Australian Scientists Develop Biological AI System for Molecule Evolution

Jul 7, 2025
Researchers at the University of Sydney have developed PROTEUS, a biological AI system that accelerates molecule evolution in mammal cells, potentially revolutionizing gene therapies.

Australian scientists at the University of Sydney have developed a groundbreaking research system named PROTEUS, which uses 'biological artificial intelligence' to design and evolve molecules with new or improved functions directly in mammal cells. This system, detailed in a recent announcement, provides a powerful new tool for developing more specific and effective research tools or gene therapies.

PROTEUS employs 'directed evolution', a lab technique that mimics natural evolution, but accelerates the process to create molecules with new functions in weeks rather than years. This advancement could significantly impact the development of new medicines, including enhancing gene editing technologies like CRISPR.

The system allows researchers to program mammalian cells with genetic problems and uses directed evolution to explore millions of possible sequences, finding molecules highly adapted to solve these problems. This capability could lead to solutions that would otherwise take years for human researchers to discover.

The research, conducted at the Charles Perkins Centre in collaboration with the Centenary Institute, has already demonstrated the ability of PROTEUS to develop improved proteins and nanobodies that detect DNA damage, a key process in cancer development. The system's open-source nature invites other labs to adopt and further develop this innovative technique.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Life AI Weekly

Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.