Weekly TechBio News
Welcome back to another free edition of MetaphysicalCells 🪐🛸
🔝 Top News 🔝
➡️ Insilico Medicine: 1️⃣0️⃣ of its programs have now reached clinical stage, and this is a 🆕 and very unusual paper from Alex’s Zhavoronkov, founder and CEO at Insilico Medicine, group: LLMs and AI Life Models for Traditional Chinese Medicine-derived Geroprotector Formulation.
➡️ Several months after Exscientia merger, AI biotech outfit Recursion reworks pipeline
➡️ Lantern Advances Drug Candidate🔺LP-184 with IND Clearance for Phase 1b/2 Clinical Trial in Triple Negative Breast Cancer (TNBC)
➡️ Iambic Announces🔺Enchant v2, its Next Generation AI Model for Predicting the Clinical Viability of Drug Discovery Programs
➡️ Lundbeck joins forces with Danish Centre for AI Innovation to improve brain health by advancing drug discovery with Gefion AI supercomputer
➡️ Owkin Launches🔺 K Navigator, a Ground-breaking Agentic Co-pilot to Speed up Breakthroughs in Biomedical Research by 20x
⚓ 10x Genomics Inc and Ultima Genomics Inc
10x Genomics and Ultima Genomics partnered with Arc Institute to accelerate the development of the Arc Virtual Cell Atlas (10x Genomics and Ultima Genomics partner with Arc Institute to accelerate development of the Arc Virtual Cell Atlas). More specifically, the Arc Institute launched in February 2025 the Arc Virtual Cell Atlas, a growing resource for computation-ready single-cell measurements, starting with data from over 300 million cells. The initial release of the Atlas was Arc’s first step toward assembling, curating, and generating large-scale cellular data to fuel new insights from AI-driven biological discovery.
The Atlas has two foundational datasets: the first is a new, open source, perturbation dataset called Tahoe-100M, created by Vevo Therapeutics, comprising 100 million cells and mapping 60,000 drug-cell interactions across 50 cancer cell lines. The second dataset, scBaseCamp, is the first single-cell RNA sequencing dataset from public data to be curated and reprocessed at scale using AI agents. Arc mined observational data from more than 200 million cells representing 21 different species sourced from public repositories, and processed them to a standardized form (Arc Virtual Cell Atlas launches, combining data from over 300 million cells).
If you want more info regarding Tahoe Bio AI (previously Vevo Therapeutics Inc) ➡️
Going back now to 10x Genomics’ and Ultima Genomics’ 🆕 collaboration, by combining Arc’s expertise with 10x and Ultima’s cutting-edge technologies, they will be able to generate high-quality, perturbational single-cell data at scale.
Ultima Genomics (US) is providing high-throughput, cost-effective sequencing for the generation of AI-scale single cell datasets like the 100M Tahoe dataset. Moreover, Ultima’s UG100 sequencer was selected back in January 09, 2025 by the UK Biobank Pharma Proteomics Project (UKBB-PPP) to be the sequencing technology for the largest human proteome project in the world (Ultima Genomics Announces UG 100™ Sequencing Platform Selected for UK Biobank's Groundbreaking Human Proteome Study).
In particular, together with 14 pharma and AI companies, over 600,000 samples will be sequenced at Regeneron using the Olink Proteomics’s HT platform. The UG 100 was built for large-scale studies and factors such as quality, data accuracy, complementarity with Olink, cost-effectiveness and reliability were paramount. Ultima’s seamless integration with Olink, its ease of user adoption and compatibility with laboratory information management systems (LIMS) that will ensure streamlined workflows to support this project.
10x Genomics, Inc (NASDAQ:TXG) on the other hand is a leading life-science technology company developing and selling instruments, consumables and software for analyzing gene expression in cells, and consists of three platforms:
📍the Chromium platform for single cells: for single cell sequencing that allows scientists to see the unique gene expression patterns of each cell;
📍the Visium platform: for spatial analysis of tissue samples for whole transcriptome analysis at single cell-scale resolution (Getting started with Visium HD data analysis and third-party tools); and
📍the recently released Xenium platform for subcellular spatial mapping, to characterize up to 5,000 genes in cells and tissues with ultra precise single cell spatial imaging (Reducing Single-Cell and Spatial Analysis From Hours to Minutes: Human lung samples run on the 10x Genomics Xenium Analyzer and are processed via NVIDIA RAPIDS).
To conclude, just this week (May 5, 2025) Psomagen Inc, a multiomics service laboratory serving academic, pharma, biotech, and clinical customers, joined the Billion Cells Project led by the Chan Zuckerberg Initiative (CZI). The Billion Cells Project aims to develop a landmark single-cell dataset of one billion cells that will be used to train new AI models to advance researchers' understanding of cellular behavior and gene function. Psomagen began providing services to participating researchers in April. The project includes collaborations with several other technology partners, including Ultima Genomics, 10x Genomics and Scale Biosciences.
