Personalised cancer treatment could soon become a reality thanks to a new Artificial Intelligence (AI) technique that can predict how tumours will progress and evolve.
REVOLVER (Repeated Evolution of Cancer) identifies patterns in DNA mutation within cancers and forecasts future genetic changes. Experts believe the technique could allow doctors to stay one step ahead of cancer, boosting patient survival and leading to personalised cancer treatment.
It was developed by scientists at The Institute of Cancer Research, London (ICR) and the University of Edinburgh, UK, and funded by the Wellcome Trust, the European Research Council and Cancer Research UK.
What did the researchers find?
The ever-changing nature of tumours represents one of the biggest hurdles to treating cancer – with cancers often evolving to a drug-resistant form.
Being able to predict how a tumour will evolve could allow doctors to intervene earlier, not only stopping the cancer from evolving but also preventing it from developing resistance.
The scientists also discovered a link between certain sequences of repeated tumour mutations and survival outcome, suggesting that repeating patterns of DNA mutations could be used as an indicator of prognosis, helping to inform future treatment.
For instance, the researchers found that breast tumours which had a sequence of errors in the genetic material that codes for the tumour-suppressing protein p53, followed by mutations in chromosome 8, did not survive as long as those with other similar trajectories of genetic changes.
What are the implications for personalised cancer treatment?
“Cancer evolution is the biggest challenge we face in creating treatments that will work more effectively for patients. If we are able to predict how a tumour will evolve, the treatment could be altered before adaptation and drug resistance ever occur, putting us one step ahead of the cancer,” said ICR chief executive Professor Paul Workman, commenting on the research.
“This new approach using AI could allow treatment to be personalised in a more detailed way and at an earlier stage than is currently possible, tailoring it to the characteristics of each individual tumour and to predictions of what that tumour will look like in the future.”
This research has been published in the journal Nature Methods.