Insilico Medicine Introduces Biological Age into Virtual Cell Research: Launches Virtual Aging Cell Webpage and Previews Multi-Agent Driven VAC Generation Platform

Following a decade of exploration from the 2014 NVIDIA GTC to the PreciousGPT model series, Insilico Medicine presents the industry's first multi-agent Virtual Aging Cell (VAC) platform with biological age as a core condition.

CAMBRIDGE, Mass., Aug. 14, 2026 /PRNewswire/ -- Insilico Medicine ("Insilico", HKEX: 3696), a clinical-stage drug discovery company powered by generative artificial intelligence (AI), today announced the launch of its Virtual Aging Cell (VAC) Webpage alongside the preview of the company's Multi-Agent driven VAC platform.

Virtual cells are digital models that leverage artificial intelligence (AI) and mathematical modeling to computationally simulate cellular biology and its underlying dynamic laws. They offer powerful capabilities to predict drug responses, elucidate disease mechanisms, and support target discovery. Recognized as a frontier technology, virtual cells were named one of the seven technology breakthroughs to watch in 2025 by Nature, quickly becoming a focal point of competitive research for top global teams.

However, most existing models rely predominantly on data collected at isolated time points, capturing cells as static snapshots. Their capacity to simulate dynamic temporal processes—such as cellular differentiation, reprogramming, and aging—as well as multi-scale interactions across biological hierarchies, remains markedly constrained. Living cells are not frozen biological units; rather, they are constantly undergoing dynamic processes including division, differentiation, aging, and environmental response. A cell's state is intricately shaped by intracellular molecular networks, intercellular communications, tissue microenvironments, and individual background parameters. Consequently, integrating the temporal axis, biological age, and external interventions into a unified computational framework has emerged as a crucial trajectory for the evolution of virtual cell research.

The Virtual Aging Cell (VAC) concept introduced by Insilico directly addresses this emerging frontier. Built around biological age as a core conditional variable, the platform utilizes a multi-agent AI architecture to perform collaborative reasoning across six biological scales—molecular, intracellular, intercellular, tissue, organ, and organism/population. It aims to dynamically simulate cellular differentiation, reprogramming, and aging, offering robust computational support for target identification, cellular fate intervention, novel drug discovery, and geroscience research.

"Every computational model needs a first principle, and ours is biological age," said Alex Zhavoronkov, PhD, Founder, Co-CEO, and Chief Business Officer of Insilico Medicine. "This has been a decade-long scientific journey, from raising an industry-defining question at NVIDIA GTC in 2014, to teaching AI the language of aging biology with the PreciousGPT series, and now reimagining the virtual cell through agentic AI swarms. The VAC represents the convergence of this thesis: a platform that doesn't just read biological data, but conditionally generates the very trajectory of life's evolution. We look forward to collaborating with global pharmaceutical companies and research institutions in modeling virtual cells, virtual systems, and virtual populations across both healthy and diseased states."

A decade of Foundation: From Virtual Cell Concept to PreciousGPT Series

Insilico's exploration in virtual cells and geroscience spans a decade.

At the 2014 NVIDIA GTC conference, Insilico first articulated its vision for computational virtual cells, virtual organs, and digital populations, posing a now-famous industry question — "Can NVIDIA help solve aging?" — officially inaugurating the company's use of high-performance computing and AI to investigate the mechanisms of aging.

To translate this theoretical vision into practice, the company subsequently partnered with BioTime, a pioneer in regenerative medicine and stem cell research, on a deep collaboration called Embryonic.AI, which used Deep Neural Network Ensembles to track and modulate cell differentiation trajectories and cell fate decisions during the Embryonic-to-Fetal Transition (EFT).

In 2017, the two teams published their findings in Oncotarget, confirming that AI algorithms successfully identified COX7A1 as a key transition factor in the embryonic transformation stage. This was not only Insilico's first experimentally validated AI target discovery result, but also the first demonstration to the field that artificial intelligence could precisely capture the switches governing cell differentiation, reprogramming, and cell conversion, laying the biological foundation for subsequent virtual cell simulation.