For a deeper dive on 10x Genomics:
⚓ Nurix Therapeutics Inc Also Known As Kura Therapeutics; NASDAQ:NRIX
On April 28, 2025, Nurix presented data that demonstrate the potential of its DEL Foundation Model to enable the rapid in silico identification of novel binders for a broad range of therapeutically relevant proteins, addressing a key barrier in the discovery and development of small molecule drugs (Nurix Therapeutics Presents Data at the AACR 2025 Annual Meeting Highlighting the Transformative Potential of Its Proprietary DEL-AI Platform Leveraging Machine Learning to Speed the Discovery of Novel Drugs).
Nurix’s 🔹DEL Foundation Model🔹 is able to perform virtual DEL experiments on prospective protein target sequences to accurately predict novel binders to a large proportion of therapeutically relevant targets, including many targets considered undruggable. In plots of virtually predicted vs. experimentally-derived DEL screens against therapeutically relevant proteins, Nurix’s DEL Foundation Model demonstrated the ability to accurately predict the experimental results, including experimentally validated binders. Success of the DEL Foundation Model was found to correlate to the degree of similarity of query sequences to proteins within the DEL training set, and data demonstrated that the current model requires as little as 50% amino acid sequence similarity of a query protein to training data to enable binder prediction. Nurix’s model was also capable of inferring binders from chemical space not represented in the training set, suggesting that the model is capable of both protein sequence and chemical structure generalizations.
The development of the DEL Foundation Model was led by Nurix in collaboration with Loka, a Silicon Valley-based software development firm, and supported by Amazon Web Services (AWS), leveraging AWS SageMaker and AWS managed MLflow to provide enterprise-grade reliability and scalable infrastructure.
Few words about Nurix now.
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.
On April 02, 2025, Nurix Therapeutics announced that Sanofi has exclusively licensed an undisclosed Nurix program targeting a previously undruggable transcription factor for autoimmune diseases. The undisclosed target is a central regulator of the inflammatory response and is distinct from the previously disclosed STAT6 degrader program (Nurix Licenses a Drug Discovery Program to Sanofi Targeting a Novel Transcription Factor for Autoimmune Diseases).
On April 17, 2025, Nurix announced that FDA has cleared🚦the IND for the IRAK4 degrader GS-6791/NX-0479, enabling the initiation of a Phase 1 trial, which is anticipated to begin in Q2 2025 (Nurix Announces FDA Clearance of IND Application for GS-6791/NX-0479 - a Novel IRAK4 Degrader for Inflammatory Conditions). Nurix’s collaboration partner, Gilead Sciences, licensed the program in 2023 and is responsible for advancing this program through clinical development, and Nurix will receive a $5M milestone payment from Gilead for FDA clearance of the IND, bringing the total amount received under the 2019 collaboration agreement to $135M.
GS-6791/NX-0479 is a potent, selective, oral IRAK4 degrader. IRAK4 plays a critical role in toll-like receptor (TLR) and interleukin-1 family receptor (IL-1R) signaling and has both scaffold and kinase functions, making it an ideal target for disruption by targeted protein degradation. Degradation of IRAK4 by GS-6791/NX-0479 has potential applications in the treatment of rheumatoid arthritis and other inflammatory diseases.
⚓ AMPLY Discovery Ltd
AMPLY Discovery just secured (May 1, 2025) $1.75M in seed funding 🌱 to support its mission to develop therapies for aggressive cancers and drug-resistant infections using its proprietary AI platform (Queen's University spin-out AMPLY Discovery secures $1.75M for AI drug discovery). Twin Path Ventures, a London-based AI investor with a strong track record, led the round. Other backers included US-based Venture Science, Co-Fund NI, the British Business Bank, and QUBIS Limited.
Belfast based AMPLY Discovery, founded as a spinout from the Queen’s University Belfast in 2021, digitizes life’s diversity, using next-generation sequencing for drug discovery. The AMPLY platform connects the digital biological biome to high volume peptide, protein and RNAi extraction technology to unlock a new frontier in drug discovery. In particular, AMPLYfolio AI can process genomic, transcriptomic, meta-transcriptomic, metagenomic or synthetic data, and can utilize custom data-scanning techniques to locate regions of interest in digital biological data that other tools miss. Then by utilizing black-box unpublished ML and bioinformatic methodologies can highlight novel compounds using a complex web of thousands of metadata tags.
Moreover, AMPLY uses approaches leveraged from predictive marketing and the financial services industry and creates a "stock picking" dashboard view of the data it processes. This allows a user-driven selection of novel compounds. Additionally, AMPLY uniquely connects the digital discovery technology to high throughput peptide and RNAi synthesis and protein extraction techniques. Once a compound is identified the AMPLY pipeline includes a full lab validation of the kill-efficiency of the compound against target diseases. Testing such as toxicity, anti-biofilm, biochemical handling criteria and resistance studies can be performed as desired.
Back in February 2024, AMPLY Discovery raised over €1.6M in grant funding from Innovate UK.
⚓ Rakovina Therapeutics Inc
On April 22, 2025, Rakovina Therapeutics (TSX-V: RKV) (FSE: 7JO) announced its new Scientific Advisor and collaborator, Dr. Artem Cherkasov (Rakovina Therapeutics Congratulates Scientific Advisor Dr. Artem Cherkasov on Global Recognition for Breakthrough AI Innovation in Drug Discovery). Dr. Artem Cherkasov is a professor 👨🎓 at the University of British Columbia and a principal investigator with the Vancouver Prostate Centre. Recently he was featured by the Vancouver Coastal Health Research Institute (VCHRI) in an article titled “AI innovation puts VCHRI scientist at forefront of global drug discovery avenues”, that highlights his groundbreaking contributions to the use of AI in computational drug modeling and the development of the Deep Docking™ platform—an AI engine capable of screening billions of molecules to identify the most promising drug candidates with speed and precision.
