(Press-News.org) Cambridge, Massachusetts, January 14, 2025 - Insilico Medicine (“Insilico”, HKEX:03696), a clinical-stage biotechnology company driven by generative artificial intelligence (AI), today announced the demonstration of its Nach01 multimodal foundation model deployed on Microsoft Discovery, Microsoft’s science-focused platform designed to accelerate research and development through agentic AI. This collaboration highlights Microsoft Discovery’s extensibility with third-party AI models and illustrates how R&D organizations can adopt unified, AI-native workflows for computational drug discovery. By orchestrating secure, multi-step investigations within a Microsoft Azure-native environment, the demonstration underscores key benefits—including enhanced transparency, improved reproducibility, and scalable deployment—empowering scientific teams to streamline and advance discovery processes with great assurance.
Drug discovery organizations increasingly rely on computational approaches to support hypothesis generation, molecular design, and multidimensional data analysis, but these efforts are often executed in disconnected environments that make it difficult to iterate quickly or reproduce results across teams. In the future, customers deploying Insilico’s Nach01 on the Microsoft Discovery platform will be able to orchestrate its performance as part of multi-step workflows. This will enable scientists and engineers to design end-to-end pipelines that integrate molecule generation, property prediction, and downstream analysis within a secure Azure environment.
Nach01 is a multimodal foundation model developed by Insilico Medicine and a part of the Pharma.AI platform, used for accelerating drug discovery. It leverages a large language model architecture to process both chemical structural and spatial data and was built to handle hundreds of diverse tasks in molecular design and prediction. Nach01 combines techniques from its predecessor, Nach0 available on Huggingface, including textual and 3D spatial representation learning, into a single model that can address retrosynthesis, molecular property prediction, and other complex chemistry challenges. Nach01 can support workflows across the drug discovery pipeline, from target-related research and hit generation to lead optimization, by generating and evaluating novel molecular structures, performing predictive analytics such as ADMET-related property estimation, and prioritizing candidates for further experimental validation. Insilico will publish Nach01 model to Microsoft Marketplace.
With Nach01 deployed on Microsoft Discovery, teams can register Nach01 within the platform and compose AI-driven pipelines that connect Nach01 to other computational tools, allowing them to execute workflows on demand. For example, workflows can be configured end-to-end, starting with a structure-based design step (using Nach01 to propose molecules for a given biological target), followed by an ADMET prediction step, and then passing results into additional scoring tools (e.g., QSAR models or Free-Energy calculations) and downstream analysis/visualization, configured within a single workflow. This approach can help bridge the gap between AI modeling and day-to-day discovery execution by turning what previously required manually stitched scripts for molecule generation, property prediction, and analysis into a managed and repeatable workflow that teams can share and refine.
“Insilico is building purpose-built, multimodal foundation models that can be deployed in the real world where governance, reproducibility, and scale are essential,” said Alex Zhavoronkov, PhD, Founder and CEO of Insilico Medicine. “Deploying Nach01 with Microsoft Discovery helps bring chemistry superintelligence into a unified, secure environment so teams can iterate faster and run end-to-end computational discovery workflows with greater confidence.”
The collaboration aligns with Insilico’s broader strategy of integrating AI model innovation with drug development execution through its end-to-end technology stack and validated infrastructure. Insilico continues to advance its platform and pipeline across multiple therapeutic areas, while also enabling partners to adopt AI-native discovery capabilities through scalable software and model offerings. By deploying Insilico’s multimodal chemistry foundation model on Microsoft Discovery, customers can use its orchestration capabilities to accelerate iteration cycles and enable teams to transition from scientific insight to experimentally testable candidates more efficiently.
