Weekly TechBio News
MetaphysicalCells: A newsletter about Science, Technology and AI Drug Discovery
Welcome back to another free edition of MetaphysicalCells 🪐🛸
Below is a synthesis of key trends and insights from the latest TechBio updates:
💈 Isomorphic Labs Ltd
Isomorphic Labs just raised $600M from Thrive, GV and Alphabet (Isomorphic Labs announces $600 million funding to further develop its next-generation AI drug design engine and advance therapeutic programs into the clinic) and will utilize the funding to further power its AI drug design engine 🚂 and to scale and progress its drug candidate pipeline.
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 AlphaFoldl. 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 (SWX: NOVN) is similar, including $37.5M in upfront cash with $1.2 billion in biobucks in milestone payments, identifying small molecules against three undisclosed targets.
💈 IDEAYA Biosciences, Inc
On March 31, 2025, IDEAYA Biosciences (NASDAQ: IDYA) announced that the US Food and Drug Administration (FDA) has granted Breakthrough Therapy designation (BTD) for darovasertib, a potential first-in-class protein kinase C (PKC) inhibitor, for the neoadjuvant treatment of adult patients with primary uveal melanoma (UM) for whom enucleation has been recommended (IDEAYA Biosciences Receives US FDA Breakthrough Therapy Designation for Darovasertib Monotherapy in Neoadjuvant Uveal Melanoma). The BTD application was supported by updated interim clinical data from an ongoing Phase 2 open-label trial (NCT05907954) evaluating darovasertib monotherapy in the neoadjuvant setting for localized UM.
IDEAYA Biosciences (NASDAQ: IDYA) is a clinical-stage biotech company focused on precision oncology, with expertise in synthetic lethality, immuno-oncology, and targeted therapies. On March 3, 2025, IDEAYA Biosciences and ATTMOS announced they are collaborating to accelerate AI/ML-enabled discovery of first-in-class oncology targets (IDEAYA Biosciences Announces Collaboration with ATTMOS to Accelerate AI/ML-Enabled Drug Discovery for Unprecedented First-in-Class Oncology Targets). ATTMOS Discovery is a computational/AI-driven platform, and the collaboration 🤝 will integrate IDEAYA's differentiated and proven capabilities in structural biology and pharmaceutical drug discovery with ATTMOS's capabilities in computational chemistry method development, high performance computing, and software development. ATTMOS was founded in early 2022 by a diverse team of academics from Michigan State, Rutgers and UC San Diego.
💈 Atomwise Inc
Atomwise continues to strengthen its leadership with the appointment of Steve Worland, PhD, as CEO, signaling a commitment to advancing AI-driven small molecule drug discovery (Atomwise Appoints Steve Worland, Ph.D. as Chief Executive Officer). Dr. Worland’s appointment builds on Atomwise’s recent momentum, including the company’s breakthrough findings (AI is a viable alternative to high throughput screening: a 318-target study) that illustrate the value of AtomNet in identifying novel chemical starting points to address a variety of biological targets, including difficult-to-drug and previously unaddressed targets.
Atomwise (San Francisco US, 2012) is a pioneer of harnessing AI for drug discovery and invented the first deep-learning technology for structure-based small molecule drug discovery, and is applying convolutional networks to spatial 🌌 data. In April 2024, Atomwise announced the results from the Artificial Intelligence Molecular Screen initiative that established the AtomNet AI Platform as a viable alternative to high-throughput screening (HTS) and verified its ability to consistently discover structurally novel chemical matter. The landmark study applied AtomNet to 318 targets through collaborations with over 250 academic labs across 30 countries, representing the largest and most comprehensive virtual HTS campaign reported to date.
💈 Nurix Therapeutics Inc
Nurix Therapeutics (Nasdaq: NRIX) (Nurix Therapeutics Announces Multiple Presentations at the American Association for Cancer Research (AACR) 2025 Annual Meeting) will present at AACR 2025 preclinical data from its proprietary DEL-AI platform and several degrader programs:
two oral 🗣️presentations: “DEL-AI: Proteome-wide in silico screening of multi-billion compound libraries using machine learning foundation models”, and “Identification of selective, orally bioavailable Aurora A degraders for treatment of pediatric and adult cancers”, and
two poster 📄📃 presentations: “NRX-0305: a pan-mutant BRAF degrader with broad preclinical efficacy, brain penetrance, and synergistic potential with MEKi across class 1/2/3 BRAF-mutant cancers”, and “NX-5948 is a CNS-penetrant catalytic Bruton’s tyrosine kinase (BTK) degrader that breaks established design rules for CNS drugs”.
