AI For Drug Discovery: Weekly News 🍇

🟣AI For Drug Discovery: Weekly News🟣

🟣 AsedaSciences and Euretos Partnered

On June 30, 2025, AsedaSciences and Euretos announced a strategic commercial partnership to integrate their cutting-edge platforms (AsedaSciences® and Euretos Partner to Integrate Platforms for Deeper Insights from Disease Biology to Drug Discovery). Through this partnership, Euretos’ AI-powered platform, which semantically integrates over 3️⃣0️⃣0️⃣ biomedical data sources, will be combined with AsedaSciences’ 3RnD platform, that generates, integrates and visualizes high-quality human-relevant compound toxicity ☠️ data. The integration will enable researchers to associate disease mechanisms with molecular targets and, critically, predict compound toxicity in context with those targets and associated disease states.

➡️ Euretos uses natural language processing to interpret research papers—something like 2️⃣-2️⃣.5️⃣ million new scientific papers are published each year in about 2️⃣8️⃣,1️⃣0️⃣0️⃣ active scholarly peer-reviewed journals—but this is secondary to the 3️⃣0️⃣0️⃣-plus biomedical-data repositories it integrates. In particular, at Euretos they provide biological knowledge graphs that semantically harmonize public and proprietary data, literature and patents. And they customize all these to create client-specific knowledge graphs with domain specific and/or proprietary data. Their ML models are driven by multi-omics data minimizing publication bias and by integrating predictions from different types of multi-omics networks to provide biological insight.

➡️ Aseda Sciences Inc was established with the vision of becoming a leader in optimized drug discovery by providing multi-parametric data driven, high content, high throughput phenotypic screening services to the pharmaceutical and bio-pharmaceutical industry for the assessment of compound toxicity or mechanism of action. AsedaSciences and Excelra as of March 2025 have a co-marketing agreement that aims to deliver a unified data platform for small molecules, streamlining drug discovery workflows (AsedaSciences and Excelra Announce a Co-Marketing Agreement to Deliver a Unified Data Platform for Small Molecules). This strategic agreement with Excelra aims to co-market and expand the reach of AsedaSciences' groundbreaking 3RnD^® platform, which will be strengthened with Excelra's 1️⃣0️⃣M+ chemical structure and growing GOSTAR^® database. This sets a new benchmark for information consolidation and providing content accessibility through a single, easy-to-use interface for the scientific community. ➡️ Excelra Knowledge Solutions Private Limited is a leader in biopharma data and analytics, and uniquely blends scientific understanding with technological expertise. This dual mastery empowers innovative drug discovery and development, transforming research data into actionable insights for groundbreaking discovery.

🟣 KIST’s researcher won the international competition ‘CACHE Challenge’

The Korea Institute of Science and Technology (KIST) announced on July 1, 2025 that a research team led by Chief Researcher Park Geun-wan from the Natural Product New Drug Development Center won the international competition ‘CACHE Challenge’ for predicting new drug candidates using AI, for the second consecutive time. Following a joint victory in last year's competition, which explored new drug candidate substances for the novel coronavirus infection (COVID-19), this time the team achieved a solo victory (KIST wins CACHE Challenge for AI-driven drug prediction for second straight year - CHOSUNBIZ).

The research team led by Chief Researcher Park Geun-wan discovered 🆕 drug candidates targeting the CBLB protein, which has garnered attention as a key 🔑 target 🔐 in cancer immunotherapy, using the AI model ECBS (Evolutionary Chemical Binding Similarity).

CACHE is an English acronym that stands for 'evaluation of suitability for computer exploration experiments of new drug candidates.' The CACHE Challenge is an international competition that began in 2021, objectively assessing how effectively AI technology operates in the initial stage of new drug development.

🟣 Catalio Capital Management closed its fourth venture fund, Catalio Nexus Fund IV

Catalio Capital Management announced the closing of its fourth venture fund, Catalio Nexus Fund IV, with commitments exceeding 💲4️⃣0️⃣0️⃣M across the Fund and its related co-investment vehicles (Catalio Capital Management: Over $400 Million Raised To Invest In Healthcare Companies). The fund received substantial backing from existing Catalio investors as well as new global institutional investors, RIAs, foundations, and endowments.

Catalio’s core investment approach focuses on identifying and supporting transformative healthcare companies emerging from leading academic institutions, led by repeat founders with deep scientific expertise.

Established in 2020 by Co-Founders George Petrocheilos and Dr. Jacob Vogelstein, the firm manages 💲2️⃣ billion in assets across private equity, private credit, and public equities strategies.