“At Microsoft, we’re driven by a mission to empower every organization to achieve more—and our collaboration with Insilico is a powerful testament to that mission in action. By bringing Insilico’s Nach01 foundation model into Microsoft Discovery, we’re giving research teams the ability to tap into advanced AI within a unified, secure, and scalable environment. Together, we’re showing how agentic AI and orchestrated intelligence can transform scientific insight into real‑world breakthroughs, accelerating the development of life‑changing therapies with unprecedented speed, precision, and confidence.” Aseem Datar, Corporate Vice President, Product Innovation, Microsoft Discovery and Quantum.
By integrating advanced AI and automation technologies, Insilico has significantly improved the efficiency of early-stage drug development in real-world practices, setting a benchmark for AI-driven drug discovery. Whereas traditional early-stage drug discovery typically requires 2.5 to 4 years, more than 20+ of Insilico’s internal programs initiated between 2021 and 2024 achieved PCC nomination in just 12 to 18 months on average, with only about 60–200 molecules synthesized and tested per program.
About Insilico Medicine
Insilico Medicine is a pioneering global biotechnology company dedicated to integrating artificial intelligence and automation technologies to accelerate drug discovery, drive innovation in the life sciences, and extend health longevity to people on the planet. The company was listed on the Main Board of the Hong Kong Stock Exchange on December 30, 2025, under the stock code 03696.HK.
By integrating AI and automation technologies and deep in-house drug discovery capabilities, Insilico is delivering innovative drug solutions for unmet needs, including fibrosis, oncology, immunology, pain, obesity and metabolic disorders. Additionally, Insilico extends the reach of Pharma.AI across diverse industries, including advanced materials, agriculture, nutritional products, and veterinary medicine. For more information, please visit www.insilico.co
END
Insilico Medicine integrates Nach01 Foundation Model with Microsoft Discovery to enable AI-native, enterprise-ready drug discovery workflows
2026-01-14
ELSE PRESS RELEASES FROM THIS DATE:
New study reveals precursors for forecasting summer clustered extreme precipitation events in Northeast China
2026-01-14
Against the background of accelerated global warming, the atmospheric moisture content has increased significantly and the hydrological cycle has intensified, leading to pronounced rises in both the frequency and intensity of extreme precipitation events globally. Northeast China, a region highly sensitive to climate change, has experienced increasing occurrence of clustered extreme heavy precipitation events in recent years. Improved knowledge of synoptic regimes and moisture accumulation responsible for clustered extreme heavy precipitation events (CEPEs) is essential for enhancing short-term forecasting skill and disaster prevention and mitigation.
Researchers ...
A bacterial toxin can counteract colorectal cancer growth
2026-01-14
A toxin secreted by cholera bacteria can inhibit the growth of colorectal cancer without causing any measurable damage to the body. This is shown by a new study by researchers at Umeå University, Sweden. Systemic administration of the purified bacterial substance changes the immune microenvironment in tumours, and the results may open the way for research into a new type of cancer treatment.
"The substance not only kills cancer cells directly. It reshapes the tumour environment and helps the immune system to work against the tumor without damaging healthy tissue," says Sun Nyunt Wai, professor at Umeå University and one of the lead authors behind ...
Frozen hydrogen cyanide ‘cobwebs’ offer clues to origin of life
2026-01-14
A substance poisonous to humans — hydrogen cyanide — may have helped create the seeds of life on Earth. At cold temperatures, hydrogen cyanide forms crystals. And, according to computer models reported in ACS Central Science, some of the facets on these crystals are highly reactive, enabling chemical reactions that are otherwise not possible at low temperatures. The researchers say these reactions could have started a cascade that gave rise to several building blocks of life.
“We may never know precisely how life began, but understanding how some of its ingredients take shape is within reach. Hydrogen cyanide is likely one source of this chemical ...
Physics of foam strangely resembles AI training
2026-01-14
Foams are everywhere: soap suds, shaving cream, whipped toppings and food emulsions like mayonnaise. For decades, scientists believed that foams behave like glass, their microscopic components trapped in static, disordered configurations.
