Spring TechBio News (I)
MetaphysicalCells: A newsletter about Science, Technology and AI Drug Discovery
Welcome back to MetaphysicalCells 🪐🛸
For today’s synthesis of key trends and insights from the latest TechBio News:
▶️ Spring TechBio News (I) (free edition): 🔹 Recursion and Enamine, Revvity, Medtronic and Methinks AI, Viz.AI, Predictive Oncology, Renovaro Biosciences and BioSymetrics, and many more
Spring TechBio News (II) (paid 🔐 edition): 🔹 Signios Bio, DiaGen AI, Simulations Plus, Xaira Therapeutics, Plex Research, Parse Biosciences, Sectra, Paige AI, Cadence, Oncocross, and many more
Spring TechBio News (I)
💈 Recursion Pharmaceutical Inc and Enamine Ltd
On April 09, 2025, Recursion (NASDAQ: RXRX) announced the generation of screening libraries leveraging tools within its AI/ML platform, the Recursion OS, together with Enamine's REAL Space, the world’s largest source of make-on-demand small molecules (Recursion and Enamine Release New AI-Enabled Targeted Compound Libraries). More specifically, the two companies have curated 10 enriched screening libraries from over 15,000 newly synthesized compounds designed to accelerate drug discovery against 100 key and clinically relevant drug targets in difficult to address biological areas. By combining the expansive REAL Space with the Recursion OS to predict small molecule compatibility with protein targets, the collaboration allows for the creation of smaller, highly focused libraries that outperform traditional high-throughput screening (HTS) collections.
Enamine is the developer of the world’s largest and most reputable virtual space, the REAL Space, an AI-enabled library (AI-enabled Molecular Chaperones Library, AI-enabled Allosteric Ion Channel Library, AI-enabled PARP Library, AI-enabled TF Library etc). Enamine's REAL Space represents the world’s largest, continuously expanding make-on-demand virtual library, built on insights from millions of parallel syntheses. While the vast chemical space offers incredible potential, selecting the most promising compounds for successful drug development from billions of virtual molecules can be a daunting task. That's where AI and ML come in, enabling the creation of smaller, highly focused libraries that consistently outperform traditional large HTS collections. In fact, by integrating one of Recursion's cutting-edge AI/ML tools, MatchMaker, with REAL Space the company curated 10 powerful screening libraries from 15 000 newly synthesized compounds, specifically designed to accelerate drug discovery with precision and speed.
Apart from the recent collaboration with Recursion, Enamine also has the following collaborations:
Enamine, Chemspace (offering Computational Chemistry Services), and PharmAI Discovery (leveraging advanced computational methods to identify and optimize novel therapeutic compounds) partnered on February 26, 2025 to integrate AI-driven platforms into drug discovery efforts focused on novel theranostics. This collaboration aims to streamline the identification of promising compounds and accelerate the development of innovative treatments (Enamine, Chemspace, and PharmAI Discovery Join Forces to Advance AI-Driven Drug Discovery for Novel Theranostics). On April 02, 2025, Enamine and ChemPass Collaborated to Accelerate Hit Discovery. ChemPass, is a contract research organization for computational and AI-assisted software, and the joint effort between the two companies aims to expand significantly efficient fragment hit discovery and to shorten the fragment-to-lead development cycle for challenging biological targets.
On August 16, 2024, CDDVault and Enamine announced that CDDVault now includes the complete compound collection of Enamine within its AI module for structural similarity searches (CDD Vault Integrates Enamine Compound Collection into AI-Powered Structural Similarity Searches). Enamine enables “SAR by catalog” to CDD Vault’s ultra-fast deep learning structural similarity search functionality. This vast database, now accessible within CDD Vault, enables researchers to explore over 4.3 million compounds in stock at Enamine, optimizing their search for novel drug candidates with unparalleled speed and accuracy.