So far, the Fund IV has made 16 investments, and some recent highlights in Fund IV include:

1. 👉 Co-leading PinkDx’s 💲4️⃣0️⃣M Series A fundraise aimed at developing diagnostics for gynecological ♀️🚺 cancers, building on Catalio’s extensive track record of success in cancer diagnostics.

2. 👉 Investing in the Series A financing of Superluminal Medicines, Inc, augmenting Catalio’s portfolio of AI-enabled drug discovery companies. Last month (June 25, 2025) the Japanese Axcelead Drug Discovery Partners, Inc (established in July 2017 by inheriting the drug discovery platform from Takeda Pharmaceutical) and Superluminal Medicines, Inc (based in Boston, and backed by a strong network of investors, including RA Capital, Insight Partners, NVIDIA, Catalio Capital, Eli Lilly and Company, and Gaingels) announced the intention to collaborate 🤝 on drug discovery targeting specific molecular mechanisms associated with challenging biological targets (Axcelead DDP and Superluminal Announced the Intent to Collaborate on Drug Discovery Targeting Specific Molecular Mechanisms, continuing a productive relationship).

   1. Another AI-enabled drug discovery company supported by Catalio is FogPharma, spun out of Harvard University by pioneering academic scientist and successful biotech company builder Dr. Gregory Verdine, and is a clinical-stage company that developed Helicons™, a novel therapeutic modality. Helicons are designed to combine the cell-permeability and broad tissue distribution of traditional small molecule drugs with the high specificity, broad target accessibility and rapid discovery of monoclonal antibody drugs.

3. 👉 Launching 2️⃣ 🆕 companies focused on immunology and inflammation: Rhapsogen (co-founded by Catalio Venture Partner Dr. Jeffrey Ravetch at Rockefeller University) and TBD Pharma (co-founded by Catalio Venture Partner Dr. Bert Vogelstein at Johns Hopkins University).

4. 👉 Taking advantage of attractive valuations in late-stage companies by participating in the 💲1️⃣5️⃣0️⃣M Series E financing for Imperative Care, a medical device company; a PIPE for Protara Therapeutics, an oncology company; and the 💲1️⃣8️⃣0️⃣M Series D financing for Alentis Therapeutics, a company developing antibody drug conjugates (ADC) for oncology indications.

🟣 Chai Discovery Team Released Chai-2

Chai Discovery Team introduces Chai-2, a multimodal AI model that enables zero-shot de novo antibody design. Achieving a 16% hit rate across 52 novel targets using ≤20 candidates per target, Chai-2 outperforms prior methods by over 100x and delivers validated binders in under two weeks—eliminating the need for large-scale screening.

Chai Discovery introduced on July 5, 2025 Chai-2, a multimodal generative AI platform capable of zero-shot antibody and protein binder design (Chai Discovery Team Releases Chai-2: AI Model Achieves 16% Hit Rate in De Novo Antibody Design). Unlike previous approaches that rely on extensive high-throughput screening, Chai-2 reliably designs functional binders in a single 2️⃣4️⃣-well plate setup, achieving more than 1️⃣0️⃣0️⃣-fold improvement over existing state-of-the-art methods.

Chai-2 was tested on 5️⃣2️⃣ novel targets, none of which had known antibody or nanobody binders in the Protein Data Bank (PDB). Despite this challenge, the system achieved a 1️⃣6️⃣% experimental hit rate, discovering binders for 5️⃣0️⃣% of the tested targets within a two-week cycle from computational design to wet-lab validation. This performance marks a shift from probabilistic screening to deterministic generation in molecular engineering.

Chai Discovery (also known as Chai Research) is building AI foundation models to predict and reprogram interactions between biochemical molecules, the fundamental building blocks of life, in order to accelerate drug discovery, starting with foundation models for molecular structure prediction across proteins, small molecules, DNA, RNA, covalent modifications and more.

On September 9, 2024, Chai Discovery released Chai-1, a new multi-modal foundation model for molecular structure prediction that performs across a variety of tasks relevant to drug discovery. Chai-1 enables unified prediction of proteins, small molecules, DNA, RNA, covalent modifications and more. The model is available for free via a web interface, including for commercial applications such as drug discovery. The development of Chai-1 was made possible through the support of numerous industry partners, including Dimension, Thrive Capital, OpenAI, Conviction, Neo, and Amplify Partners.