Further to Dr. Artem Cherkasov’s appointment 🪑, on May 05, 2025 Rakovina also announced the appointment of Dr. David M. Kideckel, Ph.D., MBA, as Chief Financial Officer (CFO), subject to approval from the TSX Venture Exchange (“TSXV”) (Rakovina Therapeutics Announces Appointment of Dr. David Kideckel as Chief Financial Officer). Dr. Kideckel is the Founder and Principal of the Kideckel Advisory Group Inc, which provides fractional CFO, Chief Business Officer (CBO), and capital markets services to TSX- and Nasdaq-listed companies, as well as private corporations.
Rakovina Therapeutics (TSX.V: RKV) is using cutting edge Deep Docking™ AI to target DNA-damage response (DDR) mechanisms and create innovative precision medicines with the potential to improve patient outcomes across multiple tumor types. DDR is a collection of processes that identify and correct DNA damage in our cells millions of times every day, and many cancers harbor a defect in natural DDR mechanisms.
Deep Docking is a novel DL platform that is 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. The use of DD methodology in conjunction with the FRED docking program allowed rapid and accurate calculation of docking scores for 1.36 billion molecules from the ZINC15 library against 12 prominent target proteins and demonstrated up to 100-fold data reduction and 6000-fold enrichment of high scoring molecules, without notable loss of favorably docked entities (Deep Docking: A Deep Learning Platform for Augmentation of Structure Based Drug Discovery).
By employing their proprietary DD platform they have identified so far the following promising targets for cancer treatment:
🧵 kt-2000AI against PARP (PARP inhibitors are an attractive option for anticancer drugs targeting DDR pathways).
🪡 On April 29, 2025, the company presented new preclinical data from two of its lead programs at the American Association for Cancer Research (AACR) Annual Meeting 2025, demonstrating a new class of PARP1 inhibitors with significantly improved metabolic stability, including the lowest in vitro clearance rates and the longest half-life compared to other candidates currently in development. Early animal studies revealed strong plasma exposure and a promising pharmacokinetic profile suggestive of central nervous system (CNS) penetration — a potentially significant advantage in treating brain-involved malignancies (Rakovina Therapeutics Showcases Preclinical Results of Novel AI-Discovered Cancer Therapies at AACR 2025).
🧵 and other novel DDR targets to generate best-in-class drug candidates that can be advanced to human trials or developed in collaboration with pharmaceutical partners.
🧵 Moreover on January 13, 2025, Rakovina Therapeutics announced the successful achievement of a shortlist of AI-generated molecules targeting ATR (Ataxia Telangiectasia and Rad3-related protein) with specific designs for central nervous system (CNS) penetration (Rakovina Therapeutics Announces Key Milestone in Cancer Drug Innovation in Collaboration with Variational AI). These new ATR-targeted inhibitors will now advance to chemical synthesis followed by preclinical validation, a critical step in Rakovina’s mission to address unmet medical needs in oncology.
🪡 On April 29, 2025, when the company presented new preclinical data from two of its lead programs at the American Association for Cancer Research (AACR) Annual Meeting 2025, showcased also progress from Rakovina’s ATR-specific inhibitor program developed in partnership with Variational AI. Researchers identified a focused set of lead candidates predicted to be highly potent and selective against ATR, a key DNA damage response target. These candidates are also designed with the potential to cross the blood-brain barrier, an important feature for addressing cancers affecting the CNS. The top candidates are currently being synthesized for laboratory validation (Rakovina Therapeutics Showcases Preclinical Results of Novel AI-Discovered Cancer Therapies at AACR 2025).
Additionally on May 9, 2024, Rakovina has expanded its research collaboration with Pharma Inventor and the University of British Columbia to identify novel drug candidates. In particular,
📍Pharma Inventor Inc—a British Columbia-based chemistry R&D and analytical services company serving pharmaceutical and biotech industries, as well as research institutes and academic research groups across North America—will provide medicinal chemistry support to rapidly synthesize novel lead drug candidates identified by the DD platform for further validation.
📍Regarding the University of British Columbia (UBC), Rakovina established a lead optimization research infrastructure at the University’s Vancouver Prostate Center and will provide rapid validation of novel drug candidates identified through the DD platform.
Based in Vancouver, Canada, Rakovina Therapeutics was founded in 2021 by Jeffrey Bacha, a serial entrepreneur with startups and companies operating in the biotechnology and life sciences fields.
🔺BrainStorm Therapeutics🔺
BrainStorm Therapeutics is accelerating and de-risking the discovery of breakthrough medicines for complex neurological disorders.
Integrates patient iPSC-derived brain 🧠 organoid disease models with cutting-edge computational tools of DL and network medicine to transform CNS drug discovery.