CDD Vault (2004), is a cloud based data management platform developed by Collaborative Drug Discovery, Inc (CDD) for securely managing and sharing biological and chemical data, including small molecules, nucleotides, proteins, cells and even mixtures. The CDD software company founded in 2004 as a spin-out of Eli Lilly and Company (NYSE: LLY) by Barry Bunin, PhD, utilizes its web-based database solution for managing drug discovery data, primarily through the CDD Vault product which is focused around small molecules and associated bio-assay data. CDD Vault contains several modules for collaborative project teams to manage, analyze, and share both private & public data: Registration (Chemical registration system), Activity (Experimental data), Visualization (Scientific visualization), Assays (Bioinformatics), Electronic lab notebook, Inventory management software, Curve fitting, AI in pharmacy, API/Data mapping and Chemical database.
On May 07, 2024, Pharmacelera and Enamine announced the extension of their partnership to explore an extraordinary magnitude of compounds that has been extended by a 10 fold factor, when compared to the early version. Additionally, Pharmacelera developed a protocol integrating internal scripts and the PharmScreen software for preparing 3D libraries tailored for LBVS and SBVS, that when applied to the Enamine Screening Collection (4.4M compounds), it delivers: 270M conformers for LBVS and 7.9M stereoisomers for SBVS. However, the protocol isn't just limited to Enamine’s collection since they have successfully extended it to other large commercial libraries, such as Molport Screening Compounds. For projects requiring a more targeted approach, their protocol can filter 3D libraries based on drug-like properties. With this standardized protocol and PharmScreen®’s cutting-edge capabilities, they offer one of the largest and most up-to-date 3D screening libraries (On the relevance of query definition in the performance of 3D ligand-based virtual screening) (April 2014).
Pharmacelera (2015, Spain 🇪🇸) is applying quantum theory to boost drug design via their two primary software packages: PharmScreen (for an accurate ligand-based virtual screening, 3D-LBVS), PharmQSAR (3D quantitative structure-activity relationship/QSAR tool that enables a combination of multiple fields of interaction in order to perform comparative molecular field analysis and comparative similarity indices analysis studies) and exaScreen (for novel synthesizable hits from a 3D limitless space).
Finally, A partnership with Enamine and Cresset will enable screening of ultra-large chemical spaces as part of the virtual screening process in drug discovery. Cresset, an innovative provider of integrated in silico solutions for drug discovery, has announced a collaboration with Enamine in July 2024, to develop innovative new solutions for the early drug discovery process.
Few words about Recursion.
Recursion Pharmaceuticals Inc (RXRX), which went public in April 2021, is a leader 🎩 in digital biology, and has built the world’s most advanced ultra-high throughput wet-lab and ML platform. Their ability to generate proprietary, high-dimensional, multi-modal and relatable datasets of human cellular biology at massive scale, and apply advanced ML approaches to reveal novel biological relationships, has resulted in a proven, target-agnostic drug-discovery engine.
LOWE, LLM-orchestrated workflow software, is an LLM agent, that represents the next evolution of the Recursion OS (Recursion Operating System, OS), that supports drug discovery programs by orchestrating complex workflows that chain together a variety of steps and tools, from finding significant relationships within Recursion’s Maps of Biology and Chemistry to generating novel compounds and scheduling them for synthesis and experimentation.
For more about Recursion’s collaborations and extensive pipeline:
🔺A text-guided protein design framework🔺
ProteinDT, is a multimodal framework that leverages textual descriptions for protein design, and consists of three consecutive steps: 1️⃣ ProteinCLAP, which aligns the representation of two modalities, 2️⃣ a facilitator that generates the protein representation from the text modality and 3️⃣ a decoder that creates the protein sequences from the representation.
To train ProteinDT, they constructed a large dataset, SwissProtCLAP, with 441,000 text and protein pairs, and they quantitatively verified the effectiveness of ProteinDT on three challenging tasks: 🔹over 90% accuracy for text-guided protein generation; 🔹best hit ratio on 12 zero-shot text-guided protein editing tasks; 🔹superior performance on four out of six protein property prediction benchmarks.
