New study uses AI to identify cancer cell groups

In a first for cancer research, a new AI tool called AAnet has been developed in a four-nation study co-led by Sydney’s Garvan Institute of Medical Research, which has the potential to transform characterisation and treatment of cancers.

Tumours are not made up of just one cell type, and that heterogeneity makes cancer harder to treat, and can in turn lead to worse outcomes.

For example, one therapy that kills most cells in a tumour by targeting a particular mechanism, may leave other cancerous cells there, and a chance for the cancer to grow back.

While heterogeneity is a known problematic issue, researchers haven’t been able to clearly explain how adjacent cells in a tumour differ from each other, and how to classify those differences into meaningful ways – hence the need for a new approach.

The research team developed and tested AAnet to uncover patterns in the level of gene expression of individual cells, identifying five distinct cell groups within the same tumour.

These groups behaved in different ways, helping to explain why some cancer cells resist treatment.

The study’s focus was on preclinical models of triple negative breast cancer, and human samples of ER positive, HER2 positive, and triple negative breast cancer.

The development of the AAnet AI tool’s technology was led by Associate Professor Smita Krishnaswamy from Yale University.

The senior co-authors of the study were chief scientific officer at the Garvan Institute and professor of the Faculty of Medicine and Health, Professor Sarah Kummerfeld, and lab head at the Garvan, Associate professor Christine Chaffer.

On how AAnet can be applied, Professor Kummerfeld said, “We envision a future where doctors combine this AI analysis with traditional cancer diagnoses, to develop more personalised treatments that target all cell types within a person’s unique tumour.

“These results represent a true melding of cutting-edge technology and biology that can improve patient care.

“Our study focused on breast cancer, but it could be applied to other cancers and illnesses, such as autoimmune disorders. The technology is already there.”

The Garvan Institute is home to the Garvan-Weizmann Centre for Cellular Genomics, which houses a range of new and cutting-edge technologies that can look more closely at a cell than ever before.

Through the centre, researchers are able to explore thousands of individual cells simultaneously: uncovering each cell’s genome sequence and its genetic output, and understanding what makes it unique.

Meanwhile, the Garvan is hosting a free exhibition in Darlinghurst, Sydney, during National Science Week from August 11-22.

Scientific imagery showcased as art in large-scale illuminated lightboxes is open to experience on weekdays from 2pm to 5pm.

The exhibition is also available for viewing online.

Professor Kummerfeld will be one of six leading Garvan researchers participating in a sold-out Garvan “Discovery After Dark” two-hour debate on August 20, in which the panel will participate in a topical debate about scientific creativity, and directly engage with the audience.

To view the Garvan’s special exhibition online between August 11-22, visit https://www.garvan.org.au/art-of-discovery