On September 9th, 2024, Chai Discovery (founded six months before) raised nearly 💲3️⃣0️⃣M from heavyweights Thrive Capital and OpenAI to bring AI to drug discovery.

🧃AI For Drug Discovery: Weekly News🧃

🧃 AI Startups, New Kids on the Block

🧃 Elnora AI

Elnora AI (2023, Estonia) is an antiviral drug discovery company focusing on host cells rather than directly targeting viruses and addressing the challenges posed by viral mutations and the limited size of viral genomes. This strategy, previously almost impossible due to the expansive nature of human genomic data and concerns over potential side effects, is now within our grasp, thanks to the capabilities of AI.

By integrating their AI-driven platform into antiviral drug discovery, they collect detailed experimental data, including failed experiments, from a global community of researchers, in order to tackle the 9️⃣0️⃣% failure rate in drug discovery. As a first product, they are developing a protocol optimizer to create a reproducible, unbiased dataset, promoting Open and FAIR science, and they are aiming to eliminate animal use in research. This tool allows to build an ML-readable dataset as a source of truly novel and successful drug targets. As a SaaS product, it enhances internal drug discovery projects and offers the same opportunities to all biotech and pharma companies as their clients.

Carmen Kivisild is the co-founder and CEO of this startup. She holds a PhD in Neurosciences from the University College London (UCL) and she worked as a Postdoctoral Researcher at King’s College London. Carmen co-founded Koolituskeskus PracticeGate and led it as Chief Business Development Officer (CBDO) and lecturer for 8+ Years.

Elnora raised its latest funding of 💲7️⃣1️⃣.5️⃣K from an Angel investment round on December, 21 2023. It also received an Enterprise Estonia Support (ESS) equity-free grant of 💶5️⃣0️⃣,0️⃣0️⃣0️⃣ from the European Regional Development Fund.

🧃 Maven Bio

The Y-combinator-backed Maven Bio (2023, US) has developed an AI-enabled commercial intelligence platform to evaluate therapeutic opportunities within the biopharmaceutical industry, that integrates document search, review, and analysis workflows into a single workspace and allows corporate development teams to construct comprehensive deal landscapes and perform comparative analyses efficiently.

By leveraging AI, the platform can halve the commercial failure rate, thus increasing the number of drugs approved and available to patients, and also provides research and analysis on the latest biopharma trends.

Michael Brady and Arjun Murthy are the co-founders. Arjun holds an MBA from Yale School of Management, and Michael attended the University of Pennsylvania for a Master of Computers and Informational Technology. Maven Bio raised its latest pre-seed funding round for 💲5️⃣0️⃣0️⃣K on September, 6 2023 from Y-Combinator.

🧃 QuantaBrain

🇮🇹 QuantaBrain (2023) aims to revolutionize psychiatry with imaging-based biomarkers for precise diagnoses and personalized treatments, enhancing objectivity and patient-specific care. The company has pioneered a proprietary AI-driven software for diagnosing psychiatric disorders through a quick 1-minute resting state functional magnetic resonance imaging (rs-fMRI) examination.

rs-fMRI is an entirely safe and non-invasive procedure where the patient simply rests (with the option to keep their eyes 👀 open or closed) for 1 minute inside the magnetic resonance scanner. Unlike structural imaging, functional MRI measures the flow of oxygenated blood 🩸 in the brain 🧠. As neural activity consumes oxygen, this examination provides an indirect measurement of brain activity.

Their proprietary AI software leverages urban traffic analysis techniques to analyze how oxygen is delivered and consumed across the brain. It is compatible with any scanner and MR acquisition sequence.

🧃 Metanovas Biotech

Metanovas Biotech (2021, US) has developed a suite of AI-enabled technologies (MetaNLP®, MetaKG®, MetaPep®, and MetaOmics®) that enhance the drug discovery process by integrating ML machines and big data analytics. By leveraging advanced algorithms to analyze vast datasets, the platform helps discover novel disease targets, screen potential drugs, repurpose existing medications for new indications, and predict ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties.

So far the company has created several products (🧯Anti-inflammatory peptide, 🫧 Anti-acne Peptide, 😉 Anti-wrinkle peptide, 🪥 Gingival Protection Peptide and 💃 Vaginal Care Antimicrobial Peptide) for use in the healthcare, functional foods, and cosmetics industries using its AI technology. Its strategic partners include global brands like L’Oréal, Beiersdorf, Haleon, Takeda, and Unilever. In 2024, MetaNovas was selected by the British authoritative medical and health magazine as the Leading AI Skincare Company 2024 and in 2023, MetaNovas Wins L'Oreal Big Bang 'Future New Product Research x Artificial Intelligence' Cross-Domain Championship.

