Researchers from the Institute of Cancer Research (London, UK) and the University of Edinburgh (Edinburgh, UK) have used artificial intelligence to predict how cancers will progress and evolve, which could provide the potential to design the most effective treatment for individual patients.
The study, recently published in Nature Methods, introduces the new technique called REVOLVER (Repeated evolution of cancer), which picks out patterns in DNA mutation within cancers and uses the information to forecast future genetic changes.
In addition a link was found between certain sequences of repeated tumor mutations and survival outcome. This finding could help shape future treatment as an indicator of prognosis. For example, the researchers found that breast tumors which had a sequence of errors in the genetic material that code for p53, followed by mutations in chromosome 8, survived less time than those with other similar trajectories of genetic changes.
The machine learning technique transfers knowledge about tumors across similar patients and identifies patterns in the order that genetic mutations occur in tumors that are repeated both within and between patients’ tumors, applying one tumor’s pattern of mutations to predict another’s.
A total of 768 tumor samples from 178 patients reported in previous studies for lung, breast, and kidney and bowel cancer were used for the investigation, which analyzed the data within each cancer type to accurately detect and compare changes in each tumor.
If tumors with certain patterns are found to develop resistance to a particular treatment, this novel methodology could be used to predict if patients will develop resistance in the future.
Study leader Andrea Sottoriva (Institute of Cancer Research) commented: “We’ve developed a powerful artificial intelligence tool which can make predictions about the future steps in the evolution of tumors based on certain patterns of mutation that have so far remained hidden within complex data sets.”
Sottoriva continued: “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.”