AI Reducing Animal Testing, Speeding Drug Trials

Brisbane biotech company Gelomics is helping advance a new generation of drug development through its platform for creating lab-grown human tissue models, giving researchers a more human-relevant way to test compounds in early-stage research without relying on animal experiments.

The company’s AI-powered system combines automation, machine learning and tissue engineering to support the development of human tissue models that can better reflect how drugs may behave in the body. Gelomics’ integrated laboratory device can reduce tissue manufacturing time from around four hours to about 10 minutes, helping research teams move faster while improving consistency and reproducibility.

The technology is now being used by around 300 researchers across 23 countries, underscoring growing global interest in more predictive non-animal testing tools.

At a high level, success means a significant reduction in unnecessary animal testing. That’s a core part of our mission.”

Christoph Meinert, CEO, Gelomics

This work sits within the growing field of New Approach Methodologies, or NAMs, which are helping researchers move through early testing using non-animal tools that can be more relevant to human biology. But for those methods to be accepted more widely, they have to be properly validated and backed by the right data and computing systems.

"To demonstrate the capabilities of NAM technologies, large datasets and live-cell imaging data are needed to validate through sensor-&-image-based systems, and that requires the right infrastructure," said Sam Jesudian of ARM Hub.

That capability is what ARM Hub’s data and AI services, including its data lakehouse infrastructure, are helping enable.

That infrastructure matters, because NAMs are only useful at scale if researchers can process large volumes of imaging data, build confidence in the models and produce evidence that can support regulatory decision-making. The goal is not just faster experimentation, but better tools for identifying promising therapies earlier and reducing reliance on animal testing where possible.

“We have to demonstrate that these technologies can be validated in real time or in the cloud, which requires significant digital infrastructure to accumulate large datasets,” said Sam Jesudian.

“The impact of this technology extends beyond accelerating drug development timelines,” said Christoph. “It promises substantial reductions in both the costs and ethical concerns associated with traditional research and development methodologies.”