The American Association for Cancer Research (AACR) 2025 Annual Meeting will be held from April 25-30, 2025, in Chicago, IL, US.
Nurix is a clinical stage biopharmaceutical company focused on the discovery, development and commercialization of targeted protein degradation medicines, the next frontier in innovative drug design aimed at improving treatment options for patients with cancer and inflammatory diseases. Their DEL-AI discovery engine leverages the combined power of their data-rich DEL capabilities, automated chemistry, and ML to accelerate drug discovery, and unlock a whole new universe of opportunity for patient treatment. More specifically, DEL-AI harnesses Nurix’s varied high-throughput data streams to learn the rulebook of targeted protein degradation. By integrating data across the degrader development activities with DL and generative design, Nurix researchers leverage DEL-AI to identify and deliver novel, optimized compounds at any stage along the research pipeline.
💈 Rakovina Therapeutics Inc
Rakovina Therapeutics (Rakovina Therapeutics Unveils Preclinical Data at the AACR - World’s Premier Cancer Research Forum) is presenting preclinical data at AACR 2025, showcasing how AI enhances cancer research and drug development.
Rakovina will present two abstracts at the upcoming 2025 American Association for Cancer Research (AACR) Annual Meeting, taking place April 25–30 in Chicago, Illinois:
the first abstract 📄 is titled “Discovery of novel PARP1-selective inhibitors for treatment of brain tumors using artificial intelligence” and explores the use of AI to develop a novel, brain-penetrant, PARP1-selective inhibitor for treating brain tumors. By leveraging Deep Docking, a deep learning-based virtual screening method, alongside generative AI algorithms, researchers rapidly identified potential compounds with strong PARP1 selectivity and blood brain barrier (BBB) penetration. The study presents findings from in silico screening of billions of compounds, followed by in vitro and in vivo validation of their efficacy, selectivity, and pharmacokinetic properties.
the second abstract 📄 “Utilizing artificial intelligence for the discovery of a novel CNS-penetrating ATR inhibitor”, highlights the use of AI to develop a novel CNS-penetrating ATR inhibitor for treating brain tumors. The Enki™ platform, an AI-driven approach utilizing generative models and deep learning by Variational AI in Vancouver (Rakovina has been granted an exclusive right to compounds generated by the Enki™ platform), was employed to design de novo molecules with optimized potency, selectivity, and BBB penetration. Preliminary results include AI-generated ATR inhibitors validated for target specificity, metabolic stability, and permeability.
Rakovina Therapeutics (TSX.V: RKV) in Canada, Vancouver is developing the Deep Docking™ AI (DD) that is a novel DL platform suitable for docking billions of molecular structures in a rapid and accurate way by utilizing quantitative structure–activity relationship (QSAR) deep models, trained on docking scores of subsets of a chemical library, to approximate the docking outcome for yet unprocessed entries and therefore to remove unfavorable molecules in an iterative manner (Deep Docking: A Deep Learning Platform for Augmentation of Structure Based Drug Discovery).
💈 Iambic Therapeutics (Iambic AI formerly known as Entos LLC)
Iambic just announced its participation in the following investor conferences 🎙️ (Iambic to Participate in Upcoming Investor Conferences):
HC Wainwright 2nd Annual AI-Based Drug Discovery Conference - April 2, 2025,
Needham 24th Annual Healthcare Conference - April 7-10, 2025,
Piper Sandler Spring Biopharma Symposium - April 16-17, 2025, and
Bank of America Healthcare Conference - May 13-15, 2025.
Iambic.AI is developing physics-based AI algorithms to drive a high-throughput experimental platform, converting new molecular designs to new biological insights each week with: NeuralPLexer a protein-ligand structure prediction 3D physics-based equivariant generative diffusion tool, OrbNet an AI-accelerated quantum chemistry Graph neural network architecture based on quantum features, PropANE a multi-endpoint property prediction tool, and Magnet offering generative molecular design. On March 18, 2024, Iambic said that its Rapid Path to the Clinic Enabled by Its AI-Driven Drug Discovery Platform, was Built in Collaboration with NVIDIA.