Making Brain Waves: AI Startup Speeds Disease Research With Lab in the Loop by NVIDIA
⚓ Profluent Bio Inc
On April 16, 2025, Profluent unveiled🔺ProGen3, a family of frontier protein models, trained on the world’s largest, highly curated dataset of protein sequences for protein generation. ProGen3 enables writing new biology to solve challenges across biomedicine, agriculture, and industrial applications (Profluent Introduces ProGen3, Demonstrating Scaling Laws for Foundation Models in Writing Biology).
With ProGen3, Profluent provides evidence that the AI breakthroughs that revolutionized natural language processing are now ready for impact in biology. Just as large language models learn the underlying rules and patterns of language and gain new emergent capabilities as they scale with increased data and computing power, Profluent has shown that the relationship between scale and performance also applies to biological design.
In a first for the field, the company detailed real-world evidence for scaling billion-parameter model sizes to over 3.4 billion full-length protein sequences. This achievement signals that AI biological models will continue to unlock more value as they scale, enabling a future of programmable biology and a shift from incidental discovery to intentional design.
Profluent, developing deep generative models to design and validate novel functional proteins to revolutionize biomedicine, has initially pointed their platform towards CRISPR and gene editing and under the OpenCRISPR initiative, by releasing the world’s first open-source, AI-generated gene editor. With this launch, Profluent demonstrated the first successful precision editing of the human genome with customizable gene editors designed from scratch with AI (Profluent’s new platform is like ChatGPT for genetic technology).
So far, Profluent’s large language models (LLMs) have learned from a massive scale of protein sequences overlaid with biological context to generate millions of diverse CRISPR-like proteins that do not occur in nature, thereby exponentially expanding virtually all known CRISPR families.
OpenCRISPR-1 (one of their AI-created gene editors) is an initial open-source release, freely available to license for ethical research and commercial uses. OpenCRISPR-1 maintains the prototypical architecture of a Type II Cas9 nuclease but is >400 mutations away from SpCas9 and nearly 200 mutations away from any other known natural CRISPR-associated protein. They also used their LLMs to generate a synthetic guide RNA that could be assembled with OpenCRISPR-1
➡️ Design of highly functional genome editors by modeling the universe of CRISPR-Cas sequences (OpenCRISPR-1),
➡️ Large language models generate functional protein sequences across diverse families (ProGen) and
➡️ ProGen2: Exploring the boundaries of protein language models.
Founded in 2022 and based in Berkeley, CA, Profluent announced on March 21, 2024 the close of an additional funding to bring the total raised to $44M. The $35M financing was led by Spark Capital, with participation from existing investors Insight Partners and Air Street Capital along with a syndicate of angel investors from OpenAI, Salesforce, Octant Bio, and Google including Jeff Dean, Chief Scientist of Google DeepMind. The company previously raised $9M from Insight Partners, Air Street Capital, AIX Ventures, and Convergent Ventures.
Finally, on January 07, 2025 Profluent also announced Protein2PAM, the first in a series of AI models that will broadly focus on protein-DNA interactions. Trained on large, bioinformatically curated databases of mined biological sequences, Protein2PAM demonstrates the power of Profluent’s language models to reprogram complex biological systems without the need for wet laboratory evolution or structural modeling (Profluent Demonstrates AI Can Engineer Protein-DNA Interactions Without Iterative Laboratory Screening).
⚓ Paige AI Inc
Sonrai, a leading AI precision medicine company accelerating the development of therapeutics through advanced analytics, and Paige have just announced a strategic partnership to better enable biopharma researchers, pathologists, and clinicians to harness cutting-edge AI capabilities for precision medicine research and development (Sonrai and Paige partner to bring advanced machine learning capabilities to biopharma). By integrating Paige’s state-of-the-art foundation models with Sonrai’s intuitive cloud-based data analysis and bioinformatics platform, the partnership makes AI, ML, and multi-modal data integration accessible to non-technical users, creating the ability for more organizations to access a wide range of critical R&D needs without requiring deep AI expertise.
Paige (US, 2018), that is a global leader in end-to-end digital pathology solutions and clinical AI with the first Large Foundation Model (LLM) using over one billion images from half a million pathology slides across multiple cancer types, is developing with Microsoft a new AI model larger than any other image-based AI model existing today configured with billions of parameters (Paige Announces Collaboration with Microsoft to Build the World’s Largest Image-Based AI Model to Fight Cancer). By incorporating up to four million digitized microscopy slides across multiple types of cancer from its unmatched petabyte-scale archive of clinical data, Paige will utilize Microsoft’s advanced supercomputing infrastructure to train the technology at scale and ultimately deploy it to hospitals and laboratories across the globe using Azure.
In January 9, 2024, Paige announced the release of a groundbreaking product developed from Paige’s Pathology Foundation Model, the Virchow (the first million-slide foundation model for cancer, setting the benchmark for computational pathology), that can detect cancer across more than 17 different tissue types including skin, lung and the gastrointestinal tract, along with multiple rare tumor types and metastatic deposits. Moreover, Virchow2 is an expanded multi-scale training model (H&E + IHC), boosting precision across 40+ tissue types, Virchow2G is their largest model yet—1.8B parameters—optimized for high-stakes pathology AI, and Virchow2G-Mini is a lightweight alternative, delivering high-throughput performance on limited compute.