🫧AI For Drug Discovery: Weekly News🫧

🫧 HealthTech News: 💶1️⃣M for Koios Care

Antwerp-based HealthTech startup Koios Care has closed a 💶1️⃣M funding round to accelerate its efforts in transforming the monitoring and treatment of Parkinson’s Disease with its AI-powered platform that passively collects data from smartphones 📲 and smartwatch ⌚ (Belgian HealthTech startup Koios Care raises €1 million to monitor and treat Parkinson's Disease with real-world data).

The round was led by Greek early-stage DeepTech investor Evercurious VC, with participation from Astylab Ventures, the imec.istart fund, and several angel investors, including those coordinated by HeBAN. The new funding will help Koios Care expand its digital health tool ‘Parkiwatch’ across European clinics, support regulatory clearance efforts, and build stronger partnerships with pharma companies and research institutions.

🫧 HealthTech News: 💷1️⃣.1️⃣M for Elyndra

Elyndra, a UK-headquartered AI-powered platform for the social care sector, has successfully closed a 💷1️⃣.1️⃣M funding round led by Outward VC (Elyndra secures £1.1m investment to unlock growth), to accelerate the development of elyndra’s technology which has the power to transform the care sector by optimizing care processes, improving decision-making capabilities, and ensuring better outcomes for those in care.

Founded by Marcus Williamson, elyndra has developed an integrated platform that equips care managers and frontline staff with AI-powered tools to enhance efficiency and care quality. By analyzing care data and operational processes, the technology provides insights for better care and interventions. The platform allows teams to spend more time with those in their care rather than hours of time being dedicated to administration and reporting.

🫧 Sumitomo Mitsui Trust Group Inc Has 💲3️⃣.7️⃣5️⃣M Stock Position in Absci

Sumitomo Mitsui Trust Group Inc. lifted its holdings in Absci Corporation (NASDAQ:ABSI - Free Report) by 3️⃣0️⃣.6️⃣% during the 1st quarter, according to the company in its most recent Form 13F filing with the SEC. The firm owns 1️⃣,4️⃣9️⃣3️⃣,8️⃣6️⃣5️⃣ shares of the company's stock after buying an additional 3️⃣5️⃣0️⃣,0️⃣3️⃣6️⃣ shares during the quarter. Sumitomo Mitsui Trust Group Inc. owned approximately 1️⃣.1️⃣7️⃣% of Absci worth 💲3️⃣. 7️⃣5️⃣0️⃣,0️⃣0️⃣0️⃣ at the end of the most recent quarter (Sumitomo Mitsui Trust Group Inc. Has $3.75 Million Stock Position in Absci Corporation (NASDAQ:ABSI)).

🫧 The Norrsken Foundation, one of Europe’s largest impact tech funds, has pledged 💶3️⃣0️⃣0️⃣M to support European startups to back startups

The Norrsken Foundation, one of Europe’s largest impact tech funds, has pledged 💶3️⃣0️⃣0️⃣M to support European startups using AI (Norrsken Foundation pledges €300M to support European AI-driven startups tackling global challenges). In particular, the Norrsken VC, Norrsken Launcher, and Norrsken Accelerator funds will invest 💶3️⃣0️⃣0️⃣M in European startups using AI to address major global challenges in the following areas:

• ☁️🌡️climate, such as clean energy and emission reduction,

• 🧑‍⚕️🏥⚕️health, improving healthcare systems and drug discovery,

• 🥑🥕 food, optimizing agriculture and reducing waste,

• 🎒🏫 education, and

• 🧑‍🤝‍🧑🤼 broader societal issues.

💛AI For Drug Discovery: Weekly News💛

💛 SCI Ventures invests 💲2️⃣M in Healx

SCI Ventures invested 💲2️⃣M in Healx for AI drug discovery for paralysis 🧑‍🦽 (Healx and SCI Ventures Join Forces to Uncover Cures for Paralysis with AI-Driven Drug Discovery). More specifically Healx, a pioneer in AI-powered drug discovery for rare and neglected conditions, has partnered with SCI Ventures, the world’s first specialist venture fund focused on curing paralysis, to accelerate the discovery and development of therapies for spinal cord injury (SCI) using AI. This first-of-its-kind collaboration will apply Healx’s cutting-edge AI platform to identify new promising treatments for SCI — a life-altering condition affecting over 2️⃣0️⃣ million people globally, with limited treatment options.

