Scientists develop machine learning tool able to predict cancer growth
[London, UK] Scientists have developed a new machine learning tool that can predict the evolution of cancer by analysing genetic changes, allowing doctors to design the most effective treatment for each patient.
The new research, funded by the Wellcome Trust, the European Research Council and Cancer Research UK, was published in the Nature Methods journal last week.
Led by the Institute of Cancer Research (ICR) and the University of Edinburgh, a team of experts developed a technique called Revolver (Repeated Evolution of Cancer) able to identify patterns in DNA mutations within cancers.
“It is an example of how the power of AI to detect complex patterns in data can be harnessed to further our scientific understanding to improve human health," said University of Edinburgh Professor Guido Sanguinetti.
Working with colleagues from the University of Birmingham, Stanford University and Queen Mary University of London, the researchers found a link between certain sequences of repeated tumour mutations and survival outcomes, indicating that repeating patterns of DNA mutations could predict how cancers will evolve and spread.
Using AI to predict ‘cancer’s next move’
Dr Andrea Sottoriva, from the ICR’s Evolutionary Genomics and Modelling team, who led the study along with Professor Sanguinetti, explained:
“We’ve developed a powerful artificial intelligence tool which can make predictions about the future steps in the evolution of tumours based on certain patterns of mutation that have 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.”
The experts used 768 tumour samples from 178 patients reported in previous studies for lung, breast, kidney and bowel cancer, analysing data within each cancer type to detect and compare tumour changes.
“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 Professor Paul Workman, ICR Chief Executive.
Earlier this year, Prime Minister Theresa May said the UK had an opportunity 'to lead the world in the use of data and technology to prevent illness, not just treat it, to diagnose conditions before symptoms occur and to deliver personalised treatment'.