On April 3, 2025, Paige announced that the FDA has granted Breakthrough Device designation to Paige PanCancer Detect, an AI-assisted diagnostic application intended to assist pathologists in the detection of foci that are suspicious for cancer from multiple tissues and organs (U.S. FDA Grants Paige Breakthrough Device Designation for AI Application that Detects Cancer Across Different Anatomic Sites). This marks the first 🥇 designation of its kind for an AI-enabled tool capable of identifying both common cancers and rare variants from different anatomic sites. Paige PanCancer Detect can detect regions of interest suspicious for cancer across multiple organs and different tissues, including GI, GU, lung, cervix, endometrium, breast, skin, brain and rare cancer variants.
Furthermore, on April 8, 2025 Sectra signed a distribution agreement with Paige.AI (Sectra's fully managed AI offering extended to include pathology following new Amplifier partner agreement) appointing Sectra as a reseller of the Paige Prostate Suite through Sectra's AI service—Sectra Amplifier Service. Sectra Amplifier Service is a part of its enterprise imaging solution which provides a unified strategy for all imaging needs in one single system thus both improving outcomes as well as lowering operational costs.
Apart the recent Breakthrough Device designation for Paige PanCancer Detect, Paige.AI previously secured Breakthrough Device designation for Paige Prostate Detect, an AI-powered application that aids in the detection of prostate cancer, which later became the first FDA-authorized AI application in pathology. In particular, the Paige Prostate Suite is a group of comprehensive AI applications that aid in the detection and diagnosis of prostate cancer on H&E-stained whole-slide images of prostate needle biopsies, including:
1️⃣ Paige Prostate Detect,
2️⃣ Paige Prostate Grade & Quantify,
3️⃣ Paige Prostate Perineural Invasion.
Paige is also offering, Paige Alba the Future of Integrated AI & Cancer Diagnostics, that is a pathology co-pilot designed to transform the way pathologists, oncologists and clinicians’ work by integrating pathology, radiology, and clinical data into a single AI-powered experience. By combining cutting-edge agentic AI with intuitive voice and text commands, Alba can help streamline workflows, enhance efficiency, and enable real-time insights—empowering pathologists and oncologists with a new level of confidence and efficiency in cancer diagnostics.
They also developed the PRISM: Multi-Modal AI that:
🗣️Combines Large Vision Models (LVMs) with LLMs for slide-level analysis,
🗣️Built using Virchow, PRISM analyzes and extracts insights from tissue at the whole slide level,
🗣️Converts whole-slide images into free-text pathology reports,
🗣️Detects cancer subtypes and predicts biomarkers without extensive labeled data, and
🗣️Trained from 587K slides and 195K clinical reports to generate text-based insights
📍Phase V📍
Phase V is developing a unique set of advanced technologies and innovative
statistical methods to revolutionize trial design, execution, and analysis.
PhaseV to Host New Webinar Episode on Patient-Centric Clinical Development
⚓ Deepcell Inc
On April 24, 2025, Deepcell appointed Janette Phi as the new Chief Business and Commercial Officer (Deepcell Appoints Janette Phi as Chief Business Officer, Raises Venture Round, and Expands to New Menlo Park HQ). Janette 👸 with over 25 years of research and business experience in life science and clinical instrumentation and reagent companies, is an experienced executive in both small start-ups as well as Fortune 500 companies. She has extensive knowledge of the bio-analytic sector and AI-ML, functional expertise in the inbound and outbound aspects of marketing, sales, business development, and launching new technologies into the market. Finally, she was involved in raising over $150M 💰 in corporate and venture funding at six companies.
The company also completed an initial closing of a new venture round led by 50Y VC, and has opened the round to additional institutional and strategic investors. Deepcell has further expanded its footprint with the relocation 🚚 of its headquarters to the Menlo Park Labs district to support its next phase of commercial and scientific growth.
Deepcell—spun out of Stanford University in 2017—leverages microfluidics, high resolution optics, a growing cell atlas with over 1 billion images, and AI to examine and classify cells by using its REM-I Platform released on May 17, 2023, that is a cell morphology analysis and sorting platform which comprises the REM-I benchtop instrument with the Human Foundation Model (HFM) and Axon data suite, bringing together single cell imaging, sorting and high-dimensional analysis (Deepcell Launches AI-Powered Single Cell Analysis Platform to Accelerate Cell Biology Discovery and Catalyze Field of Morpholomics).
Interestingly, the REM-I platform is offering high-resolution images of single cells completely label-free—that is increasing cell viability and keeping the cells unperturbed— that are captured at high speed, while the AI characterization of captured cell images happens in real-time.
As of January 8, 2024, Deepcell has a new research collaboration with NVIDIA to accelerate the development and adoption of advanced computer vision solutions in life sciences. Deepcell, which was already using the NVIDIA A4000 and NVIDIA AI technology, will also incorporate NVIDIA AI into its single cell analysis technology, working collaboratively with NVIDIA to co-develop new uses for generative AI and multimodal applications in cell biology.
