CAMBRIDGE, Mass. — Insilico Medicine has launched a Virtual Aging Cell webpage and previewed a new multi-agent artificial intelligence platform designed to model cellular aging and other biological processes across multiple levels of the body.
The clinical-stage, AI-powered drug discovery company said its Virtual Aging Cell, or VAC, platform uses biological age as a core variable and is intended to simulate processes including cell differentiation, reprogramming and aging.
Virtual cells are computational models that combine artificial intelligence and mathematical modeling to simulate cellular biology. Insilico said such systems could help predict drug responses, study disease mechanisms and support the discovery of new therapeutic targets.
“Every computational model needs a first principle, and ours is biological age,” said Alex Zhavoronkov, Ph.D., 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 company said most existing virtual cell models are built largely on data collected at individual points in time, limiting their ability to capture dynamic biological changes. VAC is designed to incorporate biological time and interactions across six levels: molecular, intracellular, intercellular, tissue, organ and organism or population.
Insilico’s work on virtual cells and aging biology dates back more than a decade. The company said it began exploring computational models of cells, organs and populations in 2014 and later worked with BioTime on the Embryonic.AI project, which used deep neural networks to study cell differentiation and fate.
The company subsequently developed its PreciousGPT series of AI models for aging research. Precious1GPT, released in 2023, used DNA methylation and transcriptomic data to predict biological age and distinguish disease samples from controls. Precious2GPT expanded those capabilities to generate synthetic multi-omics data with specified tissue and age characteristics.
Precious3GPT, developed with the Vadim N. Gladyshev Lab at Harvard Medical School, integrated text, tabular data and knowledge graphs across multiple species and omics modalities. The model was designed for applications including age prediction, target discovery, disease classification and compound sensitivity prediction.
“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.”
The VAC platform uses what Insilico calls a Multi-Agent Swarms architecture. Master Agents coordinate tasks and integrate information across biological levels, while Specialist Agents perform functions at individual levels and can access databases, omics tools and scientific literature.
The company said the platform is also designed to model the effects of interventions such as drug-target inhibition, gene knockout and environmental changes, with the goal of supporting research into cell reprogramming, target identification and potential anti-aging therapies.
