New Delhi– An international team of researchers has developed a groundbreaking artificial intelligence (AI) tool that promises to revolutionize cancer treatment by mapping the diverse cellular makeup within tumors, a major challenge in oncology.
The tool, named AAnet, was created by scientists at the Garvan Institute of Medical Research in Sydney in collaboration with Yale School of Medicine. It uses deep learning to analyze gene activity at the single-cell level, offering a detailed view of tumor heterogeneity — the presence of different types of cells within a single tumor that can lead to treatment resistance and recurrence, according to Xinhua news agency.
AAnet identifies five distinct cancer cell types within tumors, each exhibiting unique behaviors and varying risks of spreading. This allows oncologists to gain deeper insights into tumor biology compared to conventional approaches, which often treat tumors as homogenous entities.
“Heterogeneity is a problem because currently, we treat tumors as if they are made up of the same cell,” said Associate Professor Christine Chaffer, co-senior author of the study from the Garvan Institute. “That means we give one therapy targeting a single mechanism, but not all cancer cells may respond to it. Some survive, leading to relapse.”
By revealing the biological diversity within tumors, AAnet enables the development of combination therapies tailored to target all cancer cell subtypes at once, potentially improving treatment outcomes and reducing recurrence.
Co-developer Associate Professor Smita Krishnaswamy of Yale University said the tool is the first of its kind to distill tumor complexity into actionable cellular archetypes, marking a potential turning point in precision oncology.
Validated in breast cancer studies, the AI tool is already considered ready for clinical use and may be applied in conjunction with traditional diagnostics to develop personalized treatment plans. It also holds promise for treating other cancers and autoimmune diseases, the study said.
The research was published in the journal Cancer Discovery. (Source: IANS)