Finally on May 2, 2024, Deepcell announced the first commercial placement of the REM-I platform at the Erasmus Medical Center in Rotterdam (Deepcell Announces Successful Installation of the First Commercial REM-I Platform). This commercial milestone follows placements of pre-commercial instruments at laboratories in Europe and the U.S. for Beta testing.
⚓ Renovaro Inc
Renovaro (NASDAQ: RENB) announced on April 22, 2025 that it is expanding its ongoing strategic collaboration with Nebul, a leading AI cloud infrastructure company, to advance the early detection of cancer and other diseases. The partnership aims to leverage Renovaro’s DL and ML programs with Nebul’s high-performance computing (“HPC”) built on the latest platform to accelerate biomarker discovery and next-generation diagnostics (Renovaro Secures High-Powered Computing from Nebul Through).
Los Angeles-based Renovaro Inc accelerates precision and personalized medicine for longevity by mutually reinforcing AI and biotechnology platforms for early diagnosis, better-targeted treatments and drug discovery. Renovaro includes RenovaroBio 🧬🧪, with its advanced cell-gene immunotherapy company, and RenovaroCube 🧊, an award-winning technology bringing together proprietary AI technology, multi-omics and multi-modal data, and the expertise of a carefully selected multidisciplinary team to radically accelerate precision medicine and enable breakthrough changes in cancer care.
⚓ Ignota Labs AI
2025 has been a wonderful year for Ignota Labs in the UK, that is preventing safety failures in drug discovery with its automated toxicity labelling, analysis and screening platform. In fact, on January 28, 2025, Ignota Labs was honored to be selected for the prestigious Sanofi iDEA-Tech Award 2023-2024, a global competition aimed at accelerating breakthroughs in pharmaceutical R&D through the use of cutting-edge AI and data-driven solutions (Ignota Labs secures Sanofi’s prestigious iDEA-Tech Award). This recognition placed Ignota Labs among the elite 6.8% of applicants who were successful in the rigorous selection process. The award consists of €120,000 in funding and dedicated support from Sanofi’s expert team to empower Ignota Labs to advance its groundbreaking SAFEPATH platform, a proprietary AI-driven tool designed to address critical safety challenges that often derail drug development.
SAFEPATH integrates cheminformatics and bioinformatics to understand the mechanisms behind drug toxicity. In preclinical and clinical studies, safety assessments typically reveal what went wrong—such as liver failure or cardiac arrest—but fail to explain why these issues occurred or how they might be mitigated. However, SAFEPATH combines advanced ML models with a multimodal data approach to enable a deep understanding of toxicity mechanisms, offering actionable insights to facilitate drug turnaround.
Moreover, on 26 February 26, 2025 Ignota Labs secured $6.9M in funding to utilize AI in re-evaluating and repurposing drugs that were previously shelved due to inefficacy or safety concerns. This approach holds promise for breathing new life into abandoned drug candidates and potentially reducing R&D costs (Ignota Labs Secures $6.9M to Bring ‘Dead’ Drugs Back to Life with AI).
Ignota Labs in UK is preventing safety failures in drug discovery. Their platform not only searches through the huge ‘algorithmic space’—including all possible chemical descriptors, model architectures and hyperparameter setting combinations—to find the most accurate models in the industry. But also tells you why a compound is toxic, by breaking down and interpreting the AI’s outputs using a mixture of ML and DL techniques. This provides structural and physicochemical analysis of what is driving the toxicity, giving you the best information possible to enhance drug discovery decision-making. So far, they have curated the highest quality data from proprietary sources to build AI models on a range of in vitro toxicity endpoints: 📍mitochondrial toxicity, 📍hepatotoxicity, 📍cardiotoxicity, 📍developmental toxicity and 📍genotoxicity.
⚓ Immunai Inc
Immunai and the Parker Institute for Cancer Immunotherapy (PICI), a collaborative consortium of the world’s leading immuno-oncology experts, announced their intention to build the world’s largest single-cell dataset from patients treated with standard-of-care (SoC) immunotherapy (namely a major expansion of Immunai’s AMICA™ platform) (Immunai & Parker Institute to Build Largest Single-Cell Immune Profiling Patient Database).
Accordingly, Immunai and PICI will perform single-cell RNA sequencing (scRNA-seq) and multi-omic profiling of patient blood samples collected from PICI’s RADIOHEAD (Resistance Drivers for Immuno-Oncology Patients Interrogated by Harmonized Molecular Datasets) cohort, a prospective longitudinal study of 1,070 patients receiving immune checkpoint inhibitor treatment regimens in a community setting.
The initiative utilizes 10x Genomics’ Chromium GEM-X single-cell technology to support high-throughput, cost-effective sample processing, enabling the generation of high-quality single-cell data at scale. This dataset will be fully embedded within AMICA, strengthening its analytical capabilities and positioning it as the most comprehensive immune cell atlas available for oncology research.
Immunai is building an AI model of the immune system to facilitate the development of next-generation immunomodulatory therapeutics by combining immunomics and ML. Immunai’s rich clinico-genomic data assets are harmonized in AMICA, the Annotated Multi-Omic Immune Cell Atlas (the world’s largest immune-focused, harmonized single-cell database). Fed by massive scale curated public -omics data and proprietary cohorts and experiments, AMICA covers 10s of millions of cells across hundreds of disease settings and is growing rapidly.