💈 Revvity Inc
Revvity announced on April, 7, 2025 that its software and informatics division, Revvity Signals Software, will launch its Signals One, a unified software platform designed to streamline data management across the entire drug discovery lifecycle (Revvity Signals Software Unveils Unified Data Platform To Accelerate Drug Discovery). The Signals One platform (a cloud-native SaaS R&D solution) addresses the growing complexity of drug modalities research by delivering a complete solution that integrates advanced research capabilities such as:
➡️ Simply handle common visualization and analytics use cases, including in vitro curve fitting, in vivo data visualization, and group-comparison,
➡️ Enhance user experience and ensure IP protection with integrated Generative AI and LLM, and
➡️ Create and use ontologically aware assay repositories that follow F.A.I.R. data principles.
Revvity Signals Software (formerly PerkinElmer Informatics) is known for offering the ChemDraw solution, that along with Chem3D and ChemFinder, is part of the ChemOffice suite of programs, available for Macintosh and Microsoft Windows. The ChemOffice Professional package 📦 has the following applications:
➡️ ChemDraw is used to quickly and effectively draw molecules, reactions and biological entities and pathways, to search databases (now including SciFinder, the curated database of chemical and bibliographic information that covers several scientific and biomedical fields, with an emphasis on chemistry), to generate accurate names from structures, and to predict properties and spectra.
➡️ Chem3D generates 3D models so that chemists can view their compounds in three dimensions to assess shape and properties to maximize activity or specificity. Chem3D also includes GAMESS (The General Atomic and Molecular Electronic Structure System, that is a quantum chemistry package), and interfaces to other computational tools including Gaussian (a tool for computational chemistry), MOPAC (Molecular Orbital PACkage), Conflex (a molecular simulation program), and Autodock (a suite of automated docking tools).
➡️ ChemFinder is a chemically-intelligent personal database system that scientists use to organize their compounds and to search for and correlate structures with properties and to transform data into easy to understand visualizations, cluster maps and ideal compound profiles to easily discern structure-activity relationships.
➡️ ChemScript is a scripting language that exposes the underlying chemical structure processing power of ChemOffice to developers who want to manipulate structures and automate processes. And
➡️ ChemOffice+ Cloud, that makes it much easier to create reports to communicate chemical research.
Revvity also offers the Spotfire Visual Analytics package 📦 that includes: Lead Discovery Premium (Incisive Chemical and Biological Analytics: Analyze & visualize chemical structures, bio sequence data compare, score & segment leads based on data), Spotfire Lead Discovery Premium Biotech Bundle on the AWS cloud (Essential lead optimization tools for developing both small molecule and biologics-based therapies for any company, any size), and Spotfire Powered Clinical Solutions (Inform clinical decisions and visually explore data with Signals Clinical and custom Spotfire analytics facilitated by near real-time access to analytics ready data to help you accelerate decisions and get new treatments to patients faster).
💈 Medtronic plc and Methinks Software SL
Medtronic (NYSE: MDT) has just inked a neurovascular partnership with Methinks AI, a Barcelona, Spain-based developer of programs to detect and alert providers of strokes from patient imaging scans (Medtronic inks stroke AI partnership with European developer Methinks). The medtech giant plans to integrate Methinks AI’s apps with its portfolio of ischemic stroke treatment hardware, including blood clot aspiration systems and stent-based retrievers.
Methinks AI Stroke Solutions offers an AI medical imaging software capable of performing stroke triage x3 and unlock stroke treatments potential from non-contrast CTs including: 1️⃣ Methinks NCCT LVO detects Large Vessel Occlusions from Non-Contrast, NCCT scans, 2️⃣ Methinks NCCT ICH detects Intracranial Hemorrhages from NCCT scans and 3️⃣ Methinks CTA LVO detects Large Vessel Occlusions from Contrast CT scans. The company is a VC backed digital health start-up that recently won the prestigious EIC Accelerator of the European Commission and has obtained two gold medals in the RSNA Kaggle competitions. Finally, Medtronic: Global Healthcare Technology Leader is an Irish medical device company.