With the rapid advancement of large model technology, Dr. Alex Zhavoronkov first proposed applying multimodal Transformers to aging research at the Gordon Research Conference (GRC) in May 2022. To explore the potential of multimodal Transformers and diffusion models in life sciences, the company's AI team initiated model development that same year, building on years of accumulated expertise in aging biology and multi-omics modeling to progressively construct the PreciousGPT series of scientific foundation models dedicated to aging mechanism analysis and multi-omics generation.

In 2023, Insilico released Precious1GPT, an aging clock based on multimodal Transformers and transfer learning. The model integrated DNA methylation (epigenetic) and transcriptomic data to predict biological age and distinguish disease from control samples. Using this model, the team identified dual-purpose targets such as APLNR and IL23R, with both anti-aging and anti-age-related-disease potential. The results were published in Aging, a leading journal in the field.

Insilico further expanded the model's capabilities from evaluation and prediction to conditional generation. Released in 2024, Precious2GPT fused a Conditional Diffusion model (CDiffusion) with a decoder-only Multi-Omics Pre-trained Transformer (MoPT), capable of generating high-quality synthetic multi-omics data carrying specific tissue and age characteristics. The model's age prediction accuracy on generated data outperformed baseline models such as conditional GANs. This research was published in npj Aging, a Nature portfolio journal.

That same year, Insilico collaborated with the Vadim N. Gladyshev Lab at Harvard Medical School to release Precious3GPT. As a true multimodal Transformer, the model integrated text, tabular data, and knowledge graph representations, covering four species, including mouse, rat, monkey, and human, and three omics modalities: transcriptomics, methylation, and proteomics. It could perform cross-species age prediction, target discovery, disease/tissue/sex classification, and compound sensitivity prediction within a unified framework. Its synthetic data generation used "biological age" as one of the conditional inputs, ensuring that generated omics data carried age and time labels. The model was open-sourced on Hugging Face and GitHub concurrent with its release as a bioRxiv preprint.

From early single-target identification and validation to the evolution of multimodal foundation models, this research lineage progressively widened the boundaries of what a single model could learn about biological systems, ultimately converging on systematic modeling of the cell's full lifecycle and dynamic processes.

"Biology unfolds across time and interconnected levels, yet many computational models examine only one layer or moment in isolation," said Petrina Kamya, Ph.D., Vice President, Global Head of AI Platforms and President of Insilico Medicine Canada. "VAC is designed to bring those dimensions together, combining biological age with multi-agent reasoning to explore how changes in a cell's age affect tissues, organs, and the broader organism. Our goal is to create a more dynamic environment for studying disease, evaluating interventions, and finding new opportunities for drug discovery."

Agentic AI Driven: From Molecular Simulation to Organism Evolution

While the PreciousGPT model series laid the foundational data and conditional generation capabilities for understanding cellular omics and aging mechanisms, the VAC platform released today introduces a Multi-Agent Swarms architecture, granting it genuine intelligent reasoning capabilities to simulate dynamic living systems.

Unlike most industry approaches that treat the cell as a "static snapshot" at a particular moment, cells in living organisms exist within a network of multi-scale interactions and continuous dynamic evolution. To capture this biological complexity, Insilico constructed a multi-agent collaborative architecture VAC platform, redefining the computational biology paradigm across three core dimensions:

• Biological time as a core condition. Unlike static expression profile prediction, the multi-agent architecture treats "biological age" as the core conditional variable that penetrates every scale. When reasoning about cell differentiation, reprogramming, or disease progression, the agent swarm can dynamically assess the differential responses of tissue microenvironments across young, mature, and aged life stages, ensuring that biological time naturally permeates every reasoning step.
  