Founded in December 2018 and with a global team that spans New York City, Tel Aviv, Prague and Zurich, in March 2021 Immunai acquired Dropprint Genomics, a Y-combinator backed, single cell genomics software company based in San Francisco. Dropprint’s database of immune cells further expanded AMICA.
In July 2021, Immunai made the transformational acquisition of NEBION, a world leader in biocuration and data integration. NEBION structured hundreds of thousands of samples and millions of cells across thousands of public studies under a unified clinical ontology, all powered by bespoke expert curation. This data has supercharged AMICA’s growth and expanded their target discovery efforts into a wide range of inflammatory and oncological settings.
After the acquisition, Nebion’s main product GENEVESTIGATOR that curates public and private transcriptomics data continues to be developed and commercialized. GENEVESTIGATOR has the following key applications for curated gene expression data: ➡️ Effective discovery through compendium-wide analysis, ➡️ Unbiased data-driven decision making, ➡️ Straightforward prioritization and validation of targets and biomarkers, ➡️ Innovative drug repurposing and repositioning, ➡️ Convenient identification of relevant experimental model systems, ➡️ Reliable prediction of side effects, and ➡️ Robust ML through clean data.
On September 26, 2024, Immunai and AstraZeneca announced a $18 Million AI Collaboration to Transform Cancer Drug Development. This partnership aims to enhance the development of oncology therapies through advanced data analysis. The collaboration will leverage Immunai’s proprietary technologies, including its immune cell atlas, AMICA, and the Immunodynamics Engine (IDE). As a result, AstraZeneca (LON: AZN) will utilize Immunai’s platform to inform clinical decision-making in its oncology trials.
IDE was designed to enhance clinical decision-making in order to: 📍Prioritize trial arm or patient subgroup, 📍Validate therapeutic hypotheses with deep mechanistic insight, 📍Identify candidate patient stratification biomarkers, 📍Add confidence to preclinical efficacy and safety evaluation, and 📍Identify targets with the highest potential for therapeutic impact.
Finally in 2024, Immunai announced a multi-year collaboration with Teva Pharmaceuticals to collaborate in Immunology and Immuno-oncology programs (Immunai and Teva launch multi-tear AI collaboration for smarter drug development). This collaboration will leverage Immunai’s proprietary immune cell atlas, AMICA, and its AI model IDE, to enhance clinical decision-making in Teva's Immunology trials. Key focus areas will include drug mechanism of action, dose selection, and biomarker analyses.
⚓ Intellomx OMICS Ltd
Intellomx (Intelligent OMICS Ltd) announced on April 28, 2025 the deployment of Intellomx Pilot, delivering rapid identification of novel drugs arising from its existing precision therapeutic target identification capability, offering pharmaceutical innovators a powerful tool to streamline and de-risk the drug discovery process (Intellomx Launches Swarm-Based AI Platform to Accelerate and De-Risk Novel Target and Drug Discovery).
Intellomx Pilot represents a major leap forward in virtual 🖥️ drug screening 🔎. Pilot rapidly identifies pharmacophoric features within AI-predicted targets and performs high-throughput docking simulations across a chemical space of over 500 million small molecules. This enables fast, structure-informed hit identification and lead optimization, with a strong emphasis on drug-likeness, target selectivity, and minimized off-target risks.
Intellomx (spinout from Nottingham Trent University) has an Intuitive Informed Intelligence I3 methodology that finds novel biological targets that drive disease and their Digital Twin helps to predict pre-clinical toxicity effects, saving up to 90% of pre-clinical development costs and reducing the need for animal trials. Intellomx has developed cutting edge systems biology and bioinformatics approaches, based on computational intelligence, which identify robust nonlinear biomarkers associated with clinical features concordant across multiple data sets. This has allowed the study of interactions between key features in the context of a given problem. These approaches in effect determine the level of influence of a set of driver markers in a given biological system, allowing determination of the molecular drivers of a system to yield a given phenotype.
Intellomx expertise can be used to rapidly (2-4 weeks) screen large numbers of protein or transcriptomic biomarkers, using non-linear in silico methods to identify biomarkers that address biomedical, physiological, and clinical questions in molecular data. The approach can also identify and validate new molecular drivers associated with clinical physiological features, specific to the disease being analyzed. The markers identified have been validated in extensive cohorts and shown to have excellent biological relevance with high sensitivity and specificity. The Intellomx approach allows systematic screening of millions of molecular combinations and interactions per hour, without the need for extensive, exploratory wet lab discovery time and costs.
On August 10, 2023, Intelligent Omics Ltd (Intellomx) announced that it has joined Johnson & Johnson Innovation–JLABS, a premier life science incubator program. JLABS provides entrepreneurs with the lab space, resources and support needed to bring breakthrough healthcare solutions to patients around the world (AI Drug Discovery Pioneer Intellomx Joins Johnson & Johnson Innovation).
On September 1, 2023, Intellomx announced a target discovery collaboration with Janssen Research & Development, LLC (Janssen) to evaluate novel biological targets for the treatment of hematological cancers. The collaboration will combine Intellomx’s proprietary AI platform, which integrates multi-omics data and DL algorithms to uncover novel disease mechanisms and therapeutic opportunities for treatment, with Janssen's expertise in data science, oncology research and development.
