The Fascination of Technology Virtual Mouse as an Alternative to Animal Testing

Related Vendors

Taiwan Machine Tool & Accessory Builders' Association (TMBA)

SIMTOS (Seoul International Machine Tool Show)

In our "Fascination Technology" section, we present impressive projects from research and development to engineers every week. Today: How a virtual AI mouse aims to reduce animal testing.

Artificial intelligence (AI) can save lives—at least the lives of mice. Researchers at Empa have developed an AI-supported computer model of a laboratory mouse that, using machine learning, can predict how various nanomaterials distribute within the mouse's organism. Developed according to the safe-and-sustainable-by-design principle, the model could not only serve as a decision-making aid in drug development in the future but also reduce the number of animal experiments.

Nanotechnology Delivers Active Substances Precisely

If a tumor has managed to nest in the brain of a living being, it has—from the tumor's perspective—done so particularly cleverly. It has hidden behind one of the most powerful barriers with which the body protects its vital organs: the blood-brain barrier, a highly selective filter that allows only specific substances to pass through. Most medications do not belong to this category. For medicine, finding an effective chemotherapy for brain tumors is therefore a major challenge. In recent years, medical research has found a promising ally: nanotechnology. Nanomaterials can, figuratively speaking, take on the role of mail carriers delivering active substances to the desired destination. Since nanoparticles are unimaginably small—about 500 times smaller than the diameter of a human hair—some of them can pass the body's protective barriers without damaging them. To use the example of a brain tumor: nanoparticles could transport chemotherapeutic agents across the blood-brain barrier into the brain, where they could then combat the brain tumor.

Virtual Mouse Receives Virtual Nanoparticles

However, nanoparticles must exhibit very specific properties depending on the task they are meant to perform: depending on their shape, material composition, and size, they distribute differently in the body and accumulate in different organs. Therefore, it is necessary to determine which particles perform their task most effectively while causing minimal harm. So far, researchers have used animal models, mostly mice, to address these questions: they administered various nanomaterials to mice and then examined how they distributed in the mouse's body and what side effects they had. However, these animal studies are not only labor-intensive, time-consuming, and expensive but also ethically problematic. Empa researcher Jimeng Wu, a Ph.D. student in the departments of Nanomaterials in Health and Technology and Society, has therefore developed a virtual mouse on which these tests can be conducted much more quickly using AI. For this so-called physiologically based pharmacokinetic model (PBPK model), Wu used 18 mouse studies as a foundation, meaning data from experiments performed by various research teams on actual mice. Additionally, she integrated a statistical method, Bayesian analysis with Markov-chain Monte Carlo simulations, into her model. The result is a virtual mouse to which one can administer – also virtual—nanoparticles.

AI Mouse Adapts

The model then calculates their distribution in the mouse's body based on their properties such as size, coating, and surface charge. Compared to a traditional PBPK model, which is calibrated for only a single substance at a time, Wu's AI mouse has a significant advantage: "The model can adjust its parameters to the measurable properties of the respective nanoparticle," explains Jimeng Wu. This capability is thanks to the tool's multivariate linear regression model, an approach of machine learning. This AI-supported screening tool allows researchers to virtually test which type of nanoparticles is best suited for a specific task before actually producing these particles. This saves time and costs, providing decision-making assistance before launching an expensive clinical study.

Fascination With Technology

Preventing Heart Diseases with AI