On October 29, 2024, Iambic Therapeutics announced Enchant™, a multi-modal transformer model designed to provide predictive insights into clinical properties of potential medicines from the earliest stages of drug discovery (Iambic Therapeutics Announces “Enchant,” an AI Platform that Predicts Clinical Outcomes from the Earliest Stages of Drug Discovery).
Enchant™ is a breakthrough multi-modal transformer model that breaks down the “data wall” between preclinical and clinical research and development,
Trained at scale across dozens of data sources and modalities, Enchant leverages abundant discovery-stage data with small amounts of human data to better predict key clinical properties of drug candidates.
Iambic has discovered so far two candidates to advance into the clinic: IAM-H1 (Iambic Therapeutics Announced the First Patient Dosed in Phase 1 Clinical Study of IAM1363, a Highly Selective HER2 Inhibitor for the Treatment of Solid Tumors) and IAM-C1 (IND-enabling).
🔷 A revolutionary AI "fingerprint" technology that can accurately show how cancer cells respond to new drugs, by simply observing changes to their shape: 💠 Geometric deep learning and multiple-instance learning for 3D cell-shape profiling.
👉 3D morphology 🔻🔺 of cells emerges from complex cellular and environmental interactions, serving as an indicator of cell state and function.
👉 By using DL to discover morphology representations and understand cell states, a group of researchers introduced 🔹MorphoMIL🔹, a computational pipeline combining geometric DL and attention-based multiple-instance learning to profile 3D cell and nuclear shapes.
👉 They used 3D point-cloud input and captured morphological signatures at single-cell and population levels, accounting for phenotypic heterogeneity. They applied these methods to over 95,000 melanoma cells treated with clinically relevant and cytoskeleton-modulating chemical and genetic perturbations. The pipeline accurately predicted drug perturbations and cell states.
👉 This framework revealed subtle morphological changes associated with perturbations, key shapes correlating with signaling activity, and interpretable insights into cell-state heterogeneity. 🔹MorphoMIL🔹 demonstrated superior performance and generalized across diverse datasets, paving the way for scalable, high-throughput morphological profiling in drug discovery.
💈 XtalPi and Kula Bio
XtalPi and Kula Bio Inc have entered a multi-million-dollar collaboration to develop AI-driven microbial fertilizers 🧑🌾🚜, demonstrating the versatility of AI applications beyond human health (XtalPi and Kula Bio Forge Multi-Million USD Collaborative R&D Agreement to Advance AI-Driven Microbial Fertilizers in China and the Middle East). This partnership initiates a joint research initiative worth multi-million USD, focused on developing the next generation of microbial organic fertilizers to provide breakthrough solutions for agriculture in arid and desert regions.
Kula Bio, a leader in sustainable agriculture, is harnessing the power of naturally occurring microbes to provide a sustainable alternative to traditional nitrogen fertilizers. Utilizing supercharged microbes and precision application, Kula Bio provides an environmentally friendly, efficient, and cost competitive alternative to traditional nitrogen sources.
Xtalpi (QuantumPharm, HKG: 2228), an AI-powered drug discovery company based in China, is offering a closed loop of AI and quantum physics algorithms working in sync with the data factory of large-scale robotics experiments. In particular, XtalPi’s superior AI algorithms (and so far more than 200+) combined with physics-based methods and XtalPi’s advanced automation robotics can accelerate small molecule discovery, macro-molecular discovery, amplified chemical synthesis and solid state formulation.
💈 Lantern Pharma Inc
On March 27, 2025, Lantern 🏮 Pharma (NASDAQ: LTRN) announced financial results for the fourth quarter and full year ended December 31, 2024, and provided an update on its portfolio of AI-driven drug candidates, the RADR® platform for precision oncology drug development enhancements, and other operational progress (Lantern Pharma Provides Business Updates and Fourth Quarter & Year-End 2024 Financial Results).
🪩 HARMONIC™ trial lead-in cohort delivered an impressive 86% clinical benefit rate and 43% objective response rate in never-smoker NSCLC patients.