  
• Six-scale agent swarm collaboration. Rather than attempting to compress all biological data into a single Transformer or graph neural network, the VAC system deploys agent swarms spanning different functions and scale gradients. Master Agents handle global task scheduling and cross-level logic integration, while Specialist Agents execute specialized tasks at each level. Individual agents can independently access databases, omics tools, and literature knowledge graphs, and engage in adaptive negotiation and joint reasoning across six biological scales — molecular, intracellular, intercellular, tissue, organ, and organism.
  
  
• From state observation to fate intervention. Traditional virtual cells are largely limited to one-directional state description and expression profile imputation. The VAC platform, by contrast, is designed to answer the question "how to reverse and reshape cell fate." When the system simulates interventions such as drug-target inhibition, gene knockout, or specific environmental stimuli, agents at each level can reason in real time about microenvironment changes, downstream pathway cascades, and cross-scale structural remodeling from micro to macro — providing end-to-end reasoning for stem cell reprogramming and systemic anti-aging strategies.

"What distinguishes VAC is not the number of hierarchical levels or agents, but the combination of bidirectional Master Agent coordination and first-class organism context storage. Among the papers we surveyed, no existing system simultaneously possesses these features: six biological hierarchies, an agent for every biological entity, dual top-down and bottom-up Master Agents, and a shared organism context that prioritizes age as a variable. The preview we are going to release is an important step toward a virtual cell that can model not just states, but changes." Vladimir Naumov, Ph.D., Head of TargetID of Insilico Medicine.

By deeply fusing the omics perception capabilities of the PreciousGPT foundation models with the cross-scale reasoning capabilities of the VAC multi-agent architecture, the VAC platform achieves a leap from single-omics "snapshot" characterization to "dynamic biological system simulation" spanning health and disease states — providing a highly interpretable digital testing environment for target identification, cell reprogramming protocol design, and anti-aging drug evaluation.

Platform Preview and Future Horizons

With the launch of the Virtual Aging Cell Webpage, Insilico has released an initial demo preview video of the VAC platform. Additionally, Insilico will continue the conversation at ARDD 2026 (the 13th Aging Research and Drug Discovery Conference) in Boston, engaging with top academic and industry partners in the longevity research field on the next steps in virtual cell platform development, and sharing the latest practices and validations of multimodal foundation models and multi-agent systems in aging intervention, cell reprogramming, and target discovery.

As an AI-native company, Insilico is setting industry records by redefining the efficiency and scalability of drug discovery through its advanced AI platform and automation lab. While traditional early-stage drug discovery typically spans 2.5 to 4 years, Insilico consistently reaches developmental candidate (DC) nomination in an average of just 12 to 18 months, synthesizing and testing only 60 to 200 molecules per program.

Since 2021, the company has nominated 33 PCCs, 13 of which have received IND approvals or clearances. Notably, 9 of these DC nominations have been announced since the beginning of 2026, including 2 candidates originating in the UAE, the first milestone in the region's history. These achievements fully demonstrated the scalability and efficiency of Insilico's AI-driven R&D productivity.

Building on this AI-driven momentum, Insilico has successfully achieved clinical validation for multiple AI-discovered and AI-designed molecules generated by its Pharma.AI platform. Its most advanced program, Rentosertib, completed a Phase IIa clinical trial establishing proof of concept for safety and efficacy trends, with landmark findings published in Nature Medicine in March 2025.

This track record, combined with the vast repository of proprietary data accumulated through its R&D engine, provides robust, real-world grounding for the Virtual Aging Cell platform's dry-lab and wet-lab validation loop and target authenticity.

For more information about Insilico's Virtual Aging Cell, please visit: https://virtualcell.insilico.com .

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 healthy 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, and obesity and metabolic disorders. Additionally, Insilico extends the reach of Pharma. AI across diverse industries, such as advanced materials, agriculture, nutritional products and veterinary medicine.

For more information, please visit www.insilico.com

SOURCE Insilico Medicine