💈 Viz.ai Inc
Viz.ai recently announced new clinical data demonstrating how the Viz HCM module enables faster, accurate detection of signs of hypertrophic cardiomyopathy 🫀 (HCM) to help ensure that more patients receive the care they need. Four studies, which will be presented at the American College of Cardiology’s (ACC) Annual Scientific Session & Expo 2025, indicate the real-world impact of Viz.ai in clinical practice with earlier detection and triaging of new patients with HCM, a commonly inherited heart disease that often goes undetected (Four New Studies Demonstrate that Viz.ai Finds New Patients with Hypertrophic Cardiomyopathy Earlier When Embedded into the Clinical Workflow). Moreover, the Viz HCM module developed as part of a multi-year agreement between Viz.ai and Bristol Myers Squibb (NYSE:BMY) (Viz.ai secured Bristol Myers Squibb's backing for hypertrophic cardiomyopathy-spotting AI), is the first 🥇 and only AI algorithm cleared by the U.S. Food and Drug Administration (FDA) for HCM.
In top of that, the Viz HCM module was just recognized in the Health Medical & Biotech category and Cardiovascular Health Diagnostics and Monitoring subcategory (Viz.ai Receives Edison Award for HCM Module) and named an Award 🏆 Winner in the 2025 Edison Awards, for the third year in a row. The Edison Awards, named after the American inventor Thomas Alva Edison, honor excellence in new product and service development, marketing, design and innovation.
Viz.ai (located in the United States, Netherlands, United Kingdom, Israel and Portugal) sends a notification to healthcare professionals when there is a sign of a serious situation. Viz.ai’s algorithm was designed to spot signs of hypertrophic cardiomyopathy (Viz HCM) and is part of the Viz.ai Cardio Suite, a collection of the company’s heart focused diagnostic AI programs into one place for easy access by hospital customers. Viz HCM can automatically sift through routine electrocardiograms (ECG) gathered across a hospital and send an alert to the appropriate care teams if signs of HCM are detected in a patient’s ECG data.
On December 16, 2024, Viz.ai and Avicenna.AI announced the integration of Avicenna.AI's 🔹CINA-iPE (detects incidental pulmonary embolism, PE) and 🔹CINA-ASPECTS (assesses the ASPECTS, Alberta Stroke Program Early CT Score, from CT brain images) tools into the Viz.ai One platform, a combination that provides radiologists and specialists with additional insights from computed tomography (CT) scans, to advance fast and accurate decision-making, driving better patient care (Viz.ai Integrates Avicenna.AI's Tools for ASPECTS Stroke Severity Assessment and Incidental Pulmonary Embolism into Viz.ai One Platform). The AI-powered Viz.ai One is an intelligent care coordination solution that identifies more patients with a suspected disease, informs critical decisions at the point of care, and optimizes care pathways and helps improve outcomes.
Avicenna.AI in France (Empowering Radiology With AI-based Tools) offers AI solutions tailored for emergency radiology and incidental findings. Through collaboration with experts and software engineers, they enhance radiologists' efficiency by streamlining their manual tasks with cutting-edge tools for 🔹head, 🔹chest and 🔹spine. More specifically, Avicenna.AI provides efficient solutions not only for the detection of traumatic brain injury (TBI) and hemorrhagic stroke, but also for the identification and quantification of acute ischemic stroke. Their tools excel in overcoming the challenges associated with the diversity of chest conditions, non-specific indicators, and the potential overlap of symptoms with other diseases. On September 19, 2024, Avicenna.AI received 510(k) clearance from the U.S. Food and Drug Administration (FDA) for its 🔹CINA-CSpine tool, designed to support the detection and triage of cervical spine fractures from CT images (Avicenna.AI gets FDA nod for CINA-CSpine). CINA-CSpine was validated on more than 300 noncontrast CT scans provided by multiple sources in the U.S. and Europe and acquired from 36 different scanner models across five vendors, according to the firm.
To conclude, Viz.ai is the pioneer in the use of AI algorithms and ML to increase the speed of diagnosis and care, across 1,700+ hospitals and health systems in the U.S. and Europe.