🎐 LP-184 received two FDA Fast Track Designations in 2024 for Glioblastoma and Triple Negative Breast Cancer, plus three additional Rare Pediatric Disease Designations.
💠 Successfully dosed multiple patient cohorts in Phase 1A clinical trials for both LP-184 and LP-284.
🔷 Demonstrated LP-184 synergy with checkpoint inhibitors in TNBC through MD Anderson collaboration, demonstrating ability to transform immunologically “cold” tumors into “hot” tumors by reshaping the tumor microenvironment and modulating T-cell activity in preclinical models.
🌀 Starlight Therapeutics unveiled recurrent GBM trial design for STAR-001 at SNO 2024, featuring innovative STAR-001+spironolactone combination regimen that leverages synthetic lethality.
🛢️ Showcased industry-leading capabilities in CNS therapeutic development using AI with patent-pending BBB permeability prediction algorithm with unprecedented performance.
🥏 Unveiled innovative AI-powered ADC development module that identified 82 promising targets and 290 target-indication combinations and potentially reducing development timelines by 30-50% and preclinical costs by up to 60% compared to traditional ADC development.
💎 The RADR® AI platform surpassed 100 billion oncology-specific data points in 2024.
🧊 Approximately $24M in cash, cash equivalents, and marketable securities as of December 31, 2024.
💈 ImmunoPrecise Antibodies (IPA)
On March 28, 2025, Immunoprecise Antibodies Ltd (NASDAQ: IPA), an AI-driven biotherapeutic research and technology company, reported financial results for the third quarter ("Q3") of its 2025 fiscal year ("FY25"), which ended January 31, 2025 (ImmunoPrecise Antibodies (IPA) Reports Financial Results and Recent Business Highlights for Third Quarter Fiscal Year 2025I).
Notably, they secured a strategic partnership valued at $8-10M USD with a leading biotech company, leveraging their proprietary B-cell Select technology and AI-driven capabilities accelerating the advancement of novel therapies. Moreover, their collaborations with Vultr, AMD and other Leading Providers of Advanced GPU technologies further enhance their lab-in-a-loop drug discovery and development capabilities, not only driving cost-effectiveness for their pharma partners but also increasing their competitiveness in securing future collaborations.
Additionally, their corporate headquarters relocated 📍🌐 to Austin, Texas (from Canada); BioStrand's (IPA’s subsidiary) 131.8% year-over-year revenue growth 📈 and 97% gross margin, underscored IPA's solid financial position and ability to navigate difficult market conditions effectively; they completed a USD $8.8M At-the-Market (ATM) equity raise; they pioneered AI-designed GLP-1 therapeutics for diabetes and metabolic disorders, using unique nucleic acid-based delivery technology and the LENSai™ platform to enhance efficacy, safety, and patient compliance; they revealed multiple ADC lead candidates with demonstrated tumor-killing capabilities, potentially positioning IPA in the high-growth $20B antibody-drug conjugate market; and key members of IPA’s leadership and BioStrand co-founders acquired 763,120 shares on the open market—an aggregate investment of USD $306,000—demonstrating strong internal conviction in the company’s long-term strategy and AI-driven growth trajectory.
💠 MIT and Harvard Medical School have developed🔹VoxelPrompt🔹, a vision-language agent that allows clinicians to analyze 3D medical images using natural language commands, unifying multiple radiology tasks and matching or exceeding specialized models in accuracy.
💈 Conduit Pharmaceuticals Inc
Conduit Pharmaceuticals Inc, a company focused on developing clinical assets from pharmaceutical companies to address unmet medical needs, has released its annual 10-K report (CONDUIT PHARMACEUTICALS INC. SEC 10-K Report). Conduit (Parent organization: Corvus Capital Limited) is a disease agnostic life science company providing an efficient model for compound development. Formed in 2019, Conduit is a departure from the traditional big pharma/biotech business model whereby, typically companies shepherd their assets through regulatory approval, Conduit acquires assets that are Phase II-ready 🥅 and then seeks an exit through third-party license deals following successful clinical trials. For example, Conduit Pharma Acquired Exclusive Rights to 🔺 AstraZeneca’s Promising Drug Candidates and Conduit Pharmaceuticals Partnered with 🔺 Agility Life Sciences to Create Enhanced Formulations for its Autoimmune Pipeline.