Healx (Cambridge UK, 2014) utilizes AI to match existing drugs with rare diseases. In particular, its AI platform Healnet utilizes NL processing to extract disease knowledge from published sources and to complement biomedical databases and proprietary curated data. Healx’s data is integrated in the form of the largest, rare disease-focused Knowledge Graph, that shows prioritized hidden and novel connections between drugs and diseases.

The platform uses multi-omics signature reversal and AI to identify novel therapeutic hits. By using Healx lab-generated phenotypic and transcriptomics profiling data, novel disease biology, mechanisms and targets are identified, which enables the design of second-generation compounds using virtual screening, predictive modeling and phenomics For example, Lig3DLens is a 3D virtual screening tool box, to identify novel drug applications in the area of rare disorders.

Healx has a collaboration with Sanofi (Healx announces agreement with Sanofi to seek new rare disease indications for compound using AI drug discovery platform) in order to identify new disease indications using Healnet, Healx’s AI-driven drug discovery platform.

Moreover, Healx has collaborations with Ono Pharmaceutical Co Ltd/TYO: 4528 and Ovid Therapeutics Inc/NASDAQ: OVID, and ongoing projects such as:

• ☀️ Healx has initiated a Phase 2a clinical trial for HLX-0201, and

• ☀️ has signed an investment agreement with its long-term partner, Children’s Tumor Foundation (CTF), to support the advance of Healx’s AI-powered neurofibromatosis programme including its lead candidate, HLX-1502, which will enter a Phase 2 clinical trial in the coming months.

On February 24, 2025, Healx Dosed the First Rare Cancer Patient with AI-Created Drug, and has reached a historic milestone by dosing the first patient with a rare cancer treatment designed using AI (History beckons as Healx doses first rare cancer patient with AI-created drug).

For more about Healx’s collaborations and pipeline news: AI-powered drug discovery: update (IX).

💛 BrightMind.AI announced insolvency

Brightmind.AI filed for insolvency. 😥

Brightmind.AI in Vienna, Austria had as a mission to revolutionize neurological care, by bringing cutting-edge, AI-powered, non-invasive brain 🧠 stimulation technology directly into people's homes, making personalized treatment accessible to those who need it most. Their therapy showed a >5️⃣0️⃣% reduction in migraine 😶‍🌫️days, 3x better than the current standard of care.

However, even if they successfully secured agreements for access to 17,000 patients and they gained the support of Oxford University Innovation, xista science ventures, and 3xP Global, and also received endorsements from leading neurologists, at the end they lacked ⏳💰 just time and money.

💛 South Korea accelerates AI Drug Discovery

The government of South Korea plans 📙📃 to grow the AI Drug Development sector in order to reduce the drug development time and the expenses of approximately 2 trillion won to less than half (South Korea accelerates AI drug development with significant government investment - CHOSUNBIZ).

The administration of Lee Jae-myung, which professes to be an 'Artificial Intelligence (AI) government', will actively support AI-based drug development, which is currently receiving substantial investments in the global industry.

💛 Modella AI and AstraZeneca Partnered

Modella AI has signed ✒️ a multi-year agreement with AstraZeneca to expedite AI-driven oncology clinical development (Modella AI and AstraZeneca link for cancer clinical development). The partnership will give AstraZeneca access to Modella AI’s multi-modal foundation models, with rich feature extraction from different types of data, to speed up clinical development across AstraZeneca’s worldwide oncology portfolio.

Modella AI is a leader 🔝🎩 in the development of AI for biomedical imaging, enhancing diagnostic, prognostic, and therapeutic workflows. With an initial focus on pathology, the company creates innovative AI models that integrate multimodal biomarker data to enhance diagnostic, prognostic, and therapeutic workflows.

• 📣 PathChat is their AI copilot for consulting on pathology cases, and for summarizing and creating pathology reports from your microscope, slide viewer, or smartphone.

  • Modella AI's Generative AI Co-Pilot PathChat Received FDA Breakthrough Device Designation,

  • PathChat 2 is their latest multimodal generative AI model that can reason over both pathology images and text as a helpful copilot for research and education use.

• 📣 Judith is their AI agent for automating AI model development for biomedical image analysis and scientific discovery.

  • Judith is the first research-use AI agent for biomedical image analysis that accelerates scientific discovery leveraging multimodal generative AI and foundation models.

Modella is a biomedical artificial intelligence company based in Boston, Massachusetts.