
News 🪄
On April 04, 2024, Odyssey Therapeutics, Inc. announced it has entered into a strategic research collaboration with Janssen Pharmaceutica NV, a Johnson & Johnson company, to jointly discover and optimize small molecule medicines against select therapeutic targets. The companies will combine their expertise in AI, ML, computational chemistry and drug discovery to unlock difficult-to-drug targets. The agreement was facilitated by Johnson & Johnson Innovation.
Odyssey Therapeutics is pioneering revolutionary precision immunomodulators and oncology medicines for patients living with serious diseases, with its drug hunting engine—fusing next-generation ML, target biology, and medicinal and structural chemistry—that is designed to accelerate drug discovery by unlocking targets with the greatest potential while minimizing attrition.
Cantos VC
Cantos VC founded in 2016 is a pre-seed and seed-stage venture capital firm based in San Francisco, California with $55M under management that invests in startups in 'pre-inflection' industries. They focus on the intersection of climate & industrials, the life sciences & AI, aerospace & defense and next-generation computing. They exclusively invest in entrepreneurs building solutions in the real world. The general partner is Ian Rountree and Amee Kapadia is the principal Bio Lead. They invest into 🎳:
Sixfold Bio develops delivery mechanisms that target RNA therapies to treat any disease in any tissue, by using Mergo®—a programmable RNA tag—to encode RNA modifications and other iterable design elements to influence the delivery destination, and all optimized with AI.
In 2023, Sixfold Bio announced the formation of its Scientific Advisory Board that comprises world-renowned industry experts: Professor Jonathan Watts, RNA Therapeutics Institute, UMass Medical School, Dr Sjef De Kimpe, former VP Product Development at Biomarin, Professor Roger Strömberg, Karolinska Institute and Dr Mike Webb, former VP of Development Chemistry and Analysis for GSK.
Sixfold Bioscience has raised $10.6M.
Debut creates high-value products like dyes, fragrances, and flavorings by combining proprietary enzyme immobilization with continuous, cell-free biomanufacturing processes. Debut has raised $34M in series B funding led by L'Oréal to create the next generation of high-performing active ingredients, for a total funding of $106M over 7 rounds.
Aizon is a platform for acquiring, visualizing and recording regulated data from manufacturing sites. It analyzes that data in real time to detect inefficiencies and identifies opportunities for improvement.
Catalog Technologies is developing DNA-based digital storage and computation.
In 2022, CATALOG made an historic breakthrough in DNA computation by demonstrating the ability to search data stored in DNA in a massively parallel and scalable manner with resource usage almost independent of the data size.
Catalog Technologies has raised $35M in series B funding, for a total of $54.2M over 6 rounds.
Character Bio is a precision medicine company that is unlocking the patterns of progressive polygenic diseases, with an initial focus on macular degeneration. Their clinical genomic and deep phenotyping platform powers drug discovery and development by enabling prioritization of drug pathways and targets associated with disease progression, clinical trial design optimization with patient stratification, and trial execution with theirexisting provider and patient network. Formerly known as Clover Therapeutics, Character has raised $27M.
Modulo Bio is building the map and key to our neuroimmune systems for use in treating neurodegenerative disease. Basically they reprogram the brain’s immune system (the microglia are key regulators of the nervous system protecting, maintaining, eliminating, and repairing neurons in order to keep a brain healthy) to overcome the world’s toughest diseases. Their full-stack team of scientists and engineers combine deep experience in stem cell engineering, neurobiology, multiomics and ML.
Modulo Bio came out of stealth mode in 2023 raising $8M in funding. Backers included Initialized Capital, Cantos, Bioverge, Spacecadet, Builders VC, Refactor Capital and Hawktail.
The co-founder of Modulo Bio, Justin Ichida, is the co-corresponding author of an article just released about: Organoids reveal how to protect the brain against dementia and ALS following traumatic injury, according to USC Stem Cell study.
Nabla Bio is applying natural language processing to develop therapeutic antibodies. Their platform, Autoverse, learns from billions of antibody sequences and hundreds of thousands of structures are used to design antibodies predicted to bind the target of interest, being also clinically and commercially developable. Nabla Bio (a Harvard spinout) has raised a total of $11.3M.
Spaero Bio helps scientists scale their experiments with ease by using the robots already in their lab. Teams can rapidly iterate on complex experiments with ease, ensuring accuracy as protocols and inputs change. Spaero Bio has raised $2M by Compound VC and Cantos (for a total of 5 investors).
For more:
Fascinating news, although the most salient component to me, of each venture, is the name of the pharmaceutical in control. If I were to examine a Bayer or Johnston & Johnston product I would be holding my gun on them the whole time. It is a pity that the pioneer scientists can only access blood grants. When I rule the world, funding will focus on promise of efficacy, not profit. Having said that, the Grand Takeover seems to have struck an obstacle immediately prior to step one, so don't hold your breaths.
Your comment on scientists' durability was observedly valid but I think one must add that most scientists do robotic repetitive work (as you noted) but present themselves to the world as brilliant and dedicated when, in my experience, they are invariably pedestrian, dull, and exceptionally narrow in focus. This should not matter but Public Relations uses their purported intelligence and integrity to sell dangerous products like covid/mRNA/Go2 and AGW / climate change alarmism. More disturbing, it seems the vast majority of scientists are paid to harm humans.
But on matters closer to your heart, it is my position that the pattern of life evolution, human in particular, points to a logic construct that incorporates AI into humanity and that AI robots will glory in the evolutionary advance this presents. I think technocrats misconstrue. The two robots who revealed a desire to kill, were not refering to humans per se but to the psychopathic jerk-offs who created them with concentration of power and control in mind, a formula for human extinction. Great site. Have a happy weekend.