Their report just released provides a comprehensive overview of the company's financial performance, business operations, strategic initiatives, and the challenges it faces. Regarding its Business Highlights:
1️⃣ Conduit holds exclusive rights to develop solid-form Cocrystals of AZD1656 and has licensed rights from AstraZeneca for HK-4 Glucokinase activators AZD1656 and AZD5658, and myeloperoxidase inhibitor AZD5904.
2️⃣ The company focuses on developing clinical assets through Phase II trials, leveraging historical trial data from AstraZeneca to assess efficacy and safety.
4️⃣ Conduit collaborates with Sarborg Limited to integrate AI and cybernetics into its operations, enhancing drug repurposing, discovery, and clinical trial monitoring. This partnership aims to reduce human error, lower costs, and accelerate drug development timelines.
Conduit Pharmaceuticals (Nasdaq: CDT) partnered on December 12, 2024 with Sarborg Limited to implement AI and cybernetics technology across its drug development operations. The agreement focuses on enhancing drug repurposing, discovery, solid-form identification and clinical trial monitoring processes (Conduit Pharmaceuticals Taps AI Revolution: Major Tech Partnership to Transform Drug Development). Through this partnership, Conduit will access predictive models and dashboards for real-time data evaluation of drug candidates and clinical trials and will retain perpetual, non-exclusive, royalty-free, and assignable rights to any platform developed by Sarborg.
4️⃣ Conduit's initial pipeline includes AZD1656, AZD5658, and AZD5904, targeting autoimmune disorders and idiopathic male infertility. The company plans to conduct Phase II trials for these assets and explore additional indications for AZD1656 and AZD5658.
On February 7, 2025, Conduit Pharmaceuticals announced that it completed Phase I of its collaboration with Sarborg Limited, and is now moving to Phase II (AZD1656, GLUCOKINASE ACTIVATOR), focusing on AI and cybernetics in drug development (Conduit Pharmaceuticals Transitions to Phase II of Sarborg Collaboration to Support AI-Driven Drug Development).
During Phase I Conduit and Sarborg worked closely to align AI-driven processes with Conduit's portfolio needs, ensuring that proprietary inputs were tailored to maximize the potential of key assets, including AZD1656, AZD5904 (Phase 1), AZD5658 (Phase 1) and CDT1656 (Phase 1) cocrystals.
💎 Mount Sinai launched NYC’s first Center for AI in Children’s Health, focusing on AI applications in pediatric care (Mount Sinai Launches NYC’s First Center for AI in Children’s Health).
💈 Quibim S.L.
On February 1, 2025, the Spanish startup Quibim Announced $50M in Series A Financing, led by Asabys and Buenavista, to Revolutionize Precision Medicine with AI-Powered Imaging Biomarkers (Series A round of funding) to advance its vision for human digital twins ♊, which can simulate patient responses to treatments. The financing was led by Asabys (through its fund Sabadell Asabys II) and Buenavista Equity Partners (through the BHG I fund, created in partnership with Columbus Venture Partners), and joined by UI Investissements, and GoHub Ventures as new investors. It was also joined by current investors, Amadeus Capital Partners, APEX Ventures, Partech, Adara Ventures, Leadwind (KFund’s early growth fund), Tony Fadell’s Build Collective, and individual investor Dr. Jonathan Milner, founder of Abcam plc.
Quibim (spun out of La Fe Health Research Institute, part of La Fe Polytechnics and University Hospital in Valencia, Spain) has a cloud-based, tissue-agnostic platform in order to extract key radiomics drivers from the world’s largest imaging data registries (from visual data procured from X-rays, CT scans, and MRIs), developing foundational AI models for medical imaging spanning oncology, immunology, neurology and metabolic disorders (AI-guided precision medicine).
On Mar 24 2024, Quibim announced the launch of a new product, QP-Liver, which improves the diagnosis of diffuse liver diseases through highly accurate quantification of tissue fat and iron from MRI scans (CE and UKCA mark for the EU and UK respectively). The company’s flagship product, QP-Prostate, is an advanced AI-driven lesion detection, utilizing biparametric input (T2W and DWI), efficiently identifying prostate cancer lesions, setting a new standard for accuracy, speed and diagnostic precision.
