University of South Australia scientists have developed a powerful new way to uncover the genetic interactions that fuel cancer progression, paving the way for earlier and more precise treatments.<\/p>\n
The AI-driven method, published today in Royal Society Open Science, reveals that tumour progression is driven by cooperating groups of genes, rather than mutated genes acting alone.<\/p>\n
Lead researcher Dr. Andres Cifuentes-Bernal says his team used AI tools to identify groups of genes working in concert to push cancer forward.<\/p>\n
<\/p>\n
The system assesses how genes influence each other over time, providing a clearer picture of the underlying biological approaches that enable tumours to grow, spread and resist treatment.<\/p>\n
\n
<\/p>\n
Traditional genome-wide cancer studies typically focus on mutations that appear frequently across patients. While this approach has uncovered many well-known cancer drivers, it overlooks subtle or rare genetic changes. Crucially, it also misses the complex interplay between genes that allow malignant cells to gain momentum.”<\/p>\n
\n
<\/p>\n
Dr. Andres Cifuentes-Bernal, lead researcher<\/p>\n
<\/p>\n
Co-author, UniSA Associate Professor Thuc Le, says the new framework highlights the growing role of artificial intelligence in biomedical discovery, addressing a long-standing gap in cancer biology.<\/p>\n
“Cancer is not static,” he says. “It develops through a cascade of dynamic changes. Many genes act together to disrupt normal cell behaviour, but existing methods can struggle to detect that. Our approach is designed to capture that complexity.”<\/p>\n
Using large breast cancer datasets to test their method, the researchers showed that the AI-driven system not only detects well-known cancer genes but also uncovers previously hidden ones.<\/p>\n
Many of these are not mutated but still influence other genes, contributing to tumour progression.<\/p>\n
The method successfully recognised a significant number of known cancer drivers listed in the Cancer Gene Census \u2013 a respected international reference \u2013 confirming the accuracy of the approach.<\/p>\n