Now, engineers at the University of Pennsylvania have found that foams actually flow ceaselessly inside while holding their external shape. More strangely, from a mathematical perspective, this internal motion resembles the process of deep learning, the method typically used to train modern AI systems.
The discovery could hint that learning, in a broad mathematical sense, may be a common organizing ...
Bis-pseudoindoxyls: a new class of single benzene-based fluorophores for bioimaging applications
2026-01-14
Fluorophores are chemical compounds or molecules that absorb light energy at one wavelength and re-emit it as light at a longer, lower-energy wavelength, acting as glowing tags or markers. The absorption process is known as excitation, and the re-emission is visible as fluorescent light, which makes these molecules crucial for biological imaging, diagnostics, and tracing cellular molecules like proteins or lipids under normal or various infectious conditions.
Fluorophores with red-light absorption properties are ideal for bioimaging. Red light refers ...
Blocking a cancer-related pathway helps reduce spine deformities due to genetic disorder, finds new study
2026-01-14
Spinal deformities such as scoliosis and kyphosis are among the most serious complications of neurofibromatosis type 1 (NF1), a genetic disorder that affects about one in 3,000 people. These deformities often begin in childhood, worsen rapidly, and can lead to chronic pain, reduced mobility, and may require major surgery. Despite their frequency and severity, there are currently no approved drug treatments to prevent NF1-related spinal deformity.
In a new study published in Volume 13, Issue 103 of the journal Bone Research on December ...
New study explores therapeutic potential of CRISPRCas3 genome-editing system
2026-01-14
Genetic disorders occur due to alterations in the primary genetic material, deoxyribonucleic acid (DNA), of an organism. Transthyretin amyloidosis (ATTR) is a progressive disorder involving amyloid deposits of misfolded transthyretin (TTR) proteins. The deposits, mainly affecting the heart and the nerves, can lead to symptoms like heart failure and neuropathy. While one of its two major forms is associated with age, the other one is hereditary, resulting from destabilizing mutations in the TTR gene. The therapeutic efficacy of suppressing TTR production has been clearly demonstrated. Although ribonucleic acid (RNA) interference-based ...
Korea University researchers revive an abandoned depression drug target using structurally novel NK1 receptor inhibitors
2026-01-14
For decades, scientists have investigated the neurokinin-1 receptor (NK1R) as a potential target for treating major depressive disorder. Early studies suggested promise, but enthusiasm faded after clinical trials of drugs such as aprepitant failed to show clear benefits, raising doubts about whether NK1R itself was a viable antidepressant target.
Now, researchers from Korea University report that the problem may not lie with the target, but with the chemistry. In a new study led by Professors Hyeijung Yoo, Hong-Rae Kim, and Hyun Kim, published in Experimental & Molecular Medicine on November ...
Jeonbuk National University researchers highlight advancements in chemical looping fluidized bed reactors
2026-01-14
Traditional techniques of converting fossil fuels for heat and power generation and chemical production increase carbon footprint, harming society and environment. To mitigate this problem, carbon capture and storage technologies aimed at lowering carbon dioxide emissions and encompassing renewable energy utilization, circular economy, and green chemical synthesis are promising. Chemical looping is one such innovative technology. These processes—representing efficient technologies for hydrogen and chemical production applications—involve the cyclic oxidation and reduction of metal oxide particles ...
Tyrannosaurus rex grew up slowly: New study reveals the “king of dinosaurs” kept growing until age 40
2026-01-14
For decades, scientists have been counting annual growth rings—similar to tree rings—inside fossilized leg bones of Tyrannosaurus rex to estimate how old the giant carnivores were when they died and how quickly they grew to adulthood. The best estimates from previous studies were that T. rex typically stopped growing at around age 25.
An extensive new study of 17 tyrannosaur specimens, ranging from early juveniles to massive adults, now concludes that the king of carnivores took 40 years to reach its full-grown size of around eight tons. The new analysis—the most complete life ...