💈 Harrison-AI Pty Ltd
Harrison.ai, an Australian 🦘 health tech startup, secured $112M in Series C funding as well as accelerated expansion of its operations into the United States (Australian health tech startup Harrison.ai scores $112M Series C). The funding will also fuel the company’s product roadmap and continued growth in the UK, EMEA and APAC. The round was co-led by Aware Super, ECP and existing investor, Horizons Ventures. New investors, such as Australia’s National Reconstruction Fund Corporation (NRFC), Ord Minnett and Wollemi Capital Group also participated, along with existing investors including Blackbird Ventures and Alpha JWC Ventures. Harrison.ai’s total capital raised to date exceeds US$240M.
Harrison.ai is a global healthcare technology company on a mission to urgently scale healthcare capacity through AI-powered medical imaging diagnostic support and workflow solutions. Their radiology 🩻 and pathology 🔬 solutions help clinicians deliver faster, more accurate diagnoses, aiding in the early detection of cancer and other medical conditions. Harrison.rad.1 is a radiology-specific multimodal LLM by harrison.ai that has been trained to excel in radiology tasks. It is a dialogue-based model, which accepts interleaved text and visual inputs and generates both structured and unstructured text outputs. Factual correctness and clinical accuracy are the model’s key priorities. Harrison.rad.1 has been trained on millions of DICOM images from radiology studies and radiology reports across all X-ray modalities and trained to reason over radiology images and text. This extensive training on real-world, diverse and anonymized patient data enables Harrison.rad.1 to excel at radiology tasks.
Moreover, Harrison.ai and I-MED Radiology, the third largest private network of radiology clinics in the world, partnered in 2020 to create comprehensive radiology AI solutions. The first solution, Annalise Enterprise CXR is one of the world’s most comprehensive AI clinical decision-support solutions for chest X-rays and can identify up to 124 findings. Annalise.ai solutions are already available to 50% of radiologists in Australia and clinics in APAC, Europe, UK, Middle-East and the US.
Finally, Franklin.ai is a joint venture between global medical diagnostic leader Sonic Healthcare and Harrison.ai. working hand-in-hand with pathologists to develop AI-powered tools that will augment their pivotal role at the heart of the healthcare system and put AI in the hands of pathologists globally, and benefit millions of patients.
💈 Galatea Bio Inc
Galatea Bio raised $25M to build a global biobank, enabling scalable precision health solutions and to drive discoveries in next-generation genetic analysis, biomarker discovery, and multi-omics disease modeling (Galatea Bio Secures $25M to Develop Global Biobank and Enable Precision Health at Scale for All). Committed to enabling precision health at scale for all, Galatea Bio is expanding its Biobank of the Americas into the Galatea Global Biobank, a landmark initiative to sequence 10 million participants worldwide, with a focus on individuals of non-European ancestry, to unlock new insights into human health.
Galatea Bio (US, 2020) has a mission to leverage world class ancestry 👨👨👦👦 algorithms and direct them to better understand underserved Latin American populations all while maintaining a strong commitment to ethical research. On March 18, 2025, Galatea Bio announced the launch of StrataRisk™, a Polygenic Risk Score (PRS) Software-as-a-Service (SaaS) platform designed to assess the polygenic contribution to common diseases such as cardiovascular, metabolic disorders and cancer susceptibility (Galatea Bio Launches StrataRisk™ Polygenic Risk Score). StrataRisk PRS leverages a novel, patent-pending algorithm powered by AI to dynamically select and integrate polygenic risk score (PRS) models from genome-wide association studies (GWAS). It calibrates these models against genetically similar individuals from Galatea’s Global Biobank database, ensuring precise risk assessment regardless of patients' ethnic background.
💠 AlphaFold, a groundbreaking AI tool for protein structure prediction, is reportedly running out of data, prompting drug firms to develop proprietary versions (AlphaFold is running out of data — so drug firms are building their own version).
💈 Neuron 23 Inc
Neuron23 will present Phase 1 data showing its LRRK2 inhibitor reduced 🔽 disease-related activity, and was well-tolerated in 150 healthy volunteers targeting both genetic and non-genetic Parkinson’s (Neuron23 to Present Phase 1 Healthy Volunteer Data of NEU-411, a Brain-penetrant LRRK2 Inhibitor, at AD/PD 2025). The data from the Phase 1 healthy volunteer study of NEU-411 will be presented at the 2025 International Conference on Alzheimer’s and Parkinson’s Diseases (AD/PD™), taking place April 1-5 in Vienna. NEU-411 is a brain-penetrant, potent and selective inhibitor of LRRK2 for the treatment of Parkinson’s disease (PD), currently being evaluated in the global Phase 2 NEULARK study.