PredxBio Inc
PredxBio announced (April 28, 2025) a strategic collaboration with Hamamatsu Photonics K.K., a global leader in imaging 🔬technologies, that will unite Hamamatsu's advanced MoxiePlex™ multiplex immunofluorescence imaging system with PredxBio's SpaceIQ™ spatial analytics platform to deliver an integrated workflow tailored to basic and translational research tailored to immuno-oncology (PredxBio and Hamamatsu Photonics Announce Strategic Partnership to Deliver Next-Generation Spatial Biology Solutions for Cancer Research).
SpaceIQ for spatially intelligent biology has a greater than 90% accuracy in predicting patient response achieved through the use of explainable AI (xAI) and unbiased spatial analytics. The platform ingests spatial multimodal images to perform cell phenotyping, cell-cell communication, microdomain discovery, and network biology. SpaceIQ’s discovery of spatial biomarkers is based on relevant positioning of cells and the emergent network biology, which provides a holistic view of the tumor microenvironment. They capture protein-protein interactions to explore the dynamics of cell to cell communication.
PredxBio (previously known as Spatial Pathology Diagnostics, SpIntell), founded in 2017 in US, is leveraging unbiased spatial analytics—namely pathology, spatial transcriptomics and spatial proteomics to identify cell states & fusion cell types, microdomains associated with disease progression & outcomes and pathway interactions & networks—and explainable AI on multi-hyper-plexed imaging data to get to the “why” in immunotherapy trials.
In 2019, they received the HistoMapr SBIR Award and an investment from America's Seed Fund. In 2020, they established a partnership with CellNetix Pathology & Laboratories (SpIntellx and CellNetix Collaborate to Validate HistoMapr-Breast™, an Explainable AI Software Platform Featuring Advanced Spatial Analytics to Provide Intelligent Guides for Pathology Laboratories). In 2021, they established a partnership with Allegheny Health Network and they received an investment from Innovation Works. Moreover, they have 20+ peer-reviewed publications and a dominant IP position for adaptive and agnostic solutions (for transmitted light and multi-hyperplexed and any imaging platform). Plus they have a collaboration with the leading academic medical center Roswell Park Comprehensive Cancer Center.
In 2022, PredxBio and Inspirata have announced that they will collaborate to integrate the PredxBio HistoMapr-Breast™ platform (to diagnose, prognosticate and treat breast cancer) and Inspirata’s Dynamyx® software into one seamless solution (PredxBio and Inspirata Announce New Technical Partnership and Integration to Expand Access to Next Generation Explainable AI Software for Breast Biopsies). Again in 2022, PredxBio and iCura Diagnostics, a leading contract research organization focused on capitalizing multiomic data to accelerate end-to-end clinical workflow solutions and biomarker discovery, have announced a partnership to transform precision oncology through unlocking the power of genomic, proteomics, and transcriptomic data using advanced spatial analytics (SpIntellx and iCura Diagnostics Partner to Expand Access to Advanced Spatial Analytics and Explainable AI Products for Pathology and Oncology Research). Finally in 2024, PredxBio and PictorLabs, Inc, a leading digital pathology firm pioneering AI-powered virtual staining technology, announced a transformative partnership aimed at revolutionizing cancer research, diagnosis, and treatment (PredxBio and PictorLabs Forge Strategic Partnership to Advance Cancer Research and Diagnostics with Next Generation Spatial Analytics).
Opyl Limited
Opyl Limited has just successfully completed a $1.5M oversubscribed placement to accelerate the growth of its AI-driven drug discovery platform, Trialkey (Opyl Limited Secures $1.5 Million to Boost AI Drug Discovery Platform).
Opyl, Clinical Trial Recruitment and Social Media Insight in Australia 🦘, is a leader in AI-driven biostatistical validation and an ASX-listed company (ASX: OPL), transforming clinical trial designs through its advanced simulation platform, TrialKey, the SaaS platform automating processes and optimizing clinical trial designs.
By leveraging 100,000 simulations against over 30+ years of global trial data, the AI-driven biostatistical validation TrialKey delivers insights that traditional methods can’t match. With advanced computational simulations, explainable AI, and predictive modelling, TrialKey eliminates inefficiencies, scales effortlessly, and ensures regulatory alignment—providing the fastest, most reliable path to optimized trial success. Key features include the TrialGen module, which offers data-backed recommendations on study type, enrolment numbers, inclusion/exclusion criteria, endpoints, and optimal trial durations.
With market-leading accuracy achieving over +92% precision in predicting primary endpoint completion, TrialKey is trained using data from over 520,000 clinical trials and 1500+ variables. Each trial is simulated up to 100,000 times and provides robust, reliable predictions, ensuring data-driven biostatistical validation for optimized trial designs and advanced AI detective work on unstructured data (clinician notes, company filings, press cuttings). Opyl’s simulation capabilities also refine intervention models, masking types, and resource allocation, reducing costly amendments and accelerating market entry, providing a competitive advantage in clinical research.
Until next week 🧿