A team of scientists led by The University of Edinburgh and the Institute of Cancer Research London (ICR) has developed a new approach known as Revolver (Repeated evolution of cancer), which uses patterns in DNA mutation within cancers to predict future genetic changes.
Cancerous tumours are typically ever-evolving and often develop to become drug-resistant. Being able to predict how a tumour will evolve will enable clinicians to intervene earlier to halt cancer before it can evolve to become deadlier.
This data could potentially help doctors design more effective treatments and generate better outcomes for patients. The same team also found a link between certain sequences of repeated tumour mutations and survival outcome, which suggests that repeating patterns of DNA mutations could be used an indicator of prognosis and help shape treatment. The team 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, survived less time than those with other similar trajectories of genetic changes.
Machine Learning Helping to Predict Tumour Trajectory
Using machine learning the team developed a technique that transfers knowledge about tumours across similar patients. This method would identify patterns in the order that genetic mutations occur in tumours that are repeated both within and between patients’ tumours, applying one tumour’s pattern of mutations to predict another’s.
Using 768 tumour samples from 178 patients reported in previous studies for lung, breast, kidney and bowel cancer, and analysed the data within each cancer type respectively to accurately detect and compare changes in each tumour. By identifying and combining these repeating patterns with current knowledge of cancer biology and evolution this new approach could be used to forecast the trajectory of tumour development.
Dr Andrea Sottoriva, who led the study, said: “We’ve developed a powerful artificial intelligence tool which can make predictions about future steps in the evolution of tumours based on certain patterns of mutation that so far remained hidden within complex data sets. With this tool we hope to remove one of cancer’s trump cards – the fact that it evolves unpredictably, without us knowing what is going to happen next. By giving us a peek into the future, we could potentially use this AI tool to intervene at an earlier stage, predicting cancer’s next move.”
ICR chief executive Professor Paul Workman said: “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.
“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.”