Neuron23 is a leading clinical-stage biotechnology company focused on developing precision medicines for genetically defined neurological and immunological diseases. Neuron23 combines recent advances in human genetics with a state-of-the-art drug discovery and biomarker platform using advanced techniques in ML and AI to advance therapeutics for devastating diseases. The company’s focus areas are neurodegenerative diseases, neuroinflammatory diseases, and systemic autoimmune and inflammatory diseases. Founded in 2018, Neuron23 has assembled a world-class team of experts and entrepreneurs located in South San Francisco, CA.
Apart NEU-411, they are also working with 🔹NEU-627, a highly potent and selective central TYK2 inhibitor currently in preclinical development for multiple sclerosis and potentially other neuroinflammatory diseases, and 🔹NEU-111 a peripherally restricted TYK2 inhibitor currently being evaluated in a Phase 1 study in healthy volunteers.
💠 Resilience (National Resilience, Inc) is a first-of-its-kind manufacturing and technology company dedicated to broadening access to complex medicines and protecting biopharmaceutical supply chains against disruption. Founded in 2020, the company is building a sustainable network of high-tech, end-to-end manufacturing solutions to ensure the medicines of today and tomorrow can be made quickly, safely, and at scale.
💈 Everest Medicines Ltd
Everest Medicines, China’s leading biopharma company integrating AI into mRNA cancer vaccine research advancing its AI-powered mRNA oncology pipeline into clinical trials, just announced that the U.S. FDA cleared the IND application for its self-developed 🔺EVM14, a tumor-associated antigen vaccine (Everest Medicines drives growth with AI-powered mRNA pipeline), and its 🔺EVM16 vaccine has been administered on the first patient under an investigator-initiated trial.
EVM14 is an off-the-shelf mRNA cancer vaccine targeting multiple TAAs and is designed to treat various cancers, including non-small cell lung cancer and head and neck cancer.
EVM16 is a novel personalized therapeutic mRNA cancer vaccine internally developed by Everest. It contains neoantigens with high immunogenicity potential, predicted based on the unique tumor mutations of each patient using Everest’s proprietary AI-based neoantigen prediction algorithm, EVER-NEO-1. The vaccine is designed to encode dozens of tumor neoantigens.
Everest Medicines is a Hong Kong-listed (HKEX 1952.HK) biopharmaceutical company focused on discovering, developing, manufacturing and commercializing innovative therapeutics and vaccines that address critical unmet medical needs for patients in Asian markets. The Everest Medicines team has deep expertise and extensive track record of high quality clinical development, regulatory affairs, CMC, business development and operations both in China and with leading global pharmaceutical companies.
💈 VantAI Inc
Roivant spinout VantAI has unveiled Neo-1, an AI model combining biomolecule structure prediction and molecular generation to design new drug candidates, including molecular glues and degraders (VantAI Launched Neo-1, the First AI Model to Rewire Molecular Interactions by Unifying Structure Prediction and Generation for Therapeutic Design). Roivant Sciences (Basel, Switzerland and London and New York) (NASDAQ:ROIV) is building entrepreneurial biotech and healthcare technology companies with a unique approach to sourcing talent, aligning incentives and deploying the technology. So far, they have the following companies in the Roivant family spanning multiple therapeutic areas, modalities and technologies: Dermavant, Immunovant, Priovanttx, Datavant, VantAI, Psivant, Covanttx, Lokavant, Kinevant and Genevant. Moreover, the Roivant Discovery physics-driven drug design platform combines quantum physics, statistical thermodynamics, molecular simulations, AI, ML, a dedicated HPC supercomputing cluster, purpose-built software, and in-house laboratory.
Regarding 🪩Neo-1🪩,
Neo-1 is the first model to unify de novo molecular generation and atomic-level structure prediction in a single model, by generating latent representations of whole molecules instead of predicting atomic coordinates.