💈 Unlearn.AI Inc
Unlearn just announced results from a collaboration with remynd, a Belgium-based biotech company developing treatments for neurodegenerative diseases 🧠 (Unlearn and remynd Partner on Alzheimer’s Study to Strengthen Confidence in Early Clinical Signals Using Digital Twins). The results were shared at the 2025 Alzheimer’s & Parkinson’s Drug Development Summit in Boston.
The collaboration was focused on remynd’s Phase 2a clinical trial of REM127 (an investigational, first-generation small molecule therapy targeting septins in patients with mild-to-moderate Alzheimer’s Disease, AD), and Unlearn supported the study by applying its Alzheimer’s Disease-specific Digital Twin ♊ Generator (AD DTG)—a proprietary ML model trained on data from more than 26,000 participants across landmark AD datasets such as ADNI, CPAD, NACC, and EPAD. The AD DTG uses each participant’s baseline data to forecast their clinical and biomarker trajectories under standard care, generating a “digital twin” for every individual in the trial.
Moreover, Unlearn just announced Krates Ng as its Chief Technology Officer (Unlearn Appoints Krates Ng as Chief Technology Officer). Krates, as a seasoned technology leader with deep experience in enterprise software, joins the team at an optimal time in its growth as it scales to deliver software solutions that accelerate clinical trials and transform drug development.
Unlearn develops generative ML methods to predict individual health outcomes and accelerate clinical innovation, by using AI-powered digital twins on every patient. A patient’s digital twin (TwinRCTs or TwinRCTs II) is computationally created with generative AI (and it is not a matched patient from an external cohort) providing a probabilistic forecast of their specific health outcomes, while it cannot be used like data from a new patient. Unlearn's technology is regulatory-qualified and used by leading global pharmaceutical companies to run AI-powered clinical trials.
For example, on June 27, 2023 QurAlis Corporation and Unlearn announced a collaboration to accelerate and optimize QurAlis' clinical program in amyotrophic lateral sclerosis with Unlearn's advanced AI technology. On July 30, 2024, Unlearn announced one poster session at the Alzheimer's Association International Conference (AAIC) in Philadelphia together with AbbVie (Unlearn Presents Studies on AI-powered Clinical Trials with AbbVie and Johnson & Johnson Innovative Medicine at the Alzheimer's Association International Conference 2024). In its work with AbbVie, Unlearn showed how leveraging participants’ digital twins can reduce overall sample sizes by 10-15% when estimating the treatment effect on CDR-SB (Clinical Dementia Rating) at week 96 in a Phase 2 study. Alternatively, digital twins can achieve power gains of up to 7% (from 80% to up to 87%) with CDR-SB.
For more follow them on Substack: Unlearn.
💈 Predictive Oncology Inc, Renovaro Biosciences Inc and BioSymetrics Inc
On April 02, 2025, Predictive Oncology ( POAI -2.91% ▼ ) released its Q4 earnings (Predictive Oncology Reports 2024 Financial Results and Merger Plans) and announced a loss from continuing operations of approximately $10.8M on total revenue of $1.6 million for the year 2024. The company completed the sale of assets related to its subsidiary, Skyline Medical Inc., to DeRoyal Industries, which is expected to reduce ongoing expenses and sharpen its focus on AI/ML capabilities. Additionally, Predictive Oncology has developed a registry of drug candidates for potential repurposing and partnered with Tecan Group Ltd to expand drug screening capabilities.
Predictive Oncology is changing the game in drug discovery with its PEDAL platform pairing AI with a vast biobank of tumor samples (150K+ tumor samples). At Predictive they make groundbreaking drug-response predictions, from 3D tumor models—compatible with multiple cell types, drug classes, including small molecules, antibodies, antibody-drug conjugates, immunomodulatory agents, CAR-T cells, etc, and downstream analysis methods—to advanced formulation services such as an automated High Throughput Self-Interaction Chromatography, HSC™, Platform that conducts high-throughput, self-interaction chromatography screens on FDA-approved excipients for protein formulations.
