22:01, 25 February 2026

Sirius University Develops Ultra-Precise Digital Human Twins

Doctors are set to gain a powerful new tool in the fight against cancer.

Scientists at the Scientific and Technological University Sirius are building a fundamentally new digital human twin powered by artificial intelligence. The system is designed to help physicians more accurately predict how a patient’s body will respond to drugs, select safer and more reliable cancer treatments, and even anticipate tumor recurrence.

Not a New Idea – With a Critical Twist

Digital twins of individual organs and functional systems have been developed before, raising questions about what is truly new in this approach. The difference, researchers say, lies in an unprecedented level of fidelity to the biological original.

“Suppose you want to create a twin of an organ, such as a kidney or liver. These organs are made up of tissues composed of many completely different cell types, each with its own set of active genes. Existing digital twin technologies average these diverse cells into a single model – something like the ‘average temperature in a hospital.’ We aim to build a far more precise model and move beyond that kind of averaging,” said project lead Anton Buzdin.

At first glance, the task may seem impossible. The human body consists of trillions of cells. How can you build a digital twin for each of them?

But those trillions of cells fall into thousands of distinct types and subtypes. The team proposes creating digital twins for each of those categories. Once trillions are reduced to thousands, the challenge becomes far less fantastical.

AI Assembles the Mosaic

“As a result, we will create a collection of digital twins for different types of human cells. They will model what happens when a specific drug is administered not in an abstract average cell, but in each real, biologically distinct cell type,” Buzdin said.

The models are based on single-cell sequencing technologies. Artificial intelligence will help assemble a coherent picture from the mosaic of processes occurring inside individual cells.

Each digital twin will be customized to reflect a specific individual’s genetic profile, including copy number variations and mutations. Researchers expect to apply the results in personalized medicine, tailoring therapies not to generalized standards but to individual patients.

Anton Buzdin is considered one of the world’s leading researchers in molecular pathways, gene activity analysis, and cancer biomarker development. He has authored more than 300 papers published in major international journals. For several years, he led the bioinformatics analysis group at the European Organisation for Research and Treatment of Cancer (EORTC) and headed international technology startups. In 2025, he won a competition for leading and young scientists under the federal territory Sirius scientific and technological development program.

Medicine and healthcare