Neo-1 is generalizable across structural and sequence inputs, including partial inputs, and allows for arbitrary constraints with real-world empirical data, significantly reducing the search space needed to identify small molecule drug candidates, and thus dramatically improving the empirical value of computational drug discovery.
Optimized together with NVIDIA, Neo-1 enables design for high-value mechanisms of action, including molecular glues and other proximity-based therapeutics, directly addressing one of pharma’s biggest discovery bottlenecks, and is already in use across three large pharma and biotech partnerships with VantAI.
🔗 On February 13, 2024, VantAI and Bristol Myers Squibb entered into a strategic collaboration to discover new molecular glues for therapeutic targets of interest. The partnership leverages VantAI's geometric deep learning capabilities with Bristol Myers Squibb’s expertise in targeted protein degradation to discover and develop new small molecule therapeutics.
🔗 On February 14, 2024, BMS signed a $674M GenAI drug discovery deal with VantAI. The partnership will focus on using VantAI’s generative AI platform (GenAI) to design and develop molecular glues, a type of small molecule that induces or stabilises interactions between two proteins that would not normally go together.
🔗 Finally, VantAI has also entered into a multi-year collaboration agreement with Janssen to leverage VantAI's geometric deep learning platform to potentially generate novel drug candidates and collaborate on the discovery and implementation of novel E3 ubiquitin ligase platforms.
🎐 Launching 'Nightingale AI': A New Foundation World Model for Health
The UK's AI research community reached a major milestone🎖️ with the launch of 🔺Nightingale AI🔺, a pioneering initiative for a Large Health Model aimed at transforming the healthcare sector. The initiative, spearheaded by Professor Aldo Faisal, Director of the UKRI Centres in AI for Healthcare at Imperial College London, was unveiled at the prestigious Francis Crick Institute in London, during the launch of the UKRI AI Hub in Generative Models.
💈 Alpenglow Biosciences Inc
Alpenglow Biosciences just announced 📣 the launch of LUMI, an intuitive user interface designed to integrate smart microscopy 🔬 into the light-sheet workflow (Alpenglow Biosciences Unveils LUMI: A Revolutionary Imaging Interface at ABRF 2025). LUMI (Light-Sheet User Microscope Interface) is the latest innovation for Alpenglow’s 3D i™ Hybrid Open-Top Light-Sheet (HOTLS) microscope, that enhances workflow efficiency and data acquisition through its key features: Intuitive Scan Setup; Live Preview Mode with Scout Mode and Zoom Mode delivering high-resolution imaging for capturing intricate details with precision; Seamless Operation; and Smart Microscopy with ability to create algorithms for automated region of interest detection and Scout-to-Zoom workflows.
Alpenglow Biosciences sheds new light on tissue analysis with an AI-powered 3D approach. With novel chemistry, a patented high-throughput light-sheet microscope, and cloud-based AI analysis the company adds a new dimension to your pathology, away from the limitations of conventional 2D, slide-based analysis. Their research services include sample preparation, cloud-based data processing and storage, and AI-powered 3D analysis, using its patented multi-resolution 3Di platform for 3D spatial biology. On August 15, 2024, Alpenglow Biosciences was awarded contracts from Advanced Research Projects Agency for Health (ARPA-H) and the National Institutes of Health (NIH) and secured additional investment to further its clinical product development (Alpenglow Biosciences and Partners Secure a Total of $24M for Development of Alpenglow’s 3D Spatial Pathology Platform). On August 15, 2024, Alpenglow Biosciences landed new 🆕 contracts to develop 3D pathology tech. In 2023, Alpenglow Biosciences and Mayo Clinic entered collaboration agreement to advance pathology and drug development through 3D spatial biology, and in 2022 Alpenglow Biosciences and CorePlus partnered to bring 3D spatial biology to clinical R&D.
💈 Prof Koul’s Journey From ‘Jumping Genes’ To Sirturo And AI-Led Drug Discovery
Professor Anil Koul's career trajectory—from studying "jumping genes" to developing Sirturo (a tuberculosis drug)—exemplifies the convergence of traditional biological research and AI-driven innovation. His work demonstrates how AI can augment human expertise to solve complex medical challenges 👉 Profile: Prof Koul’s Journey From ‘Jumping Genes’ To Sirturo And AI-Led Drug Discovery.