CANBERRA, Dec. 10 (Xinhua) -- Scientists in Australia have developed a powerful new way to uncover the genetic interactions that fuel cancer progression, paving the way for earlier and more precise treatments.
The artificial intelligence (AI)-driven method reveals that tumor progression is driven by cooperating groups of genes, rather than mutated genes acting alone, a media release from the University of South Australia (UniSA) said Wednesday.
The UniSA team used AI tools to identify groups of genes working in concert to push cancer forward, according to the study published in Royal Society Open Science.
"The system assesses how genes influence each other over time, providing a clearer picture of the underlying biological approaches that enable tumors to grow, spread and resist treatment," said study lead researcher Andres Cifuentes Bernal at UniSA.
Traditional genome-wide cancer studies typically focus on mutations that appear frequently across patients, identifying key cancer drivers but overlooking subtle or rare genetic changes and missing the complex gene interactions that propel tumor growth, said Cifuentes Bernal.
Study co-author, UniSA Associate Professor Thuc Le, said the new framework highlights the growing role of AI in biomedical discovery, addressing a long-standing gap in cancer biology.
"Cancer is not static. It develops through a cascade of dynamic changes. Many genes act together to disrupt normal cell behavior, but existing methods can struggle to detect that. Our approach is designed to capture that complexity," Le said.
Testing the model on large breast cancer datasets, researchers found it successfully recognized many well-known cancer drivers, while also revealing novel candidates involved in cell signaling, immune response and metastasis.
The technique identifies cooperative networks rather than isolated genes, Le said, adding that these networks highlight "how genes collaborate to collectively push cancer into more aggressive states."
The researchers are hopeful their method could help pinpoint new therapeutic targets, especially for cancers lacking common high-profile mutations. ■