Predictive Oncology (headquartered in Pittsburgh, PA) announced on January 16, 2025 that plans to launch its validated flagship live cell ChemoFx® drug response assay in Europe and expanded availability in the United States. The ChemoFx® treatment selection marker and tumor profiling assay will initially focus on ovarian and other gynecological cancers and may include testing of other major tumor types of interest over time (Predictive Oncology Announces Planned European Launch of its ChemoFx® Treatment Selection Marker and Tumor Profiling Assay).
Moreover, Predictive Oncology Announced Agreement to be Acquired by Renovaro Biosciences on January 06, 2025, in exchange for preferred stock of Renovaro. Predictive and Renovaro both have proprietary AI/ML platforms with complementary technical advantages that can be leveraged together to accelerate drug discovery and reduce the risk of drug development. Los Angeles-based Renovaro Inc (NASDAQ: RENB) 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.
Unfortunately ⚠️🚨, on April 04, 2025 Renovaro provided an update regarding its Definitive Agreement with Predictive Oncology aiming to initiate the integration of AI/ML platform technologies, core laboratory capabilities and business development efforts in Europe and the United States (Renovaro Provides Update to Definitive Agreement with Predictive Oncology). More specifically:
Renovaro entered into a binding agreement merger with Predictive Oncology, Inc (“POI”) dated January 1, 2025, and supplemented with the Extension Agreement dated February 28, 2025 (collectively, the “Binding Agreements”). On April 3, 2025, Renovaro received an email from POI terminating 🔚 the merger transaction. Renovaro’s position is that POI must comply with the binding obligations thereunder and enter into an exclusive License Agreement as required in each of the Binding Agreements. Renovaro notes that POI is in breach of the Binding Agreements and has caused substantial damage to Renovaro for which it will seek redress. Failure to enter into an exclusive License Agreement on the terms set forth in the Binding Agreement on or before April 10, 2025, will cause Renovaro to seek all its legal remedies to recover all its damages and/or seek additional remedies to fully redress the breaches.
To conclude, Renovaro and BioSymetrics have also just announced a definitive merger. The combined 🪢 entity aims to leverage advanced analytics and AI capabilities to accelerate drug discovery and development, offering more robust solutions for pharmaceutical companies (Renovaro and BioSymetrics Announce Definitive Merger). This transformative partnership is designed to enhance Renovaro’s data repository, biomarker discovery capabilities, accelerate translational research, and bring precision medicine solutions to cancer and other critical disease areas.
BioSymetrics is a phenomics-driven drug discovery company that integrates clinical and experimental data using ML creating a phenograph to navigate from phenotypes to genes and to druggable targets. At the core of Renovaro’s & Biosymetrics’ collaboration is BioSymetrics’ proprietary Elion platform, a cutting-edge AI and ML engine that uncovers complex biological relationships to accelerate the discovery of diagnostics and therapeutics. By integrating Elion into Renovaro’s workflow, the combined entity aims to streamline the translation of biomarker insights into accelerated discovery timelines, enhancing precision in target identification and improving overall research efficiency, ultimately enabling faster and more effective drug discovery and therapeutic development.
💈 More News 💈
Moorfields Eye Hospital INSIGHT research hub will collaborate with artificial intelligence development company Insitro,
AbbVie, J&J to add proprietary data to AI protein model in bid to accelerate drug discovery,
Cleveland Clinic and CAS to Leverage Quantum Computing and AI in Drug Discovery Effort
Viva Biotech Announces 2024 Annual Results: Significantly Rebounding in Performance with New Stage ahead, AI Leads to a New Era of Novel Drug R&D
Japan's PRISM BioLab and Elix join forces to accelerate AI-driven drug discovery
Genflow Biosciences enters AI gene therapy research deal
InVivo Biosystems Advances AI Technology for Real Time Animal Health Monitoring
Genflow Biosciences PLC Announces Launch of AI-Powered Partnership
Obatala Sciences and Ainnocence Announce Partnership to Transform Drug Discovery Through AI and Human Biological Models
Absci to Report Business Updates and First Quarter 2025 Financial and Operating Results on May 13, 2025
For more: Spring TechBio News (II) (